rename emd module to lp

8 files changed, 8591 insertions, 0 deletions

diff --git a/ot/lp/EMD.h b/ot/lp/EMD.h
new file mode 100644
index 0000000..40d7192
--- /dev/null
+++ b/ot/lp/EMD.h
@@ -0,0 +1,29 @@
+/* This file is a c++ wrapper function for computing the transportation cost
+ * between two vectors given a cost matrix.
+ *
+ * It was written by Antoine Rolet (2014) and mainly consists of a wrapper
+ * of the code written by Nicolas Bonneel available on this page
+ *          http://people.seas.harvard.edu/~nbonneel/FastTransport/
+ *
+ * It was then modified to make it more amenable to python inline calling
+ *
+ * Please give relevant credit to the original author (Nicolas Bonneel) if
+ * you use this code for a publication.
+ *
+ */
+
+
+#ifndef EMD_H
+#define EMD_H
+
+#include <iostream>
+#include <vector>
+#include "network_simplex_simple.h"
+
+using namespace lemon;
+typedef unsigned int node_id_type;
+
+
+void EMD_wrap(int n1,int n2, double *X, double *Y,double *D, double *G, double *cost);
+
+#endif
diff --git a/ot/lp/EMD_wrap.cpp b/ot/lp/EMD_wrap.cpp
new file mode 100644
index 0000000..52cd262
--- /dev/null
+++ b/ot/lp/EMD_wrap.cpp
@@ -0,0 +1,120 @@
+/* This file is a c++ wrapper function for computing the transportation cost
+ * between two vectors given a cost matrix.
+ *
+ * It was written by Antoine Rolet (2014) and mainly consists of a wrapper
+ * of the code written by Nicolas Bonneel available on this page
+ *          http://people.seas.harvard.edu/~nbonneel/FastTransport/
+ *
+ * It was then modified to make it more amenable to python inline calling
+ *
+ * Please give relevant credit to the original author (Nicolas Bonneel) if
+ * you use this code for a publication.
+ *
+ */
+
+#include "EMD.h"
+
+
+void EMD_wrap(int n1,int n2, double *X, double *Y,double *D, double *G, double *cost)  {
+// beware M and C anre strored in row major C style!!!
+  int n, m, i,cur;
+  double  max,max_iter;
+
+
+    typedef FullBipartiteDigraph Digraph;
+  DIGRAPH_TYPEDEFS(FullBipartiteDigraph);
+
+  // Get the number of non zero coordinates for r and c
+    n=0;
+    for (node_id_type i=0; i<n1; i++) {
+        double val=*(X+i);
+        if (val>0) {
+            n++;
+        }
+    }
+    m=0;
+    for (node_id_type i=0; i<n2; i++) {
+        double val=*(Y+i);
+        if (val>0) {
+            m++;
+        }
+    }
+
+
+    // Define the graph
+
+    std::vector<int> indI(n), indJ(m);
+    std::vector<double> weights1(n), weights2(m);
+    Digraph di(n, m);
+    NetworkSimplexSimple<Digraph,double,double, node_id_type> net(di, true, n+m, n*m,max_iter);
+
+    // Set supply and demand, don't account for 0 values (faster)
+
+    max=0;
+    cur=0;
+    for (node_id_type i=0; i<n1; i++) {
+        double val=*(X+i);
+        if (val>0) {
+            weights1[ di.nodeFromId(cur) ] = val;
+            max+=val;
+            indI[cur++]=i;
+        }
+    }
+
+    // Demand is actually negative supply...
+
+    max=0;
+    cur=0;
+    for (node_id_type i=0; i<n2; i++) {
+        double val=*(Y+i);
+        if (val>0) {
+            weights2[ di.nodeFromId(cur) ] = -val;
+            indJ[cur++]=i;
+
+            max-=val;
+        }
+    }
+
+
+    net.supplyMap(&weights1[0], n, &weights2[0], m);
+
+    // Set the cost of each edge
+    max=0;
+    for (node_id_type i=0; i<n; i++) {
+        for (node_id_type j=0; j<m; j++) {
+            double val=*(D+indI[i]*n2+indJ[j]);
+            net.setCost(di.arcFromId(i*m+j), val);
+            if (val>max) {
+                max=val;
+            }
+        }
+    }
+
+
+    // Solve the problem with the network simplex algorithm
+
+    int ret=net.run();
+    if (ret!=(int)net.OPTIMAL) {
+        if (ret==(int)net.INFEASIBLE) {
+            std::cout << "Infeasible problem";
+        }
+        if (ret==(int)net.UNBOUNDED)
+        {
+            std::cout << "Unbounded problem";
+        }
+    } else
+    {
+        for (node_id_type i=0; i<n; i++)
+        {
+            for (node_id_type j=0; j<m; j++)
+            {
+                *(G+indI[i]*n2+indJ[j]) = net.flow(di.arcFromId(i*m+j));
+            }
+        };
+        *cost = net.totalCost();
+
+    };
+
+
+
+}
diff --git a/ot/lp/__init__.py b/ot/lp/__init__.py
new file mode 100644
index 0000000..65cee83
--- /dev/null
+++ b/ot/lp/__init__.py
@@ -0,0 +1,3 @@
+
+
+from . import emd
diff --git a/ot/lp/core.h b/ot/lp/core.h
new file mode 100644
index 0000000..04dddf7
--- /dev/null
+++ b/ot/lp/core.h
@@ -0,0 +1,103 @@
+/* -*- mode: C++; indent-tabs-mode: nil; -*-
+ *
+ * This file has been adapted by Nicolas Bonneel (2013), 
+ * from full_graph.h from LEMON, a generic C++ optimization library,
+ * to make the other files independant from the rest of 
+ * the original library.
+ * 
+ *
+ **** Original file Copyright Notice :
+ * Copyright (C) 2003-2010
+ * Egervary Jeno Kombinatorikus Optimalizalasi Kutatocsoport
+ * (Egervary Research Group on Combinatorial Optimization, EGRES).
+ *
+ * Permission to use, modify and distribute this software is granted
+ * provided that this copyright notice appears in all copies. For
+ * precise terms see the accompanying LICENSE file.
+ *
+ * This software is provided "AS IS" with no warranty of any kind,
+ * express or implied, and with no claim as to its suitability for any
+ * purpose.
+ *
+ */
+
+#ifndef LEMON_CORE_H
+#define LEMON_CORE_H
+
+#include <vector>
+#include <algorithm>
+
+
+// Disable the following warnings when compiling with MSVC:
+// C4250: 'class1' : inherits 'class2::member' via dominance
+// C4355: 'this' : used in base member initializer list
+// C4503: 'function' : decorated name length exceeded, name was truncated
+// C4800: 'type' : forcing value to bool 'true' or 'false' (performance warning)
+// C4996: 'function': was declared deprecated
+#ifdef _MSC_VER
+#pragma warning( disable : 4250 4355 4503 4800 4996 )
+#endif
+
+///\file
+///\brief LEMON core utilities.
+///
+///This header file contains core utilities for LEMON.
+///It is automatically included by all graph types, therefore it usually
+///do not have to be included directly.
+
+namespace lemon {
+
+  /// \brief Dummy type to make it easier to create invalid iterators.
+  ///
+  /// Dummy type to make it easier to create invalid iterators.
+  /// See \ref INVALID for the usage.
+  struct Invalid {
+  public:
+    bool operator==(Invalid) { return true;  }
+    bool operator!=(Invalid) { return false; }
+    bool operator< (Invalid) { return false; }
+  };
+
+  /// \brief Invalid iterators.
+  ///
+  /// \ref Invalid is a global type that converts to each iterator
+  /// in such a way that the value of the target iterator will be invalid.
+#ifdef LEMON_ONLY_TEMPLATES
+  const Invalid INVALID = Invalid();
+#else
+  extern const Invalid INVALID;
+#endif
+
+  /// \addtogroup gutils
+  /// @{
+
+  ///Create convenience typedefs for the digraph types and iterators
+
+  ///This \c \#define creates convenient type definitions for the following
+  ///types of \c Digraph: \c Node,  \c NodeIt, \c Arc, \c ArcIt, \c InArcIt,
+  ///\c OutArcIt, \c BoolNodeMap, \c IntNodeMap, \c DoubleNodeMap,
+  ///\c BoolArcMap, \c IntArcMap, \c DoubleArcMap.
+  ///
+  ///\note If the graph type is a dependent type, ie. the graph type depend
+  ///on a template parameter, then use \c TEMPLATE_DIGRAPH_TYPEDEFS()
+  ///macro.
+#define DIGRAPH_TYPEDEFS(Digraph)                                       \
+  typedef Digraph::Node Node;                                           \
+  typedef Digraph::Arc Arc;                                             \
+
+
+  ///Create convenience typedefs for the digraph types and iterators
+
+  ///\see DIGRAPH_TYPEDEFS
+  ///
+  ///\note Use this macro, if the graph type is a dependent type,
+  ///ie. the graph type depend on a template parameter.
+#define TEMPLATE_DIGRAPH_TYPEDEFS(Digraph)                              \
+  typedef typename Digraph::Node Node;                                  \
+  typedef typename Digraph::Arc Arc;                                    \
+
+ 
+
+} //namespace lemon
+
+#endif
diff --git a/ot/lp/emd.cpp b/ot/lp/emd.cpp
new file mode 100644
index 0000000..2343af6
--- /dev/null
+++ b/ot/lp/emd.cpp
@@ -0,0 +1,6507 @@
+/* Generated by Cython 0.23.4 */
+
+/* BEGIN: Cython Metadata
+{
+    "distutils": {
+        "depends": [
+            "/usr/lib/python2.7/dist-packages/numpy/core/include/numpy/arrayobject.h", 
+            "/usr/lib/python2.7/dist-packages/numpy/core/include/numpy/ufuncobject.h", 
+            "ot/emd/EMD.h"
+        ], 
+        "include_dirs": [
+            "/usr/lib/python2.7/dist-packages/numpy/core/include", 
+            "/home/rflamary/PYTHON/POT/ot/emd"
+        ], 
+        "language": "c++"
+    }
+}
+END: Cython Metadata */
+
+#define PY_SSIZE_T_CLEAN
+#include "Python.h"
+#ifndef Py_PYTHON_H
+    #error Python headers needed to compile C extensions, please install development version of Python.
+#elif PY_VERSION_HEX < 0x02060000 || (0x03000000 <= PY_VERSION_HEX && PY_VERSION_HEX < 0x03020000)
+    #error Cython requires Python 2.6+ or Python 3.2+.
+#else
+#define CYTHON_ABI "0_23_4"
+#include <stddef.h>
+#ifndef offsetof
+#define offsetof(type, member) ( (size_t) & ((type*)0) -> member )
+#endif
+#if !defined(WIN32) && !defined(MS_WINDOWS)
+  #ifndef __stdcall
+    #define __stdcall
+  #endif
+  #ifndef __cdecl
+    #define __cdecl
+  #endif
+  #ifndef __fastcall
+    #define __fastcall
+  #endif
+#endif
+#ifndef DL_IMPORT
+  #define DL_IMPORT(t) t
+#endif
+#ifndef DL_EXPORT
+  #define DL_EXPORT(t) t
+#endif
+#ifndef PY_LONG_LONG
+  #define PY_LONG_LONG LONG_LONG
+#endif
+#ifndef Py_HUGE_VAL
+  #define Py_HUGE_VAL HUGE_VAL
+#endif
+#ifdef PYPY_VERSION
+#define CYTHON_COMPILING_IN_PYPY 1
+#define CYTHON_COMPILING_IN_CPYTHON 0
+#else
+#define CYTHON_COMPILING_IN_PYPY 0
+#define CYTHON_COMPILING_IN_CPYTHON 1
+#endif
+#if !defined(CYTHON_USE_PYLONG_INTERNALS) && CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x02070000
+#define CYTHON_USE_PYLONG_INTERNALS 1
+#endif
+#if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX < 0x02070600 && !defined(Py_OptimizeFlag)
+#define Py_OptimizeFlag 0
+#endif
+#define __PYX_BUILD_PY_SSIZE_T "n"
+#define CYTHON_FORMAT_SSIZE_T "z"
+#if PY_MAJOR_VERSION < 3
+  #define __Pyx_BUILTIN_MODULE_NAME "__builtin__"
+  #define __Pyx_PyCode_New(a, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos)\
+          PyCode_New(a+k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos)
+  #define __Pyx_DefaultClassType PyClass_Type
+#else
+  #define __Pyx_BUILTIN_MODULE_NAME "builtins"
+  #define __Pyx_PyCode_New(a, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos)\
+          PyCode_New(a, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos)
+  #define __Pyx_DefaultClassType PyType_Type
+#endif
+#ifndef Py_TPFLAGS_CHECKTYPES
+  #define Py_TPFLAGS_CHECKTYPES 0
+#endif
+#ifndef Py_TPFLAGS_HAVE_INDEX
+  #define Py_TPFLAGS_HAVE_INDEX 0
+#endif
+#ifndef Py_TPFLAGS_HAVE_NEWBUFFER
+  #define Py_TPFLAGS_HAVE_NEWBUFFER 0
+#endif
+#ifndef Py_TPFLAGS_HAVE_FINALIZE
+  #define Py_TPFLAGS_HAVE_FINALIZE 0
+#endif
+#if PY_VERSION_HEX > 0x03030000 && defined(PyUnicode_KIND)
+  #define CYTHON_PEP393_ENABLED 1
+  #define __Pyx_PyUnicode_READY(op)       (likely(PyUnicode_IS_READY(op)) ?\
+                                              0 : _PyUnicode_Ready((PyObject *)(op)))
+  #define __Pyx_PyUnicode_GET_LENGTH(u)   PyUnicode_GET_LENGTH(u)
+  #define __Pyx_PyUnicode_READ_CHAR(u, i) PyUnicode_READ_CHAR(u, i)
+  #define __Pyx_PyUnicode_KIND(u)         PyUnicode_KIND(u)
+  #define __Pyx_PyUnicode_DATA(u)         PyUnicode_DATA(u)
+  #define __Pyx_PyUnicode_READ(k, d, i)   PyUnicode_READ(k, d, i)
+#else
+  #define CYTHON_PEP393_ENABLED 0
+  #define __Pyx_PyUnicode_READY(op)       (0)
+  #define __Pyx_PyUnicode_GET_LENGTH(u)   PyUnicode_GET_SIZE(u)
+  #define __Pyx_PyUnicode_READ_CHAR(u, i) ((Py_UCS4)(PyUnicode_AS_UNICODE(u)[i]))
+  #define __Pyx_PyUnicode_KIND(u)         (sizeof(Py_UNICODE))
+  #define __Pyx_PyUnicode_DATA(u)         ((void*)PyUnicode_AS_UNICODE(u))
+  #define __Pyx_PyUnicode_READ(k, d, i)   ((void)(k), (Py_UCS4)(((Py_UNICODE*)d)[i]))
+#endif
+#if CYTHON_COMPILING_IN_PYPY
+  #define __Pyx_PyUnicode_Concat(a, b)      PyNumber_Add(a, b)
+  #define __Pyx_PyUnicode_ConcatSafe(a, b)  PyNumber_Add(a, b)
+#else
+  #define __Pyx_PyUnicode_Concat(a, b)      PyUnicode_Concat(a, b)
+  #define __Pyx_PyUnicode_ConcatSafe(a, b)  ((unlikely((a) == Py_None) || unlikely((b) == Py_None)) ?\
+      PyNumber_Add(a, b) : __Pyx_PyUnicode_Concat(a, b))
+#endif
+#if CYTHON_COMPILING_IN_PYPY && !defined(PyUnicode_Contains)
+  #define PyUnicode_Contains(u, s)  PySequence_Contains(u, s)
+#endif
+#define __Pyx_PyString_FormatSafe(a, b)   ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : __Pyx_PyString_Format(a, b))
+#define __Pyx_PyUnicode_FormatSafe(a, b)  ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : PyUnicode_Format(a, b))
+#if PY_MAJOR_VERSION >= 3
+  #define __Pyx_PyString_Format(a, b)  PyUnicode_Format(a, b)
+#else
+  #define __Pyx_PyString_Format(a, b)  PyString_Format(a, b)
+#endif
+#if PY_MAJOR_VERSION >= 3
+  #define PyBaseString_Type            PyUnicode_Type
+  #define PyStringObject               PyUnicodeObject
+  #define PyString_Type                PyUnicode_Type
+  #define PyString_Check               PyUnicode_Check
+  #define PyString_CheckExact          PyUnicode_CheckExact
+#endif
+#if PY_MAJOR_VERSION >= 3
+  #define __Pyx_PyBaseString_Check(obj) PyUnicode_Check(obj)
+  #define __Pyx_PyBaseString_CheckExact(obj) PyUnicode_CheckExact(obj)
+#else
+  #define __Pyx_PyBaseString_Check(obj) (PyString_Check(obj) || PyUnicode_Check(obj))
+  #define __Pyx_PyBaseString_CheckExact(obj) (PyString_CheckExact(obj) || PyUnicode_CheckExact(obj))
+#endif
+#ifndef PySet_CheckExact
+  #define PySet_CheckExact(obj)        (Py_TYPE(obj) == &PySet_Type)
+#endif
+#define __Pyx_TypeCheck(obj, type) PyObject_TypeCheck(obj, (PyTypeObject *)type)
+#if PY_MAJOR_VERSION >= 3
+  #define PyIntObject                  PyLongObject
+  #define PyInt_Type                   PyLong_Type
+  #define PyInt_Check(op)              PyLong_Check(op)
+  #define PyInt_CheckExact(op)         PyLong_CheckExact(op)
+  #define PyInt_FromString             PyLong_FromString
+  #define PyInt_FromUnicode            PyLong_FromUnicode
+  #define PyInt_FromLong               PyLong_FromLong
+  #define PyInt_FromSize_t             PyLong_FromSize_t
+  #define PyInt_FromSsize_t            PyLong_FromSsize_t
+  #define PyInt_AsLong                 PyLong_AsLong
+  #define PyInt_AS_LONG                PyLong_AS_LONG
+  #define PyInt_AsSsize_t              PyLong_AsSsize_t
+  #define PyInt_AsUnsignedLongMask     PyLong_AsUnsignedLongMask
+  #define PyInt_AsUnsignedLongLongMask PyLong_AsUnsignedLongLongMask
+  #define PyNumber_Int                 PyNumber_Long
+#endif
+#if PY_MAJOR_VERSION >= 3
+  #define PyBoolObject                 PyLongObject
+#endif
+#if PY_MAJOR_VERSION >= 3 && CYTHON_COMPILING_IN_PYPY
+  #ifndef PyUnicode_InternFromString
+    #define PyUnicode_InternFromString(s) PyUnicode_FromString(s)
+  #endif
+#endif
+#if PY_VERSION_HEX < 0x030200A4
+  typedef long Py_hash_t;
+  #define __Pyx_PyInt_FromHash_t PyInt_FromLong
+  #define __Pyx_PyInt_AsHash_t   PyInt_AsLong
+#else
+  #define __Pyx_PyInt_FromHash_t PyInt_FromSsize_t
+  #define __Pyx_PyInt_AsHash_t   PyInt_AsSsize_t
+#endif
+#if PY_MAJOR_VERSION >= 3
+  #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : PyInstanceMethod_New(func))
+#else
+  #define __Pyx_PyMethod_New(func, self, klass) PyMethod_New(func, self, klass)
+#endif
+#if PY_VERSION_HEX >= 0x030500B1
+#define __Pyx_PyAsyncMethodsStruct PyAsyncMethods
+#define __Pyx_PyType_AsAsync(obj) (Py_TYPE(obj)->tp_as_async)
+#elif CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
+typedef struct {
+    unaryfunc am_await;
+    unaryfunc am_aiter;
+    unaryfunc am_anext;
+} __Pyx_PyAsyncMethodsStruct;
+#define __Pyx_PyType_AsAsync(obj) ((__Pyx_PyAsyncMethodsStruct*) (Py_TYPE(obj)->tp_reserved))
+#else
+#define __Pyx_PyType_AsAsync(obj) NULL
+#endif
+#ifndef CYTHON_RESTRICT
+  #if defined(__GNUC__)
+    #define CYTHON_RESTRICT __restrict__
+  #elif defined(_MSC_VER) && _MSC_VER >= 1400
+    #define CYTHON_RESTRICT __restrict
+  #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+    #define CYTHON_RESTRICT restrict
+  #else
+    #define CYTHON_RESTRICT
+  #endif
+#endif
+#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None)
+
+#ifndef __cplusplus
+  #error "Cython files generated with the C++ option must be compiled with a C++ compiler."
+#endif
+#ifndef CYTHON_INLINE
+  #define CYTHON_INLINE inline
+#endif
+template<typename T>
+void __Pyx_call_destructor(T& x) {
+    x.~T();
+}
+template<typename T>
+class __Pyx_FakeReference {
+  public:
+    __Pyx_FakeReference() : ptr(NULL) { }
+    __Pyx_FakeReference(const T& ref) : ptr(const_cast<T*>(&ref)) { }
+    T *operator->() { return ptr; }
+    operator T&() { return *ptr; }
+  private:
+    T *ptr;
+};
+
+#if defined(WIN32) || defined(MS_WINDOWS)
+  #define _USE_MATH_DEFINES
+#endif
+#include <math.h>
+#ifdef NAN
+#define __PYX_NAN() ((float) NAN)
+#else
+static CYTHON_INLINE float __PYX_NAN() {
+  float value;
+  memset(&value, 0xFF, sizeof(value));
+  return value;
+}
+#endif
+
+
+#if PY_MAJOR_VERSION >= 3
+  #define __Pyx_PyNumber_Divide(x,y)         PyNumber_TrueDivide(x,y)
+  #define __Pyx_PyNumber_InPlaceDivide(x,y)  PyNumber_InPlaceTrueDivide(x,y)
+#else
+  #define __Pyx_PyNumber_Divide(x,y)         PyNumber_Divide(x,y)
+  #define __Pyx_PyNumber_InPlaceDivide(x,y)  PyNumber_InPlaceDivide(x,y)
+#endif
+
+#ifndef __PYX_EXTERN_C
+  #ifdef __cplusplus
+    #define __PYX_EXTERN_C extern "C"
+  #else
+    #define __PYX_EXTERN_C extern
+  #endif
+#endif
+
+#define __PYX_HAVE__ot__emd__emd
+#define __PYX_HAVE_API__ot__emd__emd
+#include "string.h"
+#include "stdio.h"
+#include "stdlib.h"
+#include "numpy/arrayobject.h"
+#include "numpy/ufuncobject.h"
+#include "EMD.h"
+#ifdef _OPENMP
+#include <omp.h>
+#endif /* _OPENMP */
+
+#ifdef PYREX_WITHOUT_ASSERTIONS
+#define CYTHON_WITHOUT_ASSERTIONS
+#endif
+
+#ifndef CYTHON_UNUSED
+# if defined(__GNUC__)
+#   if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4))
+#     define CYTHON_UNUSED __attribute__ ((__unused__))
+#   else
+#     define CYTHON_UNUSED
+#   endif
+# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER))
+#   define CYTHON_UNUSED __attribute__ ((__unused__))
+# else
+#   define CYTHON_UNUSED
+# endif
+#endif
+#ifndef CYTHON_NCP_UNUSED
+# if CYTHON_COMPILING_IN_CPYTHON
+#  define CYTHON_NCP_UNUSED
+# else
+#  define CYTHON_NCP_UNUSED CYTHON_UNUSED
+# endif
+#endif
+typedef struct {PyObject **p; char *s; const Py_ssize_t n; const char* encoding;
+                const char is_unicode; const char is_str; const char intern; } __Pyx_StringTabEntry;
+
+#define __PYX_DEFAULT_STRING_ENCODING_IS_ASCII 0
+#define __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT 0
+#define __PYX_DEFAULT_STRING_ENCODING ""
+#define __Pyx_PyObject_FromString __Pyx_PyBytes_FromString
+#define __Pyx_PyObject_FromStringAndSize __Pyx_PyBytes_FromStringAndSize
+#define __Pyx_uchar_cast(c) ((unsigned char)c)
+#define __Pyx_long_cast(x) ((long)x)
+#define __Pyx_fits_Py_ssize_t(v, type, is_signed)  (\
+    (sizeof(type) < sizeof(Py_ssize_t))  ||\
+    (sizeof(type) > sizeof(Py_ssize_t) &&\
+          likely(v < (type)PY_SSIZE_T_MAX ||\
+                 v == (type)PY_SSIZE_T_MAX)  &&\
+          (!is_signed || likely(v > (type)PY_SSIZE_T_MIN ||\
+                                v == (type)PY_SSIZE_T_MIN)))  ||\
+    (sizeof(type) == sizeof(Py_ssize_t) &&\
+          (is_signed || likely(v < (type)PY_SSIZE_T_MAX ||\
+                               v == (type)PY_SSIZE_T_MAX)))  )
+#if defined (__cplusplus) && __cplusplus >= 201103L
+    #include <cstdlib>
+    #define __Pyx_sst_abs(value) std::abs(value)
+#elif SIZEOF_INT >= SIZEOF_SIZE_T
+    #define __Pyx_sst_abs(value) abs(value)
+#elif SIZEOF_LONG >= SIZEOF_SIZE_T
+    #define __Pyx_sst_abs(value) labs(value)
+#elif defined (_MSC_VER) && defined (_M_X64)
+    #define __Pyx_sst_abs(value) _abs64(value)
+#elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+    #define __Pyx_sst_abs(value) llabs(value)
+#elif defined (__GNUC__)
+    #define __Pyx_sst_abs(value) __builtin_llabs(value)
+#else
+    #define __Pyx_sst_abs(value) ((value<0) ? -value : value)
+#endif
+static CYTHON_INLINE char* __Pyx_PyObject_AsString(PyObject*);
+static CYTHON_INLINE char* __Pyx_PyObject_AsStringAndSize(PyObject*, Py_ssize_t* length);
+#define __Pyx_PyByteArray_FromString(s) PyByteArray_FromStringAndSize((const char*)s, strlen((const char*)s))
+#define __Pyx_PyByteArray_FromStringAndSize(s, l) PyByteArray_FromStringAndSize((const char*)s, l)
+#define __Pyx_PyBytes_FromString        PyBytes_FromString
+#define __Pyx_PyBytes_FromStringAndSize PyBytes_FromStringAndSize
+static CYTHON_INLINE PyObject* __Pyx_PyUnicode_FromString(const char*);
+#if PY_MAJOR_VERSION < 3
+    #define __Pyx_PyStr_FromString        __Pyx_PyBytes_FromString
+    #define __Pyx_PyStr_FromStringAndSize __Pyx_PyBytes_FromStringAndSize
+#else
+    #define __Pyx_PyStr_FromString        __Pyx_PyUnicode_FromString
+    #define __Pyx_PyStr_FromStringAndSize __Pyx_PyUnicode_FromStringAndSize
+#endif
+#define __Pyx_PyObject_AsSString(s)    ((signed char*) __Pyx_PyObject_AsString(s))
+#define __Pyx_PyObject_AsUString(s)    ((unsigned char*) __Pyx_PyObject_AsString(s))
+#define __Pyx_PyObject_FromCString(s)  __Pyx_PyObject_FromString((const char*)s)
+#define __Pyx_PyBytes_FromCString(s)   __Pyx_PyBytes_FromString((const char*)s)
+#define __Pyx_PyByteArray_FromCString(s)   __Pyx_PyByteArray_FromString((const char*)s)
+#define __Pyx_PyStr_FromCString(s)     __Pyx_PyStr_FromString((const char*)s)
+#define __Pyx_PyUnicode_FromCString(s) __Pyx_PyUnicode_FromString((const char*)s)
+#if PY_MAJOR_VERSION < 3
+static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const Py_UNICODE *u)
+{
+    const Py_UNICODE *u_end = u;
+    while (*u_end++) ;
+    return (size_t)(u_end - u - 1);
+}
+#else
+#define __Pyx_Py_UNICODE_strlen Py_UNICODE_strlen
+#endif
+#define __Pyx_PyUnicode_FromUnicode(u)       PyUnicode_FromUnicode(u, __Pyx_Py_UNICODE_strlen(u))
+#define __Pyx_PyUnicode_FromUnicodeAndLength PyUnicode_FromUnicode
+#define __Pyx_PyUnicode_AsUnicode            PyUnicode_AsUnicode
+#define __Pyx_NewRef(obj) (Py_INCREF(obj), obj)
+#define __Pyx_Owned_Py_None(b) __Pyx_NewRef(Py_None)
+#define __Pyx_PyBool_FromLong(b) ((b) ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False))
+static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject*);
+static CYTHON_INLINE PyObject* __Pyx_PyNumber_Int(PyObject* x);
+static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject*);
+static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t);
+#if CYTHON_COMPILING_IN_CPYTHON
+#define __pyx_PyFloat_AsDouble(x) (PyFloat_CheckExact(x) ? PyFloat_AS_DOUBLE(x) : PyFloat_AsDouble(x))
+#else
+#define __pyx_PyFloat_AsDouble(x) PyFloat_AsDouble(x)
+#endif
+#define __pyx_PyFloat_AsFloat(x) ((float) __pyx_PyFloat_AsDouble(x))
+#if PY_MAJOR_VERSION < 3 && __PYX_DEFAULT_STRING_ENCODING_IS_ASCII
+static int __Pyx_sys_getdefaultencoding_not_ascii;
+static int __Pyx_init_sys_getdefaultencoding_params(void) {
+    PyObject* sys;
+    PyObject* default_encoding = NULL;
+    PyObject* ascii_chars_u = NULL;
+    PyObject* ascii_chars_b = NULL;
+    const char* default_encoding_c;
+    sys = PyImport_ImportModule("sys");
+    if (!sys) goto bad;
+    default_encoding = PyObject_CallMethod(sys, (char*) "getdefaultencoding", NULL);
+    Py_DECREF(sys);
+    if (!default_encoding) goto bad;
+    default_encoding_c = PyBytes_AsString(default_encoding);
+    if (!default_encoding_c) goto bad;
+    if (strcmp(default_encoding_c, "ascii") == 0) {
+        __Pyx_sys_getdefaultencoding_not_ascii = 0;
+    } else {
+        char ascii_chars[128];
+        int c;
+        for (c = 0; c < 128; c++) {
+            ascii_chars[c] = c;
+        }
+        __Pyx_sys_getdefaultencoding_not_ascii = 1;
+        ascii_chars_u = PyUnicode_DecodeASCII(ascii_chars, 128, NULL);
+        if (!ascii_chars_u) goto bad;
+        ascii_chars_b = PyUnicode_AsEncodedString(ascii_chars_u, default_encoding_c, NULL);
+        if (!ascii_chars_b || !PyBytes_Check(ascii_chars_b) || memcmp(ascii_chars, PyBytes_AS_STRING(ascii_chars_b), 128) != 0) {
+            PyErr_Format(
+                PyExc_ValueError,
+                "This module compiled with c_string_encoding=ascii, but default encoding '%.200s' is not a superset of ascii.",
+                default_encoding_c);
+            goto bad;
+        }
+        Py_DECREF(ascii_chars_u);
+        Py_DECREF(ascii_chars_b);
+    }
+    Py_DECREF(default_encoding);
+    return 0;
+bad:
+    Py_XDECREF(default_encoding);
+    Py_XDECREF(ascii_chars_u);
+    Py_XDECREF(ascii_chars_b);
+    return -1;
+}
+#endif
+#if __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT && PY_MAJOR_VERSION >= 3
+#define __Pyx_PyUnicode_FromStringAndSize(c_str, size) PyUnicode_DecodeUTF8(c_str, size, NULL)
+#else
+#define __Pyx_PyUnicode_FromStringAndSize(c_str, size) PyUnicode_Decode(c_str, size, __PYX_DEFAULT_STRING_ENCODING, NULL)
+#if __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT
+static char* __PYX_DEFAULT_STRING_ENCODING;
+static int __Pyx_init_sys_getdefaultencoding_params(void) {
+    PyObject* sys;
+    PyObject* default_encoding = NULL;
+    char* default_encoding_c;
+    sys = PyImport_ImportModule("sys");
+    if (!sys) goto bad;
+    default_encoding = PyObject_CallMethod(sys, (char*) (const char*) "getdefaultencoding", NULL);
+    Py_DECREF(sys);
+    if (!default_encoding) goto bad;
+    default_encoding_c = PyBytes_AsString(default_encoding);
+    if (!default_encoding_c) goto bad;
+    __PYX_DEFAULT_STRING_ENCODING = (char*) malloc(strlen(default_encoding_c));
+    if (!__PYX_DEFAULT_STRING_ENCODING) goto bad;
+    strcpy(__PYX_DEFAULT_STRING_ENCODING, default_encoding_c);
+    Py_DECREF(default_encoding);
+    return 0;
+bad:
+    Py_XDECREF(default_encoding);
+    return -1;
+}
+#endif
+#endif
+
+
+/* Test for GCC > 2.95 */
+#if defined(__GNUC__)     && (__GNUC__ > 2 || (__GNUC__ == 2 && (__GNUC_MINOR__ > 95)))
+  #define likely(x)   __builtin_expect(!!(x), 1)
+  #define unlikely(x) __builtin_expect(!!(x), 0)
+#else /* !__GNUC__ or GCC < 2.95 */
+  #define likely(x)   (x)
+  #define unlikely(x) (x)
+#endif /* __GNUC__ */
+
+static PyObject *__pyx_m;
+static PyObject *__pyx_d;
+static PyObject *__pyx_b;
+static PyObject *__pyx_empty_tuple;
+static PyObject *__pyx_empty_bytes;
+static int __pyx_lineno;
+static int __pyx_clineno = 0;
+static const char * __pyx_cfilenm= __FILE__;
+static const char *__pyx_filename;
+
+#if !defined(CYTHON_CCOMPLEX)
+  #if defined(__cplusplus)
+    #define CYTHON_CCOMPLEX 1
+  #elif defined(_Complex_I)
+    #define CYTHON_CCOMPLEX 1
+  #else
+    #define CYTHON_CCOMPLEX 0
+  #endif
+#endif
+#if CYTHON_CCOMPLEX
+  #ifdef __cplusplus
+    #include <complex>
+  #else
+    #include <complex.h>
+  #endif
+#endif
+#if CYTHON_CCOMPLEX && !defined(__cplusplus) && defined(__sun__) && defined(__GNUC__)
+  #undef _Complex_I
+  #define _Complex_I 1.0fj
+#endif
+
+
+static const char *__pyx_f[] = {
+  "ot/emd/emd.pyx",
+  "__init__.pxd",
+  "type.pxd",
+};
+#define IS_UNSIGNED(type) (((type) -1) > 0)
+struct __Pyx_StructField_;
+#define __PYX_BUF_FLAGS_PACKED_STRUCT (1 << 0)
+typedef struct {
+  const char* name;
+  struct __Pyx_StructField_* fields;
+  size_t size;
+  size_t arraysize[8];
+  int ndim;
+  char typegroup;
+  char is_unsigned;
+  int flags;
+} __Pyx_TypeInfo;
+typedef struct __Pyx_StructField_ {
+  __Pyx_TypeInfo* type;
+  const char* name;
+  size_t offset;
+} __Pyx_StructField;
+typedef struct {
+  __Pyx_StructField* field;
+  size_t parent_offset;
+} __Pyx_BufFmt_StackElem;
+typedef struct {
+  __Pyx_StructField root;
+  __Pyx_BufFmt_StackElem* head;
+  size_t fmt_offset;
+  size_t new_count, enc_count;
+  size_t struct_alignment;
+  int is_complex;
+  char enc_type;
+  char new_packmode;
+  char enc_packmode;
+  char is_valid_array;
+} __Pyx_BufFmt_Context;
+
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":725
+ * # in Cython to enable them only on the right systems.
