diff options
| author | tlacombe <lacombe1993@gmail.com> | 2019-12-16 17:19:44 +0100 |
|---|---|---|
| committer | tlacombe <lacombe1993@gmail.com> | 2019-12-16 17:19:44 +0100 |
| commit | efebda596ae5a03dd0f15317ebfe74b5f19c78aa (patch) | |
| tree | c21581669c5dcc985bed33fd043c0999f4e20e7d /src/python | |
| parent | aba9ad68394b0c5aae22c450cac7162733132002 (diff) | |
| parent | 3f1601665cbd0b7397c9c19f55d608246192207b (diff) | |
Merge branch 'master' into wbary-theo
updating master in wbary-theo
Diffstat (limited to 'src/python')
58 files changed, 2320 insertions, 364 deletions
diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index 9e128d30..9af85eac 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -49,6 +49,9 @@ if(PYTHONINTERP_FOUND) set(GUDHI_PYTHON_MODULES "${GUDHI_PYTHON_MODULES}'alpha_complex', ") set(GUDHI_PYTHON_MODULES "${GUDHI_PYTHON_MODULES}'euclidean_witness_complex', ") set(GUDHI_PYTHON_MODULES "${GUDHI_PYTHON_MODULES}'euclidean_strong_witness_complex', ") + # Modules that should not be auto-imported in __init__.py + set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'representations', ") + set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'wasserstein', ") add_gudhi_debug_info("Python version ${PYTHON_VERSION_STRING}") add_gudhi_debug_info("Cython version ${CYTHON_VERSION}") @@ -64,6 +67,12 @@ if(PYTHONINTERP_FOUND) if(SCIPY_FOUND) add_gudhi_debug_info("Scipy version ${SCIPY_VERSION}") endif() + if(SKLEARN_FOUND) + add_gudhi_debug_info("Scikit-learn version ${SKLEARN_VERSION}") + endif() + if(OT_FOUND) + add_gudhi_debug_info("POT version ${OT_VERSION}") + endif() set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'-DBOOST_RESULT_OF_USE_DECLTYPE', ") set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'-DBOOST_ALL_NO_LIB', ") @@ -73,7 +82,7 @@ if(PYTHONINTERP_FOUND) if(MSVC) set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'/fp:strict', ") else(MSVC) - set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'-std=c++11', ") + set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'-std=c++14', ") endif(MSVC) if(CMAKE_COMPILER_IS_GNUCXX) set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'-frounding-math', ") @@ -199,6 +208,8 @@ if(PYTHONINTERP_FOUND) # Other .py files file(COPY "gudhi/persistence_graphical_tools.py" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") + file(COPY "gudhi/representations" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi/") + file(COPY "gudhi/wasserstein.py" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") add_custom_command( OUTPUT gudhi.so @@ -371,37 +382,57 @@ if(PYTHONINTERP_FOUND) # Reader utils add_gudhi_py_test(test_reader_utils) + # Wasserstein + if(OT_FOUND) + add_gudhi_py_test(test_wasserstein_distance) + endif(OT_FOUND) + + # Representations + if(SKLEARN_FOUND AND MATPLOTLIB_FOUND) + add_gudhi_py_test(test_representations) + endif() + # Documentation generation is available through sphinx - requires all modules if(SPHINX_PATH) if(MATPLOTLIB_FOUND) if(NUMPY_FOUND) if(SCIPY_FOUND) - if(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) - set (GUDHI_SPHINX_MESSAGE "Generating API documentation with Sphinx in ${CMAKE_CURRENT_BINARY_DIR}/sphinx/") - # User warning - Sphinx is a static pages generator, and configured to work fine with user_version - # Images and biblio warnings because not found on developper version - if (GUDHI_PYTHON_PATH STREQUAL "src/python") - set (GUDHI_SPHINX_MESSAGE "${GUDHI_SPHINX_MESSAGE} \n WARNING : Sphinx is configured for user version, you run it on developper version. Images and biblio will miss") - endif() - # sphinx target requires gudhi.so, because conf.py reads gudhi version from it - add_custom_target(sphinx - WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/doc - COMMAND ${CMAKE_COMMAND} -E env "PYTHONPATH=${CMAKE_CURRENT_BINARY_DIR}" - ${SPHINX_PATH} -b html ${CMAKE_CURRENT_SOURCE_DIR}/doc ${CMAKE_CURRENT_BINARY_DIR}/sphinx - DEPENDS "${CMAKE_CURRENT_BINARY_DIR}/gudhi.so" - COMMENT "${GUDHI_SPHINX_MESSAGE}" VERBATIM) - - add_test(NAME sphinx_py_test - WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR} - COMMAND ${CMAKE_COMMAND} -E env "PYTHONPATH=${CMAKE_CURRENT_BINARY_DIR}" - ${SPHINX_PATH} -b doctest ${CMAKE_CURRENT_SOURCE_DIR}/doc ${CMAKE_CURRENT_BINARY_DIR}/doctest) - - # Set missing or not modules - set(GUDHI_MODULES ${GUDHI_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MODULES") - else(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) - message("++ Python documentation module will not be compiled because it requires a Eigen3 and CGAL version >= 4.11.0") + if(SKLEARN_FOUND) + if(OT_FOUND) + if(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) + set (GUDHI_SPHINX_MESSAGE "Generating API documentation with Sphinx in ${CMAKE_CURRENT_BINARY_DIR}/sphinx/") + # User warning - Sphinx is a static pages generator, and configured to work fine with user_version + # Images and biblio warnings because not found on developper version + if (GUDHI_PYTHON_PATH STREQUAL "src/python") + set (GUDHI_SPHINX_MESSAGE "${GUDHI_SPHINX_MESSAGE} \n WARNING : Sphinx is configured for user version, you run it on developper version. Images and biblio will miss") + endif() + # sphinx target requires gudhi.so, because conf.py reads gudhi version from it + add_custom_target(sphinx + WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/doc + COMMAND ${CMAKE_COMMAND} -E env "PYTHONPATH=${CMAKE_CURRENT_BINARY_DIR}" + ${SPHINX_PATH} -b html ${CMAKE_CURRENT_SOURCE_DIR}/doc ${CMAKE_CURRENT_BINARY_DIR}/sphinx + DEPENDS "${CMAKE_CURRENT_BINARY_DIR}/gudhi.so" + COMMENT "${GUDHI_SPHINX_MESSAGE}" VERBATIM) + + add_test(NAME sphinx_py_test + WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR} + COMMAND ${CMAKE_COMMAND} -E env "PYTHONPATH=${CMAKE_CURRENT_BINARY_DIR}" + ${SPHINX_PATH} -b doctest ${CMAKE_CURRENT_SOURCE_DIR}/doc ${CMAKE_CURRENT_BINARY_DIR}/doctest) + + # Set missing or not modules + set(GUDHI_MODULES ${GUDHI_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MODULES") + else(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) + message("++ Python documentation module will not be compiled because it requires a Eigen3 and CGAL version >= 4.11.0") + set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") + endif(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) + else(OT_FOUND) + message("++ Python documentation module will not be compiled because POT was not found") + set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") + endif(OT_FOUND) + else(SKLEARN_FOUND) + message("++ Python documentation module will not be compiled because scikit-learn was not found") set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") - endif(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) + endif(SKLEARN_FOUND) else(SCIPY_FOUND) message("++ Python documentation module will not be compiled because scipy was not found") set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") diff --git a/src/python/doc/_templates/layout.html b/src/python/doc/_templates/layout.html index fe64fb3d..2f2d9c72 100644 --- a/src/python/doc/_templates/layout.html +++ b/src/python/doc/_templates/layout.html @@ -56,12 +56,16 @@ </a></p> {%- endif %} {%- endblock %} - <h2><a href="index.html">GUDHI</a></h2> - <h2><a href="fileformats.html">File formats</a></h2> - <h2><a href="installation.html">GUDHI installation</a></h2> - <h2><a href="citation.html">Acknowledging the GUDHI library</a></h2> - <h2><a href="genindex.html">Index</a></h2> - <h2><a href="examples.html">Examples</a></h2> + <b> + <ul style="list-style-type:circle;"> + <li><a href="index.html">Modules</a></li> + <li><a href="installation.html">Installation</a></li> + <li><a href="examples.html">Examples</a></li> + <li><a href="fileformats.html">File formats</a></li> + <li><a href="citation.html">Acknowledging</a></li> + <li><a href="genindex.html">Index</a></li> + </ul> + </b> {%- if sidebars != None %} {#- new style sidebar: explicitly include/exclude templates #} {%- for sidebartemplate in sidebars %} diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index f9662a6d..b7e69e12 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -9,19 +9,19 @@ Definition .. include:: alpha_complex_sum.inc -Alpha_complex is constructing a :doc:`Simplex_tree <simplex_tree_ref>` using +`AlphaComplex` is constructing a :doc:`SimplexTree <simplex_tree_ref>` using `Delaunay Triangulation <http://doc.cgal.org/latest/Triangulation/index.html#Chapter_Triangulations>`_ -:cite:`cgal:hdj-t-15b` from `CGAL <http://www.cgal.org/>`_ (the Computational Geometry Algorithms Library -:cite:`cgal:eb-15b`). +:cite:`cgal:hdj-t-19b` from `CGAL <http://www.cgal.org/>`_ (the Computational Geometry Algorithms Library +:cite:`cgal:eb-19b`). Remarks ^^^^^^^ -When Alpha_complex is constructed with an infinite value of :math:`\alpha`, the complex is a Delaunay complex. +When an :math:`\alpha`-complex is constructed with an infinite value of :math:`\alpha`, the complex is a Delaunay complex (with special filtration values). Example from points ------------------- -This example builds the Delaunay triangulation from the given points, and initializes the alpha complex with it: +This example builds the alpha-complex from the given points: .. testcode:: @@ -139,15 +139,16 @@ Non decreasing filtration values As the squared radii computed by CGAL are an approximation, it might happen