From b05d315b0994d328029d4a4fc082f6994e7f06d1 Mon Sep 17 00:00:00 2001 From: Romain Tavenard Date: Mon, 1 Jul 2019 11:06:26 +0200 Subject: Moved GPU doctests to test_gpu for tests not to fail if no GPU available --- ot/gpu/bregman.py | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'ot') diff --git a/ot/gpu/bregman.py b/ot/gpu/bregman.py index 978b307..2e2df83 100644 --- a/ot/gpu/bregman.py +++ b/ot/gpu/bregman.py @@ -70,17 +70,6 @@ def sinkhorn_knopp(a, b, M, reg, numItermax=1000, stopThr=1e-9, log : dict log dictionary return only if log==True in parameters - Examples - -------- - - >>> import ot - >>> a=[.5,.5] - >>> b=[.5,.5] - >>> M=[[0.,1.],[1.,0.]] - >>> ot.sinkhorn(a,b,M,1) - array([[ 0.36552929, 0.13447071], - [ 0.13447071, 0.36552929]]) - References ---------- -- cgit v1.2.3 From 1fe13ed9cdda363c95c84f95fc70dcd95ac276f1 Mon Sep 17 00:00:00 2001 From: Romain Tavenard Date: Mon, 1 Jul 2019 12:16:04 +0200 Subject: Fixed doctests --- .travis.yml | 2 +- ot/bregman.py | 17 +++++++--------- ot/stochastic.py | 59 +++++++++++++++++++++++--------------------------------- ot/utils.py | 6 +++--- 4 files changed, 35 insertions(+), 49 deletions(-) (limited to 'ot') diff --git a/.travis.yml b/.travis.yml index d6b4232..da68c96 100644 --- a/.travis.yml +++ b/.travis.yml @@ -32,5 +32,5 @@ install: script: - python setup.py develop - flake8 examples/ ot/ test/ - - python -m pytest -v test/ ot/ --doctest-modules --cov=ot + - python -m pytest -v test/ ot/ --doctest-modules --ignore ot/gpu/ --cov=ot # - py.test ot test diff --git a/ot/bregman.py b/ot/bregman.py index 09716e6..8225967 100644 --- a/ot/bregman.py +++ b/ot/bregman.py @@ -1360,10 +1360,9 @@ def empirical_sinkhorn(X_s, X_t, reg, a=None, b=None, metric='sqeuclidean', numI >>> reg = 0.1 >>> X_s = np.reshape(np.arange(n_s), (n_s, 1)) >>> X_t = np.reshape(np.arange(0, n_t), (n_t, 1)) - >>> emp_sinkhorn = empirical_sinkhorn(X_s, X_t, reg, verbose=False) - >>> print(emp_sinkhorn) - >>> [[4.99977301e-01 2.26989344e-05] - [2.26989344e-05 4.99977301e-01]] + >>> empirical_sinkhorn(X_s, X_t, reg, verbose=False) # doctest: +NORMALIZE_WHITESPACE + array([[4.99977301e-01, 2.26989344e-05], + [2.26989344e-05, 4.99977301e-01]]) References @@ -1451,9 +1450,8 @@ def empirical_sinkhorn2(X_s, X_t, reg, a=None, b=None, metric='sqeuclidean', num >>> reg = 0.1 >>> X_s = np.reshape(np.arange(n_s), (n_s, 1)) >>> X_t = np.reshape(np.arange(0, n_t), (n_t, 1)) - >>> loss_sinkhorn = empirical_sinkhorn2(X_s, X_t, reg, verbose=False) - >>> print(loss_sinkhorn) - >>> [4.53978687e-05] + >>> empirical_sinkhorn2(X_s, X_t, reg, verbose=False) + array([4.53978687e-05]) References @@ -1560,9 +1558,8 @@ def empirical_sinkhorn_divergence(X_s, X_t, reg, a=None, b=None, metric='sqeucli >>> reg = 0.1 >>> X_s = np.reshape(np.arange(n_s), (n_s, 1)) >>> X_t = np.reshape(np.arange(0, n_t), (n_t, 1)) - >>> emp_sinkhorn_div = empirical_sinkhorn_divergence(X_s, X_t, reg) - >>> print(emp_sinkhorn_div) - >>> [2.99977435] + >>> empirical_sinkhorn_divergence(X_s, X_t, reg) + array([2.99977435]) References diff --git a/ot/stochastic.py b/ot/stochastic.py index 85c4230..762eb3e 100644 --- a/ot/stochastic.py +++ b/ot/stochastic.py @@ -11,7 +11,7 @@ import numpy as np def coordinate_grad_semi_dual(b, M, reg, beta, i): - ''' + r''' Compute the coordinate gradient update for regularized discrete distributions for (i, :) The function computes the gradient of the semi dual problem: @@ -51,7 +51,7 @@ def coordinate_grad_semi_dual(b, M, reg, beta, i): Examples -------- - + >>> import ot >>> n_source = 7 >>> n_target = 4 >>> reg = 1 @@ -63,8 +63,7 @@ def coordinate_grad_semi_dual(b, M, reg, beta, i): >>> Y_target = rng.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) >>> method = "ASGD" - >>> asgd_pi = stochastic.solve_semi_dual_entropic(a, b, M, reg, - method, numItermax) + >>> asgd_pi = ot.stochastic.solve_semi_dual_entropic(a, b, M, reg, method, numItermax) >>> print(asgd_pi) References @@ -84,7 +83,7 @@ def coordinate_grad_semi_dual(b, M, reg, beta, i): def sag_entropic_transport(a, b, M, reg, numItermax=10000, lr=None): - ''' + r''' Compute the SAG algorithm to solve the regularized discrete measures optimal transport max problem @@ -133,7 +132,7 @@ def sag_entropic_transport(a, b, M, reg, numItermax=10000, lr=None): Examples -------- - + >>> import ot >>> n_source = 7 >>> n_target = 4 >>> reg = 1 @@ -145,8 +144,7 @@ def sag_entropic_transport(a, b, M, reg, numItermax=10000, lr=None): >>> Y_target = rng.