+ * 
+ * ctypedef npy_int8       int8_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_int16      int16_t
+ * ctypedef npy_int32      int32_t
+ */
+typedef npy_int8 __pyx_t_5numpy_int8_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":726
+ * 
+ * ctypedef npy_int8       int8_t
+ * ctypedef npy_int16      int16_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_int32      int32_t
+ * ctypedef npy_int64      int64_t
+ */
+typedef npy_int16 __pyx_t_5numpy_int16_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":727
+ * ctypedef npy_int8       int8_t
+ * ctypedef npy_int16      int16_t
+ * ctypedef npy_int32      int32_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_int64      int64_t
+ * #ctypedef npy_int96      int96_t
+ */
+typedef npy_int32 __pyx_t_5numpy_int32_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":728
+ * ctypedef npy_int16      int16_t
+ * ctypedef npy_int32      int32_t
+ * ctypedef npy_int64      int64_t             # <<<<<<<<<<<<<<
+ * #ctypedef npy_int96      int96_t
+ * #ctypedef npy_int128     int128_t
+ */
+typedef npy_int64 __pyx_t_5numpy_int64_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":732
+ * #ctypedef npy_int128     int128_t
+ * 
+ * ctypedef npy_uint8      uint8_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_uint16     uint16_t
+ * ctypedef npy_uint32     uint32_t
+ */
+typedef npy_uint8 __pyx_t_5numpy_uint8_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":733
+ * 
+ * ctypedef npy_uint8      uint8_t
+ * ctypedef npy_uint16     uint16_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_uint32     uint32_t
+ * ctypedef npy_uint64     uint64_t
+ */
+typedef npy_uint16 __pyx_t_5numpy_uint16_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":734
+ * ctypedef npy_uint8      uint8_t
+ * ctypedef npy_uint16     uint16_t
+ * ctypedef npy_uint32     uint32_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_uint64     uint64_t
+ * #ctypedef npy_uint96     uint96_t
+ */
+typedef npy_uint32 __pyx_t_5numpy_uint32_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":735
+ * ctypedef npy_uint16     uint16_t
+ * ctypedef npy_uint32     uint32_t
+ * ctypedef npy_uint64     uint64_t             # <<<<<<<<<<<<<<
+ * #ctypedef npy_uint96     uint96_t
+ * #ctypedef npy_uint128    uint128_t
+ */
+typedef npy_uint64 __pyx_t_5numpy_uint64_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":739
+ * #ctypedef npy_uint128    uint128_t
+ * 
+ * ctypedef npy_float32    float32_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_float64    float64_t
+ * #ctypedef npy_float80    float80_t
+ */
+typedef npy_float32 __pyx_t_5numpy_float32_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":740
+ * 
+ * ctypedef npy_float32    float32_t
+ * ctypedef npy_float64    float64_t             # <<<<<<<<<<<<<<
+ * #ctypedef npy_float80    float80_t
+ * #ctypedef npy_float128   float128_t
+ */
+typedef npy_float64 __pyx_t_5numpy_float64_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":749
+ * # The int types are mapped a bit surprising --
+ * # numpy.int corresponds to 'l' and numpy.long to 'q'
+ * ctypedef npy_long       int_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_longlong   long_t
+ * ctypedef npy_longlong   longlong_t
+ */
+typedef npy_long __pyx_t_5numpy_int_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":750
+ * # numpy.int corresponds to 'l' and numpy.long to 'q'
+ * ctypedef npy_long       int_t
+ * ctypedef npy_longlong   long_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_longlong   longlong_t
+ * 
+ */
+typedef npy_longlong __pyx_t_5numpy_long_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":751
+ * ctypedef npy_long       int_t
+ * ctypedef npy_longlong   long_t
+ * ctypedef npy_longlong   longlong_t             # <<<<<<<<<<<<<<
+ * 
+ * ctypedef npy_ulong      uint_t
+ */
+typedef npy_longlong __pyx_t_5numpy_longlong_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":753
+ * ctypedef npy_longlong   longlong_t
+ * 
+ * ctypedef npy_ulong      uint_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_ulonglong  ulong_t
+ * ctypedef npy_ulonglong  ulonglong_t
+ */
+typedef npy_ulong __pyx_t_5numpy_uint_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":754
+ * 
+ * ctypedef npy_ulong      uint_t
+ * ctypedef npy_ulonglong  ulong_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_ulonglong  ulonglong_t
+ * 
+ */
+typedef npy_ulonglong __pyx_t_5numpy_ulong_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":755
+ * ctypedef npy_ulong      uint_t
+ * ctypedef npy_ulonglong  ulong_t
+ * ctypedef npy_ulonglong  ulonglong_t             # <<<<<<<<<<<<<<
+ * 
+ * ctypedef npy_intp       intp_t
+ */
+typedef npy_ulonglong __pyx_t_5numpy_ulonglong_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":757
+ * ctypedef npy_ulonglong  ulonglong_t
+ * 
+ * ctypedef npy_intp       intp_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_uintp      uintp_t
+ * 
+ */
+typedef npy_intp __pyx_t_5numpy_intp_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":758
+ * 
+ * ctypedef npy_intp       intp_t
+ * ctypedef npy_uintp      uintp_t             # <<<<<<<<<<<<<<
+ * 
+ * ctypedef npy_double     float_t
+ */
+typedef npy_uintp __pyx_t_5numpy_uintp_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":760
+ * ctypedef npy_uintp      uintp_t
+ * 
+ * ctypedef npy_double     float_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_double     double_t
+ * ctypedef npy_longdouble longdouble_t
+ */
+typedef npy_double __pyx_t_5numpy_float_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":761
+ * 
+ * ctypedef npy_double     float_t
+ * ctypedef npy_double     double_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_longdouble longdouble_t
+ * 
+ */
+typedef npy_double __pyx_t_5numpy_double_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":762
+ * ctypedef npy_double     float_t
+ * ctypedef npy_double     double_t
+ * ctypedef npy_longdouble longdouble_t             # <<<<<<<<<<<<<<
+ * 
+ * ctypedef npy_cfloat      cfloat_t
+ */
+typedef npy_longdouble __pyx_t_5numpy_longdouble_t;
+#if CYTHON_CCOMPLEX
+  #ifdef __cplusplus
+    typedef ::std::complex< float > __pyx_t_float_complex;
+  #else
+    typedef float _Complex __pyx_t_float_complex;
+  #endif
+#else
+    typedef struct { float real, imag; } __pyx_t_float_complex;
+#endif
+
+#if CYTHON_CCOMPLEX
+  #ifdef __cplusplus
+    typedef ::std::complex< double > __pyx_t_double_complex;
+  #else
+    typedef double _Complex __pyx_t_double_complex;
+  #endif
+#else
+    typedef struct { double real, imag; } __pyx_t_double_complex;
+#endif
+
+
+/*--- Type declarations ---*/
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":764
+ * ctypedef npy_longdouble longdouble_t
+ * 
+ * ctypedef npy_cfloat      cfloat_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_cdouble     cdouble_t
+ * ctypedef npy_clongdouble clongdouble_t
+ */
+typedef npy_cfloat __pyx_t_5numpy_cfloat_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":765
+ * 
+ * ctypedef npy_cfloat      cfloat_t
+ * ctypedef npy_cdouble     cdouble_t             # <<<<<<<<<<<<<<
+ * ctypedef npy_clongdouble clongdouble_t
+ * 
+ */
+typedef npy_cdouble __pyx_t_5numpy_cdouble_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":766
+ * ctypedef npy_cfloat      cfloat_t
+ * ctypedef npy_cdouble     cdouble_t
+ * ctypedef npy_clongdouble clongdouble_t             # <<<<<<<<<<<<<<
+ * 
+ * ctypedef npy_cdouble     complex_t
+ */
+typedef npy_clongdouble __pyx_t_5numpy_clongdouble_t;
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":768
+ * ctypedef npy_clongdouble clongdouble_t
+ * 
+ * ctypedef npy_cdouble     complex_t             # <<<<<<<<<<<<<<
+ * 
+ * cdef inline object PyArray_MultiIterNew1(a):
+ */
+typedef npy_cdouble __pyx_t_5numpy_complex_t;
+
+/* --- Runtime support code (head) --- */
+#ifndef CYTHON_REFNANNY
+  #define CYTHON_REFNANNY 0
+#endif
+#if CYTHON_REFNANNY
+  typedef struct {
+    void (*INCREF)(void*, PyObject*, int);
+    void (*DECREF)(void*, PyObject*, int);
+    void (*GOTREF)(void*, PyObject*, int);
+    void (*GIVEREF)(void*, PyObject*, int);
+    void* (*SetupContext)(const char*, int, const char*);
+    void (*FinishContext)(void**);
+  } __Pyx_RefNannyAPIStruct;
+  static __Pyx_RefNannyAPIStruct *__Pyx_RefNanny = NULL;
+  static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname);
+  #define __Pyx_RefNannyDeclarations void *__pyx_refnanny = NULL;
+#ifdef WITH_THREAD
+  #define __Pyx_RefNannySetupContext(name, acquire_gil)\
+          if (acquire_gil) {\
+              PyGILState_STATE __pyx_gilstate_save = PyGILState_Ensure();\
+              __pyx_refnanny = __Pyx_RefNanny->SetupContext((name), __LINE__, __FILE__);\
+              PyGILState_Release(__pyx_gilstate_save);\
+          } else {\
+              __pyx_refnanny = __Pyx_RefNanny->SetupContext((name), __LINE__, __FILE__);\
+          }
+#else
+  #define __Pyx_RefNannySetupContext(name, acquire_gil)\
+          __pyx_refnanny = __Pyx_RefNanny->SetupContext((name), __LINE__, __FILE__)
+#endif
+  #define __Pyx_RefNannyFinishContext()\
+          __Pyx_RefNanny->FinishContext(&__pyx_refnanny)
+  #define __Pyx_INCREF(r)  __Pyx_RefNanny->INCREF(__pyx_refnanny, (PyObject *)(r), __LINE__)
+  #define __Pyx_DECREF(r)  __Pyx_RefNanny->DECREF(__pyx_refnanny, (PyObject *)(r), __LINE__)
+  #define __Pyx_GOTREF(r)  __Pyx_RefNanny->GOTREF(__pyx_refnanny, (PyObject *)(r), __LINE__)
+  #define __Pyx_GIVEREF(r) __Pyx_RefNanny->GIVEREF(__pyx_refnanny, (PyObject *)(r), __LINE__)
+  #define __Pyx_XINCREF(r)  do { if((r) != NULL) {__Pyx_INCREF(r); }} while(0)
+  #define __Pyx_XDECREF(r)  do { if((r) != NULL) {__Pyx_DECREF(r); }} while(0)
+  #define __Pyx_XGOTREF(r)  do { if((r) != NULL) {__Pyx_GOTREF(r); }} while(0)
+  #define __Pyx_XGIVEREF(r) do { if((r) != NULL) {__Pyx_GIVEREF(r);}} while(0)
+#else
+  #define __Pyx_RefNannyDeclarations
+  #define __Pyx_RefNannySetupContext(name, acquire_gil)
+  #define __Pyx_RefNannyFinishContext()
+  #define __Pyx_INCREF(r) Py_INCREF(r)
+  #define __Pyx_DECREF(r) Py_DECREF(r)
+  #define __Pyx_GOTREF(r)
+  #define __Pyx_GIVEREF(r)
+  #define __Pyx_XINCREF(r) Py_XINCREF(r)
+  #define __Pyx_XDECREF(r) Py_XDECREF(r)
+  #define __Pyx_XGOTREF(r)
+  #define __Pyx_XGIVEREF(r)
+#endif
+#define __Pyx_XDECREF_SET(r, v) do {\
+        PyObject *tmp = (PyObject *) r;\
+        r = v; __Pyx_XDECREF(tmp);\
+    } while (0)
+#define __Pyx_DECREF_SET(r, v) do {\
+        PyObject *tmp = (PyObject *) r;\
+        r = v; __Pyx_DECREF(tmp);\
+    } while (0)
+#define __Pyx_CLEAR(r)    do { PyObject* tmp = ((PyObject*)(r)); r = NULL; __Pyx_DECREF(tmp);} while(0)
+#define __Pyx_XCLEAR(r)   do { if((r) != NULL) {PyObject* tmp = ((PyObject*)(r)); r = NULL; __Pyx_DECREF(tmp);}} while(0)
+
+static void __Pyx_RaiseArgtupleInvalid(const char* func_name, int exact,
+    Py_ssize_t num_min, Py_ssize_t num_max, Py_ssize_t num_found);
+
+static void __Pyx_RaiseDoubleKeywordsError(const char* func_name, PyObject* kw_name);
+
+static int __Pyx_ParseOptionalKeywords(PyObject *kwds, PyObject **argnames[],\
+    PyObject *kwds2, PyObject *values[], Py_ssize_t num_pos_args,\
+    const char* function_name);
+
+static CYTHON_INLINE int __Pyx_ArgTypeTest(PyObject *obj, PyTypeObject *type, int none_allowed,
+    const char *name, int exact);
+
+static CYTHON_INLINE int  __Pyx_GetBufferAndValidate(Py_buffer* buf, PyObject* obj,
+    __Pyx_TypeInfo* dtype, int flags, int nd, int cast, __Pyx_BufFmt_StackElem* stack);
+static CYTHON_INLINE void __Pyx_SafeReleaseBuffer(Py_buffer* info);
+
+#if CYTHON_COMPILING_IN_CPYTHON
+static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) {
+    PyTypeObject* tp = Py_TYPE(obj);
+    if (likely(tp->tp_getattro))
+        return tp->tp_getattro(obj, attr_name);
+#if PY_MAJOR_VERSION < 3
+    if (likely(tp->tp_getattr))
+        return tp->tp_getattr(obj, PyString_AS_STRING(attr_name));
+#endif
+    return PyObject_GetAttr(obj, attr_name);
+}
+#else
+#define __Pyx_PyObject_GetAttrStr(o,n) PyObject_GetAttr(o,n)
+#endif
+
+static PyObject *__Pyx_GetBuiltinName(PyObject *name);
+
+static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name);
+
+#if CYTHON_COMPILING_IN_CPYTHON
+static CYTHON_INLINE PyObject* __Pyx_PyObject_Call(PyObject *func, PyObject *arg, PyObject *kw);
+#else
+#define __Pyx_PyObject_Call(func, arg, kw) PyObject_Call(func, arg, kw)
+#endif
+
+#if CYTHON_COMPILING_IN_CPYTHON
+static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg);
+#endif
+
+static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg);
+
+static CYTHON_INLINE int __Pyx_TypeTest(PyObject *obj, PyTypeObject *type);
+
+static void __Pyx_RaiseBufferFallbackError(void);
+
+static CYTHON_INLINE void __Pyx_ErrRestore(PyObject *type, PyObject *value, PyObject *tb);
+static CYTHON_INLINE void __Pyx_ErrFetch(PyObject **type, PyObject **value, PyObject **tb);
+
+static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause);
+
+#if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY
+static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key) {
+    PyObject *value;
+    value = PyDict_GetItemWithError(d, key);
+    if (unlikely(!value)) {
+        if (!PyErr_Occurred()) {
+            PyObject* args = PyTuple_Pack(1, key);
+            if (likely(args))
+                PyErr_SetObject(PyExc_KeyError, args);
+            Py_XDECREF(args);
+        }
+        return NULL;
+    }
+    Py_INCREF(value);
+    return value;
+}
+#else
+    #define __Pyx_PyDict_GetItem(d, key) PyObject_GetItem(d, key)
+#endif
+
+static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected);
+
+static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index);
+
+static CYTHON_INLINE void __Pyx_RaiseNoneNotIterableError(void);
+
+static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level);
+
+typedef struct {
+    int code_line;
+    PyCodeObject* code_object;
+} __Pyx_CodeObjectCacheEntry;
+struct __Pyx_CodeObjectCache {
+    int count;
+    int max_count;
+    __Pyx_CodeObjectCacheEntry* entries;
+};
+static struct __Pyx_CodeObjectCache __pyx_code_cache = {0,0,NULL};
+static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line);
+static PyCodeObject *__pyx_find_code_object(int code_line);
+static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object);
+
+static void __Pyx_AddTraceback(const char *funcname, int c_line,
+                               int py_line, const char *filename);
+
+typedef struct {
+  Py_ssize_t shape, strides, suboffsets;
+} __Pyx_Buf_DimInfo;
+typedef struct {
+  size_t refcount;
+  Py_buffer pybuffer;
+} __Pyx_Buffer;
+typedef struct {
+  __Pyx_Buffer *rcbuffer;
+  char *data;
+  __Pyx_Buf_DimInfo diminfo[8];
+} __Pyx_LocalBuf_ND;
+
+#if PY_MAJOR_VERSION < 3
+    static int __Pyx_GetBuffer(PyObject *obj, Py_buffer *view, int flags);
+    static void __Pyx_ReleaseBuffer(Py_buffer *view);
+#else
+    #define __Pyx_GetBuffer PyObject_GetBuffer
+    #define __Pyx_ReleaseBuffer PyBuffer_Release
+#endif
+
+
+static Py_ssize_t __Pyx_zeros[] = {0, 0, 0, 0, 0, 0, 0, 0};
+static Py_ssize_t __Pyx_minusones[] = {-1, -1, -1, -1, -1, -1, -1, -1};
+
+static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value);
+
+#if CYTHON_CCOMPLEX
+  #ifdef __cplusplus
+    #define __Pyx_CREAL(z) ((z).real())
+    #define __Pyx_CIMAG(z) ((z).imag())
+  #else
+    #define __Pyx_CREAL(z) (__real__(z))
+    #define __Pyx_CIMAG(z) (__imag__(z))
+  #endif
+#else
+    #define __Pyx_CREAL(z) ((z).real)
+    #define __Pyx_CIMAG(z) ((z).imag)
+#endif
+#if (defined(_WIN32) || defined(__clang__)) && defined(__cplusplus) && CYTHON_CCOMPLEX
+    #define __Pyx_SET_CREAL(z,x) ((z).real(x))
+    #define __Pyx_SET_CIMAG(z,y) ((z).imag(y))
+#else
+    #define __Pyx_SET_CREAL(z,x) __Pyx_CREAL(z) = (x)
+    #define __Pyx_SET_CIMAG(z,y) __Pyx_CIMAG(z) = (y)
+#endif
+
+static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float, float);
+
+#if CYTHON_CCOMPLEX
+    #define __Pyx_c_eqf(a, b)   ((a)==(b))
+    #define __Pyx_c_sumf(a, b)  ((a)+(b))
+    #define __Pyx_c_difff(a, b) ((a)-(b))
+    #define __Pyx_c_prodf(a, b) ((a)*(b))
+    #define __Pyx_c_quotf(a, b) ((a)/(b))
+    #define __Pyx_c_negf(a)     (-(a))
+  #ifdef __cplusplus
+    #define __Pyx_c_is_zerof(z) ((z)==(float)0)
+    #define __Pyx_c_conjf(z)    (::std::conj(z))
+    #if 1
+        #define __Pyx_c_absf(z)     (::std::abs(z))
+        #define __Pyx_c_powf(a, b)  (::std::pow(a, b))
+    #endif
+  #else
+    #define __Pyx_c_is_zerof(z) ((z)==0)
+    #define __Pyx_c_conjf(z)    (conjf(z))
+    #if 1
+        #define __Pyx_c_absf(z)     (cabsf(z))
+        #define __Pyx_c_powf(a, b)  (cpowf(a, b))
+    #endif
+ #endif
+#else
+    static CYTHON_INLINE int __Pyx_c_eqf(__pyx_t_float_complex, __pyx_t_float_complex);
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_sumf(__pyx_t_float_complex, __pyx_t_float_complex);
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_difff(__pyx_t_float_complex, __pyx_t_float_complex);
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_prodf(__pyx_t_float_complex, __pyx_t_float_complex);
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_quotf(__pyx_t_float_complex, __pyx_t_float_complex);
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_negf(__pyx_t_float_complex);
+    static CYTHON_INLINE int __Pyx_c_is_zerof(__pyx_t_float_complex);
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_conjf(__pyx_t_float_complex);
+    #if 1
+        static CYTHON_INLINE float __Pyx_c_absf(__pyx_t_float_complex);
+        static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_powf(__pyx_t_float_complex, __pyx_t_float_complex);
+    #endif
+#endif
+
+static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double, double);
+
+#if CYTHON_CCOMPLEX
+    #define __Pyx_c_eq(a, b)   ((a)==(b))
+    #define __Pyx_c_sum(a, b)  ((a)+(b))
+    #define __Pyx_c_diff(a, b) ((a)-(b))
+    #define __Pyx_c_prod(a, b) ((a)*(b))
+    #define __Pyx_c_quot(a, b) ((a)/(b))
+    #define __Pyx_c_neg(a)     (-(a))
+  #ifdef __cplusplus
+    #define __Pyx_c_is_zero(z) ((z)==(double)0)
+    #define __Pyx_c_conj(z)    (::std::conj(z))
+    #if 1
+        #define __Pyx_c_abs(z)     (::std::abs(z))
+        #define __Pyx_c_pow(a, b)  (::std::pow(a, b))
+    #endif
+  #else
+    #define __Pyx_c_is_zero(z) ((z)==0)
+    #define __Pyx_c_conj(z)    (conj(z))
+    #if 1
+        #define __Pyx_c_abs(z)     (cabs(z))
+        #define __Pyx_c_pow(a, b)  (cpow(a, b))
+    #endif
+ #endif
+#else
+    static CYTHON_INLINE int __Pyx_c_eq(__pyx_t_double_complex, __pyx_t_double_complex);
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_sum(__pyx_t_double_complex, __pyx_t_double_complex);
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_diff(__pyx_t_double_complex, __pyx_t_double_complex);
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_prod(__pyx_t_double_complex, __pyx_t_double_complex);
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_quot(__pyx_t_double_complex, __pyx_t_double_complex);
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_neg(__pyx_t_double_complex);
+    static CYTHON_INLINE int __Pyx_c_is_zero(__pyx_t_double_complex);
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_conj(__pyx_t_double_complex);
+    #if 1
+        static CYTHON_INLINE double __Pyx_c_abs(__pyx_t_double_complex);
+        static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_pow(__pyx_t_double_complex, __pyx_t_double_complex);
+    #endif
+#endif
+
+static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *);
+
+static CYTHON_INLINE PyObject* __Pyx_PyInt_From_enum__NPY_TYPES(enum NPY_TYPES value);
+
+static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value);
+
+static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *);
+
+static int __Pyx_check_binary_version(void);
+
+#if !defined(__Pyx_PyIdentifier_FromString)
+#if PY_MAJOR_VERSION < 3
+  #define __Pyx_PyIdentifier_FromString(s) PyString_FromString(s)
+#else
+  #define __Pyx_PyIdentifier_FromString(s) PyUnicode_FromString(s)
+#endif
+#endif
+
+static PyObject *__Pyx_ImportModule(const char *name);
+
+static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class_name, size_t size, int strict);
+
+static int __Pyx_InitStrings(__Pyx_StringTabEntry *t);
+
+
+/* Module declarations from 'cpython.buffer' */
+
+/* Module declarations from 'libc.string' */
+
+/* Module declarations from 'libc.stdio' */
+
+/* Module declarations from '__builtin__' */
+
+/* Module declarations from 'cpython.type' */
+static PyTypeObject *__pyx_ptype_7cpython_4type_type = 0;
+
+/* Module declarations from 'cpython' */
+
+/* Module declarations from 'cpython.object' */
+
+/* Module declarations from 'cpython.ref' */
+
+/* Module declarations from 'libc.stdlib' */
+
+/* Module declarations from 'numpy' */
+
+/* Module declarations from 'numpy' */
+static PyTypeObject *__pyx_ptype_5numpy_dtype = 0;
+static PyTypeObject *__pyx_ptype_5numpy_flatiter = 0;
+static PyTypeObject *__pyx_ptype_5numpy_broadcast = 0;
+static PyTypeObject *__pyx_ptype_5numpy_ndarray = 0;
+static PyTypeObject *__pyx_ptype_5numpy_ufunc = 0;
+static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *, char *, char *, int *); /*proto*/
+
+/* Module declarations from 'cython' */
+
+/* Module declarations from 'ot.emd.emd' */
+static __Pyx_TypeInfo __Pyx_TypeInfo_double = { "double", NULL, sizeof(double), { 0 }, 0, 'R', 0, 0 };
+#define __Pyx_MODULE_NAME "ot.emd.emd"
+int __pyx_module_is_main_ot__emd__emd = 0;
+
+/* Implementation of 'ot.emd.emd' */
+static PyObject *__pyx_builtin_ValueError;
+static PyObject *__pyx_builtin_range;
+static PyObject *__pyx_builtin_RuntimeError;
+static char __pyx_k_B[] = "B";
+static char __pyx_k_G[] = "G";
+static char __pyx_k_H[] = "H";
+static char __pyx_k_I[] = "I";
+static char __pyx_k_L[] = "L";
+static char __pyx_k_M[] = "M";
+static char __pyx_k_O[] = "O";
+static char __pyx_k_Q[] = "Q";
+static char __pyx_k_a[] = "a";
+static char __pyx_k_b[] = "b";
+static char __pyx_k_d[] = "d";
+static char __pyx_k_f[] = "f";
+static char __pyx_k_g[] = "g";
+static char __pyx_k_h[] = "h";
+static char __pyx_k_i[] = "i";
+static char __pyx_k_l[] = "l";
+static char __pyx_k_q[] = "q";
+static char __pyx_k_Zd[] = "Zd";
+static char __pyx_k_Zf[] = "Zf";
+static char __pyx_k_Zg[] = "Zg";
+static char __pyx_k_n1[] = "n1";
+static char __pyx_k_n2[] = "n2";
+static char __pyx_k_np[] = "np";
+static char __pyx_k_emd[] = "emd";
+static char __pyx_k_cost[] = "cost";
+static char __pyx_k_main[] = "__main__";
+static char __pyx_k_ones[] = "ones";
+static char __pyx_k_test[] = "__test__";
+static char __pyx_k_numpy[] = "numpy";
+static char __pyx_k_range[] = "range";
+static char __pyx_k_zeros[] = "zeros";
+static char __pyx_k_import[] = "__import__";
+static char __pyx_k_ValueError[] = "ValueError";
+static char __pyx_k_ot_emd_emd[] = "ot.emd.emd";
+static char __pyx_k_RuntimeError[] = "RuntimeError";
+static char __pyx_k_ndarray_is_not_C_contiguous[] = "ndarray is not C contiguous";
+static char __pyx_k_Created_on_Thu_Sep_11_08_42_08[] = "\nCreated on Thu Sep 11 08:42:08 2014\n\n@author: rflamary\n";
+static char __pyx_k_home_rflamary_PYTHON_POT_ot_emd[] = "/home/rflamary/PYTHON/POT/ot/emd/emd.pyx";
+static char __pyx_k_unknown_dtype_code_in_numpy_pxd[] = "unknown dtype code in numpy.pxd (%d)";
+static char __pyx_k_Format_string_allocated_too_shor[] = "Format string allocated too short, see comment in numpy.pxd";
+static char __pyx_k_Non_native_byte_order_not_suppor[] = "Non-native byte order not supported";
+static char __pyx_k_ndarray_is_not_Fortran_contiguou[] = "ndarray is not Fortran contiguous";
+static char __pyx_k_Format_string_allocated_too_shor_2[] = "Format string allocated too short.";
+static PyObject *__pyx_kp_u_Format_string_allocated_too_shor;
+static PyObject *__pyx_kp_u_Format_string_allocated_too_shor_2;
+static PyObject *__pyx_n_s_G;
+static PyObject *__pyx_n_s_M;
+static PyObject *__pyx_kp_u_Non_native_byte_order_not_suppor;
+static PyObject *__pyx_n_s_RuntimeError;
+static PyObject *__pyx_n_s_ValueError;
+static PyObject *__pyx_n_s_a;
+static PyObject *__pyx_n_s_b;
+static PyObject *__pyx_n_s_cost;
+static PyObject *__pyx_n_s_emd;
+static PyObject *__pyx_kp_s_home_rflamary_PYTHON_POT_ot_emd;
+static PyObject *__pyx_n_s_import;
+static PyObject *__pyx_n_s_main;
+static PyObject *__pyx_n_s_n1;
+static PyObject *__pyx_n_s_n2;
+static PyObject *__pyx_kp_u_ndarray_is_not_C_contiguous;
+static PyObject *__pyx_kp_u_ndarray_is_not_Fortran_contiguou;
+static PyObject *__pyx_n_s_np;
+static PyObject *__pyx_n_s_numpy;
+static PyObject *__pyx_n_s_ones;
+static PyObject *__pyx_n_s_ot_emd_emd;
+static PyObject *__pyx_n_s_range;
+static PyObject *__pyx_n_s_test;
+static PyObject *__pyx_kp_u_unknown_dtype_code_in_numpy_pxd;
+static PyObject *__pyx_n_s_zeros;
+static PyObject *__pyx_pf_2ot_3emd_3emd_emd(CYTHON_UNUSED PyObject *__pyx_self, PyArrayObject *__pyx_v_a, PyArrayObject *__pyx_v_b, PyArrayObject *__pyx_v_M); /* proto */
+static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, Py_buffer *__pyx_v_info, int __pyx_v_flags); /* proto */
+static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_self, Py_buffer *__pyx_v_info); /* proto */
+static PyObject *__pyx_tuple_;
+static PyObject *__pyx_tuple__2;
+static PyObject *__pyx_tuple__3;
+static PyObject *__pyx_tuple__4;
+static PyObject *__pyx_tuple__5;
+static PyObject *__pyx_tuple__6;
+static PyObject *__pyx_tuple__7;
+static PyObject *__pyx_codeobj__8;
+
+/* "ot/emd/emd.pyx":21
+ * @cython.boundscheck(False)
+ * @cython.wraparound(False)
+ * def emd( np.ndarray[double, ndim=1, mode="c"] a,np.ndarray[double, ndim=1, mode="c"]  b,np.ndarray[double, ndim=2, mode="c"]  M):             # <<<<<<<<<<<<<<
+ *     """
+ *         Solves the Earth Movers distance problem and returns the optimal transport matrix
+ */
+
+/* Python wrapper */
+static PyObject *__pyx_pw_2ot_3emd_3emd_1emd(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/
+static char __pyx_doc_2ot_3emd_3emd_emd[] = "\n        Solves the Earth Movers distance problem and returns the optimal transport matrix\n        \n        gamm=emd(a,b,M)\n    \n    .. math::\n        \\gamma = arg\\min_\\gamma <\\gamma,M>_F \n        \n        s.t. \\gamma 1 = a\n        \n             \\gamma^T 1= b \n             \n             \\gamma\\geq 0\n    where :\n    \n    - M is the metric cost matrix\n    - a and b are the sample weights\n             \n    Parameters\n    ----------\n    a : (ns,) ndarray\n        samples in the source domain (uniform waigth if empty)\n    b : (nt,) ndarray\n        samples in the target domain (uniform waigth if empty)\n    M : (ns,nt) ndarray\n        loss matrix        \n  \n    \n    Returns\n    -------\n    gamma: (ns x nt) ndarray\n        Optimal transportation matrix for the given parameters\n \n    ";
+static PyMethodDef __pyx_mdef_2ot_3emd_3emd_1emd = {"emd", (PyCFunction)__pyx_pw_2ot_3emd_3emd_1emd, METH_VARARGS|METH_KEYWORDS, __pyx_doc_2ot_3emd_3emd_emd};
+static PyObject *__pyx_pw_2ot_3emd_3emd_1emd(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) {
+  PyArrayObject *__pyx_v_a = 0;
+  PyArrayObject *__pyx_v_b = 0;
+  PyArrayObject *__pyx_v_M = 0;
+  int __pyx_lineno = 0;
+  const char *__pyx_filename = NULL;
+  int __pyx_clineno = 0;
+  PyObject *__pyx_r = 0;
+  __Pyx_RefNannyDeclarations
+  __Pyx_RefNannySetupContext("emd (wrapper)", 0);
+  {
+    static PyObject **__pyx_pyargnames[] = {&__pyx_n_s_a,&__pyx_n_s_b,&__pyx_n_s_M,0};
+    PyObject* values[3] = {0,0,0};
+    if (unlikely(__pyx_kwds)) {
+      Py_ssize_t kw_args;
+      const Py_ssize_t pos_args = PyTuple_GET_SIZE(__pyx_args);
+      switch (pos_args) {
+        case  3: values[2] = PyTuple_GET_ITEM(__pyx_args, 2);
+        case  2: values[1] = PyTuple_GET_ITEM(__pyx_args, 1);
+        case  1: values[0] = PyTuple_GET_ITEM(__pyx_args, 0);
+        case  0: break;
+        default: goto __pyx_L5_argtuple_error;
+      }
+      kw_args = PyDict_Size(__pyx_kwds);
+      switch (pos_args) {
+        case  0:
+        if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_a)) != 0)) kw_args--;
+        else goto __pyx_L5_argtuple_error;
+        case  1:
+        if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_b)) != 0)) kw_args--;
+        else {
+          __Pyx_RaiseArgtupleInvalid("emd", 1, 3, 3, 1); {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
+        }
+        case  2:
+        if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_M)) != 0)) kw_args--;
+        else {
+          __Pyx_RaiseArgtupleInvalid("emd", 1, 3, 3, 2); {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
+        }
+      }
+      if (unlikely(kw_args > 0)) {
+        if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "emd") < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
+      }
+    } else if (PyTuple_GET_SIZE(__pyx_args) != 3) {
+      goto __pyx_L5_argtuple_error;
+    } else {
+      values[0] = PyTuple_GET_ITEM(__pyx_args, 0);
+      values[1] = PyTuple_GET_ITEM(__pyx_args, 1);
+      values[2] = PyTuple_GET_ITEM(__pyx_args, 2);
+    }
+    __pyx_v_a = ((PyArrayObject *)values[0]);
+    __pyx_v_b = ((PyArrayObject *)values[1]);
+    __pyx_v_M = ((PyArrayObject *)values[2]);
+  }
+  goto __pyx_L4_argument_unpacking_done;
+  __pyx_L5_argtuple_error:;
+  __Pyx_RaiseArgtupleInvalid("emd", 1, 3, 3, PyTuple_GET_SIZE(__pyx_args)); {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
+  __pyx_L3_error:;
+  __Pyx_AddTraceback("ot.emd.emd.emd", __pyx_clineno, __pyx_lineno, __pyx_filename);
+  __Pyx_RefNannyFinishContext();
+  return NULL;
+  __pyx_L4_argument_unpacking_done:;
+  if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_a), __pyx_ptype_5numpy_ndarray, 1, "a", 0))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_b), __pyx_ptype_5numpy_ndarray, 1, "b", 0))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_M), __pyx_ptype_5numpy_ndarray, 1, "M", 0))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_r = __pyx_pf_2ot_3emd_3emd_emd(__pyx_self, __pyx_v_a, __pyx_v_b, __pyx_v_M);
+
+  /* function exit code */
+  goto __pyx_L0;
+  __pyx_L1_error:;
+  __pyx_r = NULL;
+  __pyx_L0:;
+  __Pyx_RefNannyFinishContext();
+  return __pyx_r;
+}
+
+static PyObject *__pyx_pf_2ot_3emd_3emd_emd(CYTHON_UNUSED PyObject *__pyx_self, PyArrayObject *__pyx_v_a, PyArrayObject *__pyx_v_b, PyArrayObject *__pyx_v_M) {
+  int __pyx_v_n1;
+  int __pyx_v_n2;
+  float __pyx_v_cost;
+  PyArrayObject *__pyx_v_G = 0;
+  __Pyx_LocalBuf_ND __pyx_pybuffernd_G;
+  __Pyx_Buffer __pyx_pybuffer_G;
+  __Pyx_LocalBuf_ND __pyx_pybuffernd_M;
+  __Pyx_Buffer __pyx_pybuffer_M;
+  __Pyx_LocalBuf_ND __pyx_pybuffernd_a;
+  __Pyx_Buffer __pyx_pybuffer_a;
+  __Pyx_LocalBuf_ND __pyx_pybuffernd_b;
+  __Pyx_Buffer __pyx_pybuffer_b;
+  PyObject *__pyx_r = NULL;
+  __Pyx_RefNannyDeclarations
+  PyObject *__pyx_t_1 = NULL;
+  PyObject *__pyx_t_2 = NULL;
+  PyObject *__pyx_t_3 = NULL;
+  PyObject *__pyx_t_4 = NULL;
+  PyObject *__pyx_t_5 = NULL;
+  PyArrayObject *__pyx_t_6 = NULL;
+  Py_ssize_t __pyx_t_7;
+  int __pyx_t_8;
+  PyArrayObject *__pyx_t_9 = NULL;
+  int __pyx_t_10;
+  PyObject *__pyx_t_11 = NULL;
+  PyObject *__pyx_t_12 = NULL;
+  PyObject *__pyx_t_13 = NULL;
+  PyArrayObject *__pyx_t_14 = NULL;
+  int __pyx_lineno = 0;
+  const char *__pyx_filename = NULL;
+  int __pyx_clineno = 0;
+  __Pyx_RefNannySetupContext("emd", 0);
+  __Pyx_INCREF((PyObject *)__pyx_v_a);
+  __Pyx_INCREF((PyObject *)__pyx_v_b);
+  __pyx_pybuffer_G.pybuffer.buf = NULL;
+  __pyx_pybuffer_G.refcount = 0;
+  __pyx_pybuffernd_G.data = NULL;
+  __pyx_pybuffernd_G.rcbuffer = &__pyx_pybuffer_G;
+  __pyx_pybuffer_a.pybuffer.buf = NULL;
+  __pyx_pybuffer_a.refcount = 0;
+  __pyx_pybuffernd_a.data = NULL;
+  __pyx_pybuffernd_a.rcbuffer = &__pyx_pybuffer_a;
+  __pyx_pybuffer_b.pybuffer.buf = NULL;
+  __pyx_pybuffer_b.refcount = 0;
+  __pyx_pybuffernd_b.data = NULL;
+  __pyx_pybuffernd_b.rcbuffer = &__pyx_pybuffer_b;
+  __pyx_pybuffer_M.pybuffer.buf = NULL;
+  __pyx_pybuffer_M.refcount = 0;
+  __pyx_pybuffernd_M.data = NULL;
+  __pyx_pybuffernd_M.rcbuffer = &__pyx_pybuffer_M;
+  {
+    __Pyx_BufFmt_StackElem __pyx_stack[1];
+    if (unlikely(__Pyx_GetBufferAndValidate(&__pyx_pybuffernd_a.rcbuffer->pybuffer, (PyObject*)__pyx_v_a, &__Pyx_TypeInfo_double, PyBUF_FORMAT| PyBUF_C_CONTIGUOUS, 1, 0, __pyx_stack) == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  }
+  __pyx_pybuffernd_a.diminfo[0].strides = __pyx_pybuffernd_a.rcbuffer->pybuffer.strides[0]; __pyx_pybuffernd_a.diminfo[0].shape = __pyx_pybuffernd_a.rcbuffer->pybuffer.shape[0];
+  {
+    __Pyx_BufFmt_StackElem __pyx_stack[1];
+    if (unlikely(__Pyx_GetBufferAndValidate(&__pyx_pybuffernd_b.rcbuffer->pybuffer, (PyObject*)__pyx_v_b, &__Pyx_TypeInfo_double, PyBUF_FORMAT| PyBUF_C_CONTIGUOUS, 1, 0, __pyx_stack) == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  }
+  __pyx_pybuffernd_b.diminfo[0].strides = __pyx_pybuffernd_b.rcbuffer->pybuffer.strides[0]; __pyx_pybuffernd_b.diminfo[0].shape = __pyx_pybuffernd_b.rcbuffer->pybuffer.shape[0];
+  {
+    __Pyx_BufFmt_StackElem __pyx_stack[1];
+    if (unlikely(__Pyx_GetBufferAndValidate(&__pyx_pybuffernd_M.rcbuffer->pybuffer, (PyObject*)__pyx_v_M, &__Pyx_TypeInfo_double, PyBUF_FORMAT| PyBUF_C_CONTIGUOUS, 2, 0, __pyx_stack) == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  }
+  __pyx_pybuffernd_M.diminfo[0].strides = __pyx_pybuffernd_M.rcbuffer->pybuffer.strides[0]; __pyx_pybuffernd_M.diminfo[0].shape = __pyx_pybuffernd_M.rcbuffer->pybuffer.shape[0]; __pyx_pybuffernd_M.diminfo[1].strides = __pyx_pybuffernd_M.rcbuffer->pybuffer.strides[1]; __pyx_pybuffernd_M.diminfo[1].shape = __pyx_pybuffernd_M.rcbuffer->pybuffer.shape[1];
+
+  /* "ot/emd/emd.pyx":56
+ * 
+ *     """
+ *     cdef int n1= M.shape[0]             # <<<<<<<<<<<<<<
+ *     cdef int n2= M.shape[1]
+ * 
+ */
+  __pyx_v_n1 = (__pyx_v_M->dimensions[0]);
+
+  /* "ot/emd/emd.pyx":57
+ *     """
+ *     cdef int n1= M.shape[0]
+ *     cdef int n2= M.shape[1]             # <<<<<<<<<<<<<<
+ * 
+ *     cdef float cost=0
+ */
+  __pyx_v_n2 = (__pyx_v_M->dimensions[1]);
+
+  /* "ot/emd/emd.pyx":59
+ *     cdef int n2= M.shape[1]
+ * 
+ *     cdef float cost=0             # <<<<<<<<<<<<<<
+ *     cdef np.ndarray[double, ndim=2, mode="c"] G=np.zeros([n1, n2])
+ * 
+ */
+  __pyx_v_cost = 0.0;
+
+  /* "ot/emd/emd.pyx":60
+ * 
+ *     cdef float cost=0
+ *     cdef np.ndarray[double, ndim=2, mode="c"] G=np.zeros([n1, n2])             # <<<<<<<<<<<<<<
+ * 
+ *     if not len(a):
+ */
+  __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 60; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_2);
+  __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_zeros); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 60; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_3);
+  __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
+  __pyx_t_2 = __Pyx_PyInt_From_int(__pyx_v_n1); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 60; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_2);
+  __pyx_t_4 = __Pyx_PyInt_From_int(__pyx_v_n2); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 60; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_4);
+  __pyx_t_5 = PyList_New(2); if (unlikely(!__pyx_t_5)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 60; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_5);
+  __Pyx_GIVEREF(__pyx_t_2);
+  PyList_SET_ITEM(__pyx_t_5, 0, __pyx_t_2);
+  __Pyx_GIVEREF(__pyx_t_4);
+  PyList_SET_ITEM(__pyx_t_5, 1, __pyx_t_4);
+  __pyx_t_2 = 0;
+  __pyx_t_4 = 0;
+  __pyx_t_4 = NULL;
+  if (CYTHON_COMPILING_IN_CPYTHON && unlikely(PyMethod_Check(__pyx_t_3))) {
+    __pyx_t_4 = PyMethod_GET_SELF(__pyx_t_3);
+    if (likely(__pyx_t_4)) {
+      PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_3);
+      __Pyx_INCREF(__pyx_t_4);
+      __Pyx_INCREF(function);
+      __Pyx_DECREF_SET(__pyx_t_3, function);
+    }
+  }
+  if (!__pyx_t_4) {
+    __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_t_5); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 60; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0;
+    __Pyx_GOTREF(__pyx_t_1);
+  } else {
+    __pyx_t_2 = PyTuple_New(1+1); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 60; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_2);
+    __Pyx_GIVEREF(__pyx_t_4); PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_t_4); __pyx_t_4 = NULL;
+    __Pyx_GIVEREF(__pyx_t_5);
+    PyTuple_SET_ITEM(__pyx_t_2, 0+1, __pyx_t_5);
+    __pyx_t_5 = 0;
+    __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_2, NULL); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 60; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_1);
+    __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
+  }
+  __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+  if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 60; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_t_6 = ((PyArrayObject *)__pyx_t_1);
+  {
+    __Pyx_BufFmt_StackElem __pyx_stack[1];
+    if (unlikely(__Pyx_GetBufferAndValidate(&__pyx_pybuffernd_G.rcbuffer->pybuffer, (PyObject*)__pyx_t_6, &__Pyx_TypeInfo_double, PyBUF_FORMAT| PyBUF_C_CONTIGUOUS, 2, 0, __pyx_stack) == -1)) {
+      __pyx_v_G = ((PyArrayObject *)Py_None); __Pyx_INCREF(Py_None); __pyx_pybuffernd_G.rcbuffer->pybuffer.buf = NULL;
+      {__pyx_filename = __pyx_f[0]; __pyx_lineno = 60; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    } else {__pyx_pybuffernd_G.diminfo[0].strides = __pyx_pybuffernd_G.rcbuffer->pybuffer.strides[0]; __pyx_pybuffernd_G.diminfo[0].shape = __pyx_pybuffernd_G.rcbuffer->pybuffer.shape[0]; __pyx_pybuffernd_G.diminfo[1].strides = __pyx_pybuffernd_G.rcbuffer->pybuffer.strides[1]; __pyx_pybuffernd_G.diminfo[1].shape = __pyx_pybuffernd_G.rcbuffer->pybuffer.shape[1];
+    }
+  }
+  __pyx_t_6 = 0;
+  __pyx_v_G = ((PyArrayObject *)__pyx_t_1);
+  __pyx_t_1 = 0;
+
+  /* "ot/emd/emd.pyx":62
+ *     cdef np.ndarray[double, ndim=2, mode="c"] G=np.zeros([n1, n2])
+ * 
+ *     if not len(a):             # <<<<<<<<<<<<<<
+ *         a=np.ones((n1,))/n1
+ * 
+ */
+  __pyx_t_7 = PyObject_Length(((PyObject *)__pyx_v_a)); if (unlikely(__pyx_t_7 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 62; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_t_8 = ((!(__pyx_t_7 != 0)) != 0);
+  if (__pyx_t_8) {
+
+    /* "ot/emd/emd.pyx":63
+ * 
+ *     if not len(a):
+ *         a=np.ones((n1,))/n1             # <<<<<<<<<<<<<<
+ * 
+ *     if not len(b):
+ */
+    __pyx_t_3 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_3);
+    __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_ones); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_2);
+    __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+    __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_n1); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_3);
+    __pyx_t_5 = PyTuple_New(1); if (unlikely(!__pyx_t_5)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_5);
+    __Pyx_GIVEREF(__pyx_t_3);
+    PyTuple_SET_ITEM(__pyx_t_5, 0, __pyx_t_3);
+    __pyx_t_3 = 0;
+    __pyx_t_3 = NULL;
+    if (CYTHON_COMPILING_IN_CPYTHON && unlikely(PyMethod_Check(__pyx_t_2))) {
+      __pyx_t_3 = PyMethod_GET_SELF(__pyx_t_2);
+      if (likely(__pyx_t_3)) {
+        PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2);
+        __Pyx_INCREF(__pyx_t_3);
+        __Pyx_INCREF(function);
+        __Pyx_DECREF_SET(__pyx_t_2, function);
+      }
+    }
+    if (!__pyx_t_3) {
+      __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_2, __pyx_t_5); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0;
+      __Pyx_GOTREF(__pyx_t_1);
+    } else {
+      __pyx_t_4 = PyTuple_New(1+1); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __Pyx_GIVEREF(__pyx_t_3); PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_3); __pyx_t_3 = NULL;
+      __Pyx_GIVEREF(__pyx_t_5);
+      PyTuple_SET_ITEM(__pyx_t_4, 0+1, __pyx_t_5);
+      __pyx_t_5 = 0;
+      __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_t_4, NULL); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_1);
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+    }
+    __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
+    __pyx_t_2 = __Pyx_PyInt_From_int(__pyx_v_n1); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_2);
+    __pyx_t_4 = __Pyx_PyNumber_Divide(__pyx_t_1, __pyx_t_2); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_4);
+    __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
+    __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
+    if (!(likely(((__pyx_t_4) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_4, __pyx_ptype_5numpy_ndarray))))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __pyx_t_9 = ((PyArrayObject *)__pyx_t_4);
+    {
+      __Pyx_BufFmt_StackElem __pyx_stack[1];
+      __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_a.rcbuffer->pybuffer);
+      __pyx_t_10 = __Pyx_GetBufferAndValidate(&__pyx_pybuffernd_a.rcbuffer->pybuffer, (PyObject*)__pyx_t_9, &__Pyx_TypeInfo_double, PyBUF_FORMAT| PyBUF_C_CONTIGUOUS, 1, 0, __pyx_stack);
+      if (unlikely(__pyx_t_10 < 0)) {
+        PyErr_Fetch(&__pyx_t_11, &__pyx_t_12, &__pyx_t_13);
+        if (unlikely(__Pyx_GetBufferAndValidate(&__pyx_pybuffernd_a.rcbuffer->pybuffer, (PyObject*)__pyx_v_a, &__Pyx_TypeInfo_double, PyBUF_FORMAT| PyBUF_C_CONTIGUOUS, 1, 0, __pyx_stack) == -1)) {
+          Py_XDECREF(__pyx_t_11); Py_XDECREF(__pyx_t_12); Py_XDECREF(__pyx_t_13);
+          __Pyx_RaiseBufferFallbackError();
+        } else {
+          PyErr_Restore(__pyx_t_11, __pyx_t_12, __pyx_t_13);
+        }
+      }
+      __pyx_pybuffernd_a.diminfo[0].strides = __pyx_pybuffernd_a.rcbuffer->pybuffer.strides[0]; __pyx_pybuffernd_a.diminfo[0].shape = __pyx_pybuffernd_a.rcbuffer->pybuffer.shape[0];
+      if (unlikely(__pyx_t_10 < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    }
+    __pyx_t_9 = 0;
+    __Pyx_DECREF_SET(__pyx_v_a, ((PyArrayObject *)__pyx_t_4));
+    __pyx_t_4 = 0;
+
+    /* "ot/emd/emd.pyx":62
+ *     cdef np.ndarray[double, ndim=2, mode="c"] G=np.zeros([n1, n2])
+ * 
+ *     if not len(a):             # <<<<<<<<<<<<<<
+ *         a=np.ones((n1,))/n1
+ * 
+ */
+  }
+
+  /* "ot/emd/emd.pyx":65
+ *         a=np.ones((n1,))/n1
+ * 
+ *     if not len(b):             # <<<<<<<<<<<<<<
+ *         b=np.ones((n2,))/n2
+ * 
+ */
+  __pyx_t_7 = PyObject_Length(((PyObject *)__pyx_v_b)); if (unlikely(__pyx_t_7 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 65; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_t_8 = ((!(__pyx_t_7 != 0)) != 0);
+  if (__pyx_t_8) {
+
+    /* "ot/emd/emd.pyx":66
+ * 
+ *     if not len(b):
+ *         b=np.ones((n2,))/n2             # <<<<<<<<<<<<<<
+ * 
+ *     # calling the function
+ */
+    __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 66; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_2);
+    __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_ones); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 66; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_1);
+    __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
+    __pyx_t_2 = __Pyx_PyInt_From_int(__pyx_v_n2); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 66; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_2);
+    __pyx_t_5 = PyTuple_New(1); if (unlikely(!__pyx_t_5)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 66; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_5);
+    __Pyx_GIVEREF(__pyx_t_2);
+    PyTuple_SET_ITEM(__pyx_t_5, 0, __pyx_t_2);
+    __pyx_t_2 = 0;
+    __pyx_t_2 = NULL;
+    if (CYTHON_COMPILING_IN_CPYTHON && unlikely(PyMethod_Check(__pyx_t_1))) {
+      __pyx_t_2 = PyMethod_GET_SELF(__pyx_t_1);
+      if (likely(__pyx_t_2)) {
+        PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_1);
+        __Pyx_INCREF(__pyx_t_2);
+        __Pyx_INCREF(function);
+        __Pyx_DECREF_SET(__pyx_t_1, function);
+      }
+    }
+    if (!__pyx_t_2) {
+      __pyx_t_4 = __Pyx_PyObject_CallOneArg(__pyx_t_1, __pyx_t_5); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 66; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0;
+      __Pyx_GOTREF(__pyx_t_4);
+    } else {
+      __pyx_t_3 = PyTuple_New(1+1); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 66; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __Pyx_GIVEREF(__pyx_t_2); PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_2); __pyx_t_2 = NULL;
+      __Pyx_GIVEREF(__pyx_t_5);
+      PyTuple_SET_ITEM(__pyx_t_3, 0+1, __pyx_t_5);
+      __pyx_t_5 = 0;
+      __pyx_t_4 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_t_3, NULL); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 66; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+    }
+    __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
+    __pyx_t_1 = __Pyx_PyInt_From_int(__pyx_v_n2); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 66; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_1);
+    __pyx_t_3 = __Pyx_PyNumber_Divide(__pyx_t_4, __pyx_t_1); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 66; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_3);
+    __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+    __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
+    if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 66; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __pyx_t_14 = ((PyArrayObject *)__pyx_t_3);
+    {
+      __Pyx_BufFmt_StackElem __pyx_stack[1];
+      __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_b.rcbuffer->pybuffer);
+      __pyx_t_10 = __Pyx_GetBufferAndValidate(&__pyx_pybuffernd_b.rcbuffer->pybuffer, (PyObject*)__pyx_t_14, &__Pyx_TypeInfo_double, PyBUF_FORMAT| PyBUF_C_CONTIGUOUS, 1, 0, __pyx_stack);
+      if (unlikely(__pyx_t_10 < 0)) {
+        PyErr_Fetch(&__pyx_t_13, &__pyx_t_12, &__pyx_t_11);
+        if (unlikely(__Pyx_GetBufferAndValidate(&__pyx_pybuffernd_b.rcbuffer->pybuffer, (PyObject*)__pyx_v_b, &__Pyx_TypeInfo_double, PyBUF_FORMAT| PyBUF_C_CONTIGUOUS, 1, 0, __pyx_stack) == -1)) {
+          Py_XDECREF(__pyx_t_13); Py_XDECREF(__pyx_t_12); Py_XDECREF(__pyx_t_11);
+          __Pyx_RaiseBufferFallbackError();
+        } else {
+          PyErr_Restore(__pyx_t_13, __pyx_t_12, __pyx_t_11);
+        }
+      }
+      __pyx_pybuffernd_b.diminfo[0].strides = __pyx_pybuffernd_b.rcbuffer->pybuffer.strides[0]; __pyx_pybuffernd_b.diminfo[0].shape = __pyx_pybuffernd_b.rcbuffer->pybuffer.shape[0];
+      if (unlikely(__pyx_t_10 < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 66; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    }
+    __pyx_t_14 = 0;
+    __Pyx_DECREF_SET(__pyx_v_b, ((PyArrayObject *)__pyx_t_3));
+    __pyx_t_3 = 0;
+
+    /* "ot/emd/emd.pyx":65
+ *         a=np.ones((n1,))/n1
+ * 
+ *     if not len(b):             # <<<<<<<<<<<<<<
+ *         b=np.ones((n2,))/n2
+ * 
+ */
+  }
+
+  /* "ot/emd/emd.pyx":69
+ * 
+ *     # calling the function
+ *     EMD_wrap(n1,n2,<double*> a.data,<double*> b.data,<double*> M.data,<double*> G.data,<double*> &cost)             # <<<<<<<<<<<<<<
+ * 
+ *     return G
+ */
+  EMD_wrap(__pyx_v_n1, __pyx_v_n2, ((double *)__pyx_v_a->data), ((double *)__pyx_v_b->data), ((double *)__pyx_v_M->data), ((double *)__pyx_v_G->data), ((double *)(&__pyx_v_cost)));
+
+  /* "ot/emd/emd.pyx":71
+ *     EMD_wrap(n1,n2,<double*> a.data,<double*> b.data,<double*> M.data,<double*> G.data,<double*> &cost)
+ * 
+ *     return G             # <<<<<<<<<<<<<<
+ */
+  __Pyx_XDECREF(__pyx_r);
+  __Pyx_INCREF(((PyObject *)__pyx_v_G));
+  __pyx_r = ((PyObject *)__pyx_v_G);
+  goto __pyx_L0;
+
+  /* "ot/emd/emd.pyx":21
+ * @cython.boundscheck(False)
+ * @cython.wraparound(False)
+ * def emd( np.ndarray[double, ndim=1, mode="c"] a,np.ndarray[double, ndim=1, mode="c"]  b,np.ndarray[double, ndim=2, mode="c"]  M):             # <<<<<<<<<<<<<<
+ *     """
+ *         Solves the Earth Movers distance problem and returns the optimal transport matrix
+ */
+
+  /* function exit code */
+  __pyx_L1_error:;
+  __Pyx_XDECREF(__pyx_t_1);
+  __Pyx_XDECREF(__pyx_t_2);
+  __Pyx_XDECREF(__pyx_t_3);
+  __Pyx_XDECREF(__pyx_t_4);
+  __Pyx_XDECREF(__pyx_t_5);
+  { PyObject *__pyx_type, *__pyx_value, *__pyx_tb;
+    __Pyx_ErrFetch(&__pyx_type, &__pyx_value, &__pyx_tb);
+    __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_G.rcbuffer->pybuffer);
+    __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_M.rcbuffer->pybuffer);
+    __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_a.rcbuffer->pybuffer);
+    __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_b.rcbuffer->pybuffer);
+  __Pyx_ErrRestore(__pyx_type, __pyx_value, __pyx_tb);}
+  __Pyx_AddTraceback("ot.emd.emd.emd", __pyx_clineno, __pyx_lineno, __pyx_filename);
+  __pyx_r = NULL;
+  goto __pyx_L2;
+  __pyx_L0:;
+  __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_G.rcbuffer->pybuffer);
+  __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_M.rcbuffer->pybuffer);
+  __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_a.rcbuffer->pybuffer);
+  __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_b.rcbuffer->pybuffer);
+  __pyx_L2:;
+  __Pyx_XDECREF((PyObject *)__pyx_v_G);
+  __Pyx_XDECREF((PyObject *)__pyx_v_a);
+  __Pyx_XDECREF((PyObject *)__pyx_v_b);
+  __Pyx_XGIVEREF(__pyx_r);
+  __Pyx_RefNannyFinishContext();
+  return __pyx_r;
+}
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":197
+ *         # experimental exception made for __getbuffer__ and __releasebuffer__
+ *         # -- the details of this may change.