that these alpha squared values do not quite define a proper filtration (i.e. non-decreasing with respect to inclusion). -We fix that up by calling `Simplex_tree::make_filtration_non_decreasing()` (cf. +We fix that up by calling :func:`~gudhi.SimplexTree.make_filtration_non_decreasing` (cf. `C++ version <http://gudhi.gforge.inria.fr/doc/latest/index.html>`_). Prune above given filtration value ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -The simplex tree is pruned from the given maximum alpha squared value (cf. `Simplex_tree::prune_above_filtration()` -in the `C++ version <http://gudhi.gforge.inria.fr/doc/latest/index.html>`_). Note that this does not provide any kind -of speed-up, since we always first build the full filtered complex, so it is recommended not to use `max_alpha_square`. +The simplex tree is pruned from the given maximum alpha squared value (cf. +:func:`~gudhi.SimplexTree.prune_above_filtration`). Note that this does not provide any kind +of speed-up, since we always first build the full filtered complex, so it is recommended not to use +:paramref:`~gudhi.AlphaComplex.create_simplex_tree.max_alpha_square`. In the following example, a threshold of 59 is used. diff --git a/src/python/doc/conf.py b/src/python/doc/conf.py index e4c718c3..3cc5d1d6 100755 --- a/src/python/doc/conf.py +++ b/src/python/doc/conf.py @@ -39,7 +39,9 @@ extensions = [ 'sphinx.ext.mathjax', 'sphinx.ext.ifconfig', 'sphinx.ext.viewcode', + 'sphinx.ext.napoleon', 'sphinxcontrib.bibtex', + 'sphinx_paramlinks', ] todo_include_todos = True diff --git a/src/python/doc/examples.rst b/src/python/doc/examples.rst index edbc2f72..a42227e3 100644 --- a/src/python/doc/examples.rst +++ b/src/python/doc/examples.rst @@ -16,6 +16,9 @@ Examples * :download:`periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py <../example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py>` * :download:`bottleneck_basic_example.py <../example/bottleneck_basic_example.py>` * :download:`gudhi_graphical_tools_example.py <../example/gudhi_graphical_tools_example.py>` + * :download:`plot_simplex_tree_dim012.py <../example/plot_simplex_tree_dim012.py>` + * :download:`plot_rips_complex.py <../example/plot_rips_complex.py>` + * :download:`plot_alpha_complex.py <../example/plot_alpha_complex.py>` * :download:`witness_complex_from_nearest_landmark_table.py <../example/witness_complex_from_nearest_landmark_table.py>` * :download:`euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py>` * :download:`euclidean_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py>` diff --git a/src/python/doc/img/sklearn-tda.png b/src/python/doc/img/sklearn-tda.png Binary files differnew file mode 100644 index 00000000..f0ff07f4 --- /dev/null +++ b/src/python/doc/img/sklearn-tda.png diff --git a/src/python/doc/index.rst b/src/python/doc/index.rst index e379bc23..c36a578f 100644 --- a/src/python/doc/index.rst +++ b/src/python/doc/index.rst @@ -1,5 +1,5 @@ -GUDHI Python module documentation -################################# +GUDHI Python modules documentation +################################## .. figure:: ../../doc/common/Gudhi_banner.png @@ -23,7 +23,7 @@ Alpha complex .. include:: alpha_complex_sum.inc Rips complex -------------- +------------ .. include:: rips_complex_sum.inc @@ -73,6 +73,16 @@ Bottleneck distance .. include:: bottleneck_distance_sum.inc +Wasserstein distance +==================== + +.. include:: wasserstein_distance_sum.inc + +Persistence representations +=========================== + +.. include:: representations_sum.inc + Persistence graphical tools =========================== diff --git a/src/python/doc/installation.rst b/src/python/doc/installation.rst index 5a6ad9f4..50a697c7 100644 --- a/src/python/doc/installation.rst +++ b/src/python/doc/installation.rst @@ -8,11 +8,11 @@ Installation Conda ***** The easiest way to install the Python version of GUDHI is using -`conda <https://gudhi.inria.fr/licensing/>`_. +`conda <https://gudhi.inria.fr/conda/>`_. Compiling ********* -The library uses c++11 and requires `Boost <https://www.boost.org/>`_ ≥ 1.56.0, +The library uses c++14 and requires `Boost <https://www.boost.org/>`_ ≥ 1.56.0, `CMake <https://www.cmake.org/>`_ ≥ 3.1 to generate makefiles, `NumPy <http://numpy.org>`_ and `Cython <https://www.cython.org/>`_ to compile the GUDHI Python module. @@ -40,6 +40,20 @@ To build the GUDHI Python module, run the following commands in a terminal: cd python make +.. note:: + + :code:`make python` (or :code:`make` in python directory) is only a + `CMake custom targets <https://cmake.org/cmake/help/latest/command/add_custom_target.html>`_ + to shortcut :code:`python setup.py build_ext --inplace` command. + No specific other options (:code:`-j8` for parallel, or even :code:`make clean`, ...) are + available. + But one can use :code:`python setup.py ...` specific options in the python directory: + +.. code-block:: bash + + python setup.py clean --all # Clean former compilation + python setup.py build_ext -j 8 --inplace # Build in parallel + GUDHI Python module installation ================================ @@ -59,19 +73,40 @@ Or install it definitely in your Python packages folder: # May require sudo or administrator privileges make install +.. note:: + + :code:`make install` is only a + `CMake custom targets <https://cmake.org/cmake/help/latest/command/add_custom_target.html>`_ + to shortcut :code:`python setup.py install` command. + It does not take into account :code:`CMAKE_INSTALL_PREFIX`. + But one can use :code:`python setup.py install ...` specific options in the python directory: + +.. code-block:: bash + + python setup.py install --prefix /home/gudhi # Install in /home/gudhi directory Test suites =========== -To test your build, `py.test <http://doc.pytest.org>`_ is optional. Run the -following command in a terminal: +To test your build, `py.test <http://doc.pytest.org>`_ is required. Run the +following `Ctest <https://cmake.org/cmake/help/latest/manual/ctest.1.html>`_ +(CMake test driver program) command in a terminal: .. code-block:: bash cd /path-to-gudhi/build/python # For windows, you have to set PYTHONPATH environment variable export PYTHONPATH='$PYTHONPATH:/path-to-gudhi/build/python' - make test + ctest + +.. note:: + + One can use :code:`ctest` specific options in the python directory: + +.. code-block:: bash + + # Launch tests in parallel on 8 cores and set failing tests in verbose mode + ctest -j 8 --output-on-failure Debugging issues ================ @@ -215,12 +250,20 @@ The following examples require the `Matplotlib <http://matplotlib.org>`_: * :download:`euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py>` * :download:`euclidean_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py>` +Python Optimal Transport +======================== + +The :doc:`Wasserstein distance </wasserstein_distance_user>` +module requires `POT <https://pot.readthedocs.io/>`_, a library that provides +several solvers for optimization problems related to Optimal Transport. + SciPy ===== -The :doc:`persistence graphical tools </persistence_graphical_tools_user>` -module requires `SciPy <http://scipy.org>`_, a Python-based ecosystem of -open-source software for mathematics, science, and engineering. +The :doc:`persistence graphical tools </persistence_graphical_tools_user>` and +:doc:`Wasserstein distance </wasserstein_distance_user>` modules require `SciPy +<http://scipy.org>`_, a Python-based ecosystem of open-source software for +mathematics, science, and engineering. Threading Building Blocks ========================= diff --git a/src/python/doc/persistence_graphical_tools_user.rst b/src/python/doc/persistence_graphical_tools_user.rst index b2124fdd..f41a926b 100644 --- a/src/python/doc/persistence_graphical_tools_user.rst +++ b/src/python/doc/persistence_graphical_tools_user.rst @@ -20,6 +20,7 @@ This function can display the persistence result as a barcode: .. plot:: :include-source: + import matplotlib.pyplot as plot import gudhi off_file = gudhi.__root_source_dir__ + '/data/points/tore3D_300.off' @@ -29,7 +30,7 @@ This function can display the persistence result as a barcode: simplex_tree = rips_complex.create_simplex_tree(max_dimension=3) diag = simplex_tree.persistence(min_persistence=0.4) - plot = gudhi.plot_persistence_barcode(diag) + gudhi.plot_persistence_barcode(diag) plot.show() Show persistence as a diagram @@ -43,14 +44,15 @@ This function can display the persistence result as a diagram: .. plot:: :include-source: + import matplotlib.pyplot as plot import gudhi # rips_on_tore3D_1307.pers obtained from write_persistence_diagram method persistence_file=gudhi.__root_source_dir__ + \ '/data/persistence_diagram/rips_on_tore3D_1307.pers' - plt = gudhi.plot_persistence_diagram(persistence_file=persistence_file, + gudhi.plot_persistence_diagram(persistence_file=persistence_file, legend=True) - plt.show() + plot.show() Persistence density ------------------- @@ -63,11 +65,19 @@ If you want more information on a specific dimension, for instance: .. plot:: :include-source: + import matplotlib.pyplot as plot import gudhi - # rips_on_tore3D_1307.pers obtained from write_persistence_diagram method persistence_file=gudhi.