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) >>> method = "ASGD" - >>> asgd_pi = stochastic.solve_semi_dual_entropic(a, b, M, reg, - method, numItermax) + >>> asgd_pi = ot.stochastic.solve_semi_dual_entropic(a, b, M, reg, method, numItermax) >>> print(asgd_pi) References @@ -176,7 +174,7 @@ def sag_entropic_transport(a, b, M, reg, numItermax=10000, lr=None): def averaged_sgd_entropic_transport(a, b, M, reg, numItermax=300000, lr=None): - ''' + r''' Compute the ASGD algorithm to solve the regularized semi continous measures optimal transport max problem The function solves the following optimization problem: @@ -223,7 +221,7 @@ def averaged_sgd_entropic_transport(a, b, M, reg, numItermax=300000, lr=None): Examples -------- - + >>> import ot >>> n_source = 7 >>> n_target = 4 >>> reg = 1 @@ -235,8 +233,7 @@ def averaged_sgd_entropic_transport(a, b, M, reg, numItermax=300000, lr=None): >>> Y_target = rng.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) >>> method = "ASGD" - >>> asgd_pi = stochastic.solve_semi_dual_entropic(a, b, M, reg, - method, numItermax) + >>> asgd_pi = ot.stochastic.solve_semi_dual_entropic(a, b, M, reg, method, numItermax) >>> print(asgd_pi) References @@ -264,7 +261,7 @@ def averaged_sgd_entropic_transport(a, b, M, reg, numItermax=300000, lr=None): def c_transform_entropic(b, M, reg, beta): - ''' + r''' The goal is to recover u from the c-transform. The function computes the c_transform of a dual variable from the other @@ -303,7 +300,7 @@ def c_transform_entropic(b, M, reg, beta): Examples -------- - + >>> import ot >>> n_source = 7 >>> n_target = 4 >>> reg = 1 @@ -315,8 +312,7 @@ def c_transform_entropic(b, M, reg, beta): >>> Y_target = rng.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) >>> method = "ASGD" - >>> asgd_pi = stochastic.solve_semi_dual_entropic(a, b, M, reg, - method, numItermax) + >>> asgd_pi = ot.stochastic.solve_semi_dual_entropic(a, b, M, reg, method, numItermax) >>> print(asgd_pi) References @@ -340,7 +336,7 @@ def c_transform_entropic(b, M, reg, beta): def solve_semi_dual_entropic(a, b, M, reg, method, numItermax=10000, lr=None, log=False): - ''' + r''' Compute the transportation matrix to solve the regularized discrete measures optimal transport max problem @@ -398,7 +394,7 @@ def solve_semi_dual_entropic(a, b, M, reg, method, numItermax=10000, lr=None, Examples -------- - + >>> import ot >>> n_source = 7 >>> n_target = 4 >>> reg = 1 @@ -410,8 +406,7 @@ def solve_semi_dual_entropic(a, b, M, reg, method, numItermax=10000, lr=None, >>> Y_target = rng.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) >>> method = "ASGD" - >>> asgd_pi = stochastic.solve_semi_dual_entropic(a, b, M, reg, - method, numItermax) + >>> asgd_pi = ot.stochastic.solve_semi_dual_entropic(a, b, M, reg, method, numItermax) >>> print(asgd_pi) References @@ -451,7 +446,7 @@ def solve_semi_dual_entropic(a, b, M, reg, method, numItermax=10000, lr=None, def batch_grad_dual(a, b, M, reg, alpha, beta, batch_size, batch_alpha, batch_beta): - ''' + r''' Computes the partial gradient of the dual optimal transport problem. For each (i,j) in a batch of coordinates, the partial gradients are : @@ -506,7 +501,7 @@ def batch_grad_dual(a, b, M, reg, alpha, beta, batch_size, batch_alpha, Examples -------- - + >>> import ot >>> n_source = 7 >>> n_target = 4 >>> reg = 1 @@ -520,9 +515,7 @@ def batch_grad_dual(a, b, M, reg, alpha, beta, batch_size, batch_alpha, >>> X_source = rng.randn(n_source, 2) >>> Y_target = rng.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) - >>> sgd_dual_pi, log = stochastic.solve_dual_entropic(a, b, M, reg, - batch_size, - numItermax, lr, log) + >>> sgd_dual_pi, log = ot.stochastic.solve_dual_entropic(a, b, M, reg, batch_size, numItermax, lr, log) >>> print(log['alpha'], log['beta']) >>> print(sgd_dual_pi) @@ -548,7 +541,7 @@ def batch_grad_dual(a, b, M, reg, alpha, beta, batch_size, batch_alpha, def sgd_entropic_regularization(a, b, M, reg, batch_size, numItermax, lr): - ''' + r''' Compute the sgd algorithm to solve the regularized discrete measures optimal transport dual problem @@ -597,7 +590,7 @@ def sgd_entropic_regularization(a, b, M, reg, batch_size, numItermax, lr): Examples -------- - + >>> import ot >>> n_source = 7 >>> n_target = 4 >>> reg = 1 @@ -611,9 +604,7 @@ def sgd_entropic_regularization(a, b, M, reg, batch_size, numItermax, lr): >>> X_source = rng.randn(n_source, 2) >>> Y_target = rng.