+ *         def __getbuffer__(ndarray self, Py_buffer* info, int flags):             # <<<<<<<<<<<<<<
+ *             # This implementation of getbuffer is geared towards Cython
+ *             # requirements, and does not yet fullfill the PEP.
+ */
+
+/* Python wrapper */
+static CYTHON_UNUSED int __pyx_pw_5numpy_7ndarray_1__getbuffer__(PyObject *__pyx_v_self, Py_buffer *__pyx_v_info, int __pyx_v_flags); /*proto*/
+static CYTHON_UNUSED int __pyx_pw_5numpy_7ndarray_1__getbuffer__(PyObject *__pyx_v_self, Py_buffer *__pyx_v_info, int __pyx_v_flags) {
+  int __pyx_r;
+  __Pyx_RefNannyDeclarations
+  __Pyx_RefNannySetupContext("__getbuffer__ (wrapper)", 0);
+  __pyx_r = __pyx_pf_5numpy_7ndarray___getbuffer__(((PyArrayObject *)__pyx_v_self), ((Py_buffer *)__pyx_v_info), ((int)__pyx_v_flags));
+
+  /* function exit code */
+  __Pyx_RefNannyFinishContext();
+  return __pyx_r;
+}
+
+static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, Py_buffer *__pyx_v_info, int __pyx_v_flags) {
+  int __pyx_v_copy_shape;
+  int __pyx_v_i;
+  int __pyx_v_ndim;
+  int __pyx_v_endian_detector;
+  int __pyx_v_little_endian;
+  int __pyx_v_t;
+  char *__pyx_v_f;
+  PyArray_Descr *__pyx_v_descr = 0;
+  int __pyx_v_offset;
+  int __pyx_v_hasfields;
+  int __pyx_r;
+  __Pyx_RefNannyDeclarations
+  int __pyx_t_1;
+  int __pyx_t_2;
+  PyObject *__pyx_t_3 = NULL;
+  int __pyx_t_4;
+  int __pyx_t_5;
+  PyObject *__pyx_t_6 = NULL;
+  char *__pyx_t_7;
+  int __pyx_lineno = 0;
+  const char *__pyx_filename = NULL;
+  int __pyx_clineno = 0;
+  __Pyx_RefNannySetupContext("__getbuffer__", 0);
+  if (__pyx_v_info != NULL) {
+    __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None);
+    __Pyx_GIVEREF(__pyx_v_info->obj);
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":203
+ *             # of flags
+ * 
+ *             if info == NULL: return             # <<<<<<<<<<<<<<
+ * 
+ *             cdef int copy_shape, i, ndim
+ */
+  __pyx_t_1 = ((__pyx_v_info == NULL) != 0);
+  if (__pyx_t_1) {
+    __pyx_r = 0;
+    goto __pyx_L0;
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":206
+ * 
+ *             cdef int copy_shape, i, ndim
+ *             cdef int endian_detector = 1             # <<<<<<<<<<<<<<
+ *             cdef bint little_endian = ((<char*>&endian_detector)[0] != 0)
+ * 
+ */
+  __pyx_v_endian_detector = 1;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":207
+ *             cdef int copy_shape, i, ndim
+ *             cdef int endian_detector = 1
+ *             cdef bint little_endian = ((<char*>&endian_detector)[0] != 0)             # <<<<<<<<<<<<<<
+ * 
+ *             ndim = PyArray_NDIM(self)
+ */
+  __pyx_v_little_endian = ((((char *)(&__pyx_v_endian_detector))[0]) != 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":209
+ *             cdef bint little_endian = ((<char*>&endian_detector)[0] != 0)
+ * 
+ *             ndim = PyArray_NDIM(self)             # <<<<<<<<<<<<<<
+ * 
+ *             if sizeof(npy_intp) != sizeof(Py_ssize_t):
+ */
+  __pyx_v_ndim = PyArray_NDIM(__pyx_v_self);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":211
+ *             ndim = PyArray_NDIM(self)
+ * 
+ *             if sizeof(npy_intp) != sizeof(Py_ssize_t):             # <<<<<<<<<<<<<<
+ *                 copy_shape = 1
+ *             else:
+ */
+  __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0);
+  if (__pyx_t_1) {
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":212
+ * 
+ *             if sizeof(npy_intp) != sizeof(Py_ssize_t):
+ *                 copy_shape = 1             # <<<<<<<<<<<<<<
+ *             else:
+ *                 copy_shape = 0
+ */
+    __pyx_v_copy_shape = 1;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":211
+ *             ndim = PyArray_NDIM(self)
+ * 
+ *             if sizeof(npy_intp) != sizeof(Py_ssize_t):             # <<<<<<<<<<<<<<
+ *                 copy_shape = 1
+ *             else:
+ */
+    goto __pyx_L4;
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":214
+ *                 copy_shape = 1
+ *             else:
+ *                 copy_shape = 0             # <<<<<<<<<<<<<<
+ * 
+ *             if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS)
+ */
+  /*else*/ {
+    __pyx_v_copy_shape = 0;
+  }
+  __pyx_L4:;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":216
+ *                 copy_shape = 0
+ * 
+ *             if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS)             # <<<<<<<<<<<<<<
+ *                 and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)):
+ *                 raise ValueError(u"ndarray is not C contiguous")
+ */
+  __pyx_t_2 = (((__pyx_v_flags & PyBUF_C_CONTIGUOUS) == PyBUF_C_CONTIGUOUS) != 0);
+  if (__pyx_t_2) {
+  } else {
+    __pyx_t_1 = __pyx_t_2;
+    goto __pyx_L6_bool_binop_done;
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":217
+ * 
+ *             if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS)
+ *                 and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)):             # <<<<<<<<<<<<<<
+ *                 raise ValueError(u"ndarray is not C contiguous")
+ * 
+ */
+  __pyx_t_2 = ((!(PyArray_CHKFLAGS(__pyx_v_self, NPY_C_CONTIGUOUS) != 0)) != 0);
+  __pyx_t_1 = __pyx_t_2;
+  __pyx_L6_bool_binop_done:;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":216
+ *                 copy_shape = 0
+ * 
+ *             if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS)             # <<<<<<<<<<<<<<
+ *                 and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)):
+ *                 raise ValueError(u"ndarray is not C contiguous")
+ */
+  if (__pyx_t_1) {
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":218
+ *             if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS)
+ *                 and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)):
+ *                 raise ValueError(u"ndarray is not C contiguous")             # <<<<<<<<<<<<<<
+ * 
+ *             if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS)
+ */
+    __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple_, NULL); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 218; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_3);
+    __Pyx_Raise(__pyx_t_3, 0, 0, 0);
+    __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+    {__pyx_filename = __pyx_f[1]; __pyx_lineno = 218; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":216
+ *                 copy_shape = 0
+ * 
+ *             if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS)             # <<<<<<<<<<<<<<
+ *                 and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)):
+ *                 raise ValueError(u"ndarray is not C contiguous")
+ */
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":220
+ *                 raise ValueError(u"ndarray is not C contiguous")
+ * 
+ *             if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS)             # <<<<<<<<<<<<<<
+ *                 and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)):
+ *                 raise ValueError(u"ndarray is not Fortran contiguous")
+ */
+  __pyx_t_2 = (((__pyx_v_flags & PyBUF_F_CONTIGUOUS) == PyBUF_F_CONTIGUOUS) != 0);
+  if (__pyx_t_2) {
+  } else {
+    __pyx_t_1 = __pyx_t_2;
+    goto __pyx_L9_bool_binop_done;
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":221
+ * 
+ *             if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS)
+ *                 and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)):             # <<<<<<<<<<<<<<
+ *                 raise ValueError(u"ndarray is not Fortran contiguous")
+ * 
+ */
+  __pyx_t_2 = ((!(PyArray_CHKFLAGS(__pyx_v_self, NPY_F_CONTIGUOUS) != 0)) != 0);
+  __pyx_t_1 = __pyx_t_2;
+  __pyx_L9_bool_binop_done:;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":220
+ *                 raise ValueError(u"ndarray is not C contiguous")
+ * 
+ *             if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS)             # <<<<<<<<<<<<<<
+ *                 and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)):
+ *                 raise ValueError(u"ndarray is not Fortran contiguous")
+ */
+  if (__pyx_t_1) {
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":222
+ *             if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS)
+ *                 and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)):
+ *                 raise ValueError(u"ndarray is not Fortran contiguous")             # <<<<<<<<<<<<<<
+ * 
+ *             info.buf = PyArray_DATA(self)
+ */
+    __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__2, NULL); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 222; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_3);
+    __Pyx_Raise(__pyx_t_3, 0, 0, 0);
+    __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+    {__pyx_filename = __pyx_f[1]; __pyx_lineno = 222; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":220
+ *                 raise ValueError(u"ndarray is not C contiguous")
+ * 
+ *             if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS)             # <<<<<<<<<<<<<<
+ *                 and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)):
+ *                 raise ValueError(u"ndarray is not Fortran contiguous")
+ */
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":224
+ *                 raise ValueError(u"ndarray is not Fortran contiguous")
+ * 
+ *             info.buf = PyArray_DATA(self)             # <<<<<<<<<<<<<<
+ *             info.ndim = ndim
+ *             if copy_shape:
+ */
+  __pyx_v_info->buf = PyArray_DATA(__pyx_v_self);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":225
+ * 
+ *             info.buf = PyArray_DATA(self)
+ *             info.ndim = ndim             # <<<<<<<<<<<<<<
+ *             if copy_shape:
+ *                 # Allocate new buffer for strides and shape info.
+ */
+  __pyx_v_info->ndim = __pyx_v_ndim;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":226
+ *             info.buf = PyArray_DATA(self)
+ *             info.ndim = ndim
+ *             if copy_shape:             # <<<<<<<<<<<<<<
+ *                 # Allocate new buffer for strides and shape info.
+ *                 # This is allocated as one block, strides first.
+ */
+  __pyx_t_1 = (__pyx_v_copy_shape != 0);
+  if (__pyx_t_1) {
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":229
+ *                 # Allocate new buffer for strides and shape info.
+ *                 # This is allocated as one block, strides first.
+ *                 info.strides = <Py_ssize_t*>stdlib.malloc(sizeof(Py_ssize_t) * <size_t>ndim * 2)             # <<<<<<<<<<<<<<
+ *                 info.shape = info.strides + ndim
+ *                 for i in range(ndim):
+ */
+    __pyx_v_info->strides = ((Py_ssize_t *)malloc((((sizeof(Py_ssize_t)) * ((size_t)__pyx_v_ndim)) * 2)));
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":230
+ *                 # This is allocated as one block, strides first.
+ *                 info.strides = <Py_ssize_t*>stdlib.malloc(sizeof(Py_ssize_t) * <size_t>ndim * 2)
+ *                 info.shape = info.strides + ndim             # <<<<<<<<<<<<<<
+ *                 for i in range(ndim):
+ *                     info.strides[i] = PyArray_STRIDES(self)[i]
+ */
+    __pyx_v_info->shape = (__pyx_v_info->strides + __pyx_v_ndim);
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":231
+ *                 info.strides = <Py_ssize_t*>stdlib.malloc(sizeof(Py_ssize_t) * <size_t>ndim * 2)
+ *                 info.shape = info.strides + ndim
+ *                 for i in range(ndim):             # <<<<<<<<<<<<<<
+ *                     info.strides[i] = PyArray_STRIDES(self)[i]
+ *                     info.shape[i] = PyArray_DIMS(self)[i]
+ */
+    __pyx_t_4 = __pyx_v_ndim;
+    for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) {
+      __pyx_v_i = __pyx_t_5;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":232
+ *                 info.shape = info.strides + ndim
+ *                 for i in range(ndim):
+ *                     info.strides[i] = PyArray_STRIDES(self)[i]             # <<<<<<<<<<<<<<
+ *                     info.shape[i] = PyArray_DIMS(self)[i]
+ *             else:
+ */
+      (__pyx_v_info->strides[__pyx_v_i]) = (PyArray_STRIDES(__pyx_v_self)[__pyx_v_i]);
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":233
+ *                 for i in range(ndim):
+ *                     info.strides[i] = PyArray_STRIDES(self)[i]
+ *                     info.shape[i] = PyArray_DIMS(self)[i]             # <<<<<<<<<<<<<<
+ *             else:
+ *                 info.strides = <Py_ssize_t*>PyArray_STRIDES(self)
+ */
+      (__pyx_v_info->shape[__pyx_v_i]) = (PyArray_DIMS(__pyx_v_self)[__pyx_v_i]);
+    }
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":226
+ *             info.buf = PyArray_DATA(self)
+ *             info.ndim = ndim
+ *             if copy_shape:             # <<<<<<<<<<<<<<
+ *                 # Allocate new buffer for strides and shape info.
+ *                 # This is allocated as one block, strides first.
+ */
+    goto __pyx_L11;
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":235
+ *                     info.shape[i] = PyArray_DIMS(self)[i]
+ *             else:
+ *                 info.strides = <Py_ssize_t*>PyArray_STRIDES(self)             # <<<<<<<<<<<<<<
+ *                 info.shape = <Py_ssize_t*>PyArray_DIMS(self)
+ *             info.suboffsets = NULL
+ */
+  /*else*/ {
+    __pyx_v_info->strides = ((Py_ssize_t *)PyArray_STRIDES(__pyx_v_self));
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":236
+ *             else:
+ *                 info.strides = <Py_ssize_t*>PyArray_STRIDES(self)
+ *                 info.shape = <Py_ssize_t*>PyArray_DIMS(self)             # <<<<<<<<<<<<<<
+ *             info.suboffsets = NULL
+ *             info.itemsize = PyArray_ITEMSIZE(self)
+ */
+    __pyx_v_info->shape = ((Py_ssize_t *)PyArray_DIMS(__pyx_v_self));
+  }
+  __pyx_L11:;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":237
+ *                 info.strides = <Py_ssize_t*>PyArray_STRIDES(self)
+ *                 info.shape = <Py_ssize_t*>PyArray_DIMS(self)
+ *             info.suboffsets = NULL             # <<<<<<<<<<<<<<
+ *             info.itemsize = PyArray_ITEMSIZE(self)
+ *             info.readonly = not PyArray_ISWRITEABLE(self)
+ */
+  __pyx_v_info->suboffsets = NULL;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":238
+ *                 info.shape = <Py_ssize_t*>PyArray_DIMS(self)
+ *             info.suboffsets = NULL
+ *             info.itemsize = PyArray_ITEMSIZE(self)             # <<<<<<<<<<<<<<
+ *             info.readonly = not PyArray_ISWRITEABLE(self)
+ * 
+ */
+  __pyx_v_info->itemsize = PyArray_ITEMSIZE(__pyx_v_self);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":239
+ *             info.suboffsets = NULL
+ *             info.itemsize = PyArray_ITEMSIZE(self)
+ *             info.readonly = not PyArray_ISWRITEABLE(self)             # <<<<<<<<<<<<<<
+ * 
+ *             cdef int t
+ */
+  __pyx_v_info->readonly = (!(PyArray_ISWRITEABLE(__pyx_v_self) != 0));
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":242
+ * 
+ *             cdef int t
+ *             cdef char* f = NULL             # <<<<<<<<<<<<<<
+ *             cdef dtype descr = self.descr
+ *             cdef int offset
+ */
+  __pyx_v_f = NULL;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":243
+ *             cdef int t
+ *             cdef char* f = NULL
+ *             cdef dtype descr = self.descr             # <<<<<<<<<<<<<<
+ *             cdef int offset
+ * 
+ */
+  __pyx_t_3 = ((PyObject *)__pyx_v_self->descr);
+  __Pyx_INCREF(__pyx_t_3);
+  __pyx_v_descr = ((PyArray_Descr *)__pyx_t_3);
+  __pyx_t_3 = 0;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":246
+ *             cdef int offset
+ * 
+ *             cdef bint hasfields = PyDataType_HASFIELDS(descr)             # <<<<<<<<<<<<<<
+ * 
+ *             if not hasfields and not copy_shape:
+ */
+  __pyx_v_hasfields = PyDataType_HASFIELDS(__pyx_v_descr);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":248
+ *             cdef bint hasfields = PyDataType_HASFIELDS(descr)
+ * 
+ *             if not hasfields and not copy_shape:             # <<<<<<<<<<<<<<
+ *                 # do not call releasebuffer
+ *                 info.obj = None
+ */
+  __pyx_t_2 = ((!(__pyx_v_hasfields != 0)) != 0);
+  if (__pyx_t_2) {
+  } else {
+    __pyx_t_1 = __pyx_t_2;
+    goto __pyx_L15_bool_binop_done;
+  }
+  __pyx_t_2 = ((!(__pyx_v_copy_shape != 0)) != 0);
+  __pyx_t_1 = __pyx_t_2;
+  __pyx_L15_bool_binop_done:;
+  if (__pyx_t_1) {
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":250
+ *             if not hasfields and not copy_shape:
+ *                 # do not call releasebuffer
+ *                 info.obj = None             # <<<<<<<<<<<<<<
+ *             else:
+ *                 # need to call releasebuffer
+ */
+    __Pyx_INCREF(Py_None);
+    __Pyx_GIVEREF(Py_None);
+    __Pyx_GOTREF(__pyx_v_info->obj);
+    __Pyx_DECREF(__pyx_v_info->obj);
+    __pyx_v_info->obj = Py_None;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":248
+ *             cdef bint hasfields = PyDataType_HASFIELDS(descr)
+ * 
+ *             if not hasfields and not copy_shape:             # <<<<<<<<<<<<<<
+ *                 # do not call releasebuffer
+ *                 info.obj = None
+ */
+    goto __pyx_L14;
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":253
+ *             else:
+ *                 # need to call releasebuffer
+ *                 info.obj = self             # <<<<<<<<<<<<<<
+ * 
+ *             if not hasfields:
+ */
+  /*else*/ {
+    __Pyx_INCREF(((PyObject *)__pyx_v_self));
+    __Pyx_GIVEREF(((PyObject *)__pyx_v_self));
+    __Pyx_GOTREF(__pyx_v_info->obj);
+    __Pyx_DECREF(__pyx_v_info->obj);
+    __pyx_v_info->obj = ((PyObject *)__pyx_v_self);
+  }
+  __pyx_L14:;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":255
+ *                 info.obj = self
+ * 
+ *             if not hasfields:             # <<<<<<<<<<<<<<
+ *                 t = descr.type_num
+ *                 if ((descr.byteorder == c'>' and little_endian) or
+ */
+  __pyx_t_1 = ((!(__pyx_v_hasfields != 0)) != 0);
+  if (__pyx_t_1) {
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":256
+ * 
+ *             if not hasfields:
+ *                 t = descr.type_num             # <<<<<<<<<<<<<<
+ *                 if ((descr.byteorder == c'>' and little_endian) or
+ *                     (descr.byteorder == c'<' and not little_endian)):
+ */
+    __pyx_t_4 = __pyx_v_descr->type_num;
+    __pyx_v_t = __pyx_t_4;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":257
+ *             if not hasfields:
+ *                 t = descr.type_num
+ *                 if ((descr.byteorder == c'>' and little_endian) or             # <<<<<<<<<<<<<<
+ *                     (descr.byteorder == c'<' and not little_endian)):
+ *                     raise ValueError(u"Non-native byte order not supported")
+ */
+    __pyx_t_2 = ((__pyx_v_descr->byteorder == '>') != 0);
+    if (!__pyx_t_2) {
+      goto __pyx_L20_next_or;
+    } else {
+    }
+    __pyx_t_2 = (__pyx_v_little_endian != 0);
+    if (!__pyx_t_2) {
+    } else {
+      __pyx_t_1 = __pyx_t_2;
+      goto __pyx_L19_bool_binop_done;
+    }
+    __pyx_L20_next_or:;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":258
+ *                 t = descr.type_num
+ *                 if ((descr.byteorder == c'>' and little_endian) or
+ *                     (descr.byteorder == c'<' and not little_endian)):             # <<<<<<<<<<<<<<
+ *                     raise ValueError(u"Non-native byte order not supported")
+ *                 if   t == NPY_BYTE:        f = "b"
+ */
+    __pyx_t_2 = ((__pyx_v_descr->byteorder == '<') != 0);
+    if (__pyx_t_2) {
+    } else {
+      __pyx_t_1 = __pyx_t_2;
+      goto __pyx_L19_bool_binop_done;
+    }
+    __pyx_t_2 = ((!(__pyx_v_little_endian != 0)) != 0);
+    __pyx_t_1 = __pyx_t_2;
+    __pyx_L19_bool_binop_done:;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":257
+ *             if not hasfields:
+ *                 t = descr.type_num
+ *                 if ((descr.byteorder == c'>' and little_endian) or             # <<<<<<<<<<<<<<
+ *                     (descr.byteorder == c'<' and not little_endian)):
+ *                     raise ValueError(u"Non-native byte order not supported")
+ */
+    if (__pyx_t_1) {
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":259
+ *                 if ((descr.byteorder == c'>' and little_endian) or
+ *                     (descr.byteorder == c'<' and not little_endian)):
+ *                     raise ValueError(u"Non-native byte order not supported")             # <<<<<<<<<<<<<<
+ *                 if   t == NPY_BYTE:        f = "b"
+ *                 elif t == NPY_UBYTE:       f = "B"
+ */
+      __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__3, NULL); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 259; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __Pyx_Raise(__pyx_t_3, 0, 0, 0);
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      {__pyx_filename = __pyx_f[1]; __pyx_lineno = 259; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":257
+ *             if not hasfields:
+ *                 t = descr.type_num
+ *                 if ((descr.byteorder == c'>' and little_endian) or             # <<<<<<<<<<<<<<
+ *                     (descr.byteorder == c'<' and not little_endian)):
+ *                     raise ValueError(u"Non-native byte order not supported")
+ */
+    }
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":260
+ *                     (descr.byteorder == c'<' and not little_endian)):
+ *                     raise ValueError(u"Non-native byte order not supported")
+ *                 if   t == NPY_BYTE:        f = "b"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_UBYTE:       f = "B"
+ *                 elif t == NPY_SHORT:       f = "h"
+ */
+    switch (__pyx_v_t) {
+      case NPY_BYTE:
+      __pyx_v_f = __pyx_k_b;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":261
+ *                     raise ValueError(u"Non-native byte order not supported")
+ *                 if   t == NPY_BYTE:        f = "b"
+ *                 elif t == NPY_UBYTE:       f = "B"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_SHORT:       f = "h"
+ *                 elif t == NPY_USHORT:      f = "H"
+ */
+      case NPY_UBYTE:
+      __pyx_v_f = __pyx_k_B;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":262
+ *                 if   t == NPY_BYTE:        f = "b"
+ *                 elif t == NPY_UBYTE:       f = "B"
+ *                 elif t == NPY_SHORT:       f = "h"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_USHORT:      f = "H"
+ *                 elif t == NPY_INT:         f = "i"
+ */
+      case NPY_SHORT:
+      __pyx_v_f = __pyx_k_h;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":263
+ *                 elif t == NPY_UBYTE:       f = "B"
+ *                 elif t == NPY_SHORT:       f = "h"
+ *                 elif t == NPY_USHORT:      f = "H"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_INT:         f = "i"
+ *                 elif t == NPY_UINT:        f = "I"
+ */
+      case NPY_USHORT:
+      __pyx_v_f = __pyx_k_H;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":264
+ *                 elif t == NPY_SHORT:       f = "h"
+ *                 elif t == NPY_USHORT:      f = "H"
+ *                 elif t == NPY_INT:         f = "i"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_UINT:        f = "I"
+ *                 elif t == NPY_LONG:        f = "l"
+ */
+      case NPY_INT:
+      __pyx_v_f = __pyx_k_i;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":265
+ *                 elif t == NPY_USHORT:      f = "H"
+ *                 elif t == NPY_INT:         f = "i"
+ *                 elif t == NPY_UINT:        f = "I"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_LONG:        f = "l"
+ *                 elif t == NPY_ULONG:       f = "L"
+ */
+      case NPY_UINT:
+      __pyx_v_f = __pyx_k_I;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":266
+ *                 elif t == NPY_INT:         f = "i"
+ *                 elif t == NPY_UINT:        f = "I"
+ *                 elif t == NPY_LONG:        f = "l"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_ULONG:       f = "L"
+ *                 elif t == NPY_LONGLONG:    f = "q"
+ */
+      case NPY_LONG:
+      __pyx_v_f = __pyx_k_l;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":267
+ *                 elif t == NPY_UINT:        f = "I"
+ *                 elif t == NPY_LONG:        f = "l"
+ *                 elif t == NPY_ULONG:       f = "L"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_LONGLONG:    f = "q"
+ *                 elif t == NPY_ULONGLONG:   f = "Q"
+ */
+      case NPY_ULONG:
+      __pyx_v_f = __pyx_k_L;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":268
+ *                 elif t == NPY_LONG:        f = "l"
+ *                 elif t == NPY_ULONG:       f = "L"
+ *                 elif t == NPY_LONGLONG:    f = "q"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_ULONGLONG:   f = "Q"
+ *                 elif t == NPY_FLOAT:       f = "f"
+ */
+      case NPY_LONGLONG:
+      __pyx_v_f = __pyx_k_q;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":269
+ *                 elif t == NPY_ULONG:       f = "L"
+ *                 elif t == NPY_LONGLONG:    f = "q"
+ *                 elif t == NPY_ULONGLONG:   f = "Q"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_FLOAT:       f = "f"
+ *                 elif t == NPY_DOUBLE:      f = "d"
+ */
+      case NPY_ULONGLONG:
+      __pyx_v_f = __pyx_k_Q;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":270
+ *                 elif t == NPY_LONGLONG:    f = "q"
+ *                 elif t == NPY_ULONGLONG:   f = "Q"
+ *                 elif t == NPY_FLOAT:       f = "f"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_DOUBLE:      f = "d"
+ *                 elif t == NPY_LONGDOUBLE:  f = "g"
+ */
+      case NPY_FLOAT:
+      __pyx_v_f = __pyx_k_f;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":271
+ *                 elif t == NPY_ULONGLONG:   f = "Q"
+ *                 elif t == NPY_FLOAT:       f = "f"
+ *                 elif t == NPY_DOUBLE:      f = "d"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_LONGDOUBLE:  f = "g"
+ *                 elif t == NPY_CFLOAT:      f = "Zf"
+ */
+      case NPY_DOUBLE:
+      __pyx_v_f = __pyx_k_d;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":272
+ *                 elif t == NPY_FLOAT:       f = "f"
+ *                 elif t == NPY_DOUBLE:      f = "d"
+ *                 elif t == NPY_LONGDOUBLE:  f = "g"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_CFLOAT:      f = "Zf"
+ *                 elif t == NPY_CDOUBLE:     f = "Zd"
+ */
+      case NPY_LONGDOUBLE:
+      __pyx_v_f = __pyx_k_g;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":273
+ *                 elif t == NPY_DOUBLE:      f = "d"
+ *                 elif t == NPY_LONGDOUBLE:  f = "g"
+ *                 elif t == NPY_CFLOAT:      f = "Zf"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_CDOUBLE:     f = "Zd"
+ *                 elif t == NPY_CLONGDOUBLE: f = "Zg"
+ */
+      case NPY_CFLOAT:
+      __pyx_v_f = __pyx_k_Zf;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":274
+ *                 elif t == NPY_LONGDOUBLE:  f = "g"
+ *                 elif t == NPY_CFLOAT:      f = "Zf"
+ *                 elif t == NPY_CDOUBLE:     f = "Zd"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_CLONGDOUBLE: f = "Zg"
+ *                 elif t == NPY_OBJECT:      f = "O"
+ */
+      case NPY_CDOUBLE:
+      __pyx_v_f = __pyx_k_Zd;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":275
+ *                 elif t == NPY_CFLOAT:      f = "Zf"
+ *                 elif t == NPY_CDOUBLE:     f = "Zd"
+ *                 elif t == NPY_CLONGDOUBLE: f = "Zg"             # <<<<<<<<<<<<<<
+ *                 elif t == NPY_OBJECT:      f = "O"
+ *                 else:
+ */
+      case NPY_CLONGDOUBLE:
+      __pyx_v_f = __pyx_k_Zg;
+      break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":276
+ *                 elif t == NPY_CDOUBLE:     f = "Zd"
+ *                 elif t == NPY_CLONGDOUBLE: f = "Zg"
+ *                 elif t == NPY_OBJECT:      f = "O"             # <<<<<<<<<<<<<<
+ *                 else:
+ *                     raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t)
+ */
+      case NPY_OBJECT:
+      __pyx_v_f = __pyx_k_O;
+      break;
+      default:
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":278
+ *                 elif t == NPY_OBJECT:      f = "O"
+ *                 else:
+ *                     raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t)             # <<<<<<<<<<<<<<
+ *                 info.format = f
+ *                 return
+ */
+      __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_t); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 278; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __pyx_t_6 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_t_3); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 278; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_6);
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 278; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __Pyx_GIVEREF(__pyx_t_6);
+      PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_6);
+      __pyx_t_6 = 0;
+      __pyx_t_6 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_3, NULL); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 278; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_6);
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      __Pyx_Raise(__pyx_t_6, 0, 0, 0);
+      __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0;
+      {__pyx_filename = __pyx_f[1]; __pyx_lineno = 278; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      break;
+    }
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":279
+ *                 else:
+ *                     raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t)
+ *                 info.format = f             # <<<<<<<<<<<<<<
+ *                 return
+ *             else:
+ */
+    __pyx_v_info->format = __pyx_v_f;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":280
+ *                     raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t)
+ *                 info.format = f
+ *                 return             # <<<<<<<<<<<<<<
+ *             else:
+ *                 info.format = <char*>stdlib.malloc(_buffer_format_string_len)
+ */
+    __pyx_r = 0;
+    goto __pyx_L0;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":255
+ *                 info.obj = self
+ * 
+ *             if not hasfields:             # <<<<<<<<<<<<<<
+ *                 t = descr.type_num
+ *                 if ((descr.byteorder == c'>' and little_endian) or
+ */
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":282
+ *                 return
+ *             else:
+ *                 info.format = <char*>stdlib.malloc(_buffer_format_string_len)             # <<<<<<<<<<<<<<
+ *                 info.format[0] = c'^' # Native data types, manual alignment
+ *                 offset = 0
+ */
+  /*else*/ {
+    __pyx_v_info->format = ((char *)malloc(0xFF));
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":283
+ *             else:
+ *                 info.format = <char*>stdlib.malloc(_buffer_format_string_len)
+ *                 info.format[0] = c'^' # Native data types, manual alignment             # <<<<<<<<<<<<<<
+ *                 offset = 0
+ *                 f = _util_dtypestring(descr, info.format + 1,
+ */
+    (__pyx_v_info->format[0]) = '^';
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":284
+ *                 info.format = <char*>stdlib.malloc(_buffer_format_string_len)
+ *                 info.format[0] = c'^' # Native data types, manual alignment
+ *                 offset = 0             # <<<<<<<<<<<<<<
+ *                 f = _util_dtypestring(descr, info.format + 1,
+ *                                       info.format + _buffer_format_string_len,
+ */
+    __pyx_v_offset = 0;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":285
+ *                 info.format[0] = c'^' # Native data types, manual alignment
+ *                 offset = 0
+ *                 f = _util_dtypestring(descr, info.format + 1,             # <<<<<<<<<<<<<<
+ *                                       info.format + _buffer_format_string_len,
+ *                                       &offset)
+ */
+    __pyx_t_7 = __pyx_f_5numpy__util_dtypestring(__pyx_v_descr, (__pyx_v_info->format + 1), (__pyx_v_info->format + 0xFF), (&__pyx_v_offset)); if (unlikely(__pyx_t_7 == NULL)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 285; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __pyx_v_f = __pyx_t_7;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":288
+ *                                       info.format + _buffer_format_string_len,
+ *                                       &offset)
+ *                 f[0] = c'\0' # Terminate format string             # <<<<<<<<<<<<<<
+ * 
+ *         def __releasebuffer__(ndarray self, Py_buffer* info):
+ */
+    (__pyx_v_f[0]) = '\x00';
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":197
+ *         # experimental exception made for __getbuffer__ and __releasebuffer__
+ *         # -- the details of this may change.
+ *         def __getbuffer__(ndarray self, Py_buffer* info, int flags):             # <<<<<<<<<<<<<<
+ *             # This implementation of getbuffer is geared towards Cython
+ *             # requirements, and does not yet fullfill the PEP.