__root_source_dir__ + \ '/data/persistence_diagram/rips_on_tore3D_1307.pers' - plt = gudhi.plot_persistence_density(persistence_file=persistence_file, - max_intervals=0, dimension=1, legend=True) - plt.show() + birth_death = gudhi.read_persistence_intervals_in_dimension( + persistence_file=persistence_file, + only_this_dim=1) + pers_diag = [(1, elt) for elt in birth_death] + # Use subplots to display diagram and density side by side + fig, axes = plot.subplots(nrows=1, ncols=2, figsize=(12, 5)) + gudhi.plot_persistence_diagram(persistence=pers_diag, + axes=axes[0]) + gudhi.plot_persistence_density(persistence=pers_diag, + dimension=1, legend=True, axes=axes[1]) + plot.show() diff --git a/src/python/doc/representations.rst b/src/python/doc/representations.rst new file mode 100644 index 00000000..11dcbcf9 --- /dev/null +++ b/src/python/doc/representations.rst @@ -0,0 +1,72 @@ +:orphan: + +.. To get rid of WARNING: document isn't included in any toctree + +====================== +Representations manual +====================== + +.. include:: representations_sum.inc + +This module, originally available at https://github.com/MathieuCarriere/sklearn-tda and named sklearn_tda, aims at bridging the gap between persistence diagrams and machine learning, by providing implementations of most of the vector representations for persistence diagrams in the literature, in a scikit-learn format. More specifically, it provides tools, using the scikit-learn standard interface, to compute distances and kernels on persistence diagrams, and to convert these diagrams into vectors in Euclidean space. + +A diagram is represented as a numpy array of shape (n,2), as can be obtained from :func:`~gudhi.SimplexTree.persistence_intervals_in_dimension` for instance. Points at infinity are represented as a numpy array of shape (n,1), storing only the birth time. + +A small example is provided + +.. only:: builder_html + + * :download:`diagram_vectorizations_distances_kernels.py <../example/diagram_vectorizations_distances_kernels.py>` + + +Preprocessing +------------- +.. automodule:: gudhi.representations.preprocessing + :members: + :special-members: + :show-inheritance: + +Vector methods +-------------- +.. automodule:: gudhi.representations.vector_methods + :members: + :special-members: + :show-inheritance: + +Kernel methods +-------------- +.. automodule:: gudhi.representations.kernel_methods + :members: + :special-members: + :show-inheritance: + +Metrics +------- +.. automodule:: gudhi.representations.metrics + :members: + :special-members: + :show-inheritance: + +Basic example +------------- + +This example computes the first two Landscapes associated to a persistence diagram with four points. The landscapes are evaluated on ten samples, leading to two vectors with ten coordinates each, that are eventually concatenated in order to produce a single vector representation. + +.. testcode:: + + import numpy as np + from gudhi.representations import Landscape + # A single diagram with 4 points + D = np.array([[0.,4.],[1.,2.],[3.,8.],[6.,8.]]) + diags = [D] + l=Landscape(num_landscapes=2,resolution=10).fit_transform(diags) + print(l) + +The output is: + +.. testoutput:: + + [[1.02851895 2.05703791 2.57129739 1.54277843 0.89995409 1.92847304 + 2.95699199 3.08555686 2.05703791 1.02851895 0. 0.64282435 + 0. 0. 0.51425948 0. 0. 0. + 0.77138922 1.02851895]] diff --git a/src/python/doc/representations_sum.inc b/src/python/doc/representations_sum.inc new file mode 100644 index 00000000..700828f1 --- /dev/null +++ b/src/python/doc/representations_sum.inc @@ -0,0 +1,14 @@ +.. table:: + :widths: 30 50 20 + + +------------------------------------------------------------------+----------------------------------------------------------------+-----------------------------------------------+ + | .. figure:: | Vectorizations, distances and kernels that work on persistence | :Author: Mathieu Carrière | + | img/sklearn-tda.png | diagrams, compatible with scikit-learn. | | + | | | :Introduced in: GUDHI 3.1.0 | + | | | | + | | | :Copyright: MIT | + | | | | + | | | :Requires: scikit-learn | + +------------------------------------------------------------------+----------------------------------------------------------------+-----------------------------------------------+ + | * :doc:`representations` | + +------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/rips_complex_user.rst b/src/python/doc/rips_complex_user.rst index 3f6b960d..a8659542 100644 --- a/src/python/doc/rips_complex_user.rst +++ b/src/python/doc/rips_complex_user.rst @@ -40,12 +40,12 @@ A vertex name corresponds to the index of the point in the given range (aka. the On this example, as edges (4,5), (4,6) and (5,6) are in the complex, simplex (4,5,6) is added with the filtration value set with :math:`max(filtration(4,5), filtration(4,6), filtration(5,6))`. And so on for simplex (0,1,2,3). -If the `RipsComplex` interfaces are not detailed enough for your need, please refer to rips_persistence_step_by_step.cpp -C++ example, where the graph construction over the Simplex_tree is more detailed. +If the :doc:`RipsComplex <rips_complex_ref>` interfaces are not detailed enough for your need, please refer to +rips_persistence_step_by_step.cpp C++ example, where the graph construction over the Simplex_tree is more detailed. A Rips complex can easily become huge, even if we limit the length of the edges and the dimension of the simplices. One easy trick, before building a Rips -complex on a point cloud, is to call `sparsify_point_set` which removes points +complex on a point cloud, is to call :func:`~gudhi.sparsify_point_set` which removes points that are too close to each other. This does not change its persistence diagram by more than the length used to define "too close". @@ -57,7 +57,7 @@ a :math:`\frac{1}{1-\varepsilon}`-interleaving, although in practice the error is usually smaller. A more intuitive presentation of the idea is available in :cite:`cavanna15geometric`, and in a video :cite:`cavanna15visualizing`. Passing an extra argument `sparse=0.3` at the -construction of a `RipsComplex` object asks it to build a sparse Rips with +construction of a :class:`~gudhi.RipsComplex` object asks it to build a sparse Rips with parameter :math:`\varepsilon=0.3`, while the default `sparse=None` builds the regular Rips complex. @@ -69,7 +69,7 @@ Example from a point cloud ^^^^^^^^^^^^^^^^^^^^^^^^^^ This example builds the neighborhood graph from the given points, up to max_edge_length. -Then it creates a :doc:`Simplex_tree <simplex_tree_ref>` with it. +Then it creates a :doc:`SimplexTree <simplex_tree_ref>` with it. Finally, it is asked to display information about the simplicial complex. @@ -128,7 +128,7 @@ Example from OFF file This example builds the :doc:`RipsComplex <rips_complex_ref>` from the given points in an OFF file, and max_edge_length value. -Then it creates a :doc:`Simplex_tree <simplex_tree_ref>` with it. +Then it creates a :doc:`SimplexTree <simplex_tree_ref>` with it. Finally, it is asked to display information about the Rips complex. @@ -178,7 +178,7 @@ Example from a distance matrix ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ This example builds the one skeleton graph from the given distance matrix, and max_edge_length value. -Then it creates a :doc:`Simplex_tree <simplex_tree_ref>` with it. +Then it creates a :doc:`SimplexTree <simplex_tree_ref>` with it. Finally, it is asked to display information about the simplicial complex. @@ -233,7 +233,7 @@ Example from csv file This example builds the :doc:`RipsComplex <rips_complex_ref>` from the given distance matrix in a csv file, and max_edge_length value. -Then it creates a :doc:`Simplex_tree <simplex_tree_ref>` with it. +Then it creates a :doc:`SimplexTree <simplex_tree_ref>` with it. Finally, it is asked to display information about the Rips complex. @@ -286,7 +286,7 @@ Example from a correlation matrix Analogously to the case of distance matrix, Rips complexes can be also constructed based on correlation matrix. Given a correlation matrix M, comportment-wise 1-M is a distance matrix. This example builds the one skeleton graph from the given corelation matrix and threshold value. -Then it creates a :doc:`Simplex_tree <simplex_tree_ref>` with it. +Then it creates a :doc:`SimplexTree <simplex_tree_ref>` with it. Finally, it is asked to display information about the simplicial complex. @@ -307,7 +307,7 @@ Finally, it is asked to display information about the simplicial complex. [0.01, 0.01, 0.72, 1., 0.7], [0.89, 0.61, 0.03, 0.7, 1.]], float) - distance_matrix = np.ones((correlation_matrix.shape),float) - correlation_matrix + distance_matrix = 1 - correlation_matrix rips_complex = gudhi.RipsComplex(distance_matrix=distance_matrix, max_edge_length=1.0) simplex_tree = rips_complex.create_simplex_tree(max_dimension=1) @@ -342,6 +342,7 @@ until dimension 1 - one skeleton graph in other words), the output is: [1, 3] -> 0.99 .. note:: - As persistence diagrams points will be under the diagonal, + If you compute the persistence diagram and convert distances back to correlation values, + points in the persistence diagram will be under the diagonal, and bottleneck distance and persistence graphical tool will not work properly, this is a known issue. diff --git a/src/python/doc/simplex_tree_user.rst b/src/python/doc/simplex_tree_user.rst index aebeb29f..3df7617f 100644 --- a/src/python/doc/simplex_tree_user.rst +++ b/src/python/doc/simplex_tree_user.rst @@ -23,13 +23,9 @@ scheme. Implementation -------------- -There are two implementation of complexes. The