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) - >>> sgd_dual_pi, log = stochastic.solve_dual_entropic(a, b, M, reg, - batch_size, - numItermax, lr, log) + >>> sgd_dual_pi, log = ot.stochastic.solve_dual_entropic(a, b, M, reg, batch_size, numItermax, lr, log) >>> print(log['alpha'], log['beta']) >>> print(sgd_dual_pi) @@ -644,7 +635,7 @@ def sgd_entropic_regularization(a, b, M, reg, batch_size, numItermax, lr): def solve_dual_entropic(a, b, M, reg, batch_size, numItermax=10000, lr=1, log=False): - ''' + r''' Compute the transportation matrix to solve the regularized discrete measures optimal transport dual problem @@ -695,7 +686,7 @@ def solve_dual_entropic(a, b, M, reg, batch_size, numItermax=10000, lr=1, Examples -------- - + >>> import ot >>> n_source = 7 >>> n_target = 4 >>> reg = 1 @@ -709,9 +700,7 @@ def solve_dual_entropic(a, b, M, reg, batch_size, numItermax=10000, lr=1, >>> X_source = rng.randn(n_source, 2) >>> Y_target = rng.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) - >>> sgd_dual_pi, log = stochastic.solve_dual_entropic(a, b, M, reg, - batch_size, - numItermax, lr, log) + >>> sgd_dual_pi, log = ot.stochastic.solve_dual_entropic(a, b, M, reg, batch_size, numItermax, lr, log) >>> print(log['alpha'], log['beta']) >>> print(sgd_dual_pi) diff --git a/ot/utils.py b/ot/utils.py index efd1288..f21ceb9 100644 --- a/ot/utils.py +++ b/ot/utils.py @@ -285,9 +285,9 @@ class deprecated(object): The optional extra argument will be appended to the deprecation message and the docstring. Note: to use this with the default value for extra, put in an empty of parentheses: - >>> from ot.deprecation import deprecated - >>> @deprecated() - ... def some_function(): pass + >>> from ot.deprecation import deprecated # doctest: +SKIP + >>> @deprecated() # doctest: +SKIP + ... def some_function(): pass # doctest: +SKIP Parameters ---------- -- cgit v1.2.3 From 3a84263ffe4bbf2ac055dfd5a84e1b65c14f9cda Mon Sep 17 00:00:00 2001 From: Romain Tavenard Date: Mon, 1 Jul 2019 14:23:14 +0200 Subject: Set numpy array formatting version to post-1.13 --- .travis.yml | 2 ++ ot/bregman.py | 86 +++++++++++++++++++++++++++---------------------------- ot/lp/__init__.py | 22 +++++++------- ot/unbalanced.py | 10 +++---- 4 files changed, 61 insertions(+), 59 deletions(-) (limited to 'ot') diff --git a/.travis.yml b/.travis.yml index da68c96..f004a32 100644 --- a/.travis.yml +++ b/.travis.yml @@ -26,6 +26,8 @@ before_script: # configure a headless display to test plot generation # command to install dependencies install: - pip install -r requirements.txt + - pip install numpy>=1.14 # for numpy array formatting in doctests + - pip install scipy<1.3 # otherwise, pymanopt fails, cf - pip install flake8 pytest "pytest-cov<2.6" - pip install . # command to run tests + check syntax style diff --git a/ot/bregman.py b/ot/bregman.py index 8225967..caf4024 100644 --- a/ot/bregman.py +++ b/ot/bregman.py @@ -16,7 +16,7 @@ from .utils import unif, dist def sinkhorn(a, b, M, reg, method='sinkhorn', numItermax=1000, stopThr=1e-9, verbose=False, log=False, **kwargs): - u""" + r""" Solve the entropic regularization optimal transport problem and return the OT matrix The function solves the following optimization problem: @@ -73,12 +73,12 @@ def sinkhorn(a, b, M, reg, method='sinkhorn', numItermax=1000, -------- >>> import ot - >>> a=[.5,.5] - >>> b=[.5,.5] - >>> M=[[0.,1.],[1.,0.]] - >>> ot.sinkhorn(a,b,M,1) - array([[ 0.36552929, 0.13447071], - [ 0.13447071, 0.36552929]]) + >>> a=[.5, .5] + >>> b=[.5, .5] + >>> M=[[0., 1.], [1., 0.]] + >>> ot.sinkhorn(a, b, M, 1) + array([[0.36552929, 0.13447071], + [0.13447071, 0.36552929]]) References @@ -131,7 +131,7 @@ def sinkhorn(a, b, M, reg, method='sinkhorn', numItermax=1000, def sinkhorn2(a, b, M, reg, method='sinkhorn', numItermax=1000, stopThr=1e-9, verbose=False, log=False, **kwargs): - u""" + r""" Solve the entropic regularization optimal transport problem and return the loss The function solves the following optimization problem: @@ -188,11 +188,11 @@ def sinkhorn2(a, b, M, reg, method='sinkhorn', numItermax=1000, -------- >>> import ot - >>> a=[.5,.5] - >>> b=[.5,.5] - >>> M=[[0.,1.],[1.,0.]] - >>> ot.sinkhorn2(a,b,M,1) - array([ 0.26894142]) + >>> a=[.5, .5] + >>> b=[.5, .5] + >>> M=[[0., 1.], [1., 0.]] + >>> ot.sinkhorn2(a, b, M, 1) + array([0.26894142]) @@ -248,7 +248,7 @@ def sinkhorn2(a, b, M, reg, method='sinkhorn', numItermax=1000, def sinkhorn_knopp(a, b, M, reg, numItermax=1000, stopThr=1e-9, verbose=False, log=False, **kwargs): - """ + r""" Solve the entropic regularization optimal transport problem and return the OT matrix The function solves the following optimization problem: @@ -302,12 +302,12 @@ def sinkhorn_knopp(a, b, M, reg, numItermax=1000, -------- >>> import ot - >>> a=[.5,.5] - >>> b=[.5,.5] - >>> M=[[0.,1.],[1.,0.]] - >>> ot.sinkhorn(a,b,M,1) - array([[ 0.36552929, 0.13447071], - [ 0.13447071, 0.36552929]]) + >>> a=[.5, .5] + >>> b=[.5, .5] + >>> M=[[0., 1.], [1., 0.]] + >>> ot.sinkhorn(a, b, M, 1) + array([[0.36552929, 