+ */
+
+  /* function exit code */
+  __pyx_r = 0;
+  goto __pyx_L0;
+  __pyx_L1_error:;
+  __Pyx_XDECREF(__pyx_t_3);
+  __Pyx_XDECREF(__pyx_t_6);
+  __Pyx_AddTraceback("numpy.ndarray.__getbuffer__", __pyx_clineno, __pyx_lineno, __pyx_filename);
+  __pyx_r = -1;
+  if (__pyx_v_info != NULL && __pyx_v_info->obj != NULL) {
+    __Pyx_GOTREF(__pyx_v_info->obj);
+    __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = NULL;
+  }
+  goto __pyx_L2;
+  __pyx_L0:;
+  if (__pyx_v_info != NULL && __pyx_v_info->obj == Py_None) {
+    __Pyx_GOTREF(Py_None);
+    __Pyx_DECREF(Py_None); __pyx_v_info->obj = NULL;
+  }
+  __pyx_L2:;
+  __Pyx_XDECREF((PyObject *)__pyx_v_descr);
+  __Pyx_RefNannyFinishContext();
+  return __pyx_r;
+}
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":290
+ *                 f[0] = c'\0' # Terminate format string
+ * 
+ *         def __releasebuffer__(ndarray self, Py_buffer* info):             # <<<<<<<<<<<<<<
+ *             if PyArray_HASFIELDS(self):
+ *                 stdlib.free(info.format)
+ */
+
+/* Python wrapper */
+static CYTHON_UNUSED void __pyx_pw_5numpy_7ndarray_3__releasebuffer__(PyObject *__pyx_v_self, Py_buffer *__pyx_v_info); /*proto*/
+static CYTHON_UNUSED void __pyx_pw_5numpy_7ndarray_3__releasebuffer__(PyObject *__pyx_v_self, Py_buffer *__pyx_v_info) {
+  __Pyx_RefNannyDeclarations
+  __Pyx_RefNannySetupContext("__releasebuffer__ (wrapper)", 0);
+  __pyx_pf_5numpy_7ndarray_2__releasebuffer__(((PyArrayObject *)__pyx_v_self), ((Py_buffer *)__pyx_v_info));
+
+  /* function exit code */
+  __Pyx_RefNannyFinishContext();
+}
+
+static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_self, Py_buffer *__pyx_v_info) {
+  __Pyx_RefNannyDeclarations
+  int __pyx_t_1;
+  __Pyx_RefNannySetupContext("__releasebuffer__", 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":291
+ * 
+ *         def __releasebuffer__(ndarray self, Py_buffer* info):
+ *             if PyArray_HASFIELDS(self):             # <<<<<<<<<<<<<<
+ *                 stdlib.free(info.format)
+ *             if sizeof(npy_intp) != sizeof(Py_ssize_t):
+ */
+  __pyx_t_1 = (PyArray_HASFIELDS(__pyx_v_self) != 0);
+  if (__pyx_t_1) {
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":292
+ *         def __releasebuffer__(ndarray self, Py_buffer* info):
+ *             if PyArray_HASFIELDS(self):
+ *                 stdlib.free(info.format)             # <<<<<<<<<<<<<<
+ *             if sizeof(npy_intp) != sizeof(Py_ssize_t):
+ *                 stdlib.free(info.strides)
+ */
+    free(__pyx_v_info->format);
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":291
+ * 
+ *         def __releasebuffer__(ndarray self, Py_buffer* info):
+ *             if PyArray_HASFIELDS(self):             # <<<<<<<<<<<<<<
+ *                 stdlib.free(info.format)
+ *             if sizeof(npy_intp) != sizeof(Py_ssize_t):
+ */
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":293
+ *             if PyArray_HASFIELDS(self):
+ *                 stdlib.free(info.format)
+ *             if sizeof(npy_intp) != sizeof(Py_ssize_t):             # <<<<<<<<<<<<<<
+ *                 stdlib.free(info.strides)
+ *                 # info.shape was stored after info.strides in the same block
+ */
+  __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0);
+  if (__pyx_t_1) {
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":294
+ *                 stdlib.free(info.format)
+ *             if sizeof(npy_intp) != sizeof(Py_ssize_t):
+ *                 stdlib.free(info.strides)             # <<<<<<<<<<<<<<
+ *                 # info.shape was stored after info.strides in the same block
+ * 
+ */
+    free(__pyx_v_info->strides);
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":293
+ *             if PyArray_HASFIELDS(self):
+ *                 stdlib.free(info.format)
+ *             if sizeof(npy_intp) != sizeof(Py_ssize_t):             # <<<<<<<<<<<<<<
+ *                 stdlib.free(info.strides)
+ *                 # info.shape was stored after info.strides in the same block
+ */
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":290
+ *                 f[0] = c'\0' # Terminate format string
+ * 
+ *         def __releasebuffer__(ndarray self, Py_buffer* info):             # <<<<<<<<<<<<<<
+ *             if PyArray_HASFIELDS(self):
+ *                 stdlib.free(info.format)
+ */
+
+  /* function exit code */
+  __Pyx_RefNannyFinishContext();
+}
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":770
+ * ctypedef npy_cdouble     complex_t
+ * 
+ * cdef inline object PyArray_MultiIterNew1(a):             # <<<<<<<<<<<<<<
+ *     return PyArray_MultiIterNew(1, <void*>a)
+ * 
+ */
+
+static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__pyx_v_a) {
+  PyObject *__pyx_r = NULL;
+  __Pyx_RefNannyDeclarations
+  PyObject *__pyx_t_1 = NULL;
+  int __pyx_lineno = 0;
+  const char *__pyx_filename = NULL;
+  int __pyx_clineno = 0;
+  __Pyx_RefNannySetupContext("PyArray_MultiIterNew1", 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":771
+ * 
+ * cdef inline object PyArray_MultiIterNew1(a):
+ *     return PyArray_MultiIterNew(1, <void*>a)             # <<<<<<<<<<<<<<
+ * 
+ * cdef inline object PyArray_MultiIterNew2(a, b):
+ */
+  __Pyx_XDECREF(__pyx_r);
+  __pyx_t_1 = PyArray_MultiIterNew(1, ((void *)__pyx_v_a)); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 771; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_1);
+  __pyx_r = __pyx_t_1;
+  __pyx_t_1 = 0;
+  goto __pyx_L0;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":770
+ * ctypedef npy_cdouble     complex_t
+ * 
+ * cdef inline object PyArray_MultiIterNew1(a):             # <<<<<<<<<<<<<<
+ *     return PyArray_MultiIterNew(1, <void*>a)
+ * 
+ */
+
+  /* function exit code */
+  __pyx_L1_error:;
+  __Pyx_XDECREF(__pyx_t_1);
+  __Pyx_AddTraceback("numpy.PyArray_MultiIterNew1", __pyx_clineno, __pyx_lineno, __pyx_filename);
+  __pyx_r = 0;
+  __pyx_L0:;
+  __Pyx_XGIVEREF(__pyx_r);
+  __Pyx_RefNannyFinishContext();
+  return __pyx_r;
+}
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":773
+ *     return PyArray_MultiIterNew(1, <void*>a)
+ * 
+ * cdef inline object PyArray_MultiIterNew2(a, b):             # <<<<<<<<<<<<<<
+ *     return PyArray_MultiIterNew(2, <void*>a, <void*>b)
+ * 
+ */
+
+static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__pyx_v_a, PyObject *__pyx_v_b) {
+  PyObject *__pyx_r = NULL;
+  __Pyx_RefNannyDeclarations
+  PyObject *__pyx_t_1 = NULL;
+  int __pyx_lineno = 0;
+  const char *__pyx_filename = NULL;
+  int __pyx_clineno = 0;
+  __Pyx_RefNannySetupContext("PyArray_MultiIterNew2", 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":774
+ * 
+ * cdef inline object PyArray_MultiIterNew2(a, b):
+ *     return PyArray_MultiIterNew(2, <void*>a, <void*>b)             # <<<<<<<<<<<<<<
+ * 
+ * cdef inline object PyArray_MultiIterNew3(a, b, c):
+ */
+  __Pyx_XDECREF(__pyx_r);
+  __pyx_t_1 = PyArray_MultiIterNew(2, ((void *)__pyx_v_a), ((void *)__pyx_v_b)); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 774; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_1);
+  __pyx_r = __pyx_t_1;
+  __pyx_t_1 = 0;
+  goto __pyx_L0;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":773
+ *     return PyArray_MultiIterNew(1, <void*>a)
+ * 
+ * cdef inline object PyArray_MultiIterNew2(a, b):             # <<<<<<<<<<<<<<
+ *     return PyArray_MultiIterNew(2, <void*>a, <void*>b)
+ * 
+ */
+
+  /* function exit code */
+  __pyx_L1_error:;
+  __Pyx_XDECREF(__pyx_t_1);
+  __Pyx_AddTraceback("numpy.PyArray_MultiIterNew2", __pyx_clineno, __pyx_lineno, __pyx_filename);
+  __pyx_r = 0;
+  __pyx_L0:;
+  __Pyx_XGIVEREF(__pyx_r);
+  __Pyx_RefNannyFinishContext();
+  return __pyx_r;
+}
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":776
+ *     return PyArray_MultiIterNew(2, <void*>a, <void*>b)
+ * 
+ * cdef inline object PyArray_MultiIterNew3(a, b, c):             # <<<<<<<<<<<<<<
+ *     return PyArray_MultiIterNew(3, <void*>a, <void*>b, <void*> c)
+ * 
+ */
+
+static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__pyx_v_a, PyObject *__pyx_v_b, PyObject *__pyx_v_c) {
+  PyObject *__pyx_r = NULL;
+  __Pyx_RefNannyDeclarations
+  PyObject *__pyx_t_1 = NULL;
+  int __pyx_lineno = 0;
+  const char *__pyx_filename = NULL;
+  int __pyx_clineno = 0;
+  __Pyx_RefNannySetupContext("PyArray_MultiIterNew3", 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":777
+ * 
+ * cdef inline object PyArray_MultiIterNew3(a, b, c):
+ *     return PyArray_MultiIterNew(3, <void*>a, <void*>b, <void*> c)             # <<<<<<<<<<<<<<
+ * 
+ * cdef inline object PyArray_MultiIterNew4(a, b, c, d):
+ */
+  __Pyx_XDECREF(__pyx_r);
+  __pyx_t_1 = PyArray_MultiIterNew(3, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c)); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 777; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_1);
+  __pyx_r = __pyx_t_1;
+  __pyx_t_1 = 0;
+  goto __pyx_L0;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":776
+ *     return PyArray_MultiIterNew(2, <void*>a, <void*>b)
+ * 
+ * cdef inline object PyArray_MultiIterNew3(a, b, c):             # <<<<<<<<<<<<<<
+ *     return PyArray_MultiIterNew(3, <void*>a, <void*>b, <void*> c)
+ * 
+ */
+
+  /* function exit code */
+  __pyx_L1_error:;
+  __Pyx_XDECREF(__pyx_t_1);
+  __Pyx_AddTraceback("numpy.PyArray_MultiIterNew3", __pyx_clineno, __pyx_lineno, __pyx_filename);
+  __pyx_r = 0;
+  __pyx_L0:;
+  __Pyx_XGIVEREF(__pyx_r);
+  __Pyx_RefNannyFinishContext();
+  return __pyx_r;
+}
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":779
+ *     return PyArray_MultiIterNew(3, <void*>a, <void*>b, <void*> c)
+ * 
+ * cdef inline object PyArray_MultiIterNew4(a, b, c, d):             # <<<<<<<<<<<<<<
+ *     return PyArray_MultiIterNew(4, <void*>a, <void*>b, <void*>c, <void*> d)
+ * 
+ */
+
+static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__pyx_v_a, PyObject *__pyx_v_b, PyObject *__pyx_v_c, PyObject *__pyx_v_d) {
+  PyObject *__pyx_r = NULL;
+  __Pyx_RefNannyDeclarations
+  PyObject *__pyx_t_1 = NULL;
+  int __pyx_lineno = 0;
+  const char *__pyx_filename = NULL;
+  int __pyx_clineno = 0;
+  __Pyx_RefNannySetupContext("PyArray_MultiIterNew4", 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":780
+ * 
+ * cdef inline object PyArray_MultiIterNew4(a, b, c, d):
+ *     return PyArray_MultiIterNew(4, <void*>a, <void*>b, <void*>c, <void*> d)             # <<<<<<<<<<<<<<
+ * 
+ * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e):
+ */
+  __Pyx_XDECREF(__pyx_r);
+  __pyx_t_1 = PyArray_MultiIterNew(4, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d)); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 780; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_1);
+  __pyx_r = __pyx_t_1;
+  __pyx_t_1 = 0;
+  goto __pyx_L0;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":779
+ *     return PyArray_MultiIterNew(3, <void*>a, <void*>b, <void*> c)
+ * 
+ * cdef inline object PyArray_MultiIterNew4(a, b, c, d):             # <<<<<<<<<<<<<<
+ *     return PyArray_MultiIterNew(4, <void*>a, <void*>b, <void*>c, <void*> d)
+ * 
+ */
+
+  /* function exit code */
+  __pyx_L1_error:;
+  __Pyx_XDECREF(__pyx_t_1);
+  __Pyx_AddTraceback("numpy.PyArray_MultiIterNew4", __pyx_clineno, __pyx_lineno, __pyx_filename);
+  __pyx_r = 0;
+  __pyx_L0:;
+  __Pyx_XGIVEREF(__pyx_r);
+  __Pyx_RefNannyFinishContext();
+  return __pyx_r;
+}
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":782
+ *     return PyArray_MultiIterNew(4, <void*>a, <void*>b, <void*>c, <void*> d)
+ * 
+ * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e):             # <<<<<<<<<<<<<<
+ *     return PyArray_MultiIterNew(5, <void*>a, <void*>b, <void*>c, <void*> d, <void*> e)
+ * 
+ */
+
+static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__pyx_v_a, PyObject *__pyx_v_b, PyObject *__pyx_v_c, PyObject *__pyx_v_d, PyObject *__pyx_v_e) {
+  PyObject *__pyx_r = NULL;
+  __Pyx_RefNannyDeclarations
+  PyObject *__pyx_t_1 = NULL;
+  int __pyx_lineno = 0;
+  const char *__pyx_filename = NULL;
+  int __pyx_clineno = 0;
+  __Pyx_RefNannySetupContext("PyArray_MultiIterNew5", 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":783
+ * 
+ * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e):
+ *     return PyArray_MultiIterNew(5, <void*>a, <void*>b, <void*>c, <void*> d, <void*> e)             # <<<<<<<<<<<<<<
+ * 
+ * cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL:
+ */
+  __Pyx_XDECREF(__pyx_r);
+  __pyx_t_1 = PyArray_MultiIterNew(5, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d), ((void *)__pyx_v_e)); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 783; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_1);
+  __pyx_r = __pyx_t_1;
+  __pyx_t_1 = 0;
+  goto __pyx_L0;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":782
+ *     return PyArray_MultiIterNew(4, <void*>a, <void*>b, <void*>c, <void*> d)
+ * 
+ * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e):             # <<<<<<<<<<<<<<
+ *     return PyArray_MultiIterNew(5, <void*>a, <void*>b, <void*>c, <void*> d, <void*> e)
+ * 
+ */
+
+  /* function exit code */
+  __pyx_L1_error:;
+  __Pyx_XDECREF(__pyx_t_1);
+  __Pyx_AddTraceback("numpy.PyArray_MultiIterNew5", __pyx_clineno, __pyx_lineno, __pyx_filename);
+  __pyx_r = 0;
+  __pyx_L0:;
+  __Pyx_XGIVEREF(__pyx_r);
+  __Pyx_RefNannyFinishContext();
+  return __pyx_r;
+}
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":785
+ *     return PyArray_MultiIterNew(5, <void*>a, <void*>b, <void*>c, <void*> d, <void*> e)
+ * 
+ * cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL:             # <<<<<<<<<<<<<<
+ *     # Recursive utility function used in __getbuffer__ to get format
+ *     # string. The new location in the format string is returned.
+ */
+
+static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx_v_descr, char *__pyx_v_f, char *__pyx_v_end, int *__pyx_v_offset) {
+  PyArray_Descr *__pyx_v_child = 0;
+  int __pyx_v_endian_detector;
+  int __pyx_v_little_endian;
+  PyObject *__pyx_v_fields = 0;
+  PyObject *__pyx_v_childname = NULL;
+  PyObject *__pyx_v_new_offset = NULL;
+  PyObject *__pyx_v_t = NULL;
+  char *__pyx_r;
+  __Pyx_RefNannyDeclarations
+  PyObject *__pyx_t_1 = NULL;
+  Py_ssize_t __pyx_t_2;
+  PyObject *__pyx_t_3 = NULL;
+  PyObject *__pyx_t_4 = NULL;
+  int __pyx_t_5;
+  int __pyx_t_6;
+  int __pyx_t_7;
+  long __pyx_t_8;
+  char *__pyx_t_9;
+  int __pyx_lineno = 0;
+  const char *__pyx_filename = NULL;
+  int __pyx_clineno = 0;
+  __Pyx_RefNannySetupContext("_util_dtypestring", 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":790
+ * 
+ *     cdef dtype child
+ *     cdef int endian_detector = 1             # <<<<<<<<<<<<<<
+ *     cdef bint little_endian = ((<char*>&endian_detector)[0] != 0)
+ *     cdef tuple fields
+ */
+  __pyx_v_endian_detector = 1;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":791
+ *     cdef dtype child
+ *     cdef int endian_detector = 1
+ *     cdef bint little_endian = ((<char*>&endian_detector)[0] != 0)             # <<<<<<<<<<<<<<
+ *     cdef tuple fields
+ * 
+ */
+  __pyx_v_little_endian = ((((char *)(&__pyx_v_endian_detector))[0]) != 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":794
+ *     cdef tuple fields
+ * 
+ *     for childname in descr.names:             # <<<<<<<<<<<<<<
+ *         fields = descr.fields[childname]
+ *         child, new_offset = fields
+ */
+  if (unlikely(__pyx_v_descr->names == Py_None)) {
+    PyErr_SetString(PyExc_TypeError, "'NoneType' object is not iterable");
+    {__pyx_filename = __pyx_f[1]; __pyx_lineno = 794; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  }
+  __pyx_t_1 = __pyx_v_descr->names; __Pyx_INCREF(__pyx_t_1); __pyx_t_2 = 0;
+  for (;;) {
+    if (__pyx_t_2 >= PyTuple_GET_SIZE(__pyx_t_1)) break;
+    #if CYTHON_COMPILING_IN_CPYTHON
+    __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_3); __pyx_t_2++; if (unlikely(0 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 794; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    #else
+    __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 794; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_3);
+    #endif
+    __Pyx_XDECREF_SET(__pyx_v_childname, __pyx_t_3);
+    __pyx_t_3 = 0;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":795
+ * 
+ *     for childname in descr.names:
+ *         fields = descr.fields[childname]             # <<<<<<<<<<<<<<
+ *         child, new_offset = fields
+ * 
+ */
+    if (unlikely(__pyx_v_descr->fields == Py_None)) {
+      PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable");
+      {__pyx_filename = __pyx_f[1]; __pyx_lineno = 795; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    }
+    __pyx_t_3 = __Pyx_PyDict_GetItem(__pyx_v_descr->fields, __pyx_v_childname); if (unlikely(__pyx_t_3 == NULL)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 795; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
+    __Pyx_GOTREF(__pyx_t_3);
+    if (!(likely(PyTuple_CheckExact(__pyx_t_3))||((__pyx_t_3) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "tuple", Py_TYPE(__pyx_t_3)->tp_name), 0))) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 795; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_XDECREF_SET(__pyx_v_fields, ((PyObject*)__pyx_t_3));
+    __pyx_t_3 = 0;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":796
+ *     for childname in descr.names:
+ *         fields = descr.fields[childname]
+ *         child, new_offset = fields             # <<<<<<<<<<<<<<
+ * 
+ *         if (end - f) - <int>(new_offset - offset[0]) < 15:
+ */
+    if (likely(__pyx_v_fields != Py_None)) {
+      PyObject* sequence = __pyx_v_fields;
+      #if CYTHON_COMPILING_IN_CPYTHON
+      Py_ssize_t size = Py_SIZE(sequence);
+      #else
+      Py_ssize_t size = PySequence_Size(sequence);
+      #endif
+      if (unlikely(size != 2)) {
+        if (size > 2) __Pyx_RaiseTooManyValuesError(2);
+        else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size);
+        {__pyx_filename = __pyx_f[1]; __pyx_lineno = 796; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      }
+      #if CYTHON_COMPILING_IN_CPYTHON
+      __pyx_t_3 = PyTuple_GET_ITEM(sequence, 0); 
+      __pyx_t_4 = PyTuple_GET_ITEM(sequence, 1); 
+      __Pyx_INCREF(__pyx_t_3);
+      __Pyx_INCREF(__pyx_t_4);
+      #else
+      __pyx_t_3 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 796; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __pyx_t_4 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 796; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      #endif
+    } else {
+      __Pyx_RaiseNoneNotIterableError(); {__pyx_filename = __pyx_f[1]; __pyx_lineno = 796; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    }
+    if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_dtype))))) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 796; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_XDECREF_SET(__pyx_v_child, ((PyArray_Descr *)__pyx_t_3));
+    __pyx_t_3 = 0;
+    __Pyx_XDECREF_SET(__pyx_v_new_offset, __pyx_t_4);
+    __pyx_t_4 = 0;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":798
+ *         child, new_offset = fields
+ * 
+ *         if (end - f) - <int>(new_offset - offset[0]) < 15:             # <<<<<<<<<<<<<<
+ *             raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd")
+ * 
+ */
+    __pyx_t_4 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 798; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_4);
+    __pyx_t_3 = PyNumber_Subtract(__pyx_v_new_offset, __pyx_t_4); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 798; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_GOTREF(__pyx_t_3);
+    __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+    __pyx_t_5 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_5 == (int)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 798; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+    __pyx_t_6 = ((((__pyx_v_end - __pyx_v_f) - ((int)__pyx_t_5)) < 15) != 0);
+    if (__pyx_t_6) {
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":799
+ * 
+ *         if (end - f) - <int>(new_offset - offset[0]) < 15:
+ *             raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd")             # <<<<<<<<<<<<<<
+ * 
+ *         if ((child.byteorder == c'>' and little_endian) or
+ */
+      __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__4, NULL); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 799; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __Pyx_Raise(__pyx_t_3, 0, 0, 0);
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      {__pyx_filename = __pyx_f[1]; __pyx_lineno = 799; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":798
+ *         child, new_offset = fields
+ * 
+ *         if (end - f) - <int>(new_offset - offset[0]) < 15:             # <<<<<<<<<<<<<<
+ *             raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd")
+ * 
+ */
+    }
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":801
+ *             raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd")
+ * 
+ *         if ((child.byteorder == c'>' and little_endian) or             # <<<<<<<<<<<<<<
+ *             (child.byteorder == c'<' and not little_endian)):
+ *             raise ValueError(u"Non-native byte order not supported")
+ */
+    __pyx_t_7 = ((__pyx_v_child->byteorder == '>') != 0);
+    if (!__pyx_t_7) {
+      goto __pyx_L8_next_or;
+    } else {
+    }
+    __pyx_t_7 = (__pyx_v_little_endian != 0);
+    if (!__pyx_t_7) {
+    } else {
+      __pyx_t_6 = __pyx_t_7;
+      goto __pyx_L7_bool_binop_done;
+    }
+    __pyx_L8_next_or:;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":802
+ * 
+ *         if ((child.byteorder == c'>' and little_endian) or
+ *             (child.byteorder == c'<' and not little_endian)):             # <<<<<<<<<<<<<<
+ *             raise ValueError(u"Non-native byte order not supported")
+ *             # One could encode it in the format string and have Cython
+ */
+    __pyx_t_7 = ((__pyx_v_child->byteorder == '<') != 0);
+    if (__pyx_t_7) {
+    } else {
+      __pyx_t_6 = __pyx_t_7;
+      goto __pyx_L7_bool_binop_done;
+    }
+    __pyx_t_7 = ((!(__pyx_v_little_endian != 0)) != 0);
+    __pyx_t_6 = __pyx_t_7;
+    __pyx_L7_bool_binop_done:;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":801
+ *             raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd")
+ * 
+ *         if ((child.byteorder == c'>' and little_endian) or             # <<<<<<<<<<<<<<
+ *             (child.byteorder == c'<' and not little_endian)):
+ *             raise ValueError(u"Non-native byte order not supported")
+ */
+    if (__pyx_t_6) {
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":803
+ *         if ((child.byteorder == c'>' and little_endian) or
+ *             (child.byteorder == c'<' and not little_endian)):
+ *             raise ValueError(u"Non-native byte order not supported")             # <<<<<<<<<<<<<<
+ *             # One could encode it in the format string and have Cython
+ *             # complain instead, BUT: < and > in format strings also imply
+ */
+      __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__5, NULL); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 803; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __Pyx_Raise(__pyx_t_3, 0, 0, 0);
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      {__pyx_filename = __pyx_f[1]; __pyx_lineno = 803; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":801
+ *             raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd")
+ * 
+ *         if ((child.byteorder == c'>' and little_endian) or             # <<<<<<<<<<<<<<
+ *             (child.byteorder == c'<' and not little_endian)):
+ *             raise ValueError(u"Non-native byte order not supported")
+ */
+    }
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":813
+ * 
+ *         # Output padding bytes
+ *         while offset[0] < new_offset:             # <<<<<<<<<<<<<<
+ *             f[0] = 120 # "x"; pad byte
+ *             f += 1
+ */
+    while (1) {
+      __pyx_t_3 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 813; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __pyx_t_4 = PyObject_RichCompare(__pyx_t_3, __pyx_v_new_offset, Py_LT); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 813; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 813; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      if (!__pyx_t_6) break;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":814
+ *         # Output padding bytes
+ *         while offset[0] < new_offset:
+ *             f[0] = 120 # "x"; pad byte             # <<<<<<<<<<<<<<
+ *             f += 1
+ *             offset[0] += 1
+ */
+      (__pyx_v_f[0]) = 0x78;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":815
+ *         while offset[0] < new_offset:
+ *             f[0] = 120 # "x"; pad byte
+ *             f += 1             # <<<<<<<<<<<<<<
+ *             offset[0] += 1
+ * 
+ */
+      __pyx_v_f = (__pyx_v_f + 1);
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":816
+ *             f[0] = 120 # "x"; pad byte
+ *             f += 1
+ *             offset[0] += 1             # <<<<<<<<<<<<<<
+ * 
+ *         offset[0] += child.itemsize
+ */
+      __pyx_t_8 = 0;
+      (__pyx_v_offset[__pyx_t_8]) = ((__pyx_v_offset[__pyx_t_8]) + 1);
+    }
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":818
+ *             offset[0] += 1
+ * 
+ *         offset[0] += child.itemsize             # <<<<<<<<<<<<<<
+ * 
+ *         if not PyDataType_HASFIELDS(child):
+ */
+    __pyx_t_8 = 0;
+    (__pyx_v_offset[__pyx_t_8]) = ((__pyx_v_offset[__pyx_t_8]) + __pyx_v_child->elsize);
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":820
+ *         offset[0] += child.itemsize
+ * 
+ *         if not PyDataType_HASFIELDS(child):             # <<<<<<<<<<<<<<
+ *             t = child.type_num
+ *             if end - f < 5:
+ */
+    __pyx_t_6 = ((!(PyDataType_HASFIELDS(__pyx_v_child) != 0)) != 0);
+    if (__pyx_t_6) {
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":821
+ * 
+ *         if not PyDataType_HASFIELDS(child):
+ *             t = child.type_num             # <<<<<<<<<<<<<<
+ *             if end - f < 5:
+ *                 raise RuntimeError(u"Format string allocated too short.")
+ */
+      __pyx_t_4 = __Pyx_PyInt_From_int(__pyx_v_child->type_num); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 821; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __Pyx_XDECREF_SET(__pyx_v_t, __pyx_t_4);
+      __pyx_t_4 = 0;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":822
+ *         if not PyDataType_HASFIELDS(child):
+ *             t = child.type_num
+ *             if end - f < 5:             # <<<<<<<<<<<<<<
+ *                 raise RuntimeError(u"Format string allocated too short.")
+ * 
+ */
+      __pyx_t_6 = (((__pyx_v_end - __pyx_v_f) < 5) != 0);
+      if (__pyx_t_6) {
+
+        /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":823
+ *             t = child.type_num
+ *             if end - f < 5:
+ *                 raise RuntimeError(u"Format string allocated too short.")             # <<<<<<<<<<<<<<
+ * 
+ *             # Until ticket #99 is fixed, use integers to avoid warnings
+ */
+        __pyx_t_4 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__6, NULL); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 823; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+        __Pyx_GOTREF(__pyx_t_4);
+        __Pyx_Raise(__pyx_t_4, 0, 0, 0);
+        __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+        {__pyx_filename = __pyx_f[1]; __pyx_lineno = 823; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+
+        /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":822
+ *         if not PyDataType_HASFIELDS(child):
+ *             t = child.type_num
+ *             if end - f < 5:             # <<<<<<<<<<<<<<
+ *                 raise RuntimeError(u"Format string allocated too short.")
+ * 
+ */
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":826
+ * 
+ *             # Until ticket #99 is fixed, use integers to avoid warnings
+ *             if   t == NPY_BYTE:        f[0] =  98 #"b"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_UBYTE:       f[0] =  66 #"B"
+ *             elif t == NPY_SHORT:       f[0] = 104 #"h"
+ */
+      __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_BYTE); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 826; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 826; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 826; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 98;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":827
+ *             # Until ticket #99 is fixed, use integers to avoid warnings
+ *             if   t == NPY_BYTE:        f[0] =  98 #"b"
+ *             elif t == NPY_UBYTE:       f[0] =  66 #"B"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_SHORT:       f[0] = 104 #"h"
+ *             elif t == NPY_USHORT:      f[0] =  72 #"H"
+ */
+      __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UBYTE); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 827; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 827; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 827; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 66;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":828
+ *             if   t == NPY_BYTE:        f[0] =  98 #"b"
+ *             elif t == NPY_UBYTE:       f[0] =  66 #"B"
+ *             elif t == NPY_SHORT:       f[0] = 104 #"h"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_USHORT:      f[0] =  72 #"H"
+ *             elif t == NPY_INT:         f[0] = 105 #"i"
+ */
+      __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_SHORT); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 828; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 828; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 828; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 0x68;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":829
+ *             elif t == NPY_UBYTE:       f[0] =  66 #"B"
+ *             elif t == NPY_SHORT:       f[0] = 104 #"h"
+ *             elif t == NPY_USHORT:      f[0] =  72 #"H"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_INT:         f[0] = 105 #"i"
+ *             elif t == NPY_UINT:        f[0] =  73 #"I"
+ */
+      __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_USHORT); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 829; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 829; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 829; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 72;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":830
+ *             elif t == NPY_SHORT:       f[0] = 104 #"h"
+ *             elif t == NPY_USHORT:      f[0] =  72 #"H"
+ *             elif t == NPY_INT:         f[0] = 105 #"i"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_UINT:        f[0] =  73 #"I"
+ *             elif t == NPY_LONG:        f[0] = 108 #"l"
+ */
+      __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_INT); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 830; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 830; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 830; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 0x69;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":831
+ *             elif t == NPY_USHORT:      f[0] =  72 #"H"
+ *             elif t == NPY_INT:         f[0] = 105 #"i"
+ *             elif t == NPY_UINT:        f[0] =  73 #"I"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_LONG:        f[0] = 108 #"l"
+ *             elif t == NPY_ULONG:       f[0] = 76  #"L"
+ */
+      __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UINT); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 831; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 831; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 831; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 73;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":832
+ *             elif t == NPY_INT:         f[0] = 105 #"i"
+ *             elif t == NPY_UINT:        f[0] =  73 #"I"
+ *             elif t == NPY_LONG:        f[0] = 108 #"l"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_ULONG:       f[0] = 76  #"L"
+ *             elif t == NPY_LONGLONG:    f[0] = 113 #"q"
+ */
+      __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONG); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 832; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 832; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 832; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 0x6C;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":833
+ *             elif t == NPY_UINT:        f[0] =  73 #"I"
+ *             elif t == NPY_LONG:        f[0] = 108 #"l"
+ *             elif t == NPY_ULONG:       f[0] = 76  #"L"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_LONGLONG:    f[0] = 113 #"q"
+ *             elif t == NPY_ULONGLONG:   f[0] = 81  #"Q"
+ */
+      __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONG); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 833; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 833; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 833; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 76;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":834
+ *             elif t == NPY_LONG:        f[0] = 108 #"l"
+ *             elif t == NPY_ULONG:       f[0] = 76  #"L"
+ *             elif t == NPY_LONGLONG:    f[0] = 113 #"q"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_ULONGLONG:   f[0] = 81  #"Q"
+ *             elif t == NPY_FLOAT:       f[0] = 102 #"f"
+ */
+      __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGLONG); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 834; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 834; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 834; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 0x71;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":835
+ *             elif t == NPY_ULONG:       f[0] = 76  #"L"
+ *             elif t == NPY_LONGLONG:    f[0] = 113 #"q"
+ *             elif t == NPY_ULONGLONG:   f[0] = 81  #"Q"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_FLOAT:       f[0] = 102 #"f"
+ *             elif t == NPY_DOUBLE:      f[0] = 100 #"d"
+ */
+      __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONGLONG); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 835; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 835; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 835; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 81;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":836
+ *             elif t == NPY_LONGLONG:    f[0] = 113 #"q"
+ *             elif t == NPY_ULONGLONG:   f[0] = 81  #"Q"
+ *             elif t == NPY_FLOAT:       f[0] = 102 #"f"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_DOUBLE:      f[0] = 100 #"d"
+ *             elif t == NPY_LONGDOUBLE:  f[0] = 103 #"g"
+ */
+      __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_FLOAT); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 836; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 836; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 836; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 0x66;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":837
+ *             elif t == NPY_ULONGLONG:   f[0] = 81  #"Q"
+ *             elif t == NPY_FLOAT:       f[0] = 102 #"f"
+ *             elif t == NPY_DOUBLE:      f[0] = 100 #"d"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_LONGDOUBLE:  f[0] = 103 #"g"
+ *             elif t == NPY_CFLOAT:      f[0] = 90; f[1] = 102; f += 1 # Zf
+ */
+      __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_DOUBLE); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 837; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 837; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 837; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 0x64;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":838
+ *             elif t == NPY_FLOAT:       f[0] = 102 #"f"
+ *             elif t == NPY_DOUBLE:      f[0] = 100 #"d"
+ *             elif t == NPY_LONGDOUBLE:  f[0] = 103 #"g"             # <<<<<<<<<<<<<<
+ *             elif t == NPY_CFLOAT:      f[0] = 90; f[1] = 102; f += 1 # Zf
+ *             elif t == NPY_CDOUBLE:     f[0] = 90; f[1] = 100; f += 1 # Zd
+ */
+      __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGDOUBLE); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 838; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 838; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 838; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 0x67;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":839
+ *             elif t == NPY_DOUBLE:      f[0] = 100 #"d"
+ *             elif t == NPY_LONGDOUBLE:  f[0] = 103 #"g"
+ *             elif t == NPY_CFLOAT:      f[0] = 90; f[1] = 102; f += 1 # Zf             # <<<<<<<<<<<<<<
+ *             elif t == NPY_CDOUBLE:     f[0] = 90; f[1] = 100; f += 1 # Zd
+ *             elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg
+ */
+      __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CFLOAT); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 839; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 839; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 839; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 90;
+        (__pyx_v_f[1]) = 0x66;
+        __pyx_v_f = (__pyx_v_f + 1);
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":840
+ *             elif t == NPY_LONGDOUBLE:  f[0] = 103 #"g"
+ *             elif t == NPY_CFLOAT:      f[0] = 90; f[1] = 102; f += 1 # Zf
+ *             elif t == NPY_CDOUBLE:     f[0] = 90; f[1] = 100; f += 1 # Zd             # <<<<<<<<<<<<<<
+ *             elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg
+ *             elif t == NPY_OBJECT:      f[0] = 79 #"O"
+ */
+      __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CDOUBLE); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 840; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 840; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 840; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 90;
+        (__pyx_v_f[1]) = 0x64;
+        __pyx_v_f = (__pyx_v_f + 1);
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":841
+ *             elif t == NPY_CFLOAT:      f[0] = 90; f[1] = 102; f += 1 # Zf
+ *             elif t == NPY_CDOUBLE:     f[0] = 90; f[1] = 100; f += 1 # Zd
+ *             elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg             # <<<<<<<<<<<<<<
+ *             elif t == NPY_OBJECT:      f[0] = 79 #"O"
+ *             else:
+ */
+      __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CLONGDOUBLE); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 841; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_3);
+      __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 841; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 841; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 90;
+        (__pyx_v_f[1]) = 0x67;
+        __pyx_v_f = (__pyx_v_f + 1);
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":842
+ *             elif t == NPY_CDOUBLE:     f[0] = 90; f[1] = 100; f += 1 # Zd
+ *             elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg
+ *             elif t == NPY_OBJECT:      f[0] = 79 #"O"             # <<<<<<<<<<<<<<
+ *             else:
+ *                 raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t)
+ */
+      __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_OBJECT); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 842; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_GOTREF(__pyx_t_4);
+      __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 842; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+      __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 842; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+      if (__pyx_t_6) {
+        (__pyx_v_f[0]) = 79;
+        goto __pyx_L15;
+      }
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":844
+ *             elif t == NPY_OBJECT:      f[0] = 79 #"O"
+ *             else:
+ *                 raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t)             # <<<<<<<<<<<<<<
+ *             f += 1
+ *         else:
+ */
+      /*else*/ {
+        __pyx_t_3 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_v_t); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 844; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+        __Pyx_GOTREF(__pyx_t_3);
+        __pyx_t_4 = PyTuple_New(1); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 844; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+        __Pyx_GOTREF(__pyx_t_4);
+        __Pyx_GIVEREF(__pyx_t_3);
+        PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_3);
+        __pyx_t_3 = 0;
+        __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_4, NULL); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 844; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+        __Pyx_GOTREF(__pyx_t_3);
+        __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
+        __Pyx_Raise(__pyx_t_3, 0, 0, 0);
+        __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
+        {__pyx_filename = __pyx_f[1]; __pyx_lineno = 844; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      }
+      __pyx_L15:;
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":845
+ *             else:
+ *                 raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t)
+ *             f += 1             # <<<<<<<<<<<<<<
+ *         else:
+ *             # Cython ignores struct boundary information ("T{...}"),
+ */
+      __pyx_v_f = (__pyx_v_f + 1);
+
+      /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":820
+ *         offset[0] += child.itemsize
+ * 
+ *         if not PyDataType_HASFIELDS(child):             # <<<<<<<<<<<<<<
+ *             t = child.type_num
+ *             if end - f < 5:
+ */
+      goto __pyx_L13;
+    }
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":849
+ *             # Cython ignores struct boundary information ("T{...}"),
+ *             # so don't output it
+ *             f = _util_dtypestring(child, f, end, offset)             # <<<<<<<<<<<<<<
+ *     return f
+ * 
+ */
+    /*else*/ {
+      __pyx_t_9 = __pyx_f_5numpy__util_dtypestring(__pyx_v_child, __pyx_v_f, __pyx_v_end, __pyx_v_offset); if (unlikely(__pyx_t_9 == NULL)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 849; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+      __pyx_v_f = __pyx_t_9;
+    }
+    __pyx_L13:;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":794
+ *     cdef tuple fields
+ * 
+ *     for childname in descr.names:             # <<<<<<<<<<<<<<
+ *         fields = descr.fields[childname]
+ *         child, new_offset = fields
+ */
+  }
+  __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":850
+ *             # so don't output it
+ *             f = _util_dtypestring(child, f, end, offset)
+ *     return f             # <<<<<<<<<<<<<<
+ * 
+ * 
+ */
+  __pyx_r = __pyx_v_f;
+  goto __pyx_L0;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":785
+ *     return PyArray_MultiIterNew(5, <void*>a, <void*>b, <void*>c, <void*> d, <void*> e)
+ * 
+ * cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL:             # <<<<<<<<<<<<<<
+ *     # Recursive utility function used in __getbuffer__ to get format
+ *     # string. The new location in the format string is returned.
+ */
+
+  /* function exit code */
+  __pyx_L1_error:;
+  __Pyx_XDECREF(__pyx_t_1);
+  __Pyx_XDECREF(__pyx_t_3);
+  __Pyx_XDECREF(__pyx_t_4);
+  __Pyx_AddTraceback("numpy._util_dtypestring", __pyx_clineno, __pyx_lineno, __pyx_filename);
+  __pyx_r = NULL;
+  __pyx_L0:;
+  __Pyx_XDECREF((PyObject *)__pyx_v_child);
+  __Pyx_XDECREF(__pyx_v_fields);
+  __Pyx_XDECREF(__pyx_v_childname);
+  __Pyx_XDECREF(__pyx_v_new_offset);
+  __Pyx_XDECREF(__pyx_v_t);
+  __Pyx_RefNannyFinishContext();
+  return __pyx_r;
+}
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":966
+ * 
+ * 
+ * cdef inline void set_array_base(ndarray arr, object base):             # <<<<<<<<<<<<<<
+ *      cdef PyObject* baseptr
+ *      if base is None:
+ */
+
+static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_arr, PyObject *__pyx_v_base) {
+  PyObject *__pyx_v_baseptr;
+  __Pyx_RefNannyDeclarations
+  int __pyx_t_1;
+  int __pyx_t_2;
+  __Pyx_RefNannySetupContext("set_array_base", 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":968
+ * cdef inline void set_array_base(ndarray arr, object base):
+ *      cdef PyObject* baseptr
+ *      if base is None:             # <<<<<<<<<<<<<<
+ *          baseptr = NULL
+ *      else:
+ */
+  __pyx_t_1 = (__pyx_v_base == Py_None);
+  __pyx_t_2 = (__pyx_t_1 != 0);
+  if (__pyx_t_2) {
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":969
+ *      cdef PyObject* baseptr
+ *      if base is None:
+ *          baseptr = NULL             # <<<<<<<<<<<<<<
+ *      else:
+ *          Py_INCREF(base) # important to do this before decref below!
+ */
+    __pyx_v_baseptr = NULL;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":968
+ * cdef inline void set_array_base(ndarray arr, object base):
+ *      cdef PyObject* baseptr
+ *      if base is None:             # <<<<<<<<<<<<<<
+ *          baseptr = NULL
+ *      else:
+ */
+    goto __pyx_L3;
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":971
+ *          baseptr = NULL
+ *      else:
+ *          Py_INCREF(base) # important to do this before decref below!             # <<<<<<<<<<<<<<
+ *          baseptr = <PyObject*>base
+ *      Py_XDECREF(arr.base)
+ */
+  /*else*/ {
+    Py_INCREF(__pyx_v_base);
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":972
+ *      else:
+ *          Py_INCREF(base) # important to do this before decref below!
+ *          baseptr = <PyObject*>base             # <<<<<<<<<<<<<<
+ *      Py_XDECREF(arr.base)
+ *      arr.base = baseptr
+ */
+    __pyx_v_baseptr = ((PyObject *)__pyx_v_base);
+  }
+  __pyx_L3:;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":973
+ *          Py_INCREF(base) # important to do this before decref below!