first on is the Simplex_tree data structure. -The simplex tree is an efficient and flexible data structure for representing general (filtered) simplicial complexes. -The data structure is described in :cite`boissonnatmariasimplextreealgorithmica`. - -The second one is the Hasse_complex. The Hasse complex is a data structure representing explicitly all co-dimension 1 -incidence relations in a complex. It is consequently faster when accessing the boundary of a simplex, but is less -compact and harder to construct from scratch. +The :class:`simplex tree<gudhi.SimplexTree>` is an efficient and flexible data structure for representing general +(filtered) simplicial complexes. +The data structure is described in :cite:`boissonnatmariasimplextreealgorithmica`. Example ------- diff --git a/src/python/doc/tangential_complex_user.rst b/src/python/doc/tangential_complex_user.rst index ebfe1e29..852cf5b6 100644 --- a/src/python/doc/tangential_complex_user.rst +++ b/src/python/doc/tangential_complex_user.rst @@ -107,12 +107,12 @@ inconsistencies, but is not guaranteed to succeed. Output ^^^^^^ -The result of the computation is exported as a Simplex_tree. It is the union of +The result of the computation is exported as a :class:`~gudhi.SimplexTree`. It is the union of the stars of all the input points. A vertex in the Simplex Tree is the index of the point in the range provided by the user. The point corresponding to a -vertex can also be obtained through the Tangential_complex::get_point function. +vertex can also be obtained through the :func:`gudhi.TangentialComplex.get_point` function. Note that even if the positions of the points are perturbed, their original -positions are kept (e.g. Tangential_complex::get_point returns the original +positions are kept (e.g. :func:`~gudhi.TangentialComplex.get_point` returns the original position of the point). The result can be obtained after the computation of the Tangential complex diff --git a/src/python/doc/wasserstein_distance_sum.inc b/src/python/doc/wasserstein_distance_sum.inc new file mode 100644 index 00000000..ffd4d312 --- /dev/null +++ b/src/python/doc/wasserstein_distance_sum.inc @@ -0,0 +1,14 @@ +.. table:: + :widths: 30 50 20 + + +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ + | .. figure:: | The p-Wasserstein distance measures the similarity between two | :Author: Theo Lacombe | + | ../../doc/Bottleneck_distance/perturb_pd.png | persistence diagrams. It's the minimum value c that can be achieved | | + | :figclass: align-center | by a perfect matching between the points of the two diagrams (+ all | :Introduced in: GUDHI 3.1.0 | + | | diagonal points), where the value of a matching is defined as the | | + | Wasserstein distance is the p-th root of the sum of the | p-th root of the sum of all edge lengths to the power p. Edge lengths| :Copyright: MIT | + | edge lengths to the power p. | are measured in norm q, for :math:`1 \leq q \leq \infty`. | | + | | | :Requires: Python Optimal Transport (POT) :math:`\geq` 0.5.1 | + +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ + | * :doc:`wasserstein_distance_user` | | + +-----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst new file mode 100644 index 00000000..a049cfb5 --- /dev/null +++ b/src/python/doc/wasserstein_distance_user.rst @@ -0,0 +1,40 @@ +:orphan: + +.. To get rid of WARNING: document isn't included in any toctree + +Wasserstein distance user manual +================================ +Definition +---------- + +.. include:: wasserstein_distance_sum.inc + +This implementation is based on ideas from "Large Scale Computation of Means and Cluster for Persistence Diagrams via Optimal Transport". + +Function +-------- +.. autofunction:: gudhi.wasserstein.wasserstein_distance + + +Basic example +------------- + +This example computes the 1-Wasserstein distance from 2 persistence diagrams with euclidean ground metric. +Note that persistence diagrams must be submitted as (n x 2) numpy arrays and must not contain inf values. + +.. testcode:: + + import gudhi.wasserstein + import numpy as np + + diag1 = np.array([[2.7, 3.7],[9.6, 14.],[34.2, 34.974]]) + diag2 = np.array([[2.8, 4.45],[9.5, 14.1]]) + + message = "Wasserstein distance value = " + '%.2f' % gudhi.wasserstein.wasserstein_distance(diag1, diag2, q=2., p=1.) + print(message) + +The output is: + +.. testoutput:: + + Wasserstein distance value = 1.45 diff --git a/src/python/doc/witness_complex_user.rst b/src/python/doc/witness_complex_user.rst index 40e94134..45ba5b3b 100644 --- a/src/python/doc/witness_complex_user.rst +++ b/src/python/doc/witness_complex_user.rst @@ -47,7 +47,7 @@ which leads to definitions of **weak relaxed witness complex** (or just relaxed In particular case of 0-relaxation, weak complex corresponds to **witness complex** introduced in :cite:`de2004topological`, whereas 0-relaxed strong witness complex consists of just vertices and is not very interesting. Hence for small relaxation weak version is preferable. -However, to capture the homotopy type (for example using Gudhi::persistent_cohomology::Persistent_cohomology) it is +However, to capture the homotopy type (for example using :func:`gudhi.SimplexTree.persistence`) it is often necessary to work with higher filtration values. In this case strong relaxed witness complex is faster to compute and offers similar results. @@ -69,7 +69,7 @@ The construction of the Euclidean versions of complexes follow the same scheme: In the non-Euclidean classes, the lists of nearest landmarks are supposed to be given as input. -The constructors take on the steps 1 and 2, while the function 'create_complex' executes the step 3. +The constructors take on the steps 1 and 2, while the function :func:`!create_complex` executes the step 3. Constructing weak relaxed witness complex from an off file ---------------------------------------------------------- diff --git a/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py b/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py index b8f283b3..4079a469 100755 --- a/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py @@ -1,7 +1,8 @@ #!/usr/bin/env python -import gudhi import argparse +import matplotlib.pyplot as plot +import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. @@ -60,8 +61,8 @@ with open(args.file, "r") as f: print(simplex_tree.betti_numbers()) if args.no_diagram == False: - pplot = gudhi.plot_persistence_diagram(diag, band=args.band) - pplot.show() + gudhi.plot_persistence_diagram(diag, band=args.band) + plot.show() else: print(args.file, "is not a valid OFF file") diff --git a/src/python/example/diagram_vectorizations_distances_kernels.py b/src/python/example/diagram_vectorizations_distances_kernels.py new file mode 100755 index 00000000..119072eb --- /dev/null +++ b/src/python/example/diagram_vectorizations_distances_kernels.py @@ -0,0 +1,133 @@ +#!/usr/bin/env python + +import matplotlib.pyplot as plt +import numpy as np +from sklearn.kernel_approximation import RBFSampler +from sklearn.preprocessing import MinMaxScaler + +from gudhi.representations import DiagramSelector, Clamping, Landscape, Silhouette, BettiCurve, ComplexPolynomial,\ + TopologicalVector, DiagramScaler, BirthPersistenceTransform,\ + PersistenceImage, PersistenceWeightedGaussianKernel, Entropy, \ + PersistenceScaleSpaceKernel, SlicedWassersteinDistance,\ + SlicedWassersteinKernel, BottleneckDistance, PersistenceFisherKernel + +D = np.array([[0.,4.],[1.,2.],[3.,8.],[6.,8.], [0., np.inf], [5., np.inf]]) +diags = [D] + +diags = DiagramSelector(use=True, point_type="finite").fit_transform(diags) +diags = DiagramScaler(use=True, scalers=[([0,1], MinMaxScaler())]).fit_transform(diags) +diags = DiagramScaler(use=True, scalers=[([1], Clamping(maximum=.9))]).fit_transform(diags) + +D = diags[0] +plt.scatter(D[:,0],D[:,1]) +plt.plot([0.,1.],[0.,1.]) +plt.title("Test Persistence Diagram for vector methods") +plt.show() + +LS = Landscape(resolution=1000) +L = LS.fit_transform(diags) +plt.plot(L[0][:1000]) +plt.plot(L[0][1000:2000]) +plt.plot(L[0][2000:3000]) +plt.title("Landscape") +plt.show() + +def pow(n): + return lambda x: np.power(x[1]-x[0],n) + +SH = Silhouette(resolution=1000, weight=pow(2)) +sh = SH.fit_transform(diags) +plt.plot(sh[0]) +plt.title("Silhouette") +plt.show() + +BC = BettiCurve(resolution=1000) +bc = BC.fit_transform(diags) +plt.plot(bc[0]) +plt.title("Betti Curve") +plt.show() + +CP = ComplexPolynomial(threshold=-1, polynomial_type="T") +cp = CP.fit_transform(diags) +print("Complex polynomial is " + str(cp[0,:])) + +TV = TopologicalVector(threshold=-1) +tv = TV.fit_transform(diags) +print("Topological vector is " + str(tv[0,:])) + +PI = PersistenceImage(bandwidth=.1, weight=lambda x: x[1], im_range=[0,1,0,1], resolution=[100,100]) +pi = PI.fit_transform(diags) +plt.imshow(np.flip(np.reshape(pi[0], [100,100]), 0)) +plt.title("Persistence Image") +plt.show() + +ET = Entropy(mode="scalar") +et = ET.fit_transform(diags) +print("Entropy statistic is " + str(et[0,:])) + +ET = Entropy(mode="vector", normalized=False) +et = ET.fit_transform(diags) +plt.plot(et[0]) +plt.title("Entropy function") +plt.show() + +D = np.array([[1.,5.],[3.,6.],[2.,7.]]) +diags2 = [D] + +diags2 = DiagramScaler(use=True, scalers=[([0,1], MinMaxScaler())]).fit_transform(diags2) + +D = diags[0] +plt.scatter(D[:,0],D[:,1]) +D = diags2[0] +plt.scatter(D[:,0],D[:,1]) +plt.plot([0.,1.],[0.,1.]) +plt.title("Test