0.13447071], + [0.13447071, 0.36552929]]) References @@ -422,7 +422,7 @@ def sinkhorn_knopp(a, b, M, reg, numItermax=1000, def greenkhorn(a, b, M, reg, numItermax=10000, stopThr=1e-9, verbose=False, log=False): - """ + r""" Solve the entropic regularization optimal transport problem and return the OT matrix The algorithm used is based on the paper @@ -481,12 +481,12 @@ def greenkhorn(a, b, M, reg, numItermax=10000, stopThr=1e-9, verbose=False, log= -------- >>> import ot - >>> a=[.5,.5] - >>> b=[.5,.5] - >>> M=[[0.,1.],[1.,0.]] - >>> ot.bregman.greenkhorn(a,b,M,1) - array([[ 0.36552929, 0.13447071], - [ 0.13447071, 0.36552929]]) + >>> a=[.5, .5] + >>> b=[.5, .5] + >>> M=[[0., 1.], [1., 0.]] + >>> ot.bregman.greenkhorn(a, b, M, 1) + array([[0.36552929, 0.13447071], + [0.13447071, 0.36552929]]) References @@ -576,7 +576,7 @@ def greenkhorn(a, b, M, reg, numItermax=10000, stopThr=1e-9, verbose=False, log= def sinkhorn_stabilized(a, b, M, reg, numItermax=1000, tau=1e3, stopThr=1e-9, warmstart=None, verbose=False, print_period=20, log=False, **kwargs): - """ + r""" Solve the entropic regularization OT problem with log stabilization The function solves the following optimization problem: @@ -639,8 +639,8 @@ def sinkhorn_stabilized(a, b, M, reg, numItermax=1000, tau=1e3, stopThr=1e-9, >>> b=[.5,.5] >>> M=[[0.,1.],[1.,0.]] >>> ot.bregman.sinkhorn_stabilized(a,b,M,1) - array([[ 0.36552929, 0.13447071], - [ 0.13447071, 0.36552929]]) + array([[0.36552929, 0.13447071], + [0.13447071, 0.36552929]]) References @@ -796,7 +796,7 @@ def sinkhorn_stabilized(a, b, M, reg, numItermax=1000, tau=1e3, stopThr=1e-9, def sinkhorn_epsilon_scaling(a, b, M, reg, numItermax=100, epsilon0=1e4, numInnerItermax=100, tau=1e3, stopThr=1e-9, warmstart=None, verbose=False, print_period=10, log=False, **kwargs): - """ + r""" Solve the entropic regularization optimal transport problem with log stabilization and epsilon scaling. @@ -862,12 +862,12 @@ def sinkhorn_epsilon_scaling(a, b, M, reg, numItermax=100, epsilon0=1e4, numInne -------- >>> import ot - >>> a=[.5,.5] - >>> b=[.5,.5] - >>> M=[[0.,1.],[1.,0.]] - >>> ot.bregman.sinkhorn_epsilon_scaling(a,b,M,1) - array([[ 0.36552929, 0.13447071], - [ 0.13447071, 0.36552929]]) + >>> a=[.5, .5] + >>> b=[.5, .5] + >>> M=[[0., 1.], [1., 0.]] + >>> ot.bregman.sinkhorn_epsilon_scaling(a, b, M, 1) + array([[0.36552929, 0.13447071], + [0.13447071, 0.36552929]]) References @@ -989,7 +989,7 @@ def projC(gamma, q): def barycenter(A, M, reg, weights=None, numItermax=1000, stopThr=1e-4, verbose=False, log=False): - """Compute the entropic regularized wasserstein barycenter of distributions A + r"""Compute the entropic regularized wasserstein barycenter of distributions A The function solves the following optimization problem: @@ -1084,7 +1084,7 @@ def barycenter(A, M, reg, weights=None, numItermax=1000, def convolutional_barycenter2d(A, reg, weights=None, numItermax=10000, stopThr=1e-9, stabThr=1e-30, verbose=False, log=False): - """Compute the entropic regularized wasserstein barycenter of distributions A + r"""Compute the entropic regularized wasserstein barycenter of distributions A where A is a collection of 2D images. The function solves the following optimization problem: @@ -1195,7 +1195,7 @@ def convolutional_barycenter2d(A, reg, weights=None, numItermax=10000, stopThr=1 def unmix(a, D, M, M0, h0, reg, reg0, alpha, numItermax=1000, stopThr=1e-3, verbose=False, log=False): - """ + r""" Compute the unmixing of an observation with a given dictionary using Wasserstein distance The function solve the following optimization problem: @@ -1302,7 +1302,7 @@ def unmix(a, D, M, M0, h0, reg, reg0, alpha, numItermax=1000, def empirical_sinkhorn(X_s, X_t, reg, a=None, b=None, metric='sqeuclidean', numIterMax=10000, stopThr=1e-9, verbose=False, log=False, **kwargs): - ''' + r''' Solve the entropic regularization optimal transport problem and return the OT matrix from empirical data @@ -1391,7 +1391,7 @@ def empirical_sinkhorn(X_s, X_t, reg, a=None, b=None, metric='sqeuclidean', numI def empirical_sinkhorn2(X_s, X_t, reg, a=None, b=None, metric='sqeuclidean', numIterMax=10000, stopThr=1e-9, verbose=False, log=False, **kwargs): - ''' + r''' Solve the entropic regularization optimal transport problem from empirical data and return the OT loss @@ -1480,7 +1480,7 @@ def empirical_sinkhorn2(X_s, X_t, reg, a=None, b=None, metric='sqeuclidean', num def empirical_sinkhorn_divergence(X_s, X_t, reg, a=None, b=None, metric='sqeuclidean', numIterMax=10000, stopThr=1e-9, verbose=False, log=False, **kwargs): - ''' + r''' Compute the sinkhorn divergence loss from empirical data The function solves the