+ *          baseptr = <PyObject*>base
+ *      Py_XDECREF(arr.base)             # <<<<<<<<<<<<<<
+ *      arr.base = baseptr
+ * 
+ */
+  Py_XDECREF(__pyx_v_arr->base);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":974
+ *          baseptr = <PyObject*>base
+ *      Py_XDECREF(arr.base)
+ *      arr.base = baseptr             # <<<<<<<<<<<<<<
+ * 
+ * cdef inline object get_array_base(ndarray arr):
+ */
+  __pyx_v_arr->base = __pyx_v_baseptr;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":966
+ * 
+ * 
+ * cdef inline void set_array_base(ndarray arr, object base):             # <<<<<<<<<<<<<<
+ *      cdef PyObject* baseptr
+ *      if base is None:
+ */
+
+  /* function exit code */
+  __Pyx_RefNannyFinishContext();
+}
+
+/* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":976
+ *      arr.base = baseptr
+ * 
+ * cdef inline object get_array_base(ndarray arr):             # <<<<<<<<<<<<<<
+ *     if arr.base is NULL:
+ *         return None
+ */
+
+static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__pyx_v_arr) {
+  PyObject *__pyx_r = NULL;
+  __Pyx_RefNannyDeclarations
+  int __pyx_t_1;
+  __Pyx_RefNannySetupContext("get_array_base", 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":977
+ * 
+ * cdef inline object get_array_base(ndarray arr):
+ *     if arr.base is NULL:             # <<<<<<<<<<<<<<
+ *         return None
+ *     else:
+ */
+  __pyx_t_1 = ((__pyx_v_arr->base == NULL) != 0);
+  if (__pyx_t_1) {
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":978
+ * cdef inline object get_array_base(ndarray arr):
+ *     if arr.base is NULL:
+ *         return None             # <<<<<<<<<<<<<<
+ *     else:
+ *         return <object>arr.base
+ */
+    __Pyx_XDECREF(__pyx_r);
+    __Pyx_INCREF(Py_None);
+    __pyx_r = Py_None;
+    goto __pyx_L0;
+
+    /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":977
+ * 
+ * cdef inline object get_array_base(ndarray arr):
+ *     if arr.base is NULL:             # <<<<<<<<<<<<<<
+ *         return None
+ *     else:
+ */
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":980
+ *         return None
+ *     else:
+ *         return <object>arr.base             # <<<<<<<<<<<<<<
+ */
+  /*else*/ {
+    __Pyx_XDECREF(__pyx_r);
+    __Pyx_INCREF(((PyObject *)__pyx_v_arr->base));
+    __pyx_r = ((PyObject *)__pyx_v_arr->base);
+    goto __pyx_L0;
+  }
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":976
+ *      arr.base = baseptr
+ * 
+ * cdef inline object get_array_base(ndarray arr):             # <<<<<<<<<<<<<<
+ *     if arr.base is NULL:
+ *         return None
+ */
+
+  /* function exit code */
+  __pyx_L0:;
+  __Pyx_XGIVEREF(__pyx_r);
+  __Pyx_RefNannyFinishContext();
+  return __pyx_r;
+}
+
+static PyMethodDef __pyx_methods[] = {
+  {0, 0, 0, 0}
+};
+
+#if PY_MAJOR_VERSION >= 3
+static struct PyModuleDef __pyx_moduledef = {
+  #if PY_VERSION_HEX < 0x03020000
+    { PyObject_HEAD_INIT(NULL) NULL, 0, NULL },
+  #else
+    PyModuleDef_HEAD_INIT,
+  #endif
+    "emd",
+    __pyx_k_Created_on_Thu_Sep_11_08_42_08, /* m_doc */
+    -1, /* m_size */
+    __pyx_methods /* m_methods */,
+    NULL, /* m_reload */
+    NULL, /* m_traverse */
+    NULL, /* m_clear */
+    NULL /* m_free */
+};
+#endif
+
+static __Pyx_StringTabEntry __pyx_string_tab[] = {
+  {&__pyx_kp_u_Format_string_allocated_too_shor, __pyx_k_Format_string_allocated_too_shor, sizeof(__pyx_k_Format_string_allocated_too_shor), 0, 1, 0, 0},
+  {&__pyx_kp_u_Format_string_allocated_too_shor_2, __pyx_k_Format_string_allocated_too_shor_2, sizeof(__pyx_k_Format_string_allocated_too_shor_2), 0, 1, 0, 0},
+  {&__pyx_n_s_G, __pyx_k_G, sizeof(__pyx_k_G), 0, 0, 1, 1},
+  {&__pyx_n_s_M, __pyx_k_M, sizeof(__pyx_k_M), 0, 0, 1, 1},
+  {&__pyx_kp_u_Non_native_byte_order_not_suppor, __pyx_k_Non_native_byte_order_not_suppor, sizeof(__pyx_k_Non_native_byte_order_not_suppor), 0, 1, 0, 0},
+  {&__pyx_n_s_RuntimeError, __pyx_k_RuntimeError, sizeof(__pyx_k_RuntimeError), 0, 0, 1, 1},
+  {&__pyx_n_s_ValueError, __pyx_k_ValueError, sizeof(__pyx_k_ValueError), 0, 0, 1, 1},
+  {&__pyx_n_s_a, __pyx_k_a, sizeof(__pyx_k_a), 0, 0, 1, 1},
+  {&__pyx_n_s_b, __pyx_k_b, sizeof(__pyx_k_b), 0, 0, 1, 1},
+  {&__pyx_n_s_cost, __pyx_k_cost, sizeof(__pyx_k_cost), 0, 0, 1, 1},
+  {&__pyx_n_s_emd, __pyx_k_emd, sizeof(__pyx_k_emd), 0, 0, 1, 1},
+  {&__pyx_kp_s_home_rflamary_PYTHON_POT_ot_emd, __pyx_k_home_rflamary_PYTHON_POT_ot_emd, sizeof(__pyx_k_home_rflamary_PYTHON_POT_ot_emd), 0, 0, 1, 0},
+  {&__pyx_n_s_import, __pyx_k_import, sizeof(__pyx_k_import), 0, 0, 1, 1},
+  {&__pyx_n_s_main, __pyx_k_main, sizeof(__pyx_k_main), 0, 0, 1, 1},
+  {&__pyx_n_s_n1, __pyx_k_n1, sizeof(__pyx_k_n1), 0, 0, 1, 1},
+  {&__pyx_n_s_n2, __pyx_k_n2, sizeof(__pyx_k_n2), 0, 0, 1, 1},
+  {&__pyx_kp_u_ndarray_is_not_C_contiguous, __pyx_k_ndarray_is_not_C_contiguous, sizeof(__pyx_k_ndarray_is_not_C_contiguous), 0, 1, 0, 0},
+  {&__pyx_kp_u_ndarray_is_not_Fortran_contiguou, __pyx_k_ndarray_is_not_Fortran_contiguou, sizeof(__pyx_k_ndarray_is_not_Fortran_contiguou), 0, 1, 0, 0},
+  {&__pyx_n_s_np, __pyx_k_np, sizeof(__pyx_k_np), 0, 0, 1, 1},
+  {&__pyx_n_s_numpy, __pyx_k_numpy, sizeof(__pyx_k_numpy), 0, 0, 1, 1},
+  {&__pyx_n_s_ones, __pyx_k_ones, sizeof(__pyx_k_ones), 0, 0, 1, 1},
+  {&__pyx_n_s_ot_emd_emd, __pyx_k_ot_emd_emd, sizeof(__pyx_k_ot_emd_emd), 0, 0, 1, 1},
+  {&__pyx_n_s_range, __pyx_k_range, sizeof(__pyx_k_range), 0, 0, 1, 1},
+  {&__pyx_n_s_test, __pyx_k_test, sizeof(__pyx_k_test), 0, 0, 1, 1},
+  {&__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_k_unknown_dtype_code_in_numpy_pxd, sizeof(__pyx_k_unknown_dtype_code_in_numpy_pxd), 0, 1, 0, 0},
+  {&__pyx_n_s_zeros, __pyx_k_zeros, sizeof(__pyx_k_zeros), 0, 0, 1, 1},
+  {0, 0, 0, 0, 0, 0, 0}
+};
+static int __Pyx_InitCachedBuiltins(void) {
+  __pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 218; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_builtin_range = __Pyx_GetBuiltinName(__pyx_n_s_range); if (!__pyx_builtin_range) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 231; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_builtin_RuntimeError = __Pyx_GetBuiltinName(__pyx_n_s_RuntimeError); if (!__pyx_builtin_RuntimeError) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 799; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  return 0;
+  __pyx_L1_error:;
+  return -1;
+}
+
+static int __Pyx_InitCachedConstants(void) {
+  __Pyx_RefNannyDeclarations
+  __Pyx_RefNannySetupContext("__Pyx_InitCachedConstants", 0);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":218
+ *             if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS)
+ *                 and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)):
+ *                 raise ValueError(u"ndarray is not C contiguous")             # <<<<<<<<<<<<<<
+ * 
+ *             if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS)
+ */
+  __pyx_tuple_ = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_C_contiguous); if (unlikely(!__pyx_tuple_)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 218; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_tuple_);
+  __Pyx_GIVEREF(__pyx_tuple_);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":222
+ *             if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS)
+ *                 and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)):
+ *                 raise ValueError(u"ndarray is not Fortran contiguous")             # <<<<<<<<<<<<<<
+ * 
+ *             info.buf = PyArray_DATA(self)
+ */
+  __pyx_tuple__2 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_Fortran_contiguou); if (unlikely(!__pyx_tuple__2)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 222; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_tuple__2);
+  __Pyx_GIVEREF(__pyx_tuple__2);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":259
+ *                 if ((descr.byteorder == c'>' and little_endian) or
+ *                     (descr.byteorder == c'<' and not little_endian)):
+ *                     raise ValueError(u"Non-native byte order not supported")             # <<<<<<<<<<<<<<
+ *                 if   t == NPY_BYTE:        f = "b"
+ *                 elif t == NPY_UBYTE:       f = "B"
+ */
+  __pyx_tuple__3 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__3)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 259; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_tuple__3);
+  __Pyx_GIVEREF(__pyx_tuple__3);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":799
+ * 
+ *         if (end - f) - <int>(new_offset - offset[0]) < 15:
+ *             raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd")             # <<<<<<<<<<<<<<
+ * 
+ *         if ((child.byteorder == c'>' and little_endian) or
+ */
+  __pyx_tuple__4 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor); if (unlikely(!__pyx_tuple__4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 799; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_tuple__4);
+  __Pyx_GIVEREF(__pyx_tuple__4);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":803
+ *         if ((child.byteorder == c'>' and little_endian) or
+ *             (child.byteorder == c'<' and not little_endian)):
+ *             raise ValueError(u"Non-native byte order not supported")             # <<<<<<<<<<<<<<
+ *             # One could encode it in the format string and have Cython
+ *             # complain instead, BUT: < and > in format strings also imply
+ */
+  __pyx_tuple__5 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__5)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 803; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_tuple__5);
+  __Pyx_GIVEREF(__pyx_tuple__5);
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":823
+ *             t = child.type_num
+ *             if end - f < 5:
+ *                 raise RuntimeError(u"Format string allocated too short.")             # <<<<<<<<<<<<<<
+ * 
+ *             # Until ticket #99 is fixed, use integers to avoid warnings
+ */
+  __pyx_tuple__6 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor_2); if (unlikely(!__pyx_tuple__6)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 823; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_tuple__6);
+  __Pyx_GIVEREF(__pyx_tuple__6);
+
+  /* "ot/emd/emd.pyx":21
+ * @cython.boundscheck(False)
+ * @cython.wraparound(False)
+ * def emd( np.ndarray[double, ndim=1, mode="c"] a,np.ndarray[double, ndim=1, mode="c"]  b,np.ndarray[double, ndim=2, mode="c"]  M):             # <<<<<<<<<<<<<<
+ *     """
+ *         Solves the Earth Movers distance problem and returns the optimal transport matrix
+ */
+  __pyx_tuple__7 = PyTuple_Pack(7, __pyx_n_s_a, __pyx_n_s_b, __pyx_n_s_M, __pyx_n_s_n1, __pyx_n_s_n2, __pyx_n_s_cost, __pyx_n_s_G); if (unlikely(!__pyx_tuple__7)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_tuple__7);
+  __Pyx_GIVEREF(__pyx_tuple__7);
+  __pyx_codeobj__8 = (PyObject*)__Pyx_PyCode_New(3, 0, 7, 0, 0, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__7, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_home_rflamary_PYTHON_POT_ot_emd, __pyx_n_s_emd, 21, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__8)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_RefNannyFinishContext();
+  return 0;
+  __pyx_L1_error:;
+  __Pyx_RefNannyFinishContext();
+  return -1;
+}
+
+static int __Pyx_InitGlobals(void) {
+  if (__Pyx_InitStrings(__pyx_string_tab) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
+  return 0;
+  __pyx_L1_error:;
+  return -1;
+}
+
+#if PY_MAJOR_VERSION < 3
+PyMODINIT_FUNC initemd(void); /*proto*/
+PyMODINIT_FUNC initemd(void)
+#else
+PyMODINIT_FUNC PyInit_emd(void); /*proto*/
+PyMODINIT_FUNC PyInit_emd(void)
+#endif
+{
+  PyObject *__pyx_t_1 = NULL;
+  int __pyx_lineno = 0;
+  const char *__pyx_filename = NULL;
+  int __pyx_clineno = 0;
+  __Pyx_RefNannyDeclarations
+  #if CYTHON_REFNANNY
+  __Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny");
+  if (!__Pyx_RefNanny) {
+      PyErr_Clear();
+      __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny");
+      if (!__Pyx_RefNanny)
+          Py_FatalError("failed to import 'refnanny' module");
+  }
+  #endif
+  __Pyx_RefNannySetupContext("PyMODINIT_FUNC PyInit_emd(void)", 0);
+  if (__Pyx_check_binary_version() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_empty_tuple = PyTuple_New(0); if (unlikely(!__pyx_empty_tuple)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_empty_bytes = PyBytes_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_bytes)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  #ifdef __Pyx_CyFunction_USED
+  if (__pyx_CyFunction_init() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  #endif
+  #ifdef __Pyx_FusedFunction_USED
+  if (__pyx_FusedFunction_init() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  #endif
+  #ifdef __Pyx_Coroutine_USED
+  if (__pyx_Coroutine_init() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  #endif
+  #ifdef __Pyx_Generator_USED
+  if (__pyx_Generator_init() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  #endif
+  #ifdef __Pyx_StopAsyncIteration_USED
+  if (__pyx_StopAsyncIteration_init() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  #endif
+  /*--- Library function declarations ---*/
+  /*--- Threads initialization code ---*/
+  #if defined(__PYX_FORCE_INIT_THREADS) && __PYX_FORCE_INIT_THREADS
+  #ifdef WITH_THREAD /* Python build with threading support? */
+  PyEval_InitThreads();
+  #endif
+  #endif
+  /*--- Module creation code ---*/
+  #if PY_MAJOR_VERSION < 3
+  __pyx_m = Py_InitModule4("emd", __pyx_methods, __pyx_k_Created_on_Thu_Sep_11_08_42_08, 0, PYTHON_API_VERSION); Py_XINCREF(__pyx_m);
+  #else
+  __pyx_m = PyModule_Create(&__pyx_moduledef);
+  #endif
+  if (unlikely(!__pyx_m)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_d = PyModule_GetDict(__pyx_m); if (unlikely(!__pyx_d)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  Py_INCREF(__pyx_d);
+  __pyx_b = PyImport_AddModule(__Pyx_BUILTIN_MODULE_NAME); if (unlikely(!__pyx_b)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  #if CYTHON_COMPILING_IN_PYPY
+  Py_INCREF(__pyx_b);
+  #endif
+  if (PyObject_SetAttrString(__pyx_m, "__builtins__", __pyx_b) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
+  /*--- Initialize various global constants etc. ---*/
+  if (__Pyx_InitGlobals() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  #if PY_MAJOR_VERSION < 3 && (__PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT)
+  if (__Pyx_init_sys_getdefaultencoding_params() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  #endif
+  if (__pyx_module_is_main_ot__emd__emd) {
+    if (PyObject_SetAttrString(__pyx_m, "__name__", __pyx_n_s_main) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  }
+  #if PY_MAJOR_VERSION >= 3
+  {
+    PyObject *modules = PyImport_GetModuleDict(); if (unlikely(!modules)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    if (!PyDict_GetItemString(modules, "ot.emd.emd")) {
+      if (unlikely(PyDict_SetItemString(modules, "ot.emd.emd", __pyx_m) < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+    }
+  }
+  #endif
+  /*--- Builtin init code ---*/
+  if (__Pyx_InitCachedBuiltins() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  /*--- Constants init code ---*/
+  if (__Pyx_InitCachedConstants() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  /*--- Global init code ---*/
+  /*--- Variable export code ---*/
+  /*--- Function export code ---*/
+  /*--- Type init code ---*/
+  /*--- Type import code ---*/
+  __pyx_ptype_7cpython_4type_type = __Pyx_ImportType(__Pyx_BUILTIN_MODULE_NAME, "type", 
+  #if CYTHON_COMPILING_IN_PYPY
+  sizeof(PyTypeObject),
+  #else
+  sizeof(PyHeapTypeObject),
+  #endif
+  0); if (unlikely(!__pyx_ptype_7cpython_4type_type)) {__pyx_filename = __pyx_f[2]; __pyx_lineno = 9; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_ptype_5numpy_dtype = __Pyx_ImportType("numpy", "dtype", sizeof(PyArray_Descr), 0); if (unlikely(!__pyx_ptype_5numpy_dtype)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 155; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_ptype_5numpy_flatiter = __Pyx_ImportType("numpy", "flatiter", sizeof(PyArrayIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_flatiter)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 168; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_ptype_5numpy_broadcast = __Pyx_ImportType("numpy", "broadcast", sizeof(PyArrayMultiIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_broadcast)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 172; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_ptype_5numpy_ndarray = __Pyx_ImportType("numpy", "ndarray", sizeof(PyArrayObject), 0); if (unlikely(!__pyx_ptype_5numpy_ndarray)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 181; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __pyx_ptype_5numpy_ufunc = __Pyx_ImportType("numpy", "ufunc", sizeof(PyUFuncObject), 0); if (unlikely(!__pyx_ptype_5numpy_ufunc)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 861; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  /*--- Variable import code ---*/
+  /*--- Function import code ---*/
+  /*--- Execution code ---*/
+  #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED)
+  if (__Pyx_patch_abc() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  #endif
+
+  /* "ot/emd/emd.pyx":7
+ * @author: rflamary
+ * """
+ * import numpy as np             # <<<<<<<<<<<<<<
+ * cimport numpy as np
+ * 
+ */
+  __pyx_t_1 = __Pyx_Import(__pyx_n_s_numpy, 0, -1); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 7; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_1);
+  if (PyDict_SetItem(__pyx_d, __pyx_n_s_np, __pyx_t_1) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 7; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
+
+  /* "ot/emd/emd.pyx":21
+ * @cython.boundscheck(False)
+ * @cython.wraparound(False)
+ * def emd( np.ndarray[double, ndim=1, mode="c"] a,np.ndarray[double, ndim=1, mode="c"]  b,np.ndarray[double, ndim=2, mode="c"]  M):             # <<<<<<<<<<<<<<
+ *     """
+ *         Solves the Earth Movers distance problem and returns the optimal transport matrix
+ */
+  __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_2ot_3emd_3emd_1emd, NULL, __pyx_n_s_ot_emd_emd); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_1);
+  if (PyDict_SetItem(__pyx_d, __pyx_n_s_emd, __pyx_t_1) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 21; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
+
+  /* "ot/emd/emd.pyx":1
+ * # -*- coding: utf-8 -*-             # <<<<<<<<<<<<<<
+ * """
+ * Created on Thu Sep 11 08:42:08 2014
+ */
+  __pyx_t_1 = PyDict_New(); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_GOTREF(__pyx_t_1);
+  if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_1) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
+  __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
+
+  /* "../../../../usr/lib/python2.7/dist-packages/Cython/Includes/numpy/__init__.pxd":976
+ *      arr.base = baseptr
+ * 
+ * cdef inline object get_array_base(ndarray arr):             # <<<<<<<<<<<<<<
+ *     if arr.base is NULL:
+ *         return None
+ */
+
+  /*--- Wrapped vars code ---*/
+
+  goto __pyx_L0;
+  __pyx_L1_error:;
+  __Pyx_XDECREF(__pyx_t_1);
+  if (__pyx_m) {
+    if (__pyx_d) {
+      __Pyx_AddTraceback("init ot.emd.emd", __pyx_clineno, __pyx_lineno, __pyx_filename);
+    }
+    Py_DECREF(__pyx_m); __pyx_m = 0;
+  } else if (!PyErr_Occurred()) {
+    PyErr_SetString(PyExc_ImportError, "init ot.emd.emd");
+  }
+  __pyx_L0:;
+  __Pyx_RefNannyFinishContext();
+  #if PY_MAJOR_VERSION < 3
+  return;
+  #else
+  return __pyx_m;
+  #endif
+}
+
+/* --- Runtime support code --- */
+#if CYTHON_REFNANNY
+static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname) {
+    PyObject *m = NULL, *p = NULL;
+    void *r = NULL;
+    m = PyImport_ImportModule((char *)modname);
+    if (!m) goto end;
+    p = PyObject_GetAttrString(m, (char *)"RefNannyAPI");
+    if (!p) goto end;
+    r = PyLong_AsVoidPtr(p);
+end:
+    Py_XDECREF(p);
+    Py_XDECREF(m);
+    return (__Pyx_RefNannyAPIStruct *)r;
+}
+#endif
+
+static void __Pyx_RaiseArgtupleInvalid(
+    const char* func_name,
+    int exact,
+    Py_ssize_t num_min,
+    Py_ssize_t num_max,
+    Py_ssize_t num_found)
+{
+    Py_ssize_t num_expected;
+    const char *more_or_less;
+    if (num_found < num_min) {
+        num_expected = num_min;
+        more_or_less = "at least";
+    } else {
+        num_expected = num_max;
+        more_or_less = "at most";
+    }
+    if (exact) {
+        more_or_less = "exactly";
+    }
+    PyErr_Format(PyExc_TypeError,
+                 "%.200s() takes %.8s %" CYTHON_FORMAT_SSIZE_T "d positional argument%.1s (%" CYTHON_FORMAT_SSIZE_T "d given)",
+                 func_name, more_or_less, num_expected,
+                 (num_expected == 1) ? "" : "s", num_found);
+}
+
+static void __Pyx_RaiseDoubleKeywordsError(
+    const char* func_name,
+    PyObject* kw_name)
+{
+    PyErr_Format(PyExc_TypeError,
+        #if PY_MAJOR_VERSION >= 3
+        "%s() got multiple values for keyword argument '%U'", func_name, kw_name);
+        #else
+        "%s() got multiple values for keyword argument '%s'", func_name,
+        PyString_AsString(kw_name));
+        #endif
+}
+
+static int __Pyx_ParseOptionalKeywords(
+    PyObject *kwds,
+    PyObject **argnames[],
+    PyObject *kwds2,
+    PyObject *values[],
+    Py_ssize_t num_pos_args,
+    const char* function_name)
+{
+    PyObject *key = 0, *value = 0;
+    Py_ssize_t pos = 0;
+    PyObject*** name;
+    PyObject*** first_kw_arg = argnames + num_pos_args;
+    while (PyDict_Next(kwds, &pos, &key, &value)) {
+        name = first_kw_arg;
+        while (*name && (**name != key)) name++;
+        if (*name) {
+            values[name-argnames] = value;
+            continue;
+        }
+        name = first_kw_arg;
+        #if PY_MAJOR_VERSION < 3
+        if (likely(PyString_CheckExact(key)) || likely(PyString_Check(key))) {
+            while (*name) {
+                if ((CYTHON_COMPILING_IN_PYPY || PyString_GET_SIZE(**name) == PyString_GET_SIZE(key))
+                        && _PyString_Eq(**name, key)) {
+                    values[name-argnames] = value;
+                    break;
+                }
+                name++;
+            }
+            if (*name) continue;
+            else {
+                PyObject*** argname = argnames;
+                while (argname != first_kw_arg) {
+                    if ((**argname == key) || (
+                            (CYTHON_COMPILING_IN_PYPY || PyString_GET_SIZE(**argname) == PyString_GET_SIZE(key))
+                             && _PyString_Eq(**argname, key))) {
+                        goto arg_passed_twice;
+                    }
+                    argname++;
+                }
+            }
+        } else
+        #endif
+        if (likely(PyUnicode_Check(key))) {
+            while (*name) {
+                int cmp = (**name == key) ? 0 :
+                #if !CYTHON_COMPILING_IN_PYPY && PY_MAJOR_VERSION >= 3
+                    (PyUnicode_GET_SIZE(**name) != PyUnicode_GET_SIZE(key)) ? 1 :
+                #endif
+                    PyUnicode_Compare(**name, key);
+                if (cmp < 0 && unlikely(PyErr_Occurred())) goto bad;
+                if (cmp == 0) {
+                    values[name-argnames] = value;
+                    break;
+                }
+                name++;
+            }
+            if (*name) continue;
+            else {
+                PyObject*** argname = argnames;
+                while (argname != first_kw_arg) {
+                    int cmp = (**argname == key) ? 0 :
+                    #if !CYTHON_COMPILING_IN_PYPY && PY_MAJOR_VERSION >= 3
+                        (PyUnicode_GET_SIZE(**argname) != PyUnicode_GET_SIZE(key)) ? 1 :
+                    #endif
+                        PyUnicode_Compare(**argname, key);
+                    if (cmp < 0 && unlikely(PyErr_Occurred())) goto bad;
+                    if (cmp == 0) goto arg_passed_twice;
+                    argname++;
+                }
+            }
+        } else
+            goto invalid_keyword_type;
+        if (kwds2) {
+            if (unlikely(PyDict_SetItem(kwds2, key, value))) goto bad;
+        } else {
+            goto invalid_keyword;
+        }
+    }
+    return 0;
+arg_passed_twice:
+    __Pyx_RaiseDoubleKeywordsError(function_name, key);
+    goto bad;
+invalid_keyword_type:
+    PyErr_Format(PyExc_TypeError,
+        "%.200s() keywords must be strings", function_name);
+    goto bad;
+invalid_keyword:
+    PyErr_Format(PyExc_TypeError,
+    #if PY_MAJOR_VERSION < 3
+        "%.200s() got an unexpected keyword argument '%.200s'",
+        function_name, PyString_AsString(key));
+    #else
+        "%s() got an unexpected keyword argument '%U'",
+        function_name, key);
+    #endif
+bad:
+    return -1;
+}
+
+static void __Pyx_RaiseArgumentTypeInvalid(const char* name, PyObject *obj, PyTypeObject *type) {
+    PyErr_Format(PyExc_TypeError,
+        "Argument '%.200s' has incorrect type (expected %.200s, got %.200s)",
+        name, type->tp_name, Py_TYPE(obj)->tp_name);
+}
+static CYTHON_INLINE int __Pyx_ArgTypeTest(PyObject *obj, PyTypeObject *type, int none_allowed,
+    const char *name, int exact)
+{
+    if (unlikely(!type)) {
+        PyErr_SetString(PyExc_SystemError, "Missing type object");
+        return 0;
+    }
+    if (none_allowed && obj == Py_None) return 1;
+    else if (exact) {
+        if (likely(Py_TYPE(obj) == type)) return 1;
+        #if PY_MAJOR_VERSION == 2
+        else if ((type == &PyBaseString_Type) && likely(__Pyx_PyBaseString_CheckExact(obj))) return 1;
+        #endif
+    }
+    else {
+        if (likely(PyObject_TypeCheck(obj, type))) return 1;
+    }
+    __Pyx_RaiseArgumentTypeInvalid(name, obj, type);
+    return 0;
+}
+
+static CYTHON_INLINE int __Pyx_IsLittleEndian(void) {
+  unsigned int n = 1;
+  return *(unsigned char*)(&n) != 0;
+}
+static void __Pyx_BufFmt_Init(__Pyx_BufFmt_Context* ctx,
+                              __Pyx_BufFmt_StackElem* stack,
+                              __Pyx_TypeInfo* type) {
+  stack[0].field = &ctx->root;
+  stack[0].parent_offset = 0;
+  ctx->root.type = type;
+  ctx->root.name = "buffer dtype";
+  ctx->root.offset = 0;
+  ctx->head = stack;
+  ctx->head->field = &ctx->root;
+  ctx->fmt_offset = 0;
+  ctx->head->parent_offset = 0;
+  ctx->new_packmode = '@';
+  ctx->enc_packmode = '@';
+  ctx->new_count = 1;
+  ctx->enc_count = 0;
+  ctx->enc_type = 0;
+  ctx->is_complex = 0;
+  ctx->is_valid_array = 0;
+  ctx->struct_alignment = 0;
+  while (type->typegroup == 'S') {
+    ++ctx->head;
+    ctx->head->field = type->fields;
+    ctx->head->parent_offset = 0;
+    type = type->fields->type;
+  }
+}
+static int __Pyx_BufFmt_ParseNumber(const char** ts) {
+    int count;
+    const char* t = *ts;
+    if (*t < '0' || *t > '9') {
+      return -1;
+    } else {
+        count = *t++ - '0';
+        while (*t >= '0' && *t < '9') {
+            count *= 10;
+            count += *t++ - '0';
+        }
+    }
+    *ts = t;
+    return count;
+}
+static int __Pyx_BufFmt_ExpectNumber(const char **ts) {
+    int number = __Pyx_BufFmt_ParseNumber(ts);
+    if (number == -1)
+        PyErr_Format(PyExc_ValueError,\
+                     "Does not understand character buffer dtype format string ('%c')", **ts);
+    return number;
+}
+static void __Pyx_BufFmt_RaiseUnexpectedChar(char ch) {
+  PyErr_Format(PyExc_ValueError,
+               "Unexpected format string character: '%c'", ch);
+}
+static const char* __Pyx_BufFmt_DescribeTypeChar(char ch, int is_complex) {
+  switch (ch) {
+    case 'c': return "'char'";
+    case 'b': return "'signed char'";
+    case 'B': return "'unsigned char'";
+    case 'h': return "'short'";
+    case 'H': return "'unsigned short'";
+    case 'i': return "'int'";
+    case 'I': return "'unsigned int'";
+    case 'l': return "'long'";
+    case 'L': return "'unsigned long'";
+    case 'q': return "'long long'";
+    case 'Q': return "'unsigned long long'";
+    case 'f': return (is_complex ? "'complex float'" : "'float'");
+    case 'd': return (is_complex ? "'complex double'" : "'double'");
+    case 'g': return (is_complex ? "'complex long double'" : "'long double'");
+    case 'T': return "a struct";
+    case 'O': return "Python object";
+    case 'P': return "a pointer";
+    case 's': case 'p': return "a string";
+    case 0: return "end";
+    default: return "unparseable format string";
+  }
+}
+static size_t __Pyx_BufFmt_TypeCharToStandardSize(char ch, int is_complex) {
+  switch (ch) {
+    case '?': case 'c': case 'b': case 'B': case 's': case 'p': return 1;
+    case 'h': case 'H': return 2;
+    case 'i': case 'I': case 'l': case 'L': return 4;
+    case 'q': case 'Q': return 8;
+    case 'f': return (is_complex ? 8 : 4);
+    case 'd': return (is_complex ? 16 : 8);
+    case 'g': {
+      PyErr_SetString(PyExc_ValueError, "Python does not define a standard format string size for long double ('g')..");
+      return 0;
+    }
+    case 'O': case 'P': return sizeof(void*);
+    default:
+      __Pyx_BufFmt_RaiseUnexpectedChar(ch);
+      return 0;
+    }
+}
+static size_t __Pyx_BufFmt_TypeCharToNativeSize(char ch, int is_complex) {
+  switch (ch) {
+    case 'c': case 'b': case 'B': case 's': case 'p': return 1;
+    case 'h': case 'H': return sizeof(short);
+    case 'i': case 'I': return sizeof(int);
+    case 'l': case 'L': return sizeof(long);
+    #ifdef HAVE_LONG_LONG
+    case 'q': case 'Q': return sizeof(PY_LONG_LONG);
+    #endif
+    case 'f': return sizeof(float) * (is_complex ? 2 : 1);
+    case 'd': return sizeof(double) * (is_complex ? 2 : 1);
+    case 'g': return sizeof(long double) * (is_complex ? 2 : 1);
+    case 'O': case 'P': return sizeof(void*);
+    default: {
+      __Pyx_BufFmt_RaiseUnexpectedChar(ch);
+      return 0;
+    }
+  }
+}
+typedef struct { char c; short x; } __Pyx_st_short;
+typedef struct { char c; int x; } __Pyx_st_int;
+typedef struct { char c; long x; } __Pyx_st_long;
+typedef struct { char c; float x; } __Pyx_st_float;
+typedef struct { char c; double x; } __Pyx_st_double;
+typedef struct { char c; long double x; } __Pyx_st_longdouble;
+typedef struct { char c; void *x; } __Pyx_st_void_p;
+#ifdef HAVE_LONG_LONG
+typedef struct { char c; PY_LONG_LONG x; } __Pyx_st_longlong;
+#endif
+static size_t __Pyx_BufFmt_TypeCharToAlignment(char ch, CYTHON_UNUSED int is_complex) {
+  switch (ch) {
+    case '?': case 'c': case 'b': case 'B': case 's': case 'p': return 1;
+    case 'h': case 'H': return sizeof(__Pyx_st_short) - sizeof(short);
+    case 'i': case 'I': return sizeof(__Pyx_st_int) - sizeof(int);
+    case 'l': case 'L': return sizeof(__Pyx_st_long) - sizeof(long);
+#ifdef HAVE_LONG_LONG
+    case 'q': case 'Q': return sizeof(__Pyx_st_longlong) - sizeof(PY_LONG_LONG);
+#endif
+    case 'f': return sizeof(__Pyx_st_float) - sizeof(float);
+    case 'd': return sizeof(__Pyx_st_double) - sizeof(double);
+    case 'g': return sizeof(__Pyx_st_longdouble) - sizeof(long double);
+    case 'P': case 'O': return sizeof(__Pyx_st_void_p) - sizeof(void*);
+    default:
+      __Pyx_BufFmt_RaiseUnexpectedChar(ch);
+      return 0;
+    }
+}
+/* These are for computing the padding at the end of the struct to align
+   on the first member of the struct. This will probably the same as above,
+   but we don't have any guarantees.