Persistence Diagrams for kernel methods") +plt.show() + +def arctan(C,p): + return lambda x: C*np.arctan(np.power(x[1], p)) + +PWG = PersistenceWeightedGaussianKernel(bandwidth=1., kernel_approx=None, weight=arctan(1.,1.)) +X = PWG.fit(diags) +Y = PWG.transform(diags2) +print("PWG kernel is " + str(Y[0][0])) + +PWG = PersistenceWeightedGaussianKernel(kernel_approx=RBFSampler(gamma=1./2, n_components=100000).fit(np.ones([1,2])), weight=arctan(1.,1.)) +X = PWG.fit(diags) +Y = PWG.transform(diags2) +print("Approximate PWG kernel is " + str(Y[0][0])) + +PSS = PersistenceScaleSpaceKernel(bandwidth=1.) +X = PSS.fit(diags) +Y = PSS.transform(diags2) +print("PSS kernel is " + str(Y[0][0])) + +PSS = PersistenceScaleSpaceKernel(kernel_approx=RBFSampler(gamma=1./2, n_components=100000).fit(np.ones([1,2]))) +X = PSS.fit(diags) +Y = PSS.transform(diags2) +print("Approximate PSS kernel is " + str(Y[0][0])) + +sW = SlicedWassersteinDistance(num_directions=100) +X = sW.fit(diags) +Y = sW.transform(diags2) +print("SW distance is " + str(Y[0][0])) + +SW = SlicedWassersteinKernel(num_directions=100, bandwidth=1.) +X = SW.fit(diags) +Y = SW.transform(diags2) +print("SW kernel is " + str(Y[0][0])) + +W = BottleneckDistance(epsilon=.001) +X = W.fit(diags) +Y = W.transform(diags2) +print("Bottleneck distance is " + str(Y[0][0])) + +PF = PersistenceFisherKernel(bandwidth_fisher=1., bandwidth=1.) +X = PF.fit(diags) +Y = PF.transform(diags2) +print("PF kernel is " + str(Y[0][0])) + +PF = PersistenceFisherKernel(bandwidth_fisher=1., bandwidth=1., kernel_approx=RBFSampler(gamma=1./2, n_components=100000).fit(np.ones([1,2]))) +X = PF.fit(diags) +Y = PF.transform(diags2) +print("Approximate PF kernel is " + str(Y[0][0])) diff --git a/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py b/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py index 610ba44f..0eedd140 100755 --- a/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py @@ -1,7 +1,8 @@ #!/usr/bin/env python -import gudhi import argparse +import matplotlib.pyplot as plot +import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. @@ -75,8 +76,8 @@ with open(args.file, "r") as f: print(simplex_tree.betti_numbers()) if args.no_diagram == False: - pplot = gudhi.plot_persistence_diagram(diag, band=args.band) - pplot.show() + gudhi.plot_persistence_diagram(diag, band=args.band) + plot.show() else: print(args.file, "is not a valid OFF file") diff --git a/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py b/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py index 7587b732..1fe55737 100755 --- a/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py @@ -1,7 +1,8 @@ #!/usr/bin/env python -import gudhi import argparse +import matplotlib.pyplot as plot +import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. @@ -74,8 +75,8 @@ with open(args.file, "r") as f: print(simplex_tree.betti_numbers()) if args.no_diagram == False: - pplot = gudhi.plot_persistence_diagram(diag, band=args.band) - pplot.show() + gudhi.plot_persistence_diagram(diag, band=args.band) + plot.show() else: print(args.file, "is not a valid OFF file") diff --git a/src/python/example/gudhi_graphical_tools_example.py b/src/python/example/gudhi_graphical_tools_example.py index 3b0ca54d..37ecbf53 100755 --- a/src/python/example/gudhi_graphical_tools_example.py +++ b/src/python/example/gudhi_graphical_tools_example.py @@ -1,5 +1,6 @@ #!/usr/bin/env python +import matplotlib.pyplot as plot import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. @@ -29,15 +30,24 @@ persistence = [ (0, (0.0, 1.0)), ] gudhi.plot_persistence_barcode(persistence) +plot.show() print("#####################################################################") print("Show diagram persistence example") -pplot = gudhi.plot_persistence_diagram(persistence) -pplot.show() +gudhi.plot_persistence_diagram(persistence) +plot.show() print("#####################################################################") print("Show diagram persistence example with a confidence band") -pplot = gudhi.plot_persistence_diagram(persistence, band=0.2) -pplot.show() +gudhi.plot_persistence_diagram(persistence, band=0.2) +plot.show() + +print("#####################################################################") +print("Show barcode and diagram persistence side by side example") +fig, axes = plot.subplots(nrows=1, ncols=2) +gudhi.plot_persistence_barcode(persistence, axes = axes[0]) +gudhi.plot_persistence_diagram(persistence, axes = axes[1]) +fig.suptitle("barcode versus diagram") +plot.show() diff --git a/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py b/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py index 9cb855cd..c692e66f 100755 --- a/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py +++ b/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py @@ -1,7 +1,8 @@ #!/usr/bin/env python -import gudhi import argparse +import matplotlib.pyplot as plot +import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. @@ -70,5 +71,6 @@ if is_file_perseus(args.file): print(periodic_cubical_complex.betti_numbers()) if args.no_barcode == False: gudhi.plot_persistence_barcode(diag) + plot.show() else: print(args.file, "is not a valid perseus style file") diff --git a/src/python/example/plot_alpha_complex.py b/src/python/example/plot_alpha_complex.py new file mode 100755 index 00000000..99c18a7c --- /dev/null +++ b/src/python/example/plot_alpha_complex.py @@ -0,0 +1,37 @@ +#!/usr/bin/env python + +import numpy as np +import gudhi +ac = gudhi.AlphaComplex(off_file='../../data/points/tore3D_1307.off') +st = ac.create_simplex_tree() +points = np.array([ac.get_point(i) for i in range(st.num_vertices())]) +# We want to plot the alpha-complex with alpha=0.1. +# We are only going to plot the triangles +triangles = np.array([s[0] for s in st.get_skeleton(2) if len(s[0])==3 and s[1] <= .1]) + +# First possibility: plotly +import plotly.graph_objects as go +fig = go.Figure(data=[ + go.Mesh3d( + x=points[:,0], + y=points[:,1], + z=points[:,2], + i = triangles[:,0], + j = triangles[:,1], + k = triangles[:,2], + ) +]) +fig.show() + +# Second possibility: matplotlib +from mpl_toolkits.mplot3d import Axes3D +import matplotlib.pyplot as plt +fig = plt.figure() +ax = fig.gca(projection='3d') +ax.plot_trisurf(points[:,0], points[:,1], points[:,2], triangles=triangles) +plt.show() + +# Third possibility: mayavi +from mayavi import mlab +mlab.triangular_mesh(points[:,0], points[:,1], points[:,2], triangles); +mlab.show() diff --git a/src/python/example/plot_rips_complex.py b/src/python/example/plot_rips_complex.py new file mode 100755 index 00000000..1c878db1 --- /dev/null +++ b/src/python/example/plot_rips_complex.py @@ -0,0 +1,38 @@ +#!/usr/bin/env python + +import numpy as np +import gudhi +points = np.array(gudhi.read_off('../../data/points/Kl.off')) +rc = gudhi.RipsComplex(points=points, max_edge_length=.2) +st = rc.create_simplex_tree(max_dimension=2) +# We are only going to plot the triangles +triangles = np.array([s[0] for s in st.get_skeleton(2) if len(s[0])==3]) + +# First possibility: plotly +import plotly.graph_objects as go +fig = go.Figure(data=[ + go.Mesh3d( + # Use the first 3 coordinates, but we could as easily pick others + x=points[:,0], + y=points[:,1], + z=points[:,2], + i = triangles[:,0], + j = triangles[:,1], + k = triangles[:,2], + ) +]) +fig.show() + +# Second possibility: matplotlib +from mpl_toolkits.mplot3d import Axes3D +import matplotlib.pyplot as plt +fig = plt.figure() +ax = fig.gca(projection='3d') +ax.plot_trisurf(points[:,0], points[:,1], points[:,2], triangles=triangles) +plt.show() + +# Third possibility: mayavi +# (this may take a while) +from mayavi import mlab +mlab.triangular_mesh(points[:,0], points[:,1], points[:,2], triangles); +mlab.show() diff --git a/src/python/example/plot_simplex_tree_dim012.py b/src/python/example/plot_simplex_tree_dim012.py new file mode 100755 index 00000000..5b962131 --- /dev/null +++ b/src/python/example/plot_simplex_tree_dim012.py @@ -0,0 +1,66 @@ +#!/usr/bin/env python +import numpy as np +import gudhi + +# Coordinates of the points +points=np.array([[0,0,0],[1,0,0],[0,1,0],[0,0,1],[1,1,1],[1,1,0],[0,1,1]]) +# Build the simplicial complex with a tetrahedon, an edge and an isolated vertex +cplx=gudhi.SimplexTree() +cplx.insert([1,2,3,5]) +cplx.insert([4,6]) +cplx.insert([0]) +# List of triangles (point indices) +triangles = np.array([s[0] for s in cplx.get_skeleton(2) if len(s[0])==3]) +# List of edges (point coordinates) +edges = [] +for s in cplx.get_skeleton(1): + e = s[0] + if len(e) == 2: + edges.append(points[[e[0],e[1]]]) + +## With plotly +import plotly.graph_objects as go +# Plot triangles +f2 = go.Mesh3d( + x=points[:,0], + y=points[:,1], + z=points[:,2], + i = triangles[:,0], + j = triangles[:,1], + k = triangles[:,2], + ) +# Plot points +f0 = go.Scatter3d(x=points[:,0], y=points[:,1], z=points[:,2], mode="markers") +data = [f2, f0] +# Plot edges +for pts in edges: + seg = go.Scatter3d(x=pts[:,0],y=pts[:,1],z=pts[:,2],mode="lines",line=dict(color='green')) + data.append(seg) +fig = go.Figure(data=data,layout=dict(showlegend=False)) +# By default plotly would give each edge its own color and legend, that's too much +fig.show() + +## With matplotlib +from mpl_toolkits.mplot3d import Axes3D +from mpl_toolkits.mplot3d.art3d import Line3DCollection +import matplotlib.pyplot as plt +fig = plt.figure() +ax = fig.gca(projection='3d') +# Plot triangles +ax.plot_trisurf(points[:,0], points[:,1], points[:,2], triangles=triangles) +# Plot points +ax.scatter3D(points[:,0], points[:,1], points[:,2]) +# Plot edges +ax.add_collection3d(Line3DCollection(segments=edges)) +plt.show() + +## With mayavi +from mayavi import mlab +# Plot triangles +mlab.triangular_mesh(points[:,0], points[:,1], points[:,2], triangles); +# Plot points +mlab.points3d(points[:,0], points[:,1], points[:,2]) +# Plot edges +for pts in edges: + mlab.plot3d(pts[:,0],pts[:,1],pts[:,2],tube_radius=None) +mlab.show() diff --git a/src/python/example/rips_complex_diagram_persistence_from_correlation_matrix_file_example.py b/src/python/example/rips_complex_diagram_persistence_from_correlation_matrix_file_example.py index 3571580b..1acb187c 100755 --- a/src/python/example/rips_complex_diagram_persistence_from_correlation_matrix_file_example.py +++ b/src/python/example/rips_complex_diagram_persistence_from_correlation_matrix_file_example.py @@ -1,8 +1,9 @@ #!