following optimization problems and return the diff --git a/ot/lp/__init__.py b/ot/lp/__init__.py index a3f5b8d..8ec286b 100644 --- a/ot/lp/__init__.py +++ b/ot/lp/__init__.py @@ -25,7 +25,7 @@ __all__=['emd', 'emd2', 'barycenter', 'free_support_barycenter', 'cvx', def emd(a, b, M, numItermax=100000, log=False): - """Solves the Earth Movers distance problem and returns the OT matrix + r"""Solves the Earth Movers distance problem and returns the OT matrix .. math:: @@ -76,8 +76,8 @@ def emd(a, b, M, numItermax=100000, log=False): >>> b=[.5,.5] >>> M=[[0.,1.],[1.,0.]] >>> ot.emd(a,b,M) - array([[ 0.5, 0. ], - [ 0. , 0.5]]) + array([[0.5, 0. ], + [0. , 0.5]]) References ---------- @@ -117,7 +117,7 @@ def emd(a, b, M, numItermax=100000, log=False): def emd2(a, b, M, processes=multiprocessing.cpu_count(), numItermax=100000, log=False, return_matrix=False): - """Solves the Earth Movers distance problem and returns the loss + r"""Solves the Earth Movers distance problem and returns the loss .. math:: \gamma = arg\min_\gamma <\gamma,M>_F @@ -315,7 +315,7 @@ def free_support_barycenter(measures_locations, measures_weights, X_init, b=None def emd_1d(x_a, x_b, a=None, b=None, metric='sqeuclidean', p=1., dense=True, log=False): - """Solves the Earth Movers distance problem between 1d measures and returns + r"""Solves the Earth Movers distance problem between 1d measures and returns the OT matrix @@ -381,11 +381,11 @@ def emd_1d(x_a, x_b, a=None, b=None, metric='sqeuclidean', p=1., dense=True, >>> x_a = [2., 0.] >>> x_b = [0., 3.] >>> ot.emd_1d(x_a, x_b, a, b) - array([[0. , 0.5], - [0.5, 0. ]]) + array([[0. , 0.5], + [0.5, 0. ]]) >>> ot.emd_1d(x_a, x_b) - array([[0. , 0.5], - [0.5, 0. ]]) + array([[0. , 0.5], + [0.5, 0. ]]) References ---------- @@ -435,7 +435,7 @@ def emd_1d(x_a, x_b, a=None, b=None, metric='sqeuclidean', p=1., dense=True, def emd2_1d(x_a, x_b, a=None, b=None, metric='sqeuclidean', p=1., dense=True, log=False): - """Solves the Earth Movers distance problem between 1d measures and returns + r"""Solves the Earth Movers distance problem between 1d measures and returns the loss @@ -530,7 +530,7 @@ def emd2_1d(x_a, x_b, a=None, b=None, metric='sqeuclidean', p=1., dense=True, def wasserstein_1d(x_a, x_b, a=None, b=None, p=1.): - """Solves the p-Wasserstein distance problem between 1d measures and returns + r"""Solves the p-Wasserstein distance problem between 1d measures and returns the distance diff --git a/ot/unbalanced.py b/ot/unbalanced.py index 484ce95..b2b7b10 100644 --- a/ot/unbalanced.py +++ b/ot/unbalanced.py @@ -13,7 +13,7 @@ import numpy as np def sinkhorn_unbalanced(a, b, M, reg, alpha, method='sinkhorn', numItermax=1000, stopThr=1e-9, verbose=False, log=False, **kwargs): - u""" + r""" Solve the unbalanced entropic regularization optimal transport problem and return the loss The function solves the following optimization problem: @@ -75,7 +75,7 @@ def sinkhorn_unbalanced(a, b, M, reg, alpha, method='sinkhorn', numItermax=1000, >>> M=[[0., 1.], [1., 0.]] >>> ot.sinkhorn_unbalanced(a, b, M, 1, 1) array([[0.51122823, 0.18807035], - [0.18807035, 0.51122823]]) + [0.18807035, 0.51122823]]) References @@ -122,7 +122,7 @@ def sinkhorn_unbalanced(a, b, M, reg, alpha, method='sinkhorn', numItermax=1000, def sinkhorn_unbalanced2(a, b, M, reg, alpha, method='sinkhorn', numItermax=1000, stopThr=1e-9, verbose=False, log=False, **kwargs): - u""" + r""" Solve the entropic regularization unbalanced optimal transport problem and return the loss The function solves the following optimization problem: @@ -233,7 +233,7 @@ def sinkhorn_unbalanced2(a, b, M, reg, alpha, method='sinkhorn', def sinkhorn_knopp_unbalanced(a, b, M, reg, alpha, numItermax=1000, stopThr=1e-9, verbose=False, log=False, **kwargs): - """ + r""" Solve the entropic regularization unbalanced optimal transport problem and return the loss The function solves the following optimization problem: @@ -401,7 +401,7 @@ def sinkhorn_knopp_unbalanced(a, b, M, reg, alpha, numItermax=1000, def barycenter_unbalanced(A, M, reg, alpha, weights=None, numItermax=1000, stopThr=1e-4, verbose=False, log=False): - """Compute the entropic regularized unbalanced wasserstein barycenter of distributions A + r"""Compute the entropic regularized unbalanced wasserstein barycenter of distributions A The function solves the following optimization problem: -- cgit v1.2.3 From a08375c8dc7594e247e586fcc4d65a96771d25c7 Mon Sep 17 00:00:00 2001 From: Romain Tavenard Date: Mon, 1 Jul 2019 15:36:55 +0200 Subject: Fixed all doctests assuming functions are working properly (actually tested in tests/) --- .travis.yml | 5 +- ot/bregman.py | 2 +- ot/stochastic.py | 155 +++++++++++++++++++++++++++++++++++-------------------- ot/unbalanced.py | 2 +- 4 files changed, 104 insertions(+), 60 deletions(-) (limited to 'ot') diff --git a/.travis.yml b/.travis.yml index 275109c..2c6a5c8 100644 --- a/.travis.yml +++ b/.travis.yml @@ -26,8 +26,9 @@ before_script: # configure a headless display to test plot generation # command to install dependencies install: - pip install -r requirements.txt - - pip install numpy>=1.14 # for numpy array formatting in doctests - - pip install "scipy<1.3" # otherwise, pymanopt fails, cf + - pip install numpy>=1.14 "scipy<1.3" # for numpy array formatting in doctests + # ^ scipy version: otherwise, pymanopt fails, cf + - python -c "import numpy; import scipy; print('numpy: ', numpy.__version__); print('scipy: ', scipy.__version__)" - pip install flake8 pytest "pytest-cov<2.6" - pip install . # command to run tests + check syntax style diff --git a/ot/bregman.py b/ot/bregman.py index caf4024..50f8389 100644 --- a/ot/bregman.py +++ b/ot/bregman.py @@ -1559,7 +1559,7 @@ def empirical_sinkhorn_divergence(X_s, X_t, reg, a=None, b=None, metric='sqeucli >>> X_s = np.reshape(np.arange(n_s), (n_s, 1)) >>> X_t = np.reshape(np.arange(0, n_t), (n_t, 1)) >>> empirical_sinkhorn_divergence(X_s, X_t, reg) - array([2.99977435]) + array([1.49988718]) References diff --git a/ot/stochastic.py b/ot/stochastic.py index 762eb3e..bf3e7a7 100644 --- a/ot/stochastic.py +++ b/ot/stochastic.py @@ -52,19 +52,23 @@ def coordinate_grad_semi_dual(b, M, reg, beta, i): Examples -------- >>> import ot + >>> np.random.seed(0) >>> n_source = 7 >>> n_target = 4 - >>> reg = 1 - >>> numItermax = 300000 >>> a = ot.utils.unif(n_source) >>> b = ot.utils.unif(n_target) - >>> rng = np.random.RandomState(0) - >>> X_source = rng.randn(n_source, 2) - >>> Y_target = rng.randn(n_target, 2) + >>> X_source = np.random.randn(n_source, 2) + >>> Y_target = np.random.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) - >>> method = "ASGD" - >>> asgd_pi = ot.stochastic.solve_semi_dual_entropic(a, b, M, reg, method, numItermax) - >>> print(asgd_pi) + >>> ot.stochastic.solve_semi_dual_entropic(a, b, M, reg=1, method="ASGD", numItermax=300000) + array([[2.53942342e-02, 9.98640673e-02, 1.75945647e-02, 4.27664307e-06], + [1.21556999e-01, 1.26350515e-02, 1.30491795e-03, 7.36017394e-03], + [3.54070702e-03, 7.63581358e-02, 6.29581672e-02, 1.32812798e-07], + [2.60578198e-02, 3.35916645e-02, 8.28023223e-02, 4.05336238e-04], + [9.86808864e-03, 7.59774324e-04, 1.08702729e-02, 1.21359007e-01], + [2.17218856e-02, 9.12931802e-04, 1.87962526e-03, 1.18342700e-01], + [4.14237512e-02, 2.67487857e-02, 7.23016955e-02, 2.38291052e-03]]) + References ---------- @@ -133,19 +137,22 @@ def sag_entropic_transport(a, b, M, reg, numItermax=10000, lr=None): Examples -------- >>> import ot + >>> np.random.seed(0) >>> n_source = 7 >>> n_target = 4 - >>> reg = 1 - >>> numItermax = 300000 >>> a = ot.utils.unif(n_source) >>> b = ot.utils.unif(n_target) - >>> rng = np.random.RandomState(0) - >>> X_source = rng.randn(n_source, 2) - >>> Y_target = rng.randn(n_target, 2) + >>> X_source = np.random.randn(n_source, 2) + >>> Y_target = np.random.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) - >>> method = "ASGD" - >>> asgd_pi = ot.stochastic.solve_semi_dual_entropic(a, b, M, reg, method, numItermax) - >>> print(asgd_pi) + >>> ot.stochastic.solve_semi_dual_entropic(a, b, M, reg=1, method="ASGD", numItermax=300000) + array([[2.53942342e-02, 9.98640673e-02, 1.75945647e-02, 4.27664307e-06], + [1.21556999e-01, 1.26350515e-02, 1.30491795e-03, 7.36017394e-03], + [3.54070702e-03, 7.63581358e-02, 6.29581672e-02, 1.32812798e-07], + [2.60578198e-02, 3.35916645e-02, 8.28023223e-02, 4.05336238e-04], + [9.86808864e-03, 7.59774324e-04, 1.08702729e-02, 1.21359007e-01], + [2.17218856e-02, 9.12931802e-04, 1.87962526e-03, 1.18342700e-01], + [4.14237512e-02, 2.67487857e-02, 7.23016955e-02, 2.38291052e-03]]) References ---------- @@ -222,19 +229,22 @@ def averaged_sgd_entropic_transport(a, b, M, reg, numItermax=300000, lr=None): Examples -------- >>> import ot + >>> np.random.seed(0) >>> n_source = 7 >>> n_target = 4 - >>> reg = 1 - >>> numItermax = 300000 >>> a = ot.utils.unif(n_source) >>> b = ot.utils.unif(n_target) - >>> rng = np.random.RandomState(0) - >>> X_source = rng.randn(n_source, 2) - >>> Y_target = rng.randn(n_target, 2) + >>> X_source = np.random.randn(n_source, 2) + >>> Y_target = np.random.