+ */
+typedef struct { short x; char c; } __Pyx_pad_short;
+typedef struct { int x; char c; } __Pyx_pad_int;
+typedef struct { long x; char c; } __Pyx_pad_long;
+typedef struct { float x; char c; } __Pyx_pad_float;
+typedef struct { double x; char c; } __Pyx_pad_double;
+typedef struct { long double x; char c; } __Pyx_pad_longdouble;
+typedef struct { void *x; char c; } __Pyx_pad_void_p;
+#ifdef HAVE_LONG_LONG
+typedef struct { PY_LONG_LONG x; char c; } __Pyx_pad_longlong;
+#endif
+static size_t __Pyx_BufFmt_TypeCharToPadding(char ch, CYTHON_UNUSED int is_complex) {
+  switch (ch) {
+    case '?': case 'c': case 'b': case 'B': case 's': case 'p': return 1;
+    case 'h': case 'H': return sizeof(__Pyx_pad_short) - sizeof(short);
+    case 'i': case 'I': return sizeof(__Pyx_pad_int) - sizeof(int);
+    case 'l': case 'L': return sizeof(__Pyx_pad_long) - sizeof(long);
+#ifdef HAVE_LONG_LONG
+    case 'q': case 'Q': return sizeof(__Pyx_pad_longlong) - sizeof(PY_LONG_LONG);
+#endif
+    case 'f': return sizeof(__Pyx_pad_float) - sizeof(float);
+    case 'd': return sizeof(__Pyx_pad_double) - sizeof(double);
+    case 'g': return sizeof(__Pyx_pad_longdouble) - sizeof(long double);
+    case 'P': case 'O': return sizeof(__Pyx_pad_void_p) - sizeof(void*);
+    default:
+      __Pyx_BufFmt_RaiseUnexpectedChar(ch);
+      return 0;
+    }
+}
+static char __Pyx_BufFmt_TypeCharToGroup(char ch, int is_complex) {
+  switch (ch) {
+    case 'c':
+        return 'H';
+    case 'b': case 'h': case 'i':
+    case 'l': case 'q': case 's': case 'p':
+        return 'I';
+    case 'B': case 'H': case 'I': case 'L': case 'Q':
+        return 'U';
+    case 'f': case 'd': case 'g':
+        return (is_complex ? 'C' : 'R');
+    case 'O':
+        return 'O';
+    case 'P':
+        return 'P';
+    default: {
+      __Pyx_BufFmt_RaiseUnexpectedChar(ch);
+      return 0;
+    }
+  }
+}
+static void __Pyx_BufFmt_RaiseExpected(__Pyx_BufFmt_Context* ctx) {
+  if (ctx->head == NULL || ctx->head->field == &ctx->root) {
+    const char* expected;
+    const char* quote;
+    if (ctx->head == NULL) {
+      expected = "end";
+      quote = "";
+    } else {
+      expected = ctx->head->field->type->name;
+      quote = "'";
+    }
+    PyErr_Format(PyExc_ValueError,
+                 "Buffer dtype mismatch, expected %s%s%s but got %s",
+                 quote, expected, quote,
+                 __Pyx_BufFmt_DescribeTypeChar(ctx->enc_type, ctx->is_complex));
+  } else {
+    __Pyx_StructField* field = ctx->head->field;
+    __Pyx_StructField* parent = (ctx->head - 1)->field;
+    PyErr_Format(PyExc_ValueError,
+                 "Buffer dtype mismatch, expected '%s' but got %s in '%s.%s'",
+                 field->type->name, __Pyx_BufFmt_DescribeTypeChar(ctx->enc_type, ctx->is_complex),
+                 parent->type->name, field->name);
+  }
+}
+static int __Pyx_BufFmt_ProcessTypeChunk(__Pyx_BufFmt_Context* ctx) {
+  char group;
+  size_t size, offset, arraysize = 1;
+  if (ctx->enc_type == 0) return 0;
+  if (ctx->head->field->type->arraysize[0]) {
+    int i, ndim = 0;
+    if (ctx->enc_type == 's' || ctx->enc_type == 'p') {
+        ctx->is_valid_array = ctx->head->field->type->ndim == 1;
+        ndim = 1;
+        if (ctx->enc_count != ctx->head->field->type->arraysize[0]) {
+            PyErr_Format(PyExc_ValueError,
+                         "Expected a dimension of size %zu, got %zu",
+                         ctx->head->field->type->arraysize[0], ctx->enc_count);
+            return -1;
+        }
+    }
+    if (!ctx->is_valid_array) {
+      PyErr_Format(PyExc_ValueError, "Expected %d dimensions, got %d",
+                   ctx->head->field->type->ndim, ndim);
+      return -1;
+    }
+    for (i = 0; i < ctx->head->field->type->ndim; i++) {
+      arraysize *= ctx->head->field->type->arraysize[i];
+    }
+    ctx->is_valid_array = 0;
+    ctx->enc_count = 1;
+  }
+  group = __Pyx_BufFmt_TypeCharToGroup(ctx->enc_type, ctx->is_complex);
+  do {
+    __Pyx_StructField* field = ctx->head->field;
+    __Pyx_TypeInfo* type = field->type;
+    if (ctx->enc_packmode == '@' || ctx->enc_packmode == '^') {
+      size = __Pyx_BufFmt_TypeCharToNativeSize(ctx->enc_type, ctx->is_complex);
+    } else {
+      size = __Pyx_BufFmt_TypeCharToStandardSize(ctx->enc_type, ctx->is_complex);
+    }
+    if (ctx->enc_packmode == '@') {
+      size_t align_at = __Pyx_BufFmt_TypeCharToAlignment(ctx->enc_type, ctx->is_complex);
+      size_t align_mod_offset;
+      if (align_at == 0) return -1;
+      align_mod_offset = ctx->fmt_offset % align_at;
+      if (align_mod_offset > 0) ctx->fmt_offset += align_at - align_mod_offset;
+      if (ctx->struct_alignment == 0)
+          ctx->struct_alignment = __Pyx_BufFmt_TypeCharToPadding(ctx->enc_type,
+                                                                 ctx->is_complex);
+    }
+    if (type->size != size || type->typegroup != group) {
+      if (type->typegroup == 'C' && type->fields != NULL) {
+        size_t parent_offset = ctx->head->parent_offset + field->offset;
+        ++ctx->head;
+        ctx->head->field = type->fields;
+        ctx->head->parent_offset = parent_offset;
+        continue;
+      }
+      if ((type->typegroup == 'H' || group == 'H') && type->size == size) {
+      } else {
+          __Pyx_BufFmt_RaiseExpected(ctx);
+          return -1;
+      }
+    }
+    offset = ctx->head->parent_offset + field->offset;
+    if (ctx->fmt_offset != offset) {
+      PyErr_Format(PyExc_ValueError,
+                   "Buffer dtype mismatch; next field is at offset %" CYTHON_FORMAT_SSIZE_T "d but %" CYTHON_FORMAT_SSIZE_T "d expected",
+                   (Py_ssize_t)ctx->fmt_offset, (Py_ssize_t)offset);
+      return -1;
+    }
+    ctx->fmt_offset += size;
+    if (arraysize)
+      ctx->fmt_offset += (arraysize - 1) * size;
+    --ctx->enc_count;
+    while (1) {
+      if (field == &ctx->root) {
+        ctx->head = NULL;
+        if (ctx->enc_count != 0) {
+          __Pyx_BufFmt_RaiseExpected(ctx);
+          return -1;
+        }
+        break;
+      }
+      ctx->head->field = ++field;
+      if (field->type == NULL) {
+        --ctx->head;
+        field = ctx->head->field;
+        continue;
+      } else if (field->type->typegroup == 'S') {
+        size_t parent_offset = ctx->head->parent_offset + field->offset;
+        if (field->type->fields->type == NULL) continue;
+        field = field->type->fields;
+        ++ctx->head;
+        ctx->head->field = field;
+        ctx->head->parent_offset = parent_offset;
+        break;
+      } else {
+        break;
+      }
+    }
+  } while (ctx->enc_count);
+  ctx->enc_type = 0;
+  ctx->is_complex = 0;
+  return 0;
+}
+static CYTHON_INLINE PyObject *
+__pyx_buffmt_parse_array(__Pyx_BufFmt_Context* ctx, const char** tsp)
+{
+    const char *ts = *tsp;
+    int i = 0, number;
+    int ndim = ctx->head->field->type->ndim;
+;
+    ++ts;
+    if (ctx->new_count != 1) {
+        PyErr_SetString(PyExc_ValueError,
+                        "Cannot handle repeated arrays in format string");
+        return NULL;
+    }
+    if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL;
+    while (*ts && *ts != ')') {
+        switch (*ts) {
+            case ' ': case '\f': case '\r': case '\n': case '\t': case '\v':  continue;
+            default:  break;
+        }
+        number = __Pyx_BufFmt_ExpectNumber(&ts);
+        if (number == -1) return NULL;
+        if (i < ndim && (size_t) number != ctx->head->field->type->arraysize[i])
+            return PyErr_Format(PyExc_ValueError,
+                        "Expected a dimension of size %zu, got %d",
+                        ctx->head->field->type->arraysize[i], number);
+        if (*ts != ',' && *ts != ')')
+            return PyErr_Format(PyExc_ValueError,
+                                "Expected a comma in format string, got '%c'", *ts);
+        if (*ts == ',') ts++;
+        i++;
+    }
+    if (i != ndim)
+        return PyErr_Format(PyExc_ValueError, "Expected %d dimension(s), got %d",
+                            ctx->head->field->type->ndim, i);
+    if (!*ts) {
+        PyErr_SetString(PyExc_ValueError,
+                        "Unexpected end of format string, expected ')'");
+        return NULL;
+    }
+    ctx->is_valid_array = 1;
+    ctx->new_count = 1;
+    *tsp = ++ts;
+    return Py_None;
+}
+static const char* __Pyx_BufFmt_CheckString(__Pyx_BufFmt_Context* ctx, const char* ts) {
+  int got_Z = 0;
+  while (1) {
+    switch(*ts) {
+      case 0:
+        if (ctx->enc_type != 0 && ctx->head == NULL) {
+          __Pyx_BufFmt_RaiseExpected(ctx);
+          return NULL;
+        }
+        if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL;
+        if (ctx->head != NULL) {
+          __Pyx_BufFmt_RaiseExpected(ctx);
+          return NULL;
+        }
+        return ts;
+      case ' ':
+      case '\r':
+      case '\n':
+        ++ts;
+        break;
+      case '<':
+        if (!__Pyx_IsLittleEndian()) {
+          PyErr_SetString(PyExc_ValueError, "Little-endian buffer not supported on big-endian compiler");
+          return NULL;
+        }
+        ctx->new_packmode = '=';
+        ++ts;
+        break;
+      case '>':
+      case '!':
+        if (__Pyx_IsLittleEndian()) {
+          PyErr_SetString(PyExc_ValueError, "Big-endian buffer not supported on little-endian compiler");
+          return NULL;
+        }
+        ctx->new_packmode = '=';
+        ++ts;
+        break;
+      case '=':
+      case '@':
+      case '^':
+        ctx->new_packmode = *ts++;
+        break;
+      case 'T':
+        {
+          const char* ts_after_sub;
+          size_t i, struct_count = ctx->new_count;
+          size_t struct_alignment = ctx->struct_alignment;
+          ctx->new_count = 1;
+          ++ts;
+          if (*ts != '{') {
+            PyErr_SetString(PyExc_ValueError, "Buffer acquisition: Expected '{' after 'T'");
+            return NULL;
+          }
+          if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL;
+          ctx->enc_type = 0;
+          ctx->enc_count = 0;
+          ctx->struct_alignment = 0;
+          ++ts;
+          ts_after_sub = ts;
+          for (i = 0; i != struct_count; ++i) {
+            ts_after_sub = __Pyx_BufFmt_CheckString(ctx, ts);
+            if (!ts_after_sub) return NULL;
+          }
+          ts = ts_after_sub;
+          if (struct_alignment) ctx->struct_alignment = struct_alignment;
+        }
+        break;
+      case '}':
+        {
+          size_t alignment = ctx->struct_alignment;
+          ++ts;
+          if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL;
+          ctx->enc_type = 0;
+          if (alignment && ctx->fmt_offset % alignment) {
+            ctx->fmt_offset += alignment - (ctx->fmt_offset % alignment);
+          }
+        }
+        return ts;
+      case 'x':
+        if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL;
+        ctx->fmt_offset += ctx->new_count;
+        ctx->new_count = 1;
+        ctx->enc_count = 0;
+        ctx->enc_type = 0;
+        ctx->enc_packmode = ctx->new_packmode;
+        ++ts;
+        break;
+      case 'Z':
+        got_Z = 1;
+        ++ts;
+        if (*ts != 'f' && *ts != 'd' && *ts != 'g') {
+          __Pyx_BufFmt_RaiseUnexpectedChar('Z');
+          return NULL;
+        }
+      case 'c': case 'b': case 'B': case 'h': case 'H': case 'i': case 'I':
+      case 'l': case 'L': case 'q': case 'Q':
+      case 'f': case 'd': case 'g':
+      case 'O': case 'p':
+        if (ctx->enc_type == *ts && got_Z == ctx->is_complex &&
+            ctx->enc_packmode == ctx->new_packmode) {
+          ctx->enc_count += ctx->new_count;
+          ctx->new_count = 1;
+          got_Z = 0;
+          ++ts;
+          break;
+        }
+      case 's':
+        if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL;
+        ctx->enc_count = ctx->new_count;
+        ctx->enc_packmode = ctx->new_packmode;
+        ctx->enc_type = *ts;
+        ctx->is_complex = got_Z;
+        ++ts;
+        ctx->new_count = 1;
+        got_Z = 0;
+        break;
+      case ':':
+        ++ts;
+        while(*ts != ':') ++ts;
+        ++ts;
+        break;
+      case '(':
+        if (!__pyx_buffmt_parse_array(ctx, &ts)) return NULL;
+        break;
+      default:
+        {
+          int number = __Pyx_BufFmt_ExpectNumber(&ts);
+          if (number == -1) return NULL;
+          ctx->new_count = (size_t)number;
+        }
+    }
+  }
+}
+static CYTHON_INLINE void __Pyx_ZeroBuffer(Py_buffer* buf) {
+  buf->buf = NULL;
+  buf->obj = NULL;
+  buf->strides = __Pyx_zeros;
+  buf->shape = __Pyx_zeros;
+  buf->suboffsets = __Pyx_minusones;
+}
+static CYTHON_INLINE int __Pyx_GetBufferAndValidate(
+        Py_buffer* buf, PyObject* obj,  __Pyx_TypeInfo* dtype, int flags,
+        int nd, int cast, __Pyx_BufFmt_StackElem* stack)
+{
+  if (obj == Py_None || obj == NULL) {
+    __Pyx_ZeroBuffer(buf);
+    return 0;
+  }
+  buf->buf = NULL;
+  if (__Pyx_GetBuffer(obj, buf, flags) == -1) goto fail;
+  if (buf->ndim != nd) {
+    PyErr_Format(PyExc_ValueError,
+                 "Buffer has wrong number of dimensions (expected %d, got %d)",
+                 nd, buf->ndim);
+    goto fail;
+  }
+  if (!cast) {
+    __Pyx_BufFmt_Context ctx;
+    __Pyx_BufFmt_Init(&ctx, stack, dtype);
+    if (!__Pyx_BufFmt_CheckString(&ctx, buf->format)) goto fail;
+  }
+  if ((unsigned)buf->itemsize != dtype->size) {
+    PyErr_Format(PyExc_ValueError,
+      "Item size of buffer (%" CYTHON_FORMAT_SSIZE_T "d byte%s) does not match size of '%s' (%" CYTHON_FORMAT_SSIZE_T "d byte%s)",
+      buf->itemsize, (buf->itemsize > 1) ? "s" : "",
+      dtype->name, (Py_ssize_t)dtype->size, (dtype->size > 1) ? "s" : "");
+    goto fail;
+  }
+  if (buf->suboffsets == NULL) buf->suboffsets = __Pyx_minusones;
+  return 0;
+fail:;
+  __Pyx_ZeroBuffer(buf);
+  return -1;
+}
+static CYTHON_INLINE void __Pyx_SafeReleaseBuffer(Py_buffer* info) {
+  if (info->buf == NULL) return;
+  if (info->suboffsets == __Pyx_minusones) info->suboffsets = NULL;
+  __Pyx_ReleaseBuffer(info);
+}
+
+static PyObject *__Pyx_GetBuiltinName(PyObject *name) {
+    PyObject* result = __Pyx_PyObject_GetAttrStr(__pyx_b, name);
+    if (unlikely(!result)) {
+        PyErr_Format(PyExc_NameError,
+#if PY_MAJOR_VERSION >= 3
+            "name '%U' is not defined", name);
+#else
+            "name '%.200s' is not defined", PyString_AS_STRING(name));
+#endif
+    }
+    return result;
+}
+
+static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name) {
+    PyObject *result;
+#if CYTHON_COMPILING_IN_CPYTHON
+    result = PyDict_GetItem(__pyx_d, name);
+    if (likely(result)) {
+        Py_INCREF(result);
+    } else {
+#else
+    result = PyObject_GetItem(__pyx_d, name);
+    if (!result) {
+        PyErr_Clear();
+#endif
+        result = __Pyx_GetBuiltinName(name);
+    }
+    return result;
+}
+
+#if CYTHON_COMPILING_IN_CPYTHON
+static CYTHON_INLINE PyObject* __Pyx_PyObject_Call(PyObject *func, PyObject *arg, PyObject *kw) {
+    PyObject *result;
+    ternaryfunc call = func->ob_type->tp_call;
+    if (unlikely(!call))
+        return PyObject_Call(func, arg, kw);
+    if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object")))
+        return NULL;
+    result = (*call)(func, arg, kw);
+    Py_LeaveRecursiveCall();
+    if (unlikely(!result) && unlikely(!PyErr_Occurred())) {
+        PyErr_SetString(
+            PyExc_SystemError,
+            "NULL result without error in PyObject_Call");
+    }
+    return result;
+}
+#endif
+
+#if CYTHON_COMPILING_IN_CPYTHON
+static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg) {
+    PyObject *self, *result;
+    PyCFunction cfunc;
+    cfunc = PyCFunction_GET_FUNCTION(func);
+    self = PyCFunction_GET_SELF(func);
+    if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object")))
+        return NULL;
+    result = cfunc(self, arg);
+    Py_LeaveRecursiveCall();
+    if (unlikely(!result) && unlikely(!PyErr_Occurred())) {
+        PyErr_SetString(
+            PyExc_SystemError,
+            "NULL result without error in PyObject_Call");
+    }
+    return result;
+}
+#endif
+
+#if CYTHON_COMPILING_IN_CPYTHON
+static PyObject* __Pyx__PyObject_CallOneArg(PyObject *func, PyObject *arg) {
+    PyObject *result;
+    PyObject *args = PyTuple_New(1);
+    if (unlikely(!args)) return NULL;
+    Py_INCREF(arg);
+    PyTuple_SET_ITEM(args, 0, arg);
+    result = __Pyx_PyObject_Call(func, args, NULL);
+    Py_DECREF(args);
+    return result;
+}
+static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) {
+#ifdef __Pyx_CyFunction_USED
+    if (likely(PyCFunction_Check(func) || PyObject_TypeCheck(func, __pyx_CyFunctionType))) {
+#else
+    if (likely(PyCFunction_Check(func))) {
+#endif
+        if (likely(PyCFunction_GET_FLAGS(func) & METH_O)) {
+            return __Pyx_PyObject_CallMethO(func, arg);
+        }
+    }
+    return __Pyx__PyObject_CallOneArg(func, arg);
+}
+#else
+static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) {
+    PyObject *result;
+    PyObject *args = PyTuple_Pack(1, arg);
+    if (unlikely(!args)) return NULL;
+    result = __Pyx_PyObject_Call(func, args, NULL);
+    Py_DECREF(args);
+    return result;
+}
+#endif
+
+static CYTHON_INLINE int __Pyx_TypeTest(PyObject *obj, PyTypeObject *type) {
+    if (unlikely(!type)) {
+        PyErr_SetString(PyExc_SystemError, "Missing type object");
+        return 0;
+    }
+    if (likely(PyObject_TypeCheck(obj, type)))
+        return 1;
+    PyErr_Format(PyExc_TypeError, "Cannot convert %.200s to %.200s",
+                 Py_TYPE(obj)->tp_name, type->tp_name);
+    return 0;
+}
+
+static void __Pyx_RaiseBufferFallbackError(void) {
+  PyErr_SetString(PyExc_ValueError,
+     "Buffer acquisition failed on assignment; and then reacquiring the old buffer failed too!");
+}
+
+static CYTHON_INLINE void __Pyx_ErrRestore(PyObject *type, PyObject *value, PyObject *tb) {
+#if CYTHON_COMPILING_IN_CPYTHON
+    PyObject *tmp_type, *tmp_value, *tmp_tb;
+    PyThreadState *tstate = PyThreadState_GET();
+    tmp_type = tstate->curexc_type;
+    tmp_value = tstate->curexc_value;
+    tmp_tb = tstate->curexc_traceback;
+    tstate->curexc_type = type;
+    tstate->curexc_value = value;
+    tstate->curexc_traceback = tb;
+    Py_XDECREF(tmp_type);
+    Py_XDECREF(tmp_value);
+    Py_XDECREF(tmp_tb);
+#else
+    PyErr_Restore(type, value, tb);
+#endif
+}
+static CYTHON_INLINE void __Pyx_ErrFetch(PyObject **type, PyObject **value, PyObject **tb) {
+#if CYTHON_COMPILING_IN_CPYTHON
+    PyThreadState *tstate = PyThreadState_GET();
+    *type = tstate->curexc_type;
+    *value = tstate->curexc_value;
+    *tb = tstate->curexc_traceback;
+    tstate->curexc_type = 0;
+    tstate->curexc_value = 0;
+    tstate->curexc_traceback = 0;
+#else
+    PyErr_Fetch(type, value, tb);
+#endif
+}
+
+#if PY_MAJOR_VERSION < 3
+static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb,
+                        CYTHON_UNUSED PyObject *cause) {
+    Py_XINCREF(type);
+    if (!value || value == Py_None)
+        value = NULL;
+    else
+        Py_INCREF(value);
+    if (!tb || tb == Py_None)
+        tb = NULL;
+    else {
+        Py_INCREF(tb);
+        if (!PyTraceBack_Check(tb)) {
+            PyErr_SetString(PyExc_TypeError,
+                "raise: arg 3 must be a traceback or None");
+            goto raise_error;
+        }
+    }
+    if (PyType_Check(type)) {
+#if CYTHON_COMPILING_IN_PYPY
+        if (!value) {
+            Py_INCREF(Py_None);
+            value = Py_None;
+        }
+#endif
+        PyErr_NormalizeException(&type, &value, &tb);
+    } else {
+        if (value) {
+            PyErr_SetString(PyExc_TypeError,
+                "instance exception may not have a separate value");
+            goto raise_error;
+        }
+        value = type;
+        type = (PyObject*) Py_TYPE(type);
+        Py_INCREF(type);
+        if (!PyType_IsSubtype((PyTypeObject *)type, (PyTypeObject *)PyExc_BaseException)) {
+            PyErr_SetString(PyExc_TypeError,
+                "raise: exception class must be a subclass of BaseException");
+            goto raise_error;
+        }
+    }
+    __Pyx_ErrRestore(type, value, tb);
+    return;
+raise_error:
+    Py_XDECREF(value);
+    Py_XDECREF(type);
+    Py_XDECREF(tb);
+    return;
+}
+#else
+static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause) {
+    PyObject* owned_instance = NULL;
+    if (tb == Py_None) {
+        tb = 0;
+    } else if (tb && !PyTraceBack_Check(tb)) {
+        PyErr_SetString(PyExc_TypeError,
+            "raise: arg 3 must be a traceback or None");
+        goto bad;
+    }
+    if (value == Py_None)
+        value = 0;
+    if (PyExceptionInstance_Check(type)) {
+        if (value) {
+            PyErr_SetString(PyExc_TypeError,
+                "instance exception may not have a separate value");
+            goto bad;
+        }
+        value = type;
+        type = (PyObject*) Py_TYPE(value);
+    } else if (PyExceptionClass_Check(type)) {
+        PyObject *instance_class = NULL;
+        if (value && PyExceptionInstance_Check(value)) {
+            instance_class = (PyObject*) Py_TYPE(value);
+            if (instance_class != type) {
+                int is_subclass = PyObject_IsSubclass(instance_class, type);
+                if (!is_subclass) {
+                    instance_class = NULL;
+                } else if (unlikely(is_subclass == -1)) {
+                    goto bad;
+                } else {
+                    type = instance_class;
+                }
+            }
+        }
+        if (!instance_class) {
+            PyObject *args;
+            if (!value)
+                args = PyTuple_New(0);
+            else if (PyTuple_Check(value)) {
+                Py_INCREF(value);
+                args = value;
+            } else
+                args = PyTuple_Pack(1, value);
+            if (!args)
+                goto bad;
+            owned_instance = PyObject_Call(type, args, NULL);
+            Py_DECREF(args);
+            if (!owned_instance)
+                goto bad;
+            value = owned_instance;
+            if (!PyExceptionInstance_Check(value)) {
+                PyErr_Format(PyExc_TypeError,
+                             "calling %R should have returned an instance of "
+                             "BaseException, not %R",
+                             type, Py_TYPE(value));
+                goto bad;
+            }
+        }
+    } else {
+        PyErr_SetString(PyExc_TypeError,
+            "raise: exception class must be a subclass of BaseException");
+        goto bad;
+    }
+#if PY_VERSION_HEX >= 0x03030000
+    if (cause) {
+#else
+    if (cause && cause != Py_None) {
+#endif
+        PyObject *fixed_cause;
+        if (cause == Py_None) {
+            fixed_cause = NULL;
+        } else if (PyExceptionClass_Check(cause)) {
+            fixed_cause = PyObject_CallObject(cause, NULL);
+            if (fixed_cause == NULL)
+                goto bad;
+        } else if (PyExceptionInstance_Check(cause)) {
+            fixed_cause = cause;
+            Py_INCREF(fixed_cause);
+        } else {
+            PyErr_SetString(PyExc_TypeError,
+                            "exception causes must derive from "
+                            "BaseException");
+            goto bad;
+        }
+        PyException_SetCause(value, fixed_cause);
+    }
+    PyErr_SetObject(type, value);
+    if (tb) {
+#if CYTHON_COMPILING_IN_PYPY
+        PyObject *tmp_type, *tmp_value, *tmp_tb;
+        PyErr_Fetch(&tmp_type, &tmp_value, &tmp_tb);
+        Py_INCREF(tb);
+        PyErr_Restore(tmp_type, tmp_value, tb);
+        Py_XDECREF(tmp_tb);
+#else
+        PyThreadState *tstate = PyThreadState_GET();
+        PyObject* tmp_tb = tstate->curexc_traceback;
+        if (tb != tmp_tb) {
+            Py_INCREF(tb);
+            tstate->curexc_traceback = tb;
+            Py_XDECREF(tmp_tb);
+        }
+#endif
+    }
+bad:
+    Py_XDECREF(owned_instance);
+    return;
+}
+#endif
+
+static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) {
+    PyErr_Format(PyExc_ValueError,
+                 "too many values to unpack (expected %" CYTHON_FORMAT_SSIZE_T "d)", expected);
+}
+
+static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index) {
+    PyErr_Format(PyExc_ValueError,
+                 "need more than %" CYTHON_FORMAT_SSIZE_T "d value%.1s to unpack",
+                 index, (index == 1) ? "" : "s");
+}
+
+static CYTHON_INLINE void __Pyx_RaiseNoneNotIterableError(void) {
+    PyErr_SetString(PyExc_TypeError, "'NoneType' object is not iterable");
+}
+
+static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) {
+    PyObject *empty_list = 0;
+    PyObject *module = 0;
+    PyObject *global_dict = 0;
+    PyObject *empty_dict = 0;
+    PyObject *list;
+    #if PY_VERSION_HEX < 0x03030000
+    PyObject *py_import;
+    py_import = __Pyx_PyObject_GetAttrStr(__pyx_b, __pyx_n_s_import);
+    if (!py_import)
+        goto bad;
+    #endif
+    if (from_list)
+        list = from_list;
+    else {
+        empty_list = PyList_New(0);
+        if (!empty_list)
+            goto bad;
+        list = empty_list;
+    }
+    global_dict = PyModule_GetDict(__pyx_m);
+    if (!global_dict)
+        goto bad;
+    empty_dict = PyDict_New();
+    if (!empty_dict)
+        goto bad;
+    {
+        #if PY_MAJOR_VERSION >= 3
+        if (level == -1) {
+            if (strchr(__Pyx_MODULE_NAME, '.')) {
+                #if PY_VERSION_HEX < 0x03030000
+                PyObject *py_level = PyInt_FromLong(1);
+                if (!py_level)
+                    goto bad;
+                module = PyObject_CallFunctionObjArgs(py_import,
+                    name, global_dict, empty_dict, list, py_level, NULL);
+                Py_DECREF(py_level);
+                #else
+                module = PyImport_ImportModuleLevelObject(
+                    name, global_dict, empty_dict, list, 1);
+                #endif
+                if (!module) {
+                    if (!PyErr_ExceptionMatches(PyExc_ImportError))
+                        goto bad;
+                    PyErr_Clear();
+                }
+            }
+            level = 0;
+        }
+        #endif
+        if (!module) {
+            #if PY_VERSION_HEX < 0x03030000
+            PyObject *py_level = PyInt_FromLong(level);
+            if (!py_level)
+                goto bad;
+            module = PyObject_CallFunctionObjArgs(py_import,
+                name, global_dict, empty_dict, list, py_level, NULL);
+            Py_DECREF(py_level);
+            #else
+            module = PyImport_ImportModuleLevelObject(
+                name, global_dict, empty_dict, list, level);
+            #endif
+        }
+    }
+bad:
+    #if PY_VERSION_HEX < 0x03030000
+    Py_XDECREF(py_import);
+    #endif
+    Py_XDECREF(empty_list);
+    Py_XDECREF(empty_dict);
+    return module;
+}
+
+static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) {
+    int start = 0, mid = 0, end = count - 1;
+    if (end >= 0 && code_line > entries[end].code_line) {
+        return count;
+    }
+    while (start < end) {
+        mid = start + (end - start) / 2;
+        if (code_line < entries[mid].code_line) {
+            end = mid;
+        } else if (code_line > entries[mid].code_line) {
+             start = mid + 1;
+        } else {
+            return mid;
+        }
+    }
+    if (code_line <= entries[mid].code_line) {
+        return mid;
+    } else {
+        return mid + 1;
+    }
+}
+static PyCodeObject *__pyx_find_code_object(int code_line) {
+    PyCodeObject* code_object;
+    int pos;
+    if (unlikely(!code_line) || unlikely(!__pyx_code_cache.entries)) {
+        return NULL;
+    }
+    pos = __pyx_bisect_code_objects(__pyx_code_cache.entries, __pyx_code_cache.count, code_line);
+    if (unlikely(pos >= __pyx_code_cache.count) || unlikely(__pyx_code_cache.entries[pos].code_line != code_line)) {
+        return NULL;
+    }
+    code_object = __pyx_code_cache.entries[pos].code_object;
+    Py_INCREF(code_object);
+    return code_object;
+}
+static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object) {
+    int pos, i;
+    __Pyx_CodeObjectCacheEntry* entries = __pyx_code_cache.entries;
+    if (unlikely(!code_line)) {
+        return;
+    }
+    if (unlikely(!entries)) {
+        entries = (__Pyx_CodeObjectCacheEntry*)PyMem_Malloc(64*sizeof(__Pyx_CodeObjectCacheEntry));
+        if (likely(entries)) {
+            __pyx_code_cache.entries = entries;
+            __pyx_code_cache.max_count = 64;
+            __pyx_code_cache.count = 1;
+            entries[0].code_line = code_line;
+            entries[0].code_object = code_object;
+            Py_INCREF(code_object);
+        }
+        return;
+    }
+    pos = __pyx_bisect_code_objects(__pyx_code_cache.entries, __pyx_code_cache.count, code_line);
+    if ((pos < __pyx_code_cache.count) && unlikely(__pyx_code_cache.entries[pos].code_line == code_line)) {
+        PyCodeObject* tmp = entries[pos].code_object;
+        entries[pos].code_object = code_object;
+        Py_DECREF(tmp);
+        return;
+    }
+    if (__pyx_code_cache.count == __pyx_code_cache.max_count) {
+        int new_max = __pyx_code_cache.max_count + 64;
+        entries = (__Pyx_CodeObjectCacheEntry*)PyMem_Realloc(
+            __pyx_code_cache.entries, (size_t)new_max*sizeof(__Pyx_CodeObjectCacheEntry));
+        if (unlikely(!entries)) {
+            return;
+        }
+        __pyx_code_cache.entries = entries;
+        __pyx_code_cache.max_count = new_max;
+    }
+    for (i=__pyx_code_cache.count; i>pos; i--) {
+        entries[i] = entries[i-1];
+    }
+    entries[pos].code_line = code_line;
+    entries[pos].code_object = code_object;
+    __pyx_code_cache.count++;
+    Py_INCREF(code_object);
+}
+
+#include "compile.h"
+#include "frameobject.h"
+#include "traceback.h"
+static PyCodeObject* __Pyx_CreateCodeObjectForTraceback(
+            const char *funcname, int c_line,
+            int py_line, const char *filename) {
+    PyCodeObject *py_code = 0;
+    PyObject *py_srcfile = 0;
+    PyObject *py_funcname = 0;
+    #if PY_MAJOR_VERSION < 3
+    py_srcfile = PyString_FromString(filename);
+    #else
+    py_srcfile = PyUnicode_FromString(filename);
+    #endif
+    if (!py_srcfile) goto bad;
+    if (c_line) {
+        #if PY_MAJOR_VERSION < 3
+        py_funcname = PyString_FromFormat( "%s (%s:%d)", funcname, __pyx_cfilenm, c_line);
+        #else
+        py_funcname = PyUnicode_FromFormat( "%s (%s:%d)", funcname, __pyx_cfilenm, c_line);
+        #endif
+    }
+    else {
+        #if PY_MAJOR_VERSION < 3
+        py_funcname = PyString_FromString(funcname);
+        #else
+        py_funcname = PyUnicode_FromString(funcname);
+        #endif
+    }
+    if (!py_funcname) goto bad;
+    py_code = __Pyx_PyCode_New(
+        0,
+        0,
+        0,
+        0,
+        0,
+        __pyx_empty_bytes, /*PyObject *code,*/
+        __pyx_empty_tuple, /*PyObject *consts,*/
+        __pyx_empty_tuple, /*PyObject *names,*/
+        __pyx_empty_tuple, /*PyObject *varnames,*/
+        __pyx_empty_tuple, /*PyObject *freevars,*/
+        __pyx_empty_tuple, /*PyObject *cellvars,*/
+        py_srcfile,   /*PyObject *filename,*/
+        py_funcname,  /*PyObject *name,*/
+        py_line,
+        __pyx_empty_bytes  /*PyObject *lnotab*/
+    );
+    Py_DECREF(py_srcfile);
+    Py_DECREF(py_funcname);
+    return py_code;
+bad:
+    Py_XDECREF(py_srcfile);
+    Py_XDECREF(py_funcname);
+    return NULL;
+}
+static void __Pyx_AddTraceback(const char *funcname, int c_line,
+                               int py_line, const char *filename) {
+    PyCodeObject *py_code = 0;
+    PyFrameObject *py_frame = 0;
+    py_code = __pyx_find_code_object(c_line ? c_line : py_line);
+    if (!py_code) {
+        py_code = __Pyx_CreateCodeObjectForTraceback(
+            funcname, c_line, py_line, filename);
+        if (!py_code) goto bad;
+        __pyx_insert_code_object(c_line ? c_line : py_line, py_code);
+    }
+    py_frame = PyFrame_New(
+        PyThreadState_GET(), /*PyThreadState *tstate,*/
+        py_code,             /*PyCodeObject *code,*/
+        __pyx_d,      /*PyObject *globals,*/
+        0                    /*PyObject *locals*/
+    );
+    if (!py_frame) goto bad;
+    py_frame->f_lineno = py_line;
+    PyTraceBack_Here(py_frame);
+bad:
+    Py_XDECREF(py_code);
+    Py_XDECREF(py_frame);
+}
+
+#if PY_MAJOR_VERSION < 3
+static int __Pyx_GetBuffer(PyObject *obj, Py_buffer *view, int flags) {
+    if (PyObject_CheckBuffer(obj)) return PyObject_GetBuffer(obj, view, flags);
+        if (PyObject_TypeCheck(obj, __pyx_ptype_5numpy_ndarray)) return __pyx_pw_5numpy_7ndarray_1__getbuffer__(obj, view, flags);
+    PyErr_Format(PyExc_TypeError, "'%.200s' does not have the buffer interface", Py_TYPE(obj)->tp_name);
+    return -1;
+}
+static void __Pyx_ReleaseBuffer(Py_buffer *view) {
+    PyObject *obj = view->obj;
+    if (!obj) return;
+    if (PyObject_CheckBuffer(obj)) {
+        PyBuffer_Release(view);
+        return;
+    }
+        if (PyObject_TypeCheck(obj, __pyx_ptype_5numpy_ndarray)) { __pyx_pw_5numpy_7ndarray_3__releasebuffer__(obj, view); return; }
+    Py_DECREF(obj);
+    view->obj = NULL;
+}
+#endif
+
+
+        static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value) {
+    const int neg_one = (int) -1, const_zero = (int) 0;
+    const int is_unsigned = neg_one > const_zero;
+    if (is_unsigned) {
+        if (sizeof(int) < sizeof(long)) {
+            return PyInt_FromLong((long) value);
+        } else if (sizeof(int) <= sizeof(unsigned long)) {
+            return PyLong_FromUnsignedLong((unsigned long) value);
+        } else if (sizeof(int) <= sizeof(unsigned PY_LONG_LONG)) {
+            return PyLong_FromUnsignedLongLong((unsigned PY_LONG_LONG) value);
+        }
+    } else {
+        if (sizeof(int) <= sizeof(long)) {
+            return PyInt_FromLong((long) value);
+        } else if (sizeof(int) <= sizeof(PY_LONG_LONG)) {
+            return PyLong_FromLongLong((PY_LONG_LONG) value);
+        }
+    }
+    {
+        int one = 1; int little = (int)*(unsigned char *)&one;
+        unsigned char *bytes = (unsigned char *)&value;
+        return _PyLong_FromByteArray(bytes, sizeof(int),
+                                     little, !is_unsigned);
+    }
+}
+
+#if CYTHON_CCOMPLEX
+  #ifdef __cplusplus
+    static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float x, float y) {
+      return ::std::complex< float >(x, y);
+    }
+  #else
+    static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float x, float y) {
+      return x + y*(__pyx_t_float_complex)_Complex_I;
+    }
+  #endif
+#else
+    static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float x, float y) {
+      __pyx_t_float_complex z;
+      z.real = x;
+      z.imag = y;
+      return z;
+    }
+#endif
+
+#if CYTHON_CCOMPLEX
+#else
+    static CYTHON_INLINE int __Pyx_c_eqf(__pyx_t_float_complex a, __pyx_t_float_complex b) {
+       return (a.real == b.real) && (a.imag == b.imag);
+    }
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_sumf(__pyx_t_float_complex a, __pyx_t_float_complex b) {
+        __pyx_t_float_complex z;
+        z.real = a.real + b.real;
+        z.imag = a.imag + b.imag;
+        return z;
+    }
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_difff(__pyx_t_float_complex a, __pyx_t_float_complex b) {
+        __pyx_t_float_complex z;
+        z.real = a.real - b.real;
+        z.imag = a.imag - b.imag;
+        return z;
+    }
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_prodf(__pyx_t_float_complex a, __pyx_t_float_complex b) {
+        __pyx_t_float_complex z;
+        z.real = a.real * b.real - a.imag * b.imag;
+        z.imag = a.real * b.imag + a.imag * b.real;
+        return z;
+    }
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_quotf(__pyx_t_float_complex a, __pyx_t_float_complex b) {
+        __pyx_t_float_complex z;
+        float denom = b.real * b.real + b.imag * b.imag;
+        z.real = (a.real * b.real + a.imag * b.imag) / denom;
+        z.imag = (a.imag * b.real - a.real * b.imag) / denom;
+        return z;
+    }
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_negf(__pyx_t_float_complex a) {
+        __pyx_t_float_complex z;
+        z.real = -a.real;
+        z.imag = -a.imag;
+        return z;
+    }
+    static CYTHON_INLINE int __Pyx_c_is_zerof(__pyx_t_float_complex a) {
+       return (a.real == 0) && (a.imag == 0);
+    }
+    static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_conjf(__pyx_t_float_complex a) {
+        __pyx_t_float_complex z;
+        z.real =  a.real;
+        z.imag = -a.imag;
+        return z;
+    }
+    #if 1
+        static CYTHON_INLINE float __Pyx_c_absf(__pyx_t_float_complex z) {
+          #if !defined(HAVE_HYPOT) || defined(_MSC_VER)
+            return sqrtf(z.real*z.real + z.imag*z.imag);
+          #else
+            return hypotf(z.real, z.imag);
+          #endif
+        }
+        static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_powf(__pyx_t_float_complex a, __pyx_t_float_complex b) {
+            __pyx_t_float_complex z;
+            float r, lnr, theta, z_r, z_theta;
+            if (b.imag == 0 && b.real == (int)b.real) {
+                if (b.real < 0) {
+                    float denom = a.real * a.real + a.imag * a.imag;
+                    a.real = a.real / denom;
+                    a.imag = -a.imag / denom;
+                    b.real = -b.real;
+                }
+                switch ((int)b.real) {
+                    case 0:
+                        z.real = 1;
+                        z.imag = 0;
+                        return z;
+                    case 1:
+                        return a;
+                    case 2:
+                        z = __Pyx_c_prodf(a, a);
+                        return __Pyx_c_prodf(a, a);
+                    case 3:
+                        z = __Pyx_c_prodf(a, a);
+                        return __Pyx_c_prodf(z, a);
+                    case 4:
+                        z = __Pyx_c_prodf(a, a);
+                        return __Pyx_c_prodf(z, z);
+                }
+            }
+            if (a.imag == 0) {
+                if (a.real == 0) {
+                    return a;
+                }
+                r = a.real;
+                theta = 0;
+            } else {
+                r = __Pyx_c_absf(a);
+                theta = atan2f(a.imag, a.real);
+            }
+            lnr = logf(r);
+            z_r = expf(lnr * b.real - theta * b.imag);
+            z_theta = theta * b.real + lnr * b.imag;
+            z.real = z_r * cosf(z_theta);
+            z.imag = z_r * sinf(z_theta);
+            return z;
+        }
+    #endif
+#endif
+
+#if CYTHON_CCOMPLEX
+  #ifdef __cplusplus
+    static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double x, double y) {
+      return ::std::complex< double >(x, y);
+    }
+  #else
+    static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double x, double y) {
+      return x + y*(__pyx_t_double_complex)_Complex_I;
+    }
+  #endif
+#else
+    static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double x, double y) {
+      __pyx_t_double_complex z;
+      z.real = x;
+      z.imag = y;
+      return z;
+    }
+#endif
+
+#if CYTHON_CCOMPLEX
+#else
+    static CYTHON_INLINE int __Pyx_c_eq(__pyx_t_double_complex a, __pyx_t_double_complex b) {
+       return (a.real == b.real) && (a.imag == b.imag);
+    }
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_sum(__pyx_t_double_complex a, __pyx_t_double_complex b) {
+        __pyx_t_double_complex z;
+        z.real = a.real + b.real;
+        z.imag = a.imag + b.imag;
+        return z;
+    }
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_diff(__pyx_t_double_complex a, __pyx_t_double_complex b) {
+        __pyx_t_double_complex z;
+        z.real = a.real - b.real;
+        z.imag = a.imag - b.imag;
+        return z;
+    }
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_prod(__pyx_t_double_complex a, __pyx_t_double_complex b) {
+        __pyx_t_double_complex z;
+        z.real = a.real * b.real - a.imag * b.imag;
+        z.imag = a.real * b.imag + a.imag * b.real;
+        return z;
+    }
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_quot(__pyx_t_double_complex a, __pyx_t_double_complex b) {
+        __pyx_t_double_complex z;
+        double denom = b.real * b.real + b.imag * b.imag;
+        z.real = (a.real * b.real + a.imag * b.imag) / denom;
+        z.imag = (a.imag * b.real - a.real * b.imag) / denom;
+        return z;
+    }
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_neg(__pyx_t_double_complex a) {
+        __pyx_t_double_complex z;
+        z.real = -a.real;
+        z.imag = -a.imag;
+        return z;
+    }
+    static CYTHON_INLINE int __Pyx_c_is_zero(__pyx_t_double_complex a) {
+       return (a.real == 0) && (a.imag == 0);
+    }
+    static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_conj(__pyx_t_double_complex a) {
+        __pyx_t_double_complex z;
+        z.real =  a.real;
+        z.imag = -a.imag;
+        return z;
+    }
+    #if 1
+        static CYTHON_INLINE double __Pyx_c_abs(__pyx_t_double_complex z) {
+          #if !defined(HAVE_HYPOT) || defined(_MSC_VER)
+            return sqrt(z.real*z.real + z.imag*z.imag);
+          #else
+            return hypot(z.real, z.imag);
+          #endif
+        }
+        static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_pow(__pyx_t_double_complex a, __pyx_t_double_complex b) {
+            __pyx_t_double_complex z;
+            double r, lnr, theta, z_r, z_theta;
+            if (b.imag == 0 && b.real == (int)b.real) {
+                if (b.real < 0) {
+                    double denom = a.real * a.real + a.imag * a.imag;
+                    a.real = a.real / denom;
+                    a.imag = -a.imag / denom;
+                    b.real = -b.real;
+                }
+                switch ((int)b.real) {
+                    case 0:
+                        z.real = 1;
+                        z.imag = 0;
+                        return z;
+                    case 1:
+                        return a;
+                    case 2:
+                        z = __Pyx_c_prod(a, a);
+                        return __Pyx_c_prod(a, a);
+                    case 3:
+                        z = __Pyx_c_prod(a, a);
+                        return __Pyx_c_prod(z, a);
+                    case 4:
+                        z = __Pyx_c_prod(a, a);
+                        return __Pyx_c_prod(z, z);
+                }
+            }
+            if (a.imag == 0) {
+                if (a.real == 0) {
+                    return a;
+                }
+                r = a.real;
+                theta = 0;
+            } else {
+                r = __Pyx_c_abs(a);
+                theta = atan2(a.imag, a.real);
+            }
+            lnr = log(r);
+            z_r = exp(lnr * b.real - theta * b.imag);
+            z_theta = theta * b.real + lnr * b.imag;
+            z.real = z_r * cos(z_theta);
+            z.imag = z_r * sin(z_theta);
+            return z;
+        }
+    #endif
+#endif
+
+#define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\
+    __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 0)
+#define __PYX_VERIFY_RETURN_INT_EXC(target_type, func_type, func_value)\
+    __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 1)
+#define __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, exc)\
+    {\
+        func_type value = func_value;\
+        if (sizeof(target_type) < sizeof(func_type)) {\
+            if (unlikely(value != (func_type) (target_type) value)) {\
+                func_type zero = 0;\
+                if (exc && unlikely(value == (func_type)-1 && PyErr_Occurred()))\
+                    return (target_type) -1;\
+                if (is_unsigned && unlikely(value < zero))\
+                    goto raise_neg_overflow;\
+                else\
+                    goto raise_overflow;\
+            }\
+        }\
+        return (target_type) value;\
+    }
+
+#if CYTHON_USE_PYLONG_INTERNALS
+  #include "longintrepr.h"
+#endif
+
+static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) {
+    const int neg_one = (int) -1, const_zero = (int) 0;
+    const int is_unsigned = neg_one > const_zero;
+#if PY_MAJOR_VERSION < 3
+    if (likely(PyInt_Check(x))) {
+        if (sizeof(int) < sizeof(long)) {
+            __PYX_VERIFY_RETURN_INT(int, long, PyInt_AS_LONG(x))
+        } else {
+            long val = PyInt_AS_LONG(x);
+            if (is_unsigned && unlikely(val < 0)) {
+                goto raise_neg_overflow;
+            }
+            return (int) val;
+        }
+    } else
+#endif
+    if (likely(PyLong_Check(x))) {
+        if (is_unsigned) {
+#if CYTHON_USE_PYLONG_INTERNALS
+            const digit* digits = ((PyLongObject*)x)->ob_digit;
+            switch (Py_SIZE(x)) {
+                case  0: return (int) 0;
+                case  1: __PYX_VERIFY_RETURN_INT(int, digit, digits[0])
+                case 2:
+                    if (8 * sizeof(int) > 1 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(int) >= 2 * PyLong_SHIFT) {
+                            return (int) (((((int)digits[1]) << PyLong_SHIFT) | (int)digits[0]));
+                        }
+                    }
+                    break;
+                case 3:
+                    if (8 * sizeof(int) > 2 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(int) >= 3 * PyLong_SHIFT) {
+                            return (int) (((((((int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0]));
+                        }
+                    }
+                    break;
+                case 4:
+                    if (8 * sizeof(int) > 3 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(int) >= 4 * PyLong_SHIFT) {
+                            return (int) (((((((((int)digits[3]) << PyLong_SHIFT) | (int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0]));
+                        }
+                    }
+                    break;
+            }
+#endif
+#if CYTHON_COMPILING_IN_CPYTHON
+            if (unlikely(Py_SIZE(x) < 0)) {
+                goto raise_neg_overflow;
+            }
+#else
+            {
+                int result = PyObject_RichCompareBool(x, Py_False, Py_LT);
+                if (unlikely(result < 0))
+                    return (int) -1;
+                if (unlikely(result == 1))
+                    goto raise_neg_overflow;
+            }
+#endif
+            if (sizeof(int) <= sizeof(unsigned long)) {
+                __PYX_VERIFY_RETURN_INT_EXC(int, unsigned long, PyLong_AsUnsignedLong(x))
+            } else if (sizeof(int) <= sizeof(unsigned PY_LONG_LONG)) {
+                __PYX_VERIFY_RETURN_INT_EXC(int, unsigned PY_LONG_LONG, PyLong_AsUnsignedLongLong(x))
+            }
+        } else {
+#if CYTHON_USE_PYLONG_INTERNALS
+            const digit* digits = ((PyLongObject*)x)->ob_digit;
+            switch (Py_SIZE(x)) {
+                case  0: return (int) 0;
+                case -1: __PYX_VERIFY_RETURN_INT(int, sdigit, -(sdigit) digits[0])
+                case  1: __PYX_VERIFY_RETURN_INT(int,  digit, +digits[0])
+                case -2:
+                    if (8 * sizeof(int) - 1 > 1 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(int, long, -(long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(int) - 1 > 2 * PyLong_SHIFT) {
+                            return (int) (((int)-1)*(((((int)digits[1]) << PyLong_SHIFT) | (int)digits[0])));
+                        }
+                    }
+                    break;
+                case 2:
+                    if (8 * sizeof(int) > 1 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(int) - 1 > 2 * PyLong_SHIFT) {
+                            return (int) ((((((int)digits[1]) << PyLong_SHIFT) | (int)digits[0])));
+                        }
+                    }
+                    break;
+                case -3:
+                    if (8 * sizeof(int) - 1 > 2 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(int, long, -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(int) - 1 > 3 * PyLong_SHIFT) {
+                            return (int) (((int)-1)*(((((((int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0])));
+                        }
+                    }
+                    break;
+                case 3:
+                    if (8 * sizeof(int) > 2 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(int) - 1 > 3 * PyLong_SHIFT) {
+                            return (int) ((((((((int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0])));
+                        }
+                    }
+                    break;
+                case -4:
+                    if (8 * sizeof(int) - 1 > 3 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(int, long, -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(int) - 1 > 4 * PyLong_SHIFT) {
+                            return (int) (((int)-1)*(((((((((int)digits[3]) << PyLong_SHIFT) | (int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0])));
+                        }
+                    }
+                    break;
+                case 4:
+                    if (8 * sizeof(int) > 3 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(int) - 1 > 4 * PyLong_SHIFT) {
+                            return (int) ((((((((((int)digits[3]) << PyLong_SHIFT) | (int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0])));
+                        }
+                    }
+                    break;
+            }
+#endif
+            if (sizeof(int) <= sizeof(long)) {
+                __PYX_VERIFY_RETURN_INT_EXC(int, long, PyLong_AsLong(x))
+            } else if (sizeof(int) <= sizeof(PY_LONG_LONG)) {
+                __PYX_VERIFY_RETURN_INT_EXC(int, PY_LONG_LONG, PyLong_AsLongLong(x))
+            }
+        }
+        {
+#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray)
+            PyErr_SetString(PyExc_RuntimeError,
+                            "_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers");
+#else
+            int val;
+            PyObject *v = __Pyx_PyNumber_Int(x);
+ #if PY_MAJOR_VERSION < 3
+            if (likely(v) && !PyLong_Check(v)) {
+                PyObject *tmp = v;
+                v = PyNumber_Long(tmp);
+                Py_DECREF(tmp);
+            }
+ #endif
+            if (likely(v)) {
+                int one = 1; int is_little = (int)*(unsigned char *)&one;
+                unsigned char *bytes = (unsigned char *)&val;
+                int ret = _PyLong_AsByteArray((PyLongObject *)v,
+                                              bytes, sizeof(val),
+                                              is_little, !is_unsigned);
+                Py_DECREF(v);
+                if (likely(!ret))
+                    return val;
+            }
+#endif
+            return (int) -1;
+        }
+    } else {
+        int val;
+        PyObject *tmp = __Pyx_PyNumber_Int(x);
+        if (!tmp) return (int) -1;
+        val = __Pyx_PyInt_As_int(tmp);
+        Py_DECREF(tmp);
+        return val;
+    }
+raise_overflow:
+    PyErr_SetString(PyExc_OverflowError,
+        "value too large to convert to int");
+    return (int) -1;
+raise_neg_overflow:
+    PyErr_SetString(PyExc_OverflowError,
+        "can't convert negative value to int");
+    return (int) -1;
+}
+
+static CYTHON_INLINE PyObject* __Pyx_PyInt_From_enum__NPY_TYPES(enum NPY_TYPES value) {
+    const enum NPY_TYPES neg_one = (enum NPY_TYPES) -1, const_zero = (enum NPY_TYPES) 0;
+    const int is_unsigned = neg_one > const_zero;
+    if (is_unsigned) {
+        if (sizeof(enum NPY_TYPES) < sizeof(long)) {
+            return PyInt_FromLong((long) value);
+        } else if (sizeof(enum NPY_TYPES) <= sizeof(unsigned long)) {
+            return PyLong_FromUnsignedLong((unsigned long) value);
+        } else if (sizeof(enum NPY_TYPES) <= sizeof(unsigned PY_LONG_LONG)) {
+            return PyLong_FromUnsignedLongLong((unsigned PY_LONG_LONG) value);
+        }
+    } else {
+        if (sizeof(enum NPY_TYPES) <= sizeof(long)) {
+            return PyInt_FromLong((long) value);
+        } else if (sizeof(enum NPY_TYPES) <= sizeof(PY_LONG_LONG)) {
+            return PyLong_FromLongLong((PY_LONG_LONG) value);
+        }
+    }
+    {
+        int one = 1; int little = (int)*(unsigned char *)&one;
+        unsigned char *bytes = (unsigned char *)&value;
+        return _PyLong_FromByteArray(bytes, sizeof(enum NPY_TYPES),
+                                     little, !is_unsigned);
+    }
+}
+
+static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) {
+    const long neg_one = (long) -1, const_zero = (long) 0;
+    const int is_unsigned = neg_one > const_zero;
+    if (is_unsigned) {
+        if (sizeof(long) < sizeof(long)) {
+            return PyInt_FromLong((long) value);
+        } else if (sizeof(long) <= sizeof(unsigned long)) {
+            return PyLong_FromUnsignedLong((unsigned long) value);
+        } else if (sizeof(long) <= sizeof(unsigned PY_LONG_LONG)) {
+            return PyLong_FromUnsignedLongLong((unsigned PY_LONG_LONG) value);
+        }
+    } else {
+        if (sizeof(long) <= sizeof(long)) {
+            return PyInt_FromLong((long) value);
+        } else if (sizeof(long) <= sizeof(PY_LONG_LONG)) {
+            return PyLong_FromLongLong((PY_LONG_LONG) value);
+        }
+    }
+    {
+        int one = 1; int little = (int)*(unsigned char *)&one;
+        unsigned char *bytes = (unsigned char *)&value;
+        return _PyLong_FromByteArray(bytes, sizeof(long),
+                                     little, !is_unsigned);
+    }
+}
+
+static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) {
+    const long neg_one = (long) -1, const_zero = (long) 0;
+    const int is_unsigned = neg_one > const_zero;
+#if PY_MAJOR_VERSION < 3
+    if (likely(PyInt_Check(x))) {
+        if (sizeof(long) < sizeof(long)) {
+            __PYX_VERIFY_RETURN_INT(long, long, PyInt_AS_LONG(x))
+        } else {
+            long val = PyInt_AS_LONG(x);
+            if (is_unsigned && unlikely(val < 0)) {
+                goto raise_neg_overflow;
+            }
+            return (long) val;
+        }
+    } else
+#endif
+    if (likely(PyLong_Check(x))) {
+        if (is_unsigned) {
+#if CYTHON_USE_PYLONG_INTERNALS
+            const digit* digits = ((PyLongObject*)x)->ob_digit;
+            switch (Py_SIZE(x)) {
+                case  0: return (long) 0;
+                case  1: __PYX_VERIFY_RETURN_INT(long, digit, digits[0])
+                case 2:
+                    if (8 * sizeof(long) > 1 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(long) >= 2 * PyLong_SHIFT) {
+                            return (long) (((((long)digits[1]) << PyLong_SHIFT) | (long)digits[0]));
+                        }
+                    }
+                    break;
+                case 3:
+                    if (8 * sizeof(long) > 2 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(long) >= 3 * PyLong_SHIFT) {
+                            return (long) (((((((long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0]));
+                        }
+                    }
+                    break;
+                case 4:
+                    if (8 * sizeof(long) > 3 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(long) >= 4 * PyLong_SHIFT) {
+                            return (long) (((((((((long)digits[3]) << PyLong_SHIFT) | (long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0]));
+                        }
+                    }
+                    break;
+            }
+#endif
+#if CYTHON_COMPILING_IN_CPYTHON
+            if (unlikely(Py_SIZE(x) < 0)) {
+                goto raise_neg_overflow;
+            }
+#else
+            {
+                int result = PyObject_RichCompareBool(x, Py_False, Py_LT);
+                if (unlikely(result < 0))
+                    return (long) -1;
+                if (unlikely(result == 1))
+                    goto raise_neg_overflow;
+            }
+#endif
+            if (sizeof(long) <= sizeof(unsigned long)) {
+                __PYX_VERIFY_RETURN_INT_EXC(long, unsigned long, PyLong_AsUnsignedLong(x))
+            } else if (sizeof(long) <= sizeof(unsigned PY_LONG_LONG)) {
+                __PYX_VERIFY_RETURN_INT_EXC(long, unsigned PY_LONG_LONG, PyLong_AsUnsignedLongLong(x))
+            }
+        } else {
+#if CYTHON_USE_PYLONG_INTERNALS
+            const digit* digits = ((PyLongObject*)x)->ob_digit;
+            switch (Py_SIZE(x)) {
+                case  0: return (long) 0;
+                case -1: __PYX_VERIFY_RETURN_INT(long, sdigit, -(sdigit) digits[0])
+                case  1: __PYX_VERIFY_RETURN_INT(long,  digit, +digits[0])
+                case -2:
+                    if (8 * sizeof(long) - 1 > 1 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(long, long, -(long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) {
+                            return (long) (((long)-1)*(((((long)digits[1]) << PyLong_SHIFT) | (long)digits[0])));
+                        }
+                    }
+                    break;
+                case 2:
+                    if (8 * sizeof(long) > 1 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) {
+                            return (long) ((((((long)digits[1]) << PyLong_SHIFT) | (long)digits[0])));
+                        }
+                    }
+                    break;
+                case -3:
+                    if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(long, long, -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) {
+                            return (long) (((long)-1)*(((((((long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0])));
+                        }
+                    }
+                    break;
+                case 3:
+                    if (8 * sizeof(long) > 2 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) {
+                            return (long) ((((((((long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0])));
+                        }
+                    }
+                    break;
+                case -4:
+                    if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(long, long, -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) {
+                            return (long) (((long)-1)*(((((((((long)digits[3]) << PyLong_SHIFT) | (long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0])));
+                        }
+                    }
+                    break;
+                case 4:
+                    if (8 * sizeof(long) > 3 * PyLong_SHIFT) {
+                        if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) {
+                            __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])))
+                        } else if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) {
+                            return (long) ((((((((((long)digits[3]) << PyLong_SHIFT) | (long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0])));
+                        }
+                    }
+                    break;
+            }
+#endif
+            if (sizeof(long) <= sizeof(long)) {
+                __PYX_VERIFY_RETURN_INT_EXC(long, long, PyLong_AsLong(x))
+            } else if (sizeof(long) <= sizeof(PY_LONG_LONG)) {
+                __PYX_VERIFY_RETURN_INT_EXC(long, PY_LONG_LONG, PyLong_AsLongLong(x))
+            }
+        }
+        {
+#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray)
+            PyErr_SetString(PyExc_RuntimeError,
+                            "_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers");
+#else
+            long val;
+            PyObject *v = __Pyx_PyNumber_Int(x);
+ #if PY_MAJOR_VERSION < 3
+            if (likely(v) && !PyLong_Check(v)) {
+                PyObject *tmp = v;
+                v = PyNumber_Long(tmp);
+                Py_DECREF(tmp);
+            }
+ #endif
+            if (likely(v)) {
+                int one = 1; int is_little = (int)*(unsigned char *)&one;
+                unsigned char *bytes = (unsigned char *)&val;
+                int ret = _PyLong_AsByteArray((PyLongObject *)v,
+                                              bytes, sizeof(val),
+                                              is_little, !is_unsigned);
+                Py_DECREF(v);
+                if (likely(!ret))
+                    return val;
+            }
+#endif
+            return (long) -1;
+        }
+    } else {
+        long val;
+        PyObject *tmp = __Pyx_PyNumber_Int(x);
+        if (!tmp) return (long) -1;
+        val = __Pyx_PyInt_As_long(tmp);
+        Py_DECREF(tmp);
+        return val;
+    }
+raise_overflow:
+    PyErr_SetString(PyExc_OverflowError,
+        "value too large to convert to long");
+    return (long) -1;
+raise_neg_overflow:
+    PyErr_SetString(PyExc_OverflowError,
+        "can't convert negative value to long");
+    return (long) -1;
+}
+
+static int __Pyx_check_binary_version(void) {
+    char ctversion[4], rtversion[4];
+    PyOS_snprintf(ctversion, 4, "%d.%d", PY_MAJOR_VERSION, PY_MINOR_VERSION);
+    PyOS_snprintf(rtversion, 4, "%s", Py_GetVersion());
+    if (ctversion[0] != rtversion[0] || ctversion[2] != rtversion[2]) {
+        char message[200];
+        PyOS_snprintf(message, sizeof(message),
+                      "compiletime version %s of module '%.100s' "
+                      "does not match runtime version %s",
+                      ctversion, __Pyx_MODULE_NAME, rtversion);
+        return PyErr_WarnEx(NULL, message, 1);
+    }
+    return 0;
+}
+
+#ifndef __PYX_HAVE_RT_ImportModule
+#define __PYX_HAVE_RT_ImportModule
+static PyObject *__Pyx_ImportModule(const char *name) {
+    PyObject *py_name = 0;
+    PyObject *py_module = 0;
+    py_name = __Pyx_PyIdentifier_FromString(name);
+    if (!py_name)
+        goto bad;
+    py_module = PyImport_Import(py_name);
+    Py_DECREF(py_name);
+    return py_module;
+bad:
+    Py_XDECREF(py_name);
+    return 0;
+}
+#endif
+
+#ifndef __PYX_HAVE_RT_ImportType
+#define __PYX_HAVE_RT_ImportType
+static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class_name,
+    size_t size, int strict)
+{
+    PyObject *py_module = 0;
+    PyObject *result = 0;
+    PyObject *py_name = 0;
+    char warning[200];
+    Py_ssize_t basicsize;
+#ifdef Py_LIMITED_API
+    PyObject *py_basicsize;
+#endif
+    py_module = __Pyx_ImportModule(module_name);
+    if (!py_module)
+        goto bad;
+    py_name = __Pyx_PyIdentifier_FromString(class_name);
+    if (!py_name)
+        goto bad;
+    result = PyObject_GetAttr(py_module, py_name);
+    Py_DECREF(py_name);
+    py_name = 0;
+    Py_DECREF(py_module);
+    py_module = 0;
+    if (!result)
+        goto bad;
+    if (!PyType_Check(result)) {
+        PyErr_Format(PyExc_TypeError,
+            "%.200s.%.200s is not a type object",
+            module_name, class_name);
+        goto bad;
+    }
+#ifndef Py_LIMITED_API
+    basicsize = ((PyTypeObject *)result)->tp_basicsize;
+#else
+    py_basicsize = PyObject_GetAttrString(result, "__basicsize__");
+    if (!py_basicsize)
+        goto bad;
+    basicsize = PyLong_AsSsize_t(py_basicsize);
+    Py_DECREF(py_basicsize);
+    py_basicsize = 0;
+    if (basicsize == (Py_ssize_t)-1 && PyErr_Occurred())
+        goto bad;
+#endif
+    if (!strict && (size_t)basicsize > size) {
+        PyOS_snprintf(warning, sizeof(warning),
+            "%s.%s size changed, may indicate binary incompatibility",
+            module_name, class_name);
+        if (PyErr_WarnEx(NULL, warning, 0) < 0) goto bad;
+    }
+    else if ((size_t)basicsize != size) {
+        PyErr_Format(PyExc_ValueError,
+            "%.200s.%.200s has the wrong size, try recompiling",
+            module_name, class_name);
+        goto bad;
+    }
+    return (PyTypeObject *)result;
+bad:
+    Py_XDECREF(py_module);
+    Py_XDECREF(result);
+    return NULL;
+}
+#endif
+
+static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) {
+    while (t->p) {
+        #if PY_MAJOR_VERSION < 3
+        if (t->is_unicode) {
+            *t->p = PyUnicode_DecodeUTF8(t->s, t->n - 1, NULL);
+        } else if (t->intern) {
+            *t->p = PyString_InternFromString(t->s);
+        } else {
+            *t->p = PyString_FromStringAndSize(t->s, t->n - 1);
+        }
+        #else
+        if (t->is_unicode | t->is_str) {
+            if (t->intern) {
+                *t->p = PyUnicode_InternFromString(t->s);
+            } else if (t->encoding) {
+                *t->p = PyUnicode_Decode(t->s, t->n - 1, t->encoding, NULL);
+            } else {
+                *t->p = PyUnicode_FromStringAndSize(t->s, t->n - 1);
+            }
+        } else {
+            *t->p = PyBytes_FromStringAndSize(t->s, t->n - 1);
+        }
+        #endif
+        if (!*t->p)
+            return -1;
+        ++t;
+    }
+    return 0;
+}
+
+static CYTHON_INLINE PyObject* __Pyx_PyUnicode_FromString(const char* c_str) {
+    return __Pyx_PyUnicode_FromStringAndSize(c_str, (Py_ssize_t)strlen(c_str));
+}
+static CYTHON_INLINE char* __Pyx_PyObject_AsString(PyObject* o) {
+    Py_ssize_t ignore;
+    return __Pyx_PyObject_AsStringAndSize(o, &ignore);
+}
+static CYTHON_INLINE char* __Pyx_PyObject_AsStringAndSize(PyObject* o, Py_ssize_t *length) {
+#if CYTHON_COMPILING_IN_CPYTHON && (__PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT)
+    if (
+#if PY_MAJOR_VERSION < 3 && __PYX_DEFAULT_STRING_ENCODING_IS_ASCII
+            __Pyx_sys_getdefaultencoding_not_ascii &&
+#endif
+            PyUnicode_Check(o)) {
+#if PY_VERSION_HEX < 0x03030000
+        char* defenc_c;
+        PyObject* defenc = _PyUnicode_AsDefaultEncodedString(o, NULL);
+        if (!defenc) return NULL;
+        defenc_c = PyBytes_AS_STRING(defenc);
+#if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII
+        {
+            char* end = defenc_c + PyBytes_GET_SIZE(defenc);
+            char* c;
+            for (c = defenc_c; c < end; c++) {
+                if ((unsigned char) (*c) >= 128) {
+                    PyUnicode_AsASCIIString(o);
+                    return NULL;
+                }
+            }
+        }
+#endif
+        *length = PyBytes_GET_SIZE(defenc);
+        return defenc_c;
+#else
+        if (__Pyx_PyUnicode_READY(o) == -1) return NULL;
+#if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII
+        if (PyUnicode_IS_ASCII(o)) {
+            *length = PyUnicode_GET_LENGTH(o);
+            return PyUnicode_AsUTF8(o);
+        } else {
+            PyUnicode_AsASCIIString(o);
+            return NULL;
+        }
+#else
+        return PyUnicode_AsUTF8AndSize(o, length);
+#endif
+#endif
+    } else
+#endif
+#if (!CYTHON_COMPILING_IN_PYPY) || (defined(PyByteArray_AS_STRING) && defined(PyByteArray_GET_SIZE))
+    if (PyByteArray_Check(o)) {
+        *length = PyByteArray_GET_SIZE(o);
+        return PyByteArray_AS_STRING(o);
+    } else
+#endif
+    {
+        char* result;
+        int r = PyBytes_AsStringAndSize(o, &result, length);
+        if (unlikely(r < 0)) {
+            return NULL;
+        } else {
+            return result;
+        }
+    }
+}
+static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject* x) {
+   int is_true = x == Py_True;
+   if (is_true | (x == Py_False) | (x == Py_None)) return is_true;
+   else return PyObject_IsTrue(x);
+}
+static CYTHON_INLINE PyObject* __Pyx_PyNumber_Int(PyObject* x) {
+  PyNumberMethods *m;
+  const char *name = NULL;
+  PyObject *res = NULL;
+#if PY_MAJOR_VERSION < 3
+  if (PyInt_Check(x) || PyLong_Check(x))
+#else
+  if (PyLong_Check(x))
+#endif
+    return __Pyx_NewRef(x);
+  m = Py_TYPE(x)->tp_as_number;
+#if PY_MAJOR_VERSION < 3
+  if (m && m->nb_int) {
+    name = "int";
+    res = PyNumber_Int(x);
+  }
+  else if (m && m->nb_long) {
+    name = "long";
+    res = PyNumber_Long(x);
+  }
+#else
+  if (m && m->nb_int) {
+    name = "int";
+    res = PyNumber_Long(x);
+  }
+#endif
+  if (res) {
+#if PY_MAJOR_VERSION < 3
+    if (!PyInt_Check(res) && !PyLong_Check(res)) {
+#else
+    if (!PyLong_Check(res)) {
+#endif
+      PyErr_Format(PyExc_TypeError,
+                   "__%.4s__ returned non-%.4s (type %.200s)",
+                   name, name, Py_TYPE(res)->tp_name);
+      Py_DECREF(res);
+      return NULL;
+    }
+  }
+  else if (!PyErr_Occurred()) {
+    PyErr_SetString(PyExc_TypeError,
+                    "an integer is required");
+  }
+  return res;
+}
+static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject* b) {
+  Py_ssize_t ival;
+  PyObject *x;
+#if PY_MAJOR_VERSION < 3
+  if (likely(PyInt_CheckExact(b))) {
+    if (sizeof(Py_ssize_t) >= sizeof(long))
+        return PyInt_AS_LONG(b);
+    else
+        return PyInt_AsSsize_t(x);
+  }
+#endif
+  if (likely(PyLong_CheckExact(b))) {
+    #if CYTHON_USE_PYLONG_INTERNALS
+    const digit* digits = ((PyLongObject*)b)->ob_digit;
+    const Py_ssize_t size = Py_SIZE(b);
+    if (likely(__Pyx_sst_abs(size) <= 1)) {
+        ival = likely(size) ? digits[0] : 0;
+        if (size == -1) ival = -ival;
+        return ival;
+    } else {
+      switch (size) {
+         case 2:
+           if (8 * sizeof(Py_ssize_t) > 2 * PyLong_SHIFT) {
+             return (Py_ssize_t) (((((size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0]));
+           }
+           break;
+         case -2:
+           if (8 * sizeof(Py_ssize_t) > 2 * PyLong_SHIFT) {
+             return -(Py_ssize_t) (((((size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0]));
+           }
+           break;
+         case 3:
+           if (8 * sizeof(Py_ssize_t) > 3 * PyLong_SHIFT) {
+             return (Py_ssize_t) (((((((size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0]));
+           }
+           break;
+         case -3:
+           if (8 * sizeof(Py_ssize_t) > 3 * PyLong_SHIFT) {
+             return -(Py_ssize_t) (((((((size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0]));
+           }
+           break;
+         case 4:
+           if (8 * sizeof(Py_ssize_t) > 4 * PyLong_SHIFT) {
+             return (Py_ssize_t) (((((((((size_t)digits[3]) << PyLong_SHIFT) | (size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0]));
+           }
+           break;
+         case -4:
+           if (8 * sizeof(Py_ssize_t) > 4 * PyLong_SHIFT) {
+             return -(Py_ssize_t) (((((((((size_t)digits[3]) << PyLong_SHIFT) | (size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0]));
+           }
+           break;
+      }
+    }
+    #endif
+    return PyLong_AsSsize_t(b);
+  }
+  x = PyNumber_Index(b);
+  if (!x) return -1;
+  ival = PyInt_AsSsize_t(x);
+  Py_DECREF(x);
+  return ival;
+}
+static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t ival) {
+    return PyInt_FromSize_t(ival);
+}
+
+
+#endif /* Py_PYTHON_H */
diff --git a/ot/lp/emd.pyx b/ot/lp/emd.pyx
new file mode 100644
index 0000000..753b195
--- /dev/null
+++ b/ot/lp/emd.pyx
@@ -0,0 +1,71 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Sep 11 08:42:08 2014
+
+@author: rflamary
+"""
+import numpy as np
+cimport numpy as np
+
+cimport cython
+
+
+
+cdef extern from "EMD.h":
+    void EMD_wrap(int n1,int n2, double *X, double *Y,double *D, double *G, double *cost)
+
+
+
+@cython.boundscheck(False)
+@cython.wraparound(False)
+def emd( np.ndarray[double, ndim=1, mode="c"] a,np.ndarray[double, ndim=1, mode="c"]  b,np.ndarray[double, ndim=2, mode="c"]  M):
+    """
+        Solves the Earth Movers distance problem and returns the optimal transport matrix
+        
+        gamm=emd(a,b,M)
+    
+    .. math::
+        \gamma = arg\min_\gamma <\gamma,M>_F 
+        
+        s.t. \gamma 1 = a
+        
+             \gamma^T 1= b 
+             
+             \gamma\geq 0
+    where :
+    
+    - M is the metric cost matrix
+    - a and b are the sample weights
+             
+    Parameters
+    ----------
+    a : (ns,) ndarray
+        samples in the source domain (uniform waigth if empty)
+    b : (nt,) ndarray
+        samples in the target domain (uniform waigth if empty)
+    M : (ns,nt) ndarray
+        loss matrix        
+  
+    
+    Returns
+    -------
+    gamma: (ns x nt) ndarray
+        Optimal transportation matrix for the given parameters
+ 
+    """
+    cdef int n1= M.shape[0]
+    cdef int n2= M.shape[1]
+
+    cdef float cost=0
+    cdef np.ndarray[double, ndim=2, mode="c"] G=np.zeros([n1, n2])
+    
+    if not len(a):
+        a=np.ones((n1,))/n1
+
+    if not len(b):
+        b=np.ones((n2,))/n2
+
+    # calling the function
+    EMD_wrap(n1,n2,<double*> a.data,<double*> b.data,<double*> M.data,<double*> G.data,<double*> &cost)
+
+    return G
diff --git a/ot/lp/full_bipartitegraph.h b/ot/lp/full_bipartitegraph.h
new file mode 100644
index 0000000..87a1bec
--- /dev/null
+++ b/ot/lp/full_bipartitegraph.h
@@ -0,0 +1,215 @@
+/* -*- mode: C++; indent-tabs-mode: nil; -*-
+ *
+ * This file has been adapted by Nicolas Bonneel (2013), 
+ * from full_graph.h from LEMON, a generic C++ optimization library,
+ * to implement a lightweight fully connected bipartite graph. A previous
+ * version of this file is used as part of the Displacement Interpolation 
+ * project, 
+ * Web: http://www.cs.ubc.ca/labs/imager/tr/2011/DisplacementInterpolation/
+ * 
+ *
+ **** Original file Copyright Notice :
+ * Copyright (C) 2003-2010
+ * Egervary Jeno Kombinatorikus Optimalizalasi Kutatocsoport
+ * (Egervary Research Group on Combinatorial Optimization, EGRES).
+ *
+ * Permission to use, modify and distribute this software is granted
+ * provided that this copyright notice appears in all copies. For
+ * precise terms see the accompanying LICENSE file.
+ *
+ * This software is provided "AS IS" with no warranty of any kind,
+ * express or implied, and with no claim as to its suitability for any
+ * purpose.
+ *
+ */
+
+#ifndef LEMON_FULL_BIPARTITE_GRAPH_H
+#define LEMON_FULL_BIPARTITE_GRAPH_H
+
+#include "core.h"
+
+///\ingroup graphs
+///\file
+///\brief FullBipartiteDigraph and FullBipartiteGraph classes.
+
+
+namespace lemon {
+
+
+  class FullBipartiteDigraphBase {
+  public:
+
+    typedef FullBipartiteDigraphBase Digraph;
+
+    //class Node;
+	typedef int Node;
+    //class Arc;
+	typedef long long Arc;
+
+  protected:
+
+    int _node_num;
+    long long _arc_num;
+	
+    FullBipartiteDigraphBase() {}
+
+    void construct(int n1, int n2) { _node_num = n1+n2; _arc_num = n1 * n2; _n1=n1; _n2=n2;}
+
+  public:
+
+	int _n1, _n2;
+
+
+    Node operator()(int ix) const { return Node(ix); }
+    static int index(const Node& node) { return node; }
+
+    Arc arc(const Node& s, const Node& t) const {
+		if (s<_n1 && t>=_n1)
+			return Arc(s * _n2 + (t-_n1) );
+		else
+			return Arc(-1);
+    }
+
+    int nodeNum() const { return _node_num; }
+    long long arcNum() const { return _arc_num; }
+
+    int maxNodeId() const { return _node_num - 1; }
+    long long maxArcId() const { return _arc_num - 1; }
+
+    Node source(Arc arc) const { return arc / _n2; }
+    Node target(Arc arc) const { return (arc % _n2) + _n1; }
+
+    static int id(Node node) { return node; }
+    static long long id(Arc arc) { return arc; }
+
+    static Node nodeFromId(int id) { return Node(id);}
+    static Arc arcFromId(int id) { return Arc(id);}
+
+
+    Arc findArc(Node s, Node t, Arc prev = -1) const {
+      return prev == -1 ? arc(s, t) : -1;
+    }
+
+    void first(Node& node) const {
+      node = _node_num - 1;
+    }
+
+    static void next(Node& node) {
+      --node;
+    }
+
+    void first(Arc& arc) const {
+      arc = _arc_num - 1;
+    }
+
+    static void next(Arc& arc) {
+      --arc;
+    }
+
+    void firstOut(Arc& arc, const Node& node) const {
+		if (node>=_n1)
+			arc = -1;
+		else
+			arc = (node + 1) * _n2 - 1;
+    }
+
+    void nextOut(Arc& arc) const {
+      if (arc % _n2 == 0) arc = 0;
+      --arc;
+    }
+
+    void firstIn(Arc& arc, const Node& node) const {
+		if (node<_n1)
+			arc = -1;
+		else
+			arc = _arc_num + node - _node_num;
+    }
+
+    void nextIn(Arc& arc) const {
+      arc -= _n2;
+      if (arc < 0) arc = -1;
+    }
+
+  };
+
+  /// \ingroup graphs
+  ///
+  /// \brief A directed full graph class.
+  ///
+  /// FullBipartiteDigraph is a simple and fast implmenetation of directed full
+  /// (complete) graphs. It contains an arc from each node to each node
+  /// (including a loop for each node), therefore the number of arcs
+  /// is the square of the number of nodes.
+  /// This class is completely static and it needs constant memory space.
+  /// Thus you can neither add nor delete nodes or arcs, however
+  /// the structure can be resized using resize().
+  ///
+  /// This type fully conforms to the \ref concepts::Digraph "Digraph concept".
+  /// Most of its member functions and nested classes are documented
+  /// only in the concept class.
+  ///
+  /// This class provides constant time counting for nodes and arcs.
+  ///
+  /// \note FullBipartiteDigraph and FullBipartiteGraph classes are very similar,
+  /// but there are two differences. While this class conforms only
+  /// to the \ref concepts::Digraph "Digraph" concept, FullBipartiteGraph
+  /// conforms to the \ref concepts::Graph "Graph" concept,
+  /// moreover FullBipartiteGraph does not contain a loop for each
+  /// node as this class does.
+  ///
+  /// \sa FullBipartiteGraph
+  class FullBipartiteDigraph : public FullBipartiteDigraphBase {
+    typedef FullBipartiteDigraphBase Parent;
+
+  public:
+
+    /// \brief Default constructor.
+    ///
+    /// Default constructor. The number of nodes and arcs will be zero.
+    FullBipartiteDigraph() { construct(0,0); }
+
+    /// \brief Constructor
+    ///
+    /// Constructor.
+    /// \param n The number of the nodes.
+    FullBipartiteDigraph(int n1, int n2) { construct(n1, n2); }
+
+
+    /// \brief Returns the node with the given index.
+    ///
+    /// Returns the node with the given index. Since this structure is
+    /// completely static, the nodes can be indexed with integers from
+    /// the range <tt>[0..nodeNum()-1]</tt>.
+    /// The index of a node is the same as its ID.
+    /// \sa index()
+    Node operator()(int ix) const { return Parent::operator()(ix); }
+
+    /// \brief Returns the index of the given node.
+    ///
+    /// Returns the index of the given node. Since this structure is
+    /// completely static, the nodes can be indexed with integers from
+    /// the range <tt>[0..nodeNum()-1]</tt>.
+    /// The index of a node is the same as its ID.
+    /// \sa operator()()
+    static int index(const Node& node) { return Parent::index(node); }
+
+    /// \brief Returns the arc connecting the given nodes.
+    ///
+    /// Returns the arc connecting the given nodes.
+    /*Arc arc(Node u, Node v) const {
+      return Parent::arc(u, v);
+    }*/
+
+    /// \brief Number of nodes.
+    int nodeNum() const { return Parent::nodeNum(); }
+    /// \brief Number of arcs.
+    long long arcNum() const { return Parent::arcNum(); }
+  };
+
+
+
+
+} //namespace lemon
+
+
+#endif //LEMON_FULL_GRAPH_H
diff --git a/ot/lp/network_simplex_simple.h b/ot/lp/network_simplex_simple.h
new file mode 100644
index 0000000..64856a0
--- /dev/null
+++ b/ot/lp/network_simplex_simple.h
@@ -0,0 +1,1543 @@
+/* -*- mode: C++; indent-tabs-mode: nil; -*-
+ *
+ *
+ * This file has been adapted by Nicolas Bonneel (2013),
+ * from network_simplex.h from LEMON, a generic C++ optimization library,
+ * to implement a lightweight network simplex for mass transport, more
+ * memory efficient that the original file. A previous version of this file
+ * is used as part of the Displacement Interpolation project,
+ * Web: http://www.cs.ubc.ca/labs/imager/tr/2011/DisplacementInterpolation/
+ *
+ *
+ **** Original file Copyright Notice :
+ *
+ * Copyright (C) 2003-2010
+ * Egervary Jeno Kombinatorikus Optimalizalasi Kutatocsoport
+ * (Egervary Research Group on Combinatorial Optimization, EGRES).
+ *
+ * Permission to use, modify and distribute this software is granted
+ * provided that this copyright notice appears in all copies. For
+ * precise terms see the accompanying LICENSE file.
+ *
+ * This software is provided "AS IS" with no warranty of any kind,
+ * express or implied, and with no claim as to its suitability for any
+ * purpose.
+ *
+ */
+
+#ifndef LEMON_NETWORK_SIMPLEX_SIMPLE_H
+#define LEMON_NETWORK_SIMPLEX_SIMPLE_H
+#define DEBUG_LVL 0
+#define EPSILON 10*2.2204460492503131e-016
+#define MAX_DEBUG_ITER 100000
+
+
+/// \ingroup min_cost_flow_algs
+///
+/// \file
+/// \brief Network Simplex algorithm for finding a minimum cost flow.
+
+// if your compiler has troubles with stdext or hashmaps, just comment the following line to use a slower std::map instead
+//#define HASHMAP
+
+#include <vector>
+#include <limits>
+#include <algorithm>
+#ifdef HASHMAP
+#include <hash_map>
+#else
+#include <map>
+#endif
+#include <cmath>
+//#include "core.h"
+//#include "lmath.h"
+
+//#include "sparse_array_n.h"
+#include "full_bipartitegraph.h"
+
+#define INVALIDNODE -1
+#define INVALID (-1)
+
+namespace lemon {
+
+
+    template <typename T>
+	class ProxyObject;
+
+	template<typename T>
+	class SparseValueVector
+	{
+	public:
+		SparseValueVector(int n=0)
+		{
+		}
+		void resize(int n=0){};
+		T operator[](const int id) const
+		{
+#ifdef HASHMAP
+			typename stdext::hash_map<int,T>::const_iterator it = data.find(id);
+#else
+			typename std::map<int,T>::const_iterator it = data.find(id);
+#endif
+			if (it==data.end())
+				return 0;
+			else
+				return it->second;
+		}
+
+		ProxyObject<T> operator[](const int id)
+		{
+			return ProxyObject<T>( this, id );
+		}
+
+        //private:
+#ifdef HASHMAP
+		stdext::hash_map<int,T> data;
+#else
+		std::map<int,T> data;
+#endif
+
+	};
+
+	template <typename T>
+	class ProxyObject {
+	public:
+		ProxyObject( SparseValueVector<T> *v, int idx ){_v=v; _idx=idx;};
+		ProxyObject<T> & operator=( const T &v ) {
+			// If we get here, we know that operator[] was called to perform a write access,
+			// so we can insert an item in the vector if needed
+			if (v!=0)
+				_v->data[_idx]=v;
+			return *this;
+		}
+
+		operator T() {
+			// If we get here, we know that operator[] was called to perform a read access,
+			// so we can simply return the existing object
+#ifdef HASHMAP
+			typename stdext::hash_map<int,T>::iterator it = _v->data.find(_idx);
+#else
+			typename std::map<int,T>::iterator it = _v->data.find(_idx);
+#endif
+			if (it==_v->data.end())
+				return 0;
+			else
+				return it->second;
+		}
+
+		void operator+=(T val)
+		{
+			if (val==0) return;
+#ifdef HASHMAP
+			typename stdext::hash_map<int,T>::iterator it = _v->data.find(_idx);
+#else
+			typename std::map<int,T>::iterator it = _v->data.find(_idx);
+#endif
+			if (it==_v->data.end())
+				_v->data[_idx] = val;
+			else
+			{
+				T sum = it->second + val;
+				if (sum==0)
+					_v->data.erase(it);
+				else
+					it->second = sum;
+			}
+		}
+		void operator-=(T val)
+		{
+			if (val==0) return;
+#ifdef HASHMAP
+			typename stdext::hash_map<int,T>::iterator it = _v->data.find(_idx);
+#else
+			typename std::map<int,T>::iterator it = _v->data.find(_idx);
+#endif
+			if (it==_v->data.end())
+				_v->data[_idx] = -val;
+			else
+			{
+				T sum = it->second - val;
+				if (sum==0)
+					_v->data.erase(it);
+				else
+					it->second = sum;
+			}
+		}
+
+		SparseValueVector<T> *_v;
+		int _idx;
+	};
+
+
+
+    /// \addtogroup min_cost_flow_algs
+    /// @{
+
+    /// \brief Implementation of the primal Network Simplex algorithm
+    /// for finding a \ref min_cost_flow "minimum cost flow".
+    ///
+    /// \ref NetworkSimplexSimple implements the primal Network Simplex algorithm
+    /// for finding a \ref min_cost_flow "minimum cost flow"
+    /// \ref amo93networkflows, \ref dantzig63linearprog,
+    /// \ref kellyoneill91netsimplex.
+    /// This algorithm is a highly efficient specialized version of the
+    /// linear programming simplex method directly for the minimum cost
+    /// flow problem.
+    ///
+    /// In general, %NetworkSimplexSimple is the fastest implementation available
+    /// in LEMON for this problem.
+    /// Moreover, it supports both directions of the supply/demand inequality
+    /// constraints. For more information, see \ref SupplyType.
+    ///
+    /// Most of the parameters of the problem (except for the digraph)
+    /// can be given using separate functions, and the algorithm can be
+    /// executed using the \ref run() function. If some parameters are not
+    /// specified, then default values will be used.
+    ///
+    /// \tparam GR The digraph type the algorithm runs on.
+    /// \tparam V The number type used for flow amounts, capacity bounds
+    /// and supply values in the algorithm. By default, it is \c int.
+    /// \tparam C The number type used for costs and potentials in the
+    /// algorithm. By default, it is the same as \c V.
+    ///
+    /// \warning Both number types must be signed and all input data must
+    /// be integer.
+    ///
+    /// \note %NetworkSimplexSimple provides five different pivot rule
+    /// implementations, from which the most efficient one is used
+    /// by default. For more information, see \ref PivotRule.
+    template <typename GR, typename V = int, typename C = V, typename NodesType = unsigned short int>
+    class NetworkSimplexSimple
+    {
+    public:
+
+        /// \brief Constructor.
+        ///
+        /// The constructor of the class.
+        ///
+        /// \param graph The digraph the algorithm runs on.
+        /// \param arc_mixing Indicate if the arcs have to be stored in a
+        /// mixed order in the internal data structure.
+        /// In special cases, it could lead to better overall performance,
+        /// but it is usually slower. Therefore it is disabled by default.
+        NetworkSimplexSimple(const GR& graph, bool arc_mixing, int nbnodes, long long nb_arcs,double maxiters) :
+        _graph(graph),  //_arc_id(graph),
+        _arc_mixing(arc_mixing), _init_nb_nodes(nbnodes), _init_nb_arcs(nb_arcs),
+        MAX(std::numeric_limits<Value>::max()),
+        INF(std::numeric_limits<Value>::has_infinity ?
+            std::numeric_limits<Value>::infinity() : MAX)
+        {
+            // Reset data structures
+            reset();
+            max_iter=maxiters;
+        }
+
+        /// The type of the flow amounts, capacity bounds and supply values
+        typedef V Value;
+        /// The type of the arc costs
+        typedef C Cost;
+
+    public:
+
+        /// \brief Problem type constants for the \c run() function.
+        ///
+        /// Enum type containing the problem type constants that can be
+        /// returned by the \ref run() function of the algorithm.
+        enum ProblemType {
+            /// The problem has no feasible solution (flow).
+            INFEASIBLE,
+            /// The problem has optimal solution (i.e. it is feasible and
+            /// bounded), and the algorithm has found optimal flow and node
+            /// potentials (primal and dual solutions).
+            OPTIMAL,
+            /// The objective function of the problem is unbounded, i.e.
+            /// there is a directed cycle having negative total cost and
+            /// infinite upper bound.
+            UNBOUNDED
+        };
+
+        /// \brief Constants for selecting the type of the supply constraints.
+        ///
+        /// Enum type containing constants for selecting the supply type,
+        /// i.e. the direction of the inequalities in the supply/demand
+        /// constraints of the \ref min_cost_flow "minimum cost flow problem".
+        ///
+        /// The default supply type is \c GEQ, the \c LEQ type can be
+        /// selected using \ref supplyType().
+        /// The equality form is a special case of both supply types.
+        enum SupplyType {
+            /// This option means that there are <em>"greater or equal"</em>
+            /// supply/demand constraints in the definition of the problem.
+            GEQ,
+            /// This option means that there are <em>"less or equal"</em>
+            /// supply/demand constraints in the definition of the problem.
+            LEQ
+        };
+
+
+
+    private:
+
+        double max_iter;
+        TEMPLATE_DIGRAPH_TYPEDEFS(GR);
+
+        typedef std::vector<int> IntVector;
+        typedef std::vector<NodesType> UHalfIntVector;
+        typedef std::vector<Value> ValueVector;
+        typedef std::vector<Cost> CostVector;
+        //	typedef SparseValueVector<Cost> CostVector;
+        typedef std::vector<char> BoolVector;
+        // Note: vector<char> is used instead of vector<bool> for efficiency reasons
+
+        // State constants for arcs
+        enum ArcState {
+            STATE_UPPER = -1,
+            STATE_TREE  =  0,
+            STATE_LOWER =  1
+        };
+
+        typedef std::vector<signed char> StateVector;
+        // Note: vector<signed char> is used instead of vector<ArcState> for
+        // efficiency reasons
+
+    private:
+
+        // Data related to the underlying digraph
+        const GR &_graph;
+        int _node_num;
+        int _arc_num;
+        int _all_arc_num;
+        int _search_arc_num;
+
+        // Parameters of the problem
+        SupplyType _stype;
+        Value _sum_supply;
+
+        inline int _node_id(int n) const {return _node_num-n-1;} ;
+
+	    //IntArcMap _arc_id;
+        UHalfIntVector _source;
+        UHalfIntVector _target;
+        bool _arc_mixing;
+    public:
+        // Node and arc data
+        CostVector _cost;
+        ValueVector _supply;
+        ValueVector _flow;
+        //SparseValueVector<Value> _flow;
+        CostVector _pi;
+
+
+    private:
+        // Data for storing the spanning tree structure
+        IntVector _parent;
+        IntVector _pred;
+        IntVector _thread;
+        IntVector _rev_thread;
+        IntVector _succ_num;
+        IntVector _last_succ;
+        IntVector _dirty_revs;
+        BoolVector _forward;
+        StateVector _state;
+        int _root;
+
+        // Temporary data used in the current pivot iteration
+        int in_arc, join, u_in, v_in, u_out, v_out;
+        int first, second, right, last;
+        int stem, par_stem, new_stem;
+        Value delta;
+
+        const Value MAX;
+
+        int mixingCoeff;
+
+    public:
+
+        /// \brief Constant for infinite upper bounds (capacities).