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) - >>> method = "ASGD" - >>> asgd_pi = ot.stochastic.solve_semi_dual_entropic(a, b, M, reg, method, numItermax) - >>> print(asgd_pi) + >>> ot.stochastic.solve_semi_dual_entropic(a, b, M, reg=1, method="ASGD", numItermax=300000) + array([[2.53942342e-02, 9.98640673e-02, 1.75945647e-02, 4.27664307e-06], + [1.21556999e-01, 1.26350515e-02, 1.30491795e-03, 7.36017394e-03], + [3.54070702e-03, 7.63581358e-02, 6.29581672e-02, 1.32812798e-07], + [2.60578198e-02, 3.35916645e-02, 8.28023223e-02, 4.05336238e-04], + [9.86808864e-03, 7.59774324e-04, 1.08702729e-02, 1.21359007e-01], + [2.17218856e-02, 9.12931802e-04, 1.87962526e-03, 1.18342700e-01], + [4.14237512e-02, 2.67487857e-02, 7.23016955e-02, 2.38291052e-03]]) References ---------- @@ -301,19 +311,22 @@ def c_transform_entropic(b, M, reg, beta): Examples -------- >>> import ot + >>> np.random.seed(0) >>> n_source = 7 >>> n_target = 4 - >>> reg = 1 - >>> numItermax = 300000 >>> a = ot.utils.unif(n_source) >>> b = ot.utils.unif(n_target) - >>> rng = np.random.RandomState(0) - >>> X_source = rng.randn(n_source, 2) - >>> Y_target = rng.randn(n_target, 2) + >>> X_source = np.random.randn(n_source, 2) + >>> Y_target = np.random.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) - >>> method = "ASGD" - >>> asgd_pi = ot.stochastic.solve_semi_dual_entropic(a, b, M, reg, method, numItermax) - >>> print(asgd_pi) + >>> ot.stochastic.solve_semi_dual_entropic(a, b, M, reg=1, method="ASGD", numItermax=300000) + array([[2.53942342e-02, 9.98640673e-02, 1.75945647e-02, 4.27664307e-06], + [1.21556999e-01, 1.26350515e-02, 1.30491795e-03, 7.36017394e-03], + [3.54070702e-03, 7.63581358e-02, 6.29581672e-02, 1.32812798e-07], + [2.60578198e-02, 3.35916645e-02, 8.28023223e-02, 4.05336238e-04], + [9.86808864e-03, 7.59774324e-04, 1.08702729e-02, 1.21359007e-01], + [2.17218856e-02, 9.12931802e-04, 1.87962526e-03, 1.18342700e-01], + [4.14237512e-02, 2.67487857e-02, 7.23016955e-02, 2.38291052e-03]]) References ---------- @@ -395,19 +408,22 @@ def solve_semi_dual_entropic(a, b, M, reg, method, numItermax=10000, lr=None, Examples -------- >>> import ot + >>> np.random.seed(0) >>> n_source = 7 >>> n_target = 4 - >>> reg = 1 - >>> numItermax = 300000 >>> a = ot.utils.unif(n_source) >>> b = ot.utils.unif(n_target) - >>> rng = np.random.RandomState(0) - >>> X_source = rng.randn(n_source, 2) - >>> Y_target = rng.randn(n_target, 2) + >>> X_source = np.random.randn(n_source, 2) + >>> Y_target = np.random.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) - >>> method = "ASGD" - >>> asgd_pi = ot.stochastic.solve_semi_dual_entropic(a, b, M, reg, method, numItermax) - >>> print(asgd_pi) + >>> ot.stochastic.solve_semi_dual_entropic(a, b, M, reg=1, method="ASGD", numItermax=300000) + array([[2.53942342e-02, 9.98640673e-02, 1.75945647e-02, 4.27664307e-06], + [1.21556999e-01, 1.26350515e-02, 1.30491795e-03, 7.36017394e-03], + [3.54070702e-03, 7.63581358e-02, 6.29581672e-02, 1.32812798e-07], + [2.60578198e-02, 3.35916645e-02, 8.28023223e-02, 4.05336238e-04], + [9.86808864e-03, 7.59774324e-04, 1.08702729e-02, 1.21359007e-01], + [2.17218856e-02, 9.12931802e-04, 1.87962526e-03, 1.18342700e-01], + [4.14237512e-02, 2.67487857e-02, 7.23016955e-02, 2.38291052e-03]]) References ---------- @@ -502,22 +518,28 @@ def batch_grad_dual(a, b, M, reg, alpha, beta, batch_size, batch_alpha, Examples -------- >>> import ot + >>> np.random.seed(0) >>> n_source = 7 >>> n_target = 4 - >>> reg = 1 - >>> numItermax = 20000 - >>> lr = 0.1 - >>> batch_size = 3 - >>> log = True >>> a = ot.utils.unif(n_source) >>> b = ot.utils.unif(n_target) - >>> rng = np.random.RandomState(0) - >>> X_source = rng.randn(n_source, 2) - >>> Y_target = rng.randn(n_target, 2) + >>> X_source = np.random.randn(n_source, 2) + >>> Y_target = np.random.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) - >>> sgd_dual_pi, log = ot.stochastic.solve_dual_entropic(a, b, M, reg, batch_size, numItermax, lr, log) - >>> print(log['alpha'], log['beta']) - >>> print(sgd_dual_pi) + >>> sgd_dual_pi, log = ot.stochastic.solve_dual_entropic(a, b, M, reg=1, batch_size=3, numItermax=30000, lr=0.1, log=True) + >>> log['alpha'] + array([0.71759102, 1.57057384, 0.85576566, 0.1208211 , 0.59190466, + 1.197148 , 0.17805133]) + >>> log['beta'] + array([0.49741367, 0.57478564, 1.40075528, 2.75890102]) + >>> sgd_dual_pi + array([[2.09730063e-02, 8.38169324e-02, 7.50365455e-03, 8.72731415e-09], + [5.58432437e-03, 5.89881299e-04, 3.09558411e-05, 8.35469849e-07], + [3.26489515e-03, 7.15536035e-02, 2.99778211e-02, 3.02601593e-10], + [4.05390622e-02, 5.31085068e-02, 6.65191787e-02, 1.55812785e-06], + [7.82299812e-02, 6.12099102e-03, 4.44989098e-02, 2.37719187e-03], + [5.06266486e-02, 2.16230494e-03, 2.26215141e-03, 6.81514609e-04], + [6.06713990e-02, 3.98139808e-02, 5.46829338e-02, 8.62371424e-06]]) References ---------- @@ -526,7 +548,6 @@ def batch_grad_dual(a, b, M, reg, alpha, beta, batch_size, batch_alpha, International Conference on Learning Representation (2018), arXiv preprint arxiv:1711.02283. ''' - G = - (np.exp((alpha[batch_alpha, None] + beta[None, batch_beta] - M[batch_alpha, :][:, batch_beta]) / reg) * a[batch_alpha, None] * b[None, batch_beta]) @@ -605,8 +626,19 @@ def sgd_entropic_regularization(a, b, M, reg, batch_size, numItermax, lr): >>> Y_target = rng.