+        ///
+        /// Constant for infinite upper bounds (capacities).
+        /// It is \c std::numeric_limits<Value>::infinity() if available,
+        /// \c std::numeric_limits<Value>::max() otherwise.
+        const Value INF;
+
+    private:
+
+        // thank you to DVK and MizardX from StackOverflow for this function!
+        inline int sequence(int k) const {
+            int smallv = (k > num_total_big_subsequence_numbers) & 1;
+
+            k -= num_total_big_subsequence_numbers * smallv;
+            int subsequence_length2 = subsequence_length- smallv;
+            int subsequence_num = (k / subsequence_length2) + num_big_subseqiences * smallv;
+            int subsequence_offset = (k % subsequence_length2) * mixingCoeff;
+
+            return subsequence_offset + subsequence_num;
+        }
+        int subsequence_length;
+        int num_big_subseqiences;
+        int num_total_big_subsequence_numbers;
+
+        inline int getArcID(const Arc &arc) const
+        {
+            //int n = _arc_num-arc._id-1;
+            int n = _arc_num-GR::id(arc)-1;
+
+            //int a = mixingCoeff*(n%mixingCoeff) + n/mixingCoeff;
+            //int b = _arc_id[arc];
+            if (_arc_mixing)
+                return sequence(n);
+            else
+                return n;
+        }
+
+        // finally unused because too slow
+        inline int getSource(const int arc) const
+        {
+            //int a = _source[arc];
+            //return a;
+
+            int n = _arc_num-arc-1;
+            if (_arc_mixing)
+                n = mixingCoeff*(n%mixingCoeff) + n/mixingCoeff;
+
+            int b;
+            if (n>=0)
+                b = _node_id(_graph.source(GR::arcFromId( n ) ));
+            else
+            {
+                n = arc+1-_arc_num;
+                if ( n<=_node_num)
+                    b = _node_num;
+                else
+                    if ( n>=_graph._n1)
+                        b = _graph._n1;
+                    else
+                        b = _graph._n1-n;
+            }
+
+            return b;
+        }
+
+
+
+        // Implementation of the Block Search pivot rule
+        class BlockSearchPivotRule
+        {
+        private:
+
+            // References to the NetworkSimplexSimple class
+            const UHalfIntVector  &_source;
+            const UHalfIntVector  &_target;
+            const CostVector &_cost;
+            const StateVector &_state;
+            const CostVector &_pi;
+            int &_in_arc;
+            int _search_arc_num;
+
+            // Pivot rule data
+            int _block_size;
+            int _next_arc;
+            NetworkSimplexSimple &_ns;
+
+        public:
+
+            // Constructor
+            BlockSearchPivotRule(NetworkSimplexSimple &ns) :
+            _source(ns._source), _target(ns._target),
+            _cost(ns._cost), _state(ns._state), _pi(ns._pi),
+            _in_arc(ns.in_arc), _search_arc_num(ns._search_arc_num),
+            _next_arc(0),_ns(ns)
+            {
+                // The main parameters of the pivot rule
+                const double BLOCK_SIZE_FACTOR = 1.0;
+                const int MIN_BLOCK_SIZE = 10;
+
+                _block_size = std::max( int(BLOCK_SIZE_FACTOR *
+                                            std::sqrt(double(_search_arc_num))),
+                                       MIN_BLOCK_SIZE );
+            }
+            // Find next entering arc
+            bool findEnteringArc() {
+                Cost c, min = 0;
+                int e;
+                int cnt = _block_size;
+                double a;
+                    for (e = _next_arc; e != _search_arc_num; ++e) {
+                        c = _state[e] * (_cost[e] + _pi[_source[e]] - _pi[_target[e]]);
+                        if (c < min) {
+                            min = c;
+                            _in_arc = e;
+                        }
+                        if (--cnt == 0) {
+                            a=fabs(_pi[_source[_in_arc]])>fabs(_pi[_target[_in_arc]]) ? fabs(_pi[_source[_in_arc]]):fabs(_pi[_target[_in_arc]]);
+                            a=a>fabs(_cost[_in_arc])?a:fabs(_cost[_in_arc]);
+                            if (min <  -EPSILON*a) goto search_end;
+                            cnt = _block_size;
+                        }
+                    }
+                    for (e = 0; e != _next_arc; ++e) {
+                        c = _state[e] * (_cost[e] + _pi[_source[e]] - _pi[_target[e]]);
+                        if (c < min) {
+                            min = c;
+                            _in_arc = e;
+                        }
+                        if (--cnt == 0) {
+                            a=fabs(_pi[_source[_in_arc]])>fabs(_pi[_target[_in_arc]]) ? fabs(_pi[_source[_in_arc]]):fabs(_pi[_target[_in_arc]]);
+                            a=a>fabs(_cost[_in_arc])?a:fabs(_cost[_in_arc]);
+                            if (min <  -EPSILON*a) goto search_end;
+                            cnt = _block_size;
+                        }
+                    }
+                    a=fabs(_pi[_source[_in_arc]])>fabs(_pi[_target[_in_arc]]) ? fabs(_pi[_source[_in_arc]]):fabs(_pi[_target[_in_arc]]);
+                    a=a>fabs(_cost[_in_arc])?a:fabs(_cost[_in_arc]);
+                    if (min >=  -EPSILON*a) return false;
+
+            search_end:
+                _next_arc = e;
+                return true;
+            }
+
+        }; //class BlockSearchPivotRule
+
+
+
+    public:
+
+
+
+        int _init_nb_nodes;
+        long long _init_nb_arcs;
+
+        /// \name Parameters
+        /// The parameters of the algorithm can be specified using these
+        /// functions.
+
+        /// @{
+
+
+        /// \brief Set the costs of the arcs.
+        ///
+        /// This function sets the costs of the arcs.
+        /// If it is not used before calling \ref run(), the costs
+        /// will be set to \c 1 on all arcs.
+        ///
+        /// \param map An arc map storing the costs.
+        /// Its \c Value type must be convertible to the \c Cost type
+        /// of the algorithm.
+        ///
+        /// \return <tt>(*this)</tt>
+        template<typename CostMap>
+        NetworkSimplexSimple& costMap(const CostMap& map) {
+            Arc a; _graph.first(a);
+            for (; a != INVALID; _graph.next(a)) {
+                _cost[getArcID(a)] = map[a];
+            }
+            return *this;
+        }
+
+
+        /// \brief Set the costs of one arc.
+        ///
+        /// This function sets the costs of one arcs.
+        /// Done for memory reasons
+        ///
+        /// \param arc An arc.
+        /// \param arc A cost
+        ///
+        /// \return <tt>(*this)</tt>
+        template<typename Value>
+        NetworkSimplexSimple& setCost(const Arc& arc, const Value cost) {
+            _cost[getArcID(arc)] = cost;
+            return *this;
+        }
+
+
+        /// \brief Set the supply values of the nodes.
+        ///
+        /// This function sets the supply values of the nodes.
+        /// If neither this function nor \ref stSupply() is used before
+        /// calling \ref run(), the supply of each node will be set to zero.
+        ///
+        /// \param map A node map storing the supply values.
+        /// Its \c Value type must be convertible to the \c Value type
+        /// of the algorithm.
+        ///
+        /// \return <tt>(*this)</tt>
+        template<typename SupplyMap>
+        NetworkSimplexSimple& supplyMap(const SupplyMap& map) {
+            Node n; _graph.first(n);
+            for (; n != INVALIDNODE; _graph.next(n)) {
+                _supply[_node_id(n)] = map[n];
+            }
+            return *this;
+        }
+        template<typename SupplyMap>
+        NetworkSimplexSimple& supplyMap(const SupplyMap* map1, int n1, const SupplyMap* map2, int n2) {
+            Node n; _graph.first(n);
+            for (; n != INVALIDNODE; _graph.next(n)) {
+                if (n<n1)
+                    _supply[_node_id(n)] = map1[n];
+                else
+                    _supply[_node_id(n)] = map2[n-n1];
+            }
+            return *this;
+        }
+        template<typename SupplyMap>
+        NetworkSimplexSimple& supplyMapAll(SupplyMap val1, int n1, SupplyMap val2, int n2) {
+            Node n; _graph.first(n);
+            for (; n != INVALIDNODE; _graph.next(n)) {
+                if (n<n1)
+                    _supply[_node_id(n)] = val1;
+                else
+                    _supply[_node_id(n)] = val2;
+            }
+            return *this;
+        }
+
+        /// \brief Set single source and target nodes and a supply value.
+        ///
+        /// This function sets a single source node and a single target node
+        /// and the required flow value.
+        /// If neither this function nor \ref supplyMap() is used before
+        /// calling \ref run(), the supply of each node will be set to zero.
+        ///
+        /// Using this function has the same effect as using \ref supplyMap()
+        /// with such a map in which \c k is assigned to \c s, \c -k is
+        /// assigned to \c t and all other nodes have zero supply value.
+        ///
+        /// \param s The source node.
+        /// \param t The target node.
+        /// \param k The required amount of flow from node \c s to node \c t
+        /// (i.e. the supply of \c s and the demand of \c t).
+        ///
+        /// \return <tt>(*this)</tt>
+        NetworkSimplexSimple& stSupply(const Node& s, const Node& t, Value k) {
+            for (int i = 0; i != _node_num; ++i) {
+                _supply[i] = 0;
+            }
+            _supply[_node_id(s)] =  k;
+            _supply[_node_id(t)] = -k;
+            return *this;
+        }
+
+        /// \brief Set the type of the supply constraints.
+        ///
+        /// This function sets the type of the supply/demand constraints.
+        /// If it is not used before calling \ref run(), the \ref GEQ supply
+        /// type will be used.
+        ///
+        /// For more information, see \ref SupplyType.
+        ///
+        /// \return <tt>(*this)</tt>
+        NetworkSimplexSimple& supplyType(SupplyType supply_type) {
+            _stype = supply_type;
+            return *this;
+        }
+
+        /// @}
+
+        /// \name Execution Control
+        /// The algorithm can be executed using \ref run().
+
+        /// @{
+
+        /// \brief Run the algorithm.
+        ///
+        /// This function runs the algorithm.
+        /// The paramters can be specified using functions \ref lowerMap(),
+        /// \ref upperMap(), \ref costMap(), \ref supplyMap(), \ref stSupply(),
+        /// \ref supplyType().
+        /// For example,
+        /// \code
+        ///   NetworkSimplexSimple<ListDigraph> ns(graph);
+        ///   ns.lowerMap(lower).upperMap(upper).costMap(cost)
+        ///     .supplyMap(sup).run();
+        /// \endcode
+        ///
+        /// This function can be called more than once. All the given parameters
+        /// are kept for the next call, unless \ref resetParams() or \ref reset()
+        /// is used, thus only the modified parameters have to be set again.
+        /// If the underlying digraph was also modified after the construction
+        /// of the class (or the last \ref reset() call), then the \ref reset()
+        /// function must be called.
+        ///
+        /// \param pivot_rule The pivot rule that will be used during the
+        /// algorithm. For more information, see \ref PivotRule.
+        ///
+        /// \return \c INFEASIBLE if no feasible flow exists,
+        /// \n \c OPTIMAL if the problem has optimal solution
+        /// (i.e. it is feasible and bounded), and the algorithm has found
+        /// optimal flow and node potentials (primal and dual solutions),
+        /// \n \c UNBOUNDED if the objective function of the problem is
+        /// unbounded, i.e. there is a directed cycle having negative total
+        /// cost and infinite upper bound.
+        ///
+        /// \see ProblemType, PivotRule
+        /// \see resetParams(), reset()
+        ProblemType run() {
+#if DEBUG_LVL>0
+            mexPrintf("OPTIMAL = %d\nINFEASIBLE = %d\nUNBOUNDED = %d\n",OPTIMAL,INFEASIBLE,UNBOUNDED);
+            mexEvalString("drawnow;");
+#endif
+
+            if (!init()) return INFEASIBLE;
+#if DEBUG_LVL>0
+            mexPrintf("Init done, starting iterations\n");
+            mexEvalString("drawnow;");
+#endif
+            return start();
+        }
+
+        /// \brief Reset all the parameters that have been given before.
+        ///
+        /// This function resets all the paramaters that have been given
+        /// before using functions \ref lowerMap(), \ref upperMap(),
+        /// \ref costMap(), \ref supplyMap(), \ref stSupply(), \ref supplyType().
+        ///
+        /// It is useful for multiple \ref run() calls. Basically, all the given
+        /// parameters are kept for the next \ref run() call, unless
+        /// \ref resetParams() or \ref reset() is used.
+        /// If the underlying digraph was also modified after the construction
+        /// of the class or the last \ref reset() call, then the \ref reset()
+        /// function must be used, otherwise \ref resetParams() is sufficient.
+        ///
+        /// For example,
+        /// \code
+        ///   NetworkSimplexSimple<ListDigraph> ns(graph);
+        ///
+        ///   // First run
+        ///   ns.lowerMap(lower).upperMap(upper).costMap(cost)
+        ///     .supplyMap(sup).run();
+        ///
+        ///   // Run again with modified cost map (resetParams() is not called,
+        ///   // so only the cost map have to be set again)
+        ///   cost[e] += 100;
+        ///   ns.costMap(cost).run();
+        ///
+        ///   // Run again from scratch using resetParams()
+        ///   // (the lower bounds will be set to zero on all arcs)
+        ///   ns.resetParams();
+        ///   ns.upperMap(capacity).costMap(cost)
+        ///     .supplyMap(sup).run();
+        /// \endcode
+        ///
+        /// \return <tt>(*this)</tt>
+        ///
+        /// \see reset(), run()
+        NetworkSimplexSimple& resetParams() {
+            for (int i = 0; i != _node_num; ++i) {
+                _supply[i] = 0;
+            }
+            for (int i = 0; i != _arc_num; ++i) {
+                _cost[i] = 1;
+            }
+            _stype = GEQ;
+            return *this;
+        }
+
+
+
+        int divid (int x, int y)
+        {
+            return (x-x%y)/y;
+        }
+
+        /// \brief Reset the internal data structures and all the parameters
+        /// that have been given before.
+        ///
+        /// This function resets the internal data structures and all the
+        /// paramaters that have been given before using functions \ref lowerMap(),
+        /// \ref upperMap(), \ref costMap(), \ref supplyMap(), \ref stSupply(),
+        /// \ref supplyType().
+        ///
+        /// It is useful for multiple \ref run() calls. Basically, all the given
+        /// parameters are kept for the next \ref run() call, unless
+        /// \ref resetParams() or \ref reset() is used.
+        /// If the underlying digraph was also modified after the construction
+        /// of the class or the last \ref reset() call, then the \ref reset()
+        /// function must be used, otherwise \ref resetParams() is sufficient.
+        ///
+        /// See \ref resetParams() for examples.
+        ///
+        /// \return <tt>(*this)</tt>
+        ///
+        /// \see resetParams(), run()
+        NetworkSimplexSimple& reset() {
+            // Resize vectors
+            _node_num = _init_nb_nodes;
+            _arc_num = _init_nb_arcs;
+            int all_node_num = _node_num + 1;
+            int max_arc_num = _arc_num + 2 * _node_num;
+
+            _source.resize(max_arc_num);
+            _target.resize(max_arc_num);
+
+            _cost.resize(max_arc_num);
+            _supply.resize(all_node_num);
+            _flow.resize(max_arc_num);
+            _pi.resize(all_node_num);
+
+            _parent.resize(all_node_num);
+            _pred.resize(all_node_num);
+            _forward.resize(all_node_num);
+            _thread.resize(all_node_num);
+            _rev_thread.resize(all_node_num);
+            _succ_num.resize(all_node_num);
+            _last_succ.resize(all_node_num);
+            _state.resize(max_arc_num);
+
+
+            //_arc_mixing=false;
+            if (_arc_mixing) {
+                // Store the arcs in a mixed order
+                int k = std::max(int(std::sqrt(double(_arc_num))), 10);
+                mixingCoeff = k;
+                subsequence_length = _arc_num / mixingCoeff + 1;
+                num_big_subseqiences = _arc_num % mixingCoeff;
+                num_total_big_subsequence_numbers = subsequence_length * num_big_subseqiences;
+
+                int i = 0, j = 0;
+                Arc a; _graph.first(a);
+                for (; a != INVALID; _graph.next(a)) {
+                    _source[i] = _node_id(_graph.source(a));
+                    _target[i] = _node_id(_graph.target(a));
+                    //_arc_id[a] = i;
+                    if ((i += k) >= _arc_num) i = ++j;
+                }
+            } else {
+                // Store the arcs in the original order
+                int i = 0;
+                Arc a; _graph.first(a);
+                for (; a != INVALID; _graph.next(a), ++i) {
+                    _source[i] = _node_id(_graph.source(a));
+                    _target[i] = _node_id(_graph.target(a));
+                    //_arc_id[a] = i;
+                }
+            }
+
+            // Reset parameters
+            resetParams();
+            return *this;
+        }
+
+        /// @}
+
+        /// \name Query Functions
+        /// The results of the algorithm can be obtained using these
+        /// functions.\n
+        /// The \ref run() function must be called before using them.
+
+        /// @{
+
+        /// \brief Return the total cost of the found flow.
+        ///
+        /// This function returns the total cost of the found flow.
+        /// Its complexity is O(e).
+        ///
+        /// \note The return type of the function can be specified as a
+        /// template parameter. For example,
+        /// \code
+        ///   ns.totalCost<double>();
+        /// \endcode
+        /// It is useful if the total cost cannot be stored in the \c Cost
+        /// type of the algorithm, which is the default return type of the
+        /// function.
+        ///
+        /// \pre \ref run() must be called before using this function.
+        /*template <typename Number>
+         Number totalCost() const {
+         Number c = 0;
+         for (ArcIt a(_graph); a != INVALID; ++a) {
+         int i = getArcID(a);
+         c += Number(_flow[i]) * Number(_cost[i]);
+         }
+         return c;
+         }*/
+
+        template <typename Number>
+        Number totalCost() const {
+            Number c = 0;
+
+            /*#ifdef HASHMAP
+             typename stdext::hash_map<int, Value>::const_iterator it;
+             #else
+             typename std::map<int, Value>::const_iterator it;
+             #endif
+             for (it = _flow.data.begin(); it!=_flow.data.end(); ++it)
+             c += Number(it->second) * Number(_cost[it->first]);
+             return c;*/
+
+            for (int i=0; i<_flow.size(); i++)
+                c += _flow[i] * Number(_cost[i]);
+            return c;
+
+        }
+
+#ifndef DOXYGEN
+        Cost totalCost() const {
+            return totalCost<Cost>();
+        }
+#endif
+
+        /// \brief Return the flow on the given arc.
+        ///
+        /// This function returns the flow on the given arc.
+        ///
+        /// \pre \ref run() must be called before using this function.
+        Value flow(const Arc& a) const {
+            return _flow[getArcID(a)];
+        }
+
+        /// \brief Return the flow map (the primal solution).
+        ///
+        /// This function copies the flow value on each arc into the given
+        /// map. The \c Value type of the algorithm must be convertible to
+        /// the \c Value type of the map.
+        ///
+        /// \pre \ref run() must be called before using this function.
+        template <typename FlowMap>
+        void flowMap(FlowMap &map) const {
+            Arc a; _graph.first(a);
+            for (; a != INVALID; _graph.next(a)) {
+                map.set(a, _flow[getArcID(a)]);
+            }
+        }
+
+        /// \brief Return the potential (dual value) of the given node.
+        ///
+        /// This function returns the potential (dual value) of the
+        /// given node.
+        ///
+        /// \pre \ref run() must be called before using this function.
+        Cost potential(const Node& n) const {
+            return _pi[_node_id(n)];
+        }
+
+        /// \brief Return the potential map (the dual solution).
+        ///
+        /// This function copies the potential (dual value) of each node
+        /// into the given map.
+        /// The \c Cost type of the algorithm must be convertible to the
+        /// \c Value type of the map.
+        ///
+        /// \pre \ref run() must be called before using this function.
+        template <typename PotentialMap>
+        void potentialMap(PotentialMap &map) const {
+            Node n; _graph.first(n);
+            for (; n != INVALID; _graph.next(n)) {
+                map.set(n, _pi[_node_id(n)]);
+            }
+        }
+
+        /// @}
+
+    private:
+
+        // Initialize internal data structures
+        bool init() {
+            if (_node_num == 0) return false;
+            /*
+            // Check the sum of supply values
+            _sum_supply = 0;
+            for (int i = 0; i != _node_num; ++i) {
+                _sum_supply += _supply[i];
+            }
+            if ( !((_stype == GEQ && _sum_supply <= _epsilon ) ||
+                   (_stype == LEQ && _sum_supply >= -_epsilon )) ) return false;
+            */
+
+            // Initialize artifical cost
+            Cost ART_COST;
+            if (std::numeric_limits<Cost>::is_exact) {
+                ART_COST = std::numeric_limits<Cost>::max() / 2 + 1;
+            } else {
+                ART_COST = 0;
+                for (int i = 0; i != _arc_num; ++i) {
+                    if (_cost[i] > ART_COST) ART_COST = _cost[i];
+                }
+                ART_COST = (ART_COST + 1) * _node_num;
+            }
+
+            // Initialize arc maps
+            for (int i = 0; i != _arc_num; ++i) {
+                //_flow[i] = 0; //by default, the sparse matrix is empty
+                _state[i] = STATE_LOWER;
+            }
+
+            // Set data for the artificial root node
+            _root = _node_num;
+            _parent[_root] = -1;
+            _pred[_root] = -1;
+            _thread[_root] = 0;
+            _rev_thread[0] = _root;
+            _succ_num[_root] = _node_num + 1;
+            _last_succ[_root] = _root - 1;
+            _supply[_root] = -_sum_supply;
+            _pi[_root] = 0;
+
+            // Add artificial arcs and initialize the spanning tree data structure
+            if (_sum_supply == 0) {
+                // EQ supply constraints
+                _search_arc_num = _arc_num;
+                _all_arc_num = _arc_num + _node_num;
+                for (int u = 0, e = _arc_num; u != _node_num; ++u, ++e) {
+                    _parent[u] = _root;
+                    _pred[u] = e;
+                    _thread[u] = u + 1;
+                    _rev_thread[u + 1] = u;
+                    _succ_num[u] = 1;
+                    _last_succ[u] = u;
+                    _state[e] = STATE_TREE;
+                    if (_supply[u] >= 0) {
+                        _forward[u] = true;
+                        _pi[u] = 0;
+                        _source[e] = u;
+                        _target[e] = _root;
+                        _flow[e] = _supply[u];
+                        _cost[e] = 0;
+                    } else {
+                        _forward[u] = false;
+                        _pi[u] = ART_COST;
+                        _source[e] = _root;
+                        _target[e] = u;
+                        _flow[e] = -_supply[u];
+                        _cost[e] = ART_COST;
+                    }
+                }
+            }
+            else if (_sum_supply > 0) {
+                // LEQ supply constraints
+                _search_arc_num = _arc_num + _node_num;
+                int f = _arc_num + _node_num;
+                for (int u = 0, e = _arc_num; u != _node_num; ++u, ++e) {
+                    _parent[u] = _root;
+                    _thread[u] = u + 1;
+                    _rev_thread[u + 1] = u;
+                    _succ_num[u] = 1;
+                    _last_succ[u] = u;
+                    if (_supply[u] >= 0) {
+                        _forward[u] = true;
+                        _pi[u] = 0;
+                        _pred[u] = e;
+                        _source[e] = u;
+                        _target[e] = _root;
+                        _flow[e] = _supply[u];
+                        _cost[e] = 0;
+                        _state[e] = STATE_TREE;
+                    } else {
+                        _forward[u] = false;
+                        _pi[u] = ART_COST;
+                        _pred[u] = f;
+                        _source[f] = _root;
+                        _target[f] = u;
+                        _flow[f] = -_supply[u];
+                        _cost[f] = ART_COST;
+                        _state[f] = STATE_TREE;
+                        _source[e] = u;
+                        _target[e] = _root;
+                        //_flow[e] = 0;  //by default, the sparse matrix is empty
+                        _cost[e] = 0;
+                        _state[e] = STATE_LOWER;
+                        ++f;
+                    }
+                }
+                _all_arc_num = f;
+            }
+            else {
+                // GEQ supply constraints
+                _search_arc_num = _arc_num + _node_num;
+                int f = _arc_num + _node_num;
+                for (int u = 0, e = _arc_num; u != _node_num; ++u, ++e) {
+                    _parent[u] = _root;
+                    _thread[u] = u + 1;
+                    _rev_thread[u + 1] = u;
+                    _succ_num[u] = 1;
+                    _last_succ[u] = u;
+                    if (_supply[u] <= 0) {
+                        _forward[u] = false;
+                        _pi[u] = 0;
+                        _pred[u] = e;
+                        _source[e] = _root;
+                        _target[e] = u;
+                        _flow[e] = -_supply[u];
+                        _cost[e] = 0;
+                        _state[e] = STATE_TREE;
+                    } else {
+                        _forward[u] = true;
+                        _pi[u] = -ART_COST;
+                        _pred[u] = f;
+                        _source[f] = u;
+                        _target[f] = _root;
+                        _flow[f] = _supply[u];
+                        _state[f] = STATE_TREE;
+                        _cost[f] = ART_COST;
+                        _source[e] = _root;
+                        _target[e] = u;
+                        //_flow[e] = 0; //by default, the sparse matrix is empty
+                        _cost[e] = 0;
+                        _state[e] = STATE_LOWER;
+                        ++f;
+                    }
+                }
+                _all_arc_num = f;
+            }
+
+            return true;
+        }
+
+        // Find the join node
+        void findJoinNode() {
+            int u = _source[in_arc];
+            int v = _target[in_arc];
+            while (u != v) {
+                if (_succ_num[u] < _succ_num[v]) {
+                    u = _parent[u];
+                } else {
+                    v = _parent[v];
+                }
+            }
+            join = u;
+        }
+
+        // Find the leaving arc of the cycle and returns true if the
+        // leaving arc is not the same as the entering arc
+        bool findLeavingArc() {
+            // Initialize first and second nodes according to the direction
+            // of the cycle
+            if (_state[in_arc] == STATE_LOWER) {
+                first  = _source[in_arc];
+                second = _target[in_arc];
+            } else {
+                first  = _target[in_arc];
+                second = _source[in_arc];
+            }
+            delta = INF;
+            int result = 0;
+            Value d;
+            int e;
+
+            // Search the cycle along the path form the first node to the root
+            for (int u = first; u != join; u = _parent[u]) {
+                e = _pred[u];
+                d = _forward[u] ? _flow[e] : INF ;
+                if (d < delta) {
+                    delta = d;
+                    u_out = u;
+                    result = 1;
+                }
+            }
+            // Search the cycle along the path form the second node to the root
+            for (int u = second; u != join; u = _parent[u]) {
+                e = _pred[u];
+                d = _forward[u] ? INF  : _flow[e];
+                if (d <= delta) {
+                    delta = d;
+                    u_out = u;
+                    result = 2;
+                }
+            }
+
+            if (result == 1) {
+                u_in = first;
+                v_in = second;
+            } else {
+                u_in = second;
+                v_in = first;
+            }
+            return result != 0;
+        }
+
+        // Change _flow and _state vectors
+        void changeFlow(bool change) {
+            // Augment along the cycle
+            if (delta > 0) {
+                Value val = _state[in_arc] * delta;
+                _flow[in_arc] += val;
+                for (int u = _source[in_arc]; u != join; u = _parent[u]) {
+                    _flow[_pred[u]] += _forward[u] ? -val : val;
+                }
+                for (int u = _target[in_arc]; u != join; u = _parent[u]) {
+                    _flow[_pred[u]] += _forward[u] ? val : -val;
+                }
+            }
+            // Update the state of the entering and leaving arcs
+            if (change) {
+                _state[in_arc] = STATE_TREE;
+                _state[_pred[u_out]] =
+                (_flow[_pred[u_out]] == 0) ? STATE_LOWER : STATE_UPPER;
+            } else {
+                _state[in_arc] = -_state[in_arc];
+            }
+        }
+
+        // Update the tree structure
+        void updateTreeStructure() {
+            int u, w;
+            int old_rev_thread = _rev_thread[u_out];
+            int old_succ_num = _succ_num[u_out];
+            int old_last_succ = _last_succ[u_out];
+            v_out = _parent[u_out];
+
+            u = _last_succ[u_in];  // the last successor of u_in
+            right = _thread[u];    // the node after it
+
+            // Handle the case when old_rev_thread equals to v_in
+            // (it also means that join and v_out coincide)
+            if (old_rev_thread == v_in) {
+                last = _thread[_last_succ[u_out]];
+            } else {
+                last = _thread[v_in];
+            }
+
+            // Update _thread and _parent along the stem nodes (i.e. the nodes
+            // between u_in and u_out, whose parent have to be changed)
+            _thread[v_in] = stem = u_in;
+            _dirty_revs.clear();
+            _dirty_revs.push_back(v_in);
+            par_stem = v_in;
+            while (stem != u_out) {
+                // Insert the next stem node into the thread list
+                new_stem = _parent[stem];
+                _thread[u] = new_stem;
+                _dirty_revs.push_back(u);
+
+                // Remove the subtree of stem from the thread list
+                w = _rev_thread[stem];
+                _thread[w] = right;
+                _rev_thread[right] = w;
+
+                // Change the parent node and shift stem nodes
+                _parent[stem] = par_stem;
+                par_stem = stem;
+                stem = new_stem;
+
+                // Update u and right
+                u = _last_succ[stem] == _last_succ[par_stem] ?
+                _rev_thread[par_stem] : _last_succ[stem];
+                right = _thread[u];
+            }
+            _parent[u_out] = par_stem;
+            _thread[u] = last;
+            _rev_thread[last] = u;
+            _last_succ[u_out] = u;
+
+            // Remove the subtree of u_out from the thread list except for
+            // the case when old_rev_thread equals to v_in
+            // (it also means that join and v_out coincide)
+            if (old_rev_thread != v_in) {
+                _thread[old_rev_thread] = right;
+                _rev_thread[right] = old_rev_thread;
+            }
+
+            // Update _rev_thread using the new _thread values
+            for (int i = 0; i != int(_dirty_revs.size()); ++i) {
+                u = _dirty_revs[i];
+                _rev_thread[_thread[u]] = u;
+            }
+
+            // Update _pred, _forward, _last_succ and _succ_num for the
+            // stem nodes from u_out to u_in
+            int tmp_sc = 0, tmp_ls = _last_succ[u_out];
+            u = u_out;
+            while (u != u_in) {
+                w = _parent[u];
+                _pred[u] = _pred[w];
+                _forward[u] = !_forward[w];
+                tmp_sc += _succ_num[u] - _succ_num[w];
+                _succ_num[u] = tmp_sc;
+                _last_succ[w] = tmp_ls;
+                u = w;
+            }
+            _pred[u_in] = in_arc;
+            _forward[u_in] = (u_in == _source[in_arc]);
+            _succ_num[u_in] = old_succ_num;
+
+            // Set limits for updating _last_succ form v_in and v_out
+            // towards the root
+            int up_limit_in = -1;
+            int up_limit_out = -1;
+            if (_last_succ[join] == v_in) {
+                up_limit_out = join;
+            } else {
+                up_limit_in = join;
+            }
+
+            // Update _last_succ from v_in towards the root
+            for (u = v_in; u != up_limit_in && _last_succ[u] == v_in;
+                 u = _parent[u]) {
+                _last_succ[u] = _last_succ[u_out];
+            }
+            // Update _last_succ from v_out towards the root
+            if (join != old_rev_thread && v_in != old_rev_thread) {
+                for (u = v_out; u != up_limit_out && _last_succ[u] == old_last_succ;
+                     u = _parent[u]) {
+                    _last_succ[u] = old_rev_thread;
+                }
+            } else {
+                for (u = v_out; u != up_limit_out && _last_succ[u] == old_last_succ;
+                     u = _parent[u]) {
+                    _last_succ[u] = _last_succ[u_out];
+                }
+            }
+
+            // Update _succ_num from v_in to join
+            for (u = v_in; u != join; u = _parent[u]) {
+                _succ_num[u] += old_succ_num;
+            }
+            // Update _succ_num from v_out to join
+            for (u = v_out; u != join; u = _parent[u]) {
+                _succ_num[u] -= old_succ_num;
+            }
+        }
+
+        // Update potentials
+        void updatePotential() {
+            Cost sigma = _forward[u_in] ?
+            _pi[v_in] - _pi[u_in] - _cost[_pred[u_in]] :
+            _pi[v_in] - _pi[u_in] + _cost[_pred[u_in]];
+            // Update potentials in the subtree, which has been moved
+            int end = _thread[_last_succ[u_in]];
+            for (int u = u_in; u != end; u = _thread[u]) {
+                _pi[u] += sigma;
+            }
+        }
+
+        // Heuristic initial pivots
+        bool initialPivots() {
+            Value curr, total = 0;
+            std::vector<Node> supply_nodes, demand_nodes;
+            Node u; _graph.first(u);
+            for (; u != INVALIDNODE; _graph.next(u)) {
+                curr = _supply[_node_id(u)];
+                if (curr > 0) {
+                    total += curr;
+                    supply_nodes.push_back(u);
+                }
+                else if (curr < 0) {
+                    demand_nodes.push_back(u);
+                }
+            }
+            if (_sum_supply > 0) total -= _sum_supply;
+            if (total <= 0) return true;
+
+            IntVector arc_vector;
+            if (_sum_supply >= 0) {
+                if (supply_nodes.size() == 1 && demand_nodes.size() == 1) {
+                    // Perform a reverse graph search from the sink to the source
+                    //typename GR::template NodeMap<bool> reached(_graph, false);
+                    BoolVector reached(_node_num, false);
+                    Node s = supply_nodes[0], t = demand_nodes[0];
+                    std::vector<Node> stack;
+                    reached[t] = true;
+                    stack.push_back(t);
+                    while (!stack.empty()) {
+                        Node u, v = stack.back();
+                        stack.pop_back();
+                        if (v == s) break;
+                        Arc a; _graph.firstIn(a, v);
+                        for (; a != INVALID; _graph.nextIn(a)) {
+                            if (reached[u = _graph.source(a)]) continue;
+                            int j = getArcID(a);
+                            if (INF >= total) {
+                                arc_vector.push_back(j);
+                                reached[u] = true;
+                                stack.push_back(u);
+                            }
+                        }
+                    }
+                } else {
+                    // Find the min. cost incomming arc for each demand node
+                    for (int i = 0; i != int(demand_nodes.size()); ++i) {
+                        Node v = demand_nodes[i];
+                        Cost c, min_cost = std::numeric_limits<Cost>::max();
+                        Arc min_arc = INVALID;
+                        Arc a; _graph.firstIn(a, v);
+                        for (; a != INVALID; _graph.nextIn(a)) {
+                            c = _cost[getArcID(a)];
+                            if (c < min_cost) {
+                                min_cost = c;
+                                min_arc = a;
+                            }
+                        }
+                        if (min_arc != INVALID) {
+                            arc_vector.push_back(getArcID(min_arc));
+                        }
+                    }
+                }
+            } else {
+                // Find the min. cost outgoing arc for each supply node
+                for (int i = 0; i != int(supply_nodes.size()); ++i) {
+                    Node u = supply_nodes[i];
+                    Cost c, min_cost = std::numeric_limits<Cost>::max();
+                    Arc min_arc = INVALID;
+                    Arc a; _graph.firstOut(a, u);
+                    for (; a != INVALID; _graph.nextOut(a)) {
+                        c = _cost[getArcID(a)];
+                        if (c < min_cost) {
+                            min_cost = c;
+                            min_arc = a;
+                        }
+                    }
+                    if (min_arc != INVALID) {
+                        arc_vector.push_back(getArcID(min_arc));
+                    }
+                }
+            }
+
+            // Perform heuristic initial pivots
+            for (int i = 0; i != int(arc_vector.size()); ++i) {
+                in_arc = arc_vector[i];
+                // l'erreur est probablement ici...
+                if (_state[in_arc] * (_cost[in_arc] + _pi[_source[in_arc]] -
+                                      _pi[_target[in_arc]]) >= 0) continue;
+                findJoinNode();
+                bool change = findLeavingArc();
+                if (delta >= MAX) return false;
+                changeFlow(change);
+                if (change) {
+                    updateTreeStructure();
+                    updatePotential();
+                }
+            }
+            return true;
+        }
+
+        // Execute the algorithm
+        ProblemType start() {
+            return start<BlockSearchPivotRule>();
+        }
+
+        template <typename PivotRuleImpl>
+        ProblemType start() {
+            PivotRuleImpl pivot(*this);
+            double prevCost=-1;
+
+            // Perform heuristic initial pivots
+            if (!initialPivots()) return UNBOUNDED;
+
+#if DEBUG_LVL>0
+            int niter=0;
+#endif
+            int iter_number=0;
+            //pivot.setDantzig(true);
+            // Execute the Network Simplex algorithm
+            while (pivot.findEnteringArc()) {
+                if(++iter_number>=max_iter&&max_iter>0){
+                    char errMess[1000];
+                  //  sprintf( errMess, "RESULT MIGHT BE INACURATE\nMax number of iteration reached, currently \%d. Sometimes iterations go on in cycle even though the solution has been reached, to check if it's the case here have a look at the minimal reduced cost. If it is very close to machine precision, you might actually have the correct solution, if not try setting the maximum number of iterations a bit higher",iter_number );
+                   // mexWarnMsgTxt(errMess);
+                    break;
+                }
+#if DEBUG_LVL>0
+                if(niter>MAX_DEBUG_ITER)
+                    break;
+                if(++niter%1000==0||niter%1000==1){
+                    double curCost=totalCost();
+                    double sumFlow=0;
+                    double a;
+                    a= (fabs(_pi[_source[in_arc]])>=fabs(_pi[_target[in_arc]])) ? fabs(_pi[_source[in_arc]]) : fabs(_pi[_target[in_arc]]);
+                    a=a>=fabs(_cost[in_arc])?a:fabs(_cost[in_arc]);
+                    for (int i=0; i<_flow.size(); i++) {
+                        sumFlow+=_state[i]*_flow[i];
+                    }
+                    mexPrintf("Sum of the flow %.100f\n%d iterations, current cost=%.20f\nReduced cost=%.30f\nPrecision   =%.30f\n",sumFlow,niter, curCost,_state[in_arc] * (_cost[in_arc] + _pi[_source[in_arc]] -_pi[_target[in_arc]]), -EPSILON*(a));
+                    mexPrintf("Arc in = (%d,%d)\n",_node_id(_source[in_arc]),_node_id(_target[in_arc]));
+                    mexPrintf("Supplies = (%f,%f)\n",_supply[_source[in_arc]],_supply[_target[in_arc]]);
+
+                    mexPrintf("%.30f\n%.30f\n%.30f\n%.30f\n%",_cost[in_arc],_pi[_source[in_arc]],_pi[_target[in_arc]],a);
+                    mexEvalString("drawnow;");
+                }
+#endif
+
+                findJoinNode();
+                bool change = findLeavingArc();
+                if (delta >= MAX) return UNBOUNDED;
+                changeFlow(change);
+                if (change) {
+                    updateTreeStructure();
+                    updatePotential();
+                }
+#if DEBUG_LVL>0
+                else{
+                    mexPrintf("No change\n");
+                }
+#endif
+#if DEBUG_LVL>1
+                mexPrintf("Arc in = (%d,%d)\n",_source[in_arc],_target[in_arc]);
+#endif
+
+            }
+
+
+#if DEBUG_LVL>0
+                double curCost=totalCost();
+                double sumFlow=0;
+                double a;
+                a= (fabs(_pi[_source[in_arc]])>=fabs(_pi[_target[in_arc]])) ? fabs(_pi[_source[in_arc]]) : fabs(_pi[_target[in_arc]]);
+                a=a>=fabs(_cost[in_arc])?a:fabs(_cost[in_arc]);
+                for (int i=0; i<_flow.size(); i++) {
+                    sumFlow+=_state[i]*_flow[i];
+                }
+                mexPrintf("Sum of the flow %.100f\n%d iterations, current cost=%.20f\nReduced cost=%.30f\nPrecision   =%.30f",sumFlow,niter, curCost,_state[in_arc] * (_cost[in_arc] + _pi[_source[in_arc]] -_pi[_target[in_arc]]), -EPSILON*(a));
+                mexPrintf("Arc in = (%d,%d)\n",_node_id(_source[in_arc]),_node_id(_target[in_arc]));
+                mexPrintf("Supplies = (%f,%f)\n",_supply[_source[in_arc]],_supply[_target[in_arc]]);
+
+                mexEvalString("drawnow;");
+#endif
+
+#if DEBUG_LVL>1
+            double sumFlow=0;
+            for (int i=0; i<_flow.size(); i++) {
+                sumFlow+=_state[i]*_flow[i];
+                if (_state[i]==STATE_TREE) {
+                    mexPrintf("Non zero value at (%d,%d)\n",_node_num+1-_source[i],_node_num+1-_target[i]);
+                }
+            }
+            mexPrintf("Sum of the flow %.100f\n%d iterations, current cost=%.20f\n",sumFlow,niter, totalCost());
+            mexEvalString("drawnow;");
+#endif
+            // Check feasibility
+            for (int e = _search_arc_num; e != _all_arc_num; ++e) {
+                if (_flow[e] != 0){
+                    if (abs(_flow[e]) > EPSILON)
+                        return INFEASIBLE;
+                    else
+                        _flow[e]=0;
+
+                }
+            }
+
+            // Shift potentials to meet the requirements of the GEQ/LEQ type
+            // optimality conditions
+            if (_sum_supply == 0) {
+                if (_stype == GEQ) {
+                    Cost max_pot = -std::numeric_limits<Cost>::max();
+                    for (int i = 0; i != _node_num; ++i) {
+                        if (_pi[i] > max_pot) max_pot = _pi[i];
+                    }
+                    if (max_pot > 0) {
+                        for (int i = 0; i != _node_num; ++i)
+                            _pi[i] -= max_pot;
+                    }
+                } else {
+                    Cost min_pot = std::numeric_limits<Cost>::max();
+                    for (int i = 0; i != _node_num; ++i) {
+                        if (_pi[i] < min_pot) min_pot = _pi[i];
+                    }
+                    if (min_pot < 0) {
+                        for (int i = 0; i != _node_num; ++i)
+                            _pi[i] -= min_pot;
+                    }
+                }
+            }
+
+            return OPTIMAL;
+        }
+
+    }; //class NetworkSimplexSimple
+
+    ///@}
+
+} //namespace lemon
+
+#endif //LEMON_NETWORK_SIMPLEX_H