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) >>> sgd_dual_pi, log = ot.stochastic.solve_dual_entropic(a, b, M, reg, batch_size, numItermax, lr, log) - >>> print(log['alpha'], log['beta']) - >>> print(sgd_dual_pi) + >>> log['alpha'] + array([0.64171798, 1.27932201, 0.78132257, 0.15638935, 0.54888354, + 1.03663469, 0.20595781]) + >>> log['beta'] + array([0.51207194, 0.58033189, 1.28922676, 2.26859736]) + >>> sgd_dual_pi + array([[1.97276541e-02, 7.81248547e-02, 6.22136048e-03, 4.95442423e-09], + [4.23494310e-03, 4.43286263e-04, 2.06927079e-05, 3.82389139e-07], + [3.07542414e-03, 6.67897769e-02, 2.48904999e-02, 1.72030247e-10], + [4.26271990e-02, 5.53375455e-02, 6.16535024e-02, 9.88812650e-07], + [7.60423265e-02, 5.89585256e-03, 3.81267087e-02, 1.39458256e-03], + [4.37557504e-02, 1.85189176e-03, 1.72335760e-03, 3.55491279e-04], + [6.33096109e-02, 4.11683954e-02, 5.02962051e-02, 5.43097516e-06]]) References ---------- @@ -701,8 +733,19 @@ def solve_dual_entropic(a, b, M, reg, batch_size, numItermax=10000, lr=1, >>> Y_target = rng.randn(n_target, 2) >>> M = ot.dist(X_source, Y_target) >>> sgd_dual_pi, log = ot.stochastic.solve_dual_entropic(a, b, M, reg, batch_size, numItermax, lr, log) - >>> print(log['alpha'], log['beta']) - >>> print(sgd_dual_pi) + >>> log['alpha'] + array([0.64057733, 1.2683513 , 0.75610161, 0.16024284, 0.54926534, + 1.0514201 , 0.19958936]) + >>> log['beta'] + array([0.51372571, 0.58843489, 1.27993921, 2.24344807]) + >>> sgd_dual_pi + array([[1.97377795e-02, 7.86706853e-02, 6.15682001e-03, 4.82586997e-09], + [4.19566963e-03, 4.42016865e-04, 2.02777272e-05, 3.68823708e-07], + [3.00379244e-03, 6.56562018e-02, 2.40462171e-02, 1.63579656e-10], + [4.28626062e-02, 5.60031599e-02, 6.13193826e-02, 9.67977735e-07], + [7.61972739e-02, 5.94609051e-03, 3.77886693e-02, 1.36046648e-03], + [4.44810042e-02, 1.89476742e-03, 1.73285847e-03, 3.51826036e-04], + [6.30118293e-02, 4.12398660e-02, 4.95148998e-02, 5.26247246e-06]]) References ---------- diff --git a/ot/unbalanced.py b/ot/unbalanced.py index b2b7b10..4a2af8a 100644 --- a/ot/unbalanced.py +++ b/ot/unbalanced.py @@ -290,7 +290,7 @@ def sinkhorn_knopp_unbalanced(a, b, M, reg, alpha, numItermax=1000, >>> a=[.5, .15] >>> b=[.5, .5] >>> M=[[0., 1.],[1., 0.]] - >>> ot.sinkhorn_knopp_unbalanced(a, b, M, 1., 1.) + >>> ot.unbalanced.sinkhorn_knopp_unbalanced(a, b, M, 1., 1.) array([[0.52761554, 0.22392482], [0.10286295, 0.32257641]]) -- cgit v1.2.3 From 8d47d32713a6e2d448fae6db7420e93b4395d5e6 Mon Sep 17 00:00:00 2001 From: Romain Tavenard Date: Tue, 2 Jul 2019 09:44:02 +0200 Subject: Bugfix (python2 in unbalanced) --- ot/unbalanced.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'ot') diff --git a/ot/unbalanced.py b/ot/unbalanced.py index 4a2af8a..44ab411 100644 --- a/ot/unbalanced.py +++ b/ot/unbalanced.py @@ -6,6 +6,7 @@ Regularized Unbalanced OT # Author: Hicham Janati # License: MIT License +from __future__ import division import warnings import numpy as np # from .utils import unif, dist @@ -287,12 +288,12 @@ def sinkhorn_knopp_unbalanced(a, b, M, reg, alpha, numItermax=1000, -------- >>> import ot - >>> a=[.5, .15] + >>> a=[.5, .5] >>> b=[.5, .5] >>> M=[[0., 1.],[1., 0.]] >>> ot.unbalanced.sinkhorn_knopp_unbalanced(a, b, M, 1., 1.) - array([[0.52761554, 0.22392482], - [0.10286295, 0.32257641]]) + array([[0.51122823, 0.18807035], + [0.18807035, 0.51122823]]) References ---------- -- cgit v1.2.3 From 5b6eb56f2d4bfdaeaa45970c386c42c21d7d1caf Mon Sep 17 00:00:00 2001 From: Romain Tavenard Date: Tue, 2 Jul 2019 09:53:15 +0200 Subject: Fix tolerance in doctest --- ot/bregman.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'ot') diff --git a/ot/bregman.py b/ot/bregman.py index 50f8389..13dfa3b 100644 --- a/ot/bregman.py +++ b/ot/bregman.py @@ -1558,8 +1558,8 @@ def empirical_sinkhorn_divergence(X_s, X_t, reg, a=None, b=None, metric='sqeucli >>> reg = 0.1 >>> X_s = np.reshape(np.arange(n_s), (n_s, 1)) >>> X_t = np.reshape(np.arange(0, n_t), (n_t, 1)) - >>> empirical_sinkhorn_divergence(X_s, X_t, reg) - array([1.49988718]) + >>> empirical_sinkhorn_divergence(X_s, X_t, reg) # doctest: +ELLIPSIS + array([1.499...]) References -- cgit v1.2.3