/usr/bin/env python -import gudhi import sys import argparse +import matplotlib.pyplot as plot +import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. @@ -83,5 +84,5 @@ invert_diag = [ ] if args.no_diagram == False: - pplot = gudhi.plot_persistence_diagram(invert_diag, band=args.band) - pplot.show() + gudhi.plot_persistence_diagram(invert_diag, band=args.band) + plot.show() diff --git a/src/python/example/rips_complex_diagram_persistence_from_distance_matrix_file_example.py b/src/python/example/rips_complex_diagram_persistence_from_distance_matrix_file_example.py index 0b9a9ba9..79ccca96 100755 --- a/src/python/example/rips_complex_diagram_persistence_from_distance_matrix_file_example.py +++ b/src/python/example/rips_complex_diagram_persistence_from_distance_matrix_file_example.py @@ -1,7 +1,8 @@ #!/usr/bin/env python -import gudhi import argparse +import matplotlib.pyplot as plot +import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. @@ -59,5 +60,5 @@ print("betti_numbers()=") print(simplex_tree.betti_numbers()) if args.no_diagram == False: - pplot = gudhi.plot_persistence_diagram(diag, band=args.band) - pplot.show() + gudhi.plot_persistence_diagram(diag, band=args.band) + plot.show() diff --git a/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py b/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py index 2b335bba..b9074cf9 100755 --- a/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py @@ -1,7 +1,8 @@ #!/usr/bin/env python -import gudhi import argparse +import matplotlib.pyplot as plot +import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. @@ -64,8 +65,8 @@ with open(args.file, "r") as f: print(simplex_tree.betti_numbers()) if args.no_diagram == False: - pplot = gudhi.plot_persistence_diagram(diag, band=args.band) - pplot.show() + gudhi.plot_persistence_diagram(diag, band=args.band) + plot.show() else: print(args.file, "is not a valid OFF file") diff --git a/src/python/example/rips_persistence_diagram.py b/src/python/example/rips_persistence_diagram.py index f5897d7b..2a90b4bc 100755 --- a/src/python/example/rips_persistence_diagram.py +++ b/src/python/example/rips_persistence_diagram.py @@ -1,5 +1,6 @@ #!/usr/bin/env python +import matplotlib.pyplot as plot import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. @@ -26,5 +27,5 @@ simplex_tree = rips.create_simplex_tree(max_dimension=1) diag = simplex_tree.persistence(homology_coeff_field=2, min_persistence=0) print("diag=", diag) -pplot = gudhi.plot_persistence_diagram(diag) -pplot.show() +gudhi.plot_persistence_diagram(diag) +plot.show() diff --git a/src/python/example/sparse_rips_persistence_diagram.py b/src/python/example/sparse_rips_persistence_diagram.py index 671d5e34..410a6a86 100755 --- a/src/python/example/sparse_rips_persistence_diagram.py +++ b/src/python/example/sparse_rips_persistence_diagram.py @@ -1,5 +1,6 @@ #!/usr/bin/env python +import matplotlib.pyplot as plot import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. @@ -28,5 +29,5 @@ simplex_tree = rips.create_simplex_tree(max_dimension=2) diag = simplex_tree.persistence(homology_coeff_field=2, min_persistence=0) print("diag=", diag) -pplot = gudhi.plot_persistence_diagram(diag) -pplot.show() +gudhi.plot_persistence_diagram(diag) +plot.show() diff --git a/src/python/example/tangential_complex_plain_homology_from_off_file_example.py b/src/python/example/tangential_complex_plain_homology_from_off_file_example.py index 456bc9eb..f0df2189 100755 --- a/src/python/example/tangential_complex_plain_homology_from_off_file_example.py +++ b/src/python/example/tangential_complex_plain_homology_from_off_file_example.py @@ -1,7 +1,8 @@ #!/usr/bin/env python -import gudhi import argparse +import matplotlib.pyplot as plot +import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. @@ -56,8 +57,8 @@ with open(args.file, "r") as f: print(st.betti_numbers()) if args.no_diagram == False: - pplot = gudhi.plot_persistence_diagram(diag, band=args.band) - pplot.show() + gudhi.plot_persistence_diagram(diag, band=args.band) + plot.show() else: print(args.file, "is not a valid OFF file") diff --git a/src/python/gudhi/__init__.py.in b/src/python/gudhi/__init__.py.in index 28bab0e1..0c462b02 100644 --- a/src/python/gudhi/__init__.py.in +++ b/src/python/gudhi/__init__.py.in @@ -1,14 +1,13 @@ from importlib import import_module -"""This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "GUDHI Editorial Board" __copyright__ = "Copyright (C) 2016 Inria" @@ -21,13 +20,16 @@ __debug_info__ = @GUDHI_PYTHON_DEBUG_INFO@ from sys import exc_info from importlib import import_module -__all__ = [@GUDHI_PYTHON_MODULES@] +__all__ = [@GUDHI_PYTHON_MODULES@ @GUDHI_PYTHON_MODULES_EXTRA@] __available_modules = '' __missing_modules = '' -# try to import * from gudhi.__module_name -for __module_name in __all__: +# Try to import * from gudhi.__module_name for default modules. +# Extra modules require an explicit import by the user (mostly because of +# unusual dependencies, but also to avoid cluttering namespace gudhi and +# speed up the basic import) +for __module_name in [@GUDHI_PYTHON_MODULES@]: try: __module = import_module('gudhi.' + __module_name) try: diff --git a/src/python/gudhi/alpha_complex.pyx b/src/python/gudhi/alpha_complex.pyx index 6d6309db..8f2c98d5 100644 --- a/src/python/gudhi/alpha_complex.pyx +++ b/src/python/gudhi/alpha_complex.pyx @@ -9,15 +9,14 @@ import os from gudhi.simplex_tree cimport * from gudhi.simplex_tree import SimplexTree -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -68,7 +67,7 @@ cdef class AlphaComplex: # The real cython constructor def __cinit__(self, points=None, off_file=''): - if off_file is not '': + if off_file: if os.path.isfile(off_file): self.thisptr = new Alpha_complex_interface(str.encode(off_file), True) else: diff --git a/src/python/gudhi/bottleneck.pyx b/src/python/gudhi/bottleneck.pyx index 4b378cbc..c2361024 100644 --- a/src/python/gudhi/bottleneck.pyx +++ b/src/python/gudhi/bottleneck.pyx @@ -3,15 +3,14 @@ from libcpp.vector cimport vector from libcpp.utility cimport pair import os -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" diff --git a/src/python/gudhi/cubical_complex.pyx b/src/python/gudhi/cubical_complex.pyx index 0dc133d1..011c407c 100644 --- a/src/python/gudhi/cubical_complex.pyx +++ b/src/python/gudhi/cubical_complex.pyx @@ -7,15 +7,14 @@ import os from numpy import array as np_array -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -66,9 +65,9 @@ cdef class CubicalComplex: # The real cython constructor def __cinit__(self, dimensions=None, top_dimensional_cells=None, perseus_file=''): - if (dimensions is not None) and (top_dimensional_cells is not None) and (perseus_file is ''): + if (dimensions is not None) and (top_dimensional_cells is not None) and (perseus_file == ''): self.thisptr = new Bitmap_cubical_complex_base_interface(dimensions, top_dimensional_cells) - elif (dimensions is None) and (top_dimensional_cells is None) and (perseus_file is not ''): + elif (dimensions is None) and (top_dimensional_cells is None) and (perseus_file != ''): if os.path.isfile(perseus_file): self.thisptr = new Bitmap_cubical_complex_base_interface(str.encode(perseus_file)) else: diff --git a/src/python/gudhi/euclidean_strong_witness_complex.pyx b/src/python/gudhi/euclidean_strong_witness_complex.pyx index 5d6e4fb9..e3f451f0 100644 --- a/src/python/gudhi/euclidean_strong_witness_complex.pyx +++ b/src/python/gudhi/euclidean_strong_witness_complex.pyx @@ -6,15 +6,14 @@ from libc.stdint cimport intptr_t from gudhi.simplex_tree cimport * from gudhi.simplex_tree import SimplexTree -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -71,7 +70,7 @@ cdef class EuclideanStrongWitnessComplex: """ stree = SimplexTree() cdef intptr_t stree_int_ptr=stree.thisptr - if limit_dimension is not -1: + if limit_dimension != -1: self.thisptr.create_simplex_tree(<Simplex_tree_interface_full_featured*>stree_int_ptr, max_alpha_square, limit_dimension) else: diff --git a/src/python/gudhi/euclidean_witness_complex.pyx b/src/python/gudhi/euclidean_witness_complex.pyx index 2531919b..84a8ea1a 100644 --- a/src/python/gudhi/euclidean_witness_complex.pyx +++ b/src/python/gudhi/euclidean_witness_complex.pyx @@ -6,15 +6,14 @@ from libc.stdint cimport intptr_t from gudhi.simplex_tree cimport * from gudhi.simplex_tree import SimplexTree -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -71,7 +70,7 @@ cdef class EuclideanWitnessComplex: """ stree = SimplexTree() cdef intptr_t stree_int_ptr=stree.thisptr - if limit_dimension is not -1: + if limit_dimension != -1: self.thisptr.create_simplex_tree(<Simplex_tree_interface_full_featured*>stree_int_ptr, max_alpha_square, limit_dimension) else: diff --git a/src/python/gudhi/nerve_gic.pyx b/src/python/gudhi/nerve_gic.pyx index 2b230b8c..acb78564 100644 --- a/src/python/gudhi/nerve_gic.pyx +++ b/src/python/gudhi/nerve_gic.pyx @@ -9,15 +9,14 @@ from libc.stdint cimport intptr_t from gudhi.simplex_tree cimport * from gudhi.simplex_tree import SimplexTree -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2018 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2018 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2018 Inria" diff --git a/src/python/gudhi/off_reader.pyx b/src/python/gudhi/off_reader.pyx index 9efd97ff..225e981c 100644 --- a/src/python/gudhi/off_reader.pyx +++ b/src/python/gudhi/off_reader.pyx @@ -3,15 +3,14 @@ from libcpp.vector cimport vector from libcpp.string cimport string import os -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -29,7 +28,7 @@ def read_off(off_file=''): :returns: The point set. :rtype: vector[vector[double]] """ - if off_file is not '': + if off_file: if os.path.isfile(off_file): return read_points_from_OFF_file(str.encode(off_file)) else: diff --git a/src/python/gudhi/periodic_cubical_complex.pyx b/src/python/gudhi/periodic_cubical_complex.pyx index 724fadd4..c89055db 100644 --- a/src/python/gudhi/periodic_cubical_complex.pyx +++ b/src/python/gudhi/periodic_cubical_complex.pyx @@ -7,15 +7,14 @@ import os from numpy import array as np_array -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -68,9 +67,9 @@ cdef class PeriodicCubicalComplex: # The real cython constructor def __cinit__(self, dimensions=None, top_dimensional_cells=None, periodic_dimensions=None, perseus_file=''): - if (dimensions is not None) and (top_dimensional_cells is not None) and (periodic_dimensions is not None) and (perseus_file is ''): + if (dimensions is not None) and (top_dimensional_cells is not None) and (periodic_dimensions is not None) and (perseus_file == ''): self.thisptr = new Periodic_cubical_complex_base_interface(dimensions, top_dimensional_cells, periodic_dimensions) - elif (dimensions is None) and (top_dimensional_cells is None) and (periodic_dimensions is None) and (perseus_file is not ''): + elif (dimensions is None) and (top_dimensional_cells is None) and (periodic_dimensions is None) and (perseus_file != ''): if os.path.isfile(perseus_file): self.thisptr = new Periodic_cubical_complex_base_interface(str.encode(perseus_file)) else: diff --git a/src/python/gudhi/persistence_graphical_tools.py b/src/python/gudhi/persistence_graphical_tools.py index 181bc8ea..7d232c85 100644 --- a/src/python/gudhi/persistence_graphical_tools.py +++ b/src/python/gudhi/persistence_graphical_tools.py @@ -5,15 +5,14 @@ import numpy as np from gudhi.reader_utils import read_persistence_intervals_in_dimension from gudhi.reader_utils import read_persistence_intervals_grouped_by_dimension -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau, Bertrand Michel - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau, Bertrand Michel +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau, Bertrand Michel" __copyright__ = "Copyright (C) 2016 Inria" @@ -44,27 +43,6 @@ def __min_birth_max_death(persistence, band=0.0): max_death += band return (min_birth, max_death) - -""" -Only 13 colors for the palette -""" -palette = [ - "#ff0000", - "#00ff00", - "#0000ff", - "#00ffff", - "#ff00ff", - "#ffff00", - "#000000", - "#880000", - "#008800", - "#000088", - "#888800", - "#880088", - "#008888", -] - - def plot_persistence_barcode( persistence=[], persistence_file="", @@ -73,6 +51,8 @@ def plot_persistence_barcode( max_barcodes=1000, inf_delta=0.1, legend=False, + colormap=None, + axes=None ): """This function plots the persistence bar code from persistence values list or from a :doc:`persistence file <fileformats>`. @@ -95,14 +75,19 @@ def plot_persistence_barcode( :type inf_delta: float. :param legend: Display the dimension color legend (default is False). :type legend: boolean. - :returns: A matplotlib object containing horizontal bar plot of persistence - (launch `show()` method on it to display it). + :param colormap: A matplotlib-like qualitative colormaps. Default is None + which means :code:`matplotlib.cm.Set1.colors`. + :type colormap: tuple of colors (3-tuple of float between 0. and 1.). + :param axes: A matplotlib-like subplot axes. If None, the plot is drawn on + a new set of axes. + :type axes: `matplotlib.axes.Axes` + :returns: (`matplotlib.axes.Axes`): The axes on which the plot was drawn. """ try: import matplotlib.pyplot as plt import matplotlib.patches as mpatches - if persistence_file is not "": + if persistence_file != "": if path.isfile(persistence_file): # Reset persistence persistence = [] @@ -116,7 +101,7 @@ def plot_persistence_barcode( print("file " + persistence_file + " not found.") return None - if max_barcodes is not 1000: + if max_barcodes != 1000: print("Deprecated parameter. It has been replaced by max_intervals") max_intervals = max_barcodes @@ -127,6 +112,11 @@ def plot_persistence_barcode( key=lambda life_time: life_time[1][1] - life_time[1][0], reverse=True, )[:max_intervals] + + if colormap == None: + colormap = plt.cm.Set1.colors + if axes == None: + fig, axes = plt.subplots(1, 1) persistence = sorted(persistence, key=lambda birth: birth[1][0]) @@ -141,41 +131,43 @@ def plot_persistence_barcode( for interval in reversed(persistence): if float(interval[1][1]) != float("inf"): # Finite death case - plt.barh( + axes.barh( ind, (interval[1][1] - interval[1][0]), height=0.8, left=interval[1][0], alpha=alpha, - color=palette[interval[0]], + color=colormap[interval[0]], linewidth=0, ) else: # Infinite death case for diagram to be nicer - plt.barh( + axes.barh( ind, (infinity - interval[1][0]), height=0.8, left=interval[1][0], alpha=alpha, - color=palette[interval[0]], + color=colormap[interval[0]], linewidth=0, ) ind = ind + 1 if legend: dimensions = list(set(item[0] for item in persistence)) - plt.legend( + axes.legend( handles=[ - mpatches.Patch(color=palette[dim], label=str(dim)) + mpatches.Patch(color=colormap[dim], label=str(dim)) for dim in dimensions ], loc="lower right", ) - plt.title("Persistence barcode") + + axes.set_title("Persistence barcode") + # Ends plot on infinity value and starts a little bit before min_birth - plt.axis([axis_start, infinity, 0, ind]) - return plt + axes.axis([axis_start, infinity, 0, ind]) + return axes except ImportError: print("This function is not available, you may be missing matplotlib.") @@ -190,6 +182,8 @@ def plot_persistence_diagram( max_plots=1000, inf_delta=0.1, legend=False, + colormap=None, + axes=None ): """This function plots the persistence diagram from persistence values list or from a :doc:`persistence file <fileformats>`. @@ -214,14 +208,19 @@ def plot_persistence_diagram( :type inf_delta: float. :param legend: Display the dimension color legend (default is False). :type legend: boolean. - :returns: A matplotlib object containing diagram plot of persistence - (launch `show()` method on it to display it). + :param colormap: A matplotlib-like qualitative colormaps. Default is None + which means :code:`matplotlib.cm.Set1.colors`. + :type colormap: tuple of colors (3-tuple of float between 0. and 1.). + :param axes: A matplotlib-like subplot axes. If None, the plot is drawn on + a new set of axes. + :type axes: `matplotlib.axes.Axes` + :returns: (`matplotlib.axes.Axes`): The axes on which the plot was drawn. """ try: import matplotlib.pyplot as plt import matplotlib.patches as mpatches - if persistence_file is not "": + if persistence_file != "": if path.isfile(persistence_file): # Reset persistence persistence = [] @@ -235,7 +234,7 @@ def plot_persistence_diagram( print("file " + persistence_file + " not found.") return None - if max_plots is not 1000: + if max_plots != 1000: print("Deprecated parameter. It has been replaced by max_intervals") max_intervals = max_plots @@ -247,6 +246,11 @@ def plot_persistence_diagram( reverse=True, )[:max_intervals] + if colormap == None: + colormap = plt.cm.Set1.colors + if axes == None: + fig, axes = plt.subplots(1, 1) + (min_birth, max_death) = __min_birth_max_death(persistence, band) delta = (max_death - min_birth) * inf_delta # Replace infinity values with max_death + delta for diagram to be more @@ -257,44 +261,44 @@ def plot_persistence_diagram( # line display of equation : birth = death x = np.linspace(axis_start, infinity, 1000) # infinity line and text - plt.plot(x, x, color="k", linewidth=1.0) - plt.plot(x, [infinity] * len(x), linewidth=1.0, color="k", alpha=alpha) - plt.text(axis_start, infinity, r"$\infty$", color="k", alpha=alpha) + axes.plot(x, x, color="k", linewidth=1.0) + axes.plot(x, [infinity] * len(x), linewidth=1.0, color="k", alpha=alpha) + axes.text(axis_start, infinity, r"$\infty$", color="k", alpha=alpha) # bootstrap band if band > 0.0: - plt.fill_between(x, x, x + band, alpha=alpha, facecolor="red") + axes.fill_between(x, x, x + band, alpha=alpha, facecolor="red") # Draw points in loop for interval in reversed(persistence): if float(interval[1][1]) != float("inf"): # Finite death case - plt.scatter( + axes.scatter( interval[1][0], interval[1][1], alpha=alpha, - color=palette[interval[0]], + color=colormap[interval[0]], ) else: # Infinite death case for diagram to be nicer - plt.scatter( - interval[1][0], infinity, alpha=alpha, color=palette[interval[0]] + axes.scatter( + interval[1][0], infinity, alpha=alpha, color=colormap[interval[0]] ) if legend: dimensions = list(set(item[0] for item in persistence)) - plt.legend( + axes.legend( handles=[ - mpatches.Patch(color=palette[dim], label=str(dim)) + mpatches.Patch(color=colormap[dim], label=str(dim)) for dim in dimensions ] ) - plt.title("Persistence diagram") - plt.xlabel("Birth") - plt.ylabel("Death") + axes.set_xlabel("Birth") + axes.set_ylabel("Death") # Ends plot on infinity value and starts a little bit before min_birth - plt.axis([axis_start, infinity, axis_start, infinity + delta]) - return plt + axes.axis([axis_start, infinity, axis_start, infinity + delta]) + axes.set_title("Persistence diagram") + return axes except ImportError: print("This function is not available, you may be missing matplotlib.") @@ -309,6 +313,7 @@ def plot_persistence_density( dimension=None, cmap=None, legend=False, + axes=None ): """This function plots the persistence density from persistence values list or from a :doc:`persistence file <fileformats>`. Be @@ -347,14 +352,16 @@ def plot_persistence_density( :type cmap: cf. matplotlib colormap. :param legend: Display the color bar values (default is False). :type legend: boolean. - :returns: A matplotlib object containing diagram plot of persistence - (launch `show()` method on it to display it). + :param axes: A matplotlib-like subplot axes. If None, the plot is drawn on + a new set of axes. + :type axes: `matplotlib.axes.Axes` + :returns: (`matplotlib.axes.Axes`): The axes on which the plot was drawn. """ try: import matplotlib.pyplot as plt from scipy.stats import kde - if persistence_file is not "": + if persistence_file != "": if dimension is None: # All dimension case dimension = -1 @@ -362,7 +369,6 @@ def plot_persistence_density( persistence_dim = read_persistence_intervals_in_dimension( persistence_file=persistence_file, only_this_dim=dimension ) - print(persistence_dim) else: print("file " + persistence_file + " not found.") return None @@ -391,9 +397,15 @@ def plot_persistence_density( birth = persistence_dim[:, 0] death = persistence_dim[:, 1] + # default cmap value cannot be done at argument definition level as matplotlib is not yet defined. + if cmap is None: + cmap = plt.cm.hot_r + if axes == None: + fig, axes = plt.subplots(1, 1) + # line display of equation : birth = death x = np.linspace(death.min(), birth.max(), 1000) - plt.plot(x, x, color="k", linewidth=1.0) + axes.plot(x, x, color="k", linewidth=1.0) # Evaluate a gaussian kde on a regular grid of nbins x nbins over data extents k = kde.gaussian_kde([birth, death], bw_method=bw_method) @@ -403,19 +415,16 @@ def plot_persistence_density( ] zi = k(np.vstack([xi.flatten(), yi.flatten()])) - # default cmap value cannot be done at argument definition level as matplotlib is not yet defined. - if cmap is None: - cmap = plt.cm.hot_r # Make the plot - plt.pcolormesh(xi, yi, zi.reshape(xi.shape), cmap=cmap) + img = axes.pcolormesh(xi, yi, zi.reshape(xi.shape), cmap=cmap) if legend: - plt.colorbar() + plt.colorbar(img, ax=axes) - plt.title("Persistence density") - plt.xlabel("Birth") - plt.ylabel("Death") - return plt + axes.set_xlabel("Birth") + axes.set_ylabel("Death") + axes.set_title("Persistence density") + return axes except ImportError: print( diff --git a/src/python/gudhi/reader_utils.pyx b/src/python/gudhi/reader_utils.pyx index 147fae71..6994c4f9 100644 --- a/src/python/gudhi/reader_utils.pyx +++ b/src/python/gudhi/reader_utils.pyx @@ -7,15 +7,14 @@ from libcpp.pair cimport pair from os import path from numpy import array as np_array -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2017 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2017 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2017 Inria" @@ -37,7 +36,7 @@ def read_lower_triangular_matrix_from_csv_file(csv_file='', separator=';'): :returns: The lower triangular matrix. :rtype: vector[vector[double]] """ - if csv_file is not '': + if csv_file: if path.isfile(csv_file): return read_matrix_from_csv_file(str.encode(csv_file), ord(separator[0])) print("file " + csv_file + " not set or not found.") @@ -56,7 +55,7 @@ def read_persistence_intervals_grouped_by_dimension(persistence_file=''): :returns: The persistence pairs grouped by dimension. :rtype: map[int, vector[pair[double, double]]] """ - if persistence_file is not '': + if persistence_file: if path.isfile(persistence_file): return read_pers_intervals_grouped_by_dimension(str.encode(persistence_file)) print("file " + persistence_file + " not set or not found.") @@ -79,7 +78,7 @@ def read_persistence_intervals_in_dimension(persistence_file='', only_this_dim=- :returns: The persistence intervals. :rtype: numpy array of dimension 2 """ - if persistence_file is not '': + if persistence_file: if path.isfile(persistence_file): return np_array(read_pers_intervals_in_dimension(str.encode( persistence_file), only_this_dim)) diff --git a/src/python/gudhi/representations/__init__.py b/src/python/gudhi/representations/__init__.py new file mode 100644 index 00000000..f020248d --- /dev/null +++ b/src/python/gudhi/representations/__init__.py @@ -0,0 +1,6 @@ +from .kernel_methods import * +from .metrics import * +from .preprocessing import * +from .vector_methods import * + +__all__ = ["kernel_methods", "metrics", "preprocessing", "vector_methods"] diff --git a/src/python/gudhi/representations/kernel_methods.py b/src/python/gudhi/representations/kernel_methods.py new file mode 100644 index 00000000..bfc83aff --- /dev/null +++ b/src/python/gudhi/representations/kernel_methods.py @@ -0,0 +1,206 @@ +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Mathieu Carrière +# +# Copyright (C) 2018-2019 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification + +import numpy as np +from sklearn.base import BaseEstimator, TransformerMixin +from sklearn.metrics import pairwise_distances +from .metrics import SlicedWassersteinDistance, PersistenceFisherDistance + +############################################# +# Kernel methods ############################ +############################################# + +class SlicedWassersteinKernel(BaseEstimator, TransformerMixin): + """ + This is a class for computing the sliced Wasserstein kernel matrix from a list of persistence diagrams. The sliced Wasserstein kernel is computed by exponentiating the corresponding sliced Wasserstein distance with a Gaussian kernel. See http://proceedings.mlr.press/v70/carriere17a.html for more details. + """ + def __init__(self, num_directions=10, bandwidth=1.0): + """ + Constructor for the SlicedWassersteinKernel class. + + Parameters: + bandwidth (double): bandwidth of the Gaussian kernel applied to the sliced Wasserstein distance (default 1.). + num_directions (int): number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the kernel computation (default 10). + """ + self.bandwidth = bandwidth + self.sw_ = SlicedWassersteinDistance(num_directions=num_directions) + + def fit(self, X, y=None): + """ + Fit the SlicedWassersteinKernel class on a list of persistence diagrams: an instance of the SlicedWassersteinDistance class is fitted on the diagrams and then stored. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + self.sw_.fit(X, y) + return self + + def transform(self, X): + """ + Compute all sliced Wasserstein kernel values between the persistence diagrams that were stored after calling the fit() method, and a given list of (possibly different) persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise sliced Wasserstein kernel values. + """ + return np.exp(-self.sw_.transform(X)/self.bandwidth) + +class PersistenceWeightedGaussianKernel(BaseEstimator, TransformerMixin): + """ + This is a class for computing the persistence weighted Gaussian kernel matrix from a list of persistence diagrams. The persistence weighted Gaussian kernel is computed by convolving the persistence diagram points with weighted Gaussian kernels. See http://proceedings.mlr.press/v48/kusano16.html for more details. + """ + def __init__(self, bandwidth=1., weight=lambda x: 1, kernel_approx=None): + """ + Constructor for the PersistenceWeightedGaussianKernel class. + + Parameters: + bandwidth (double): bandwidth of the Gaussian kernel with which persistence diagrams will be convolved (default 1.) + weight (function): weight function for the persistence diagram points (default constant function, ie lambda x: 1). This function must be defined on 2D points, ie lists or numpy arrays of the form [p_x,p_y]. + kernel_approx (class): kernel approximation class used to speed up computation (default None). Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). + """ + self.bandwidth, self.weight = bandwidth, weight + self.kernel_approx = kernel_approx + + def fit(self, X, y=None): + """ + Fit the PersistenceWeightedGaussianKernel class on a list of persistence diagrams: persistence diagrams are stored in a numpy array called **diagrams** and the kernel approximation class (if not None) is applied on them. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + self.diagrams_ = list(X) + self.ws_ = [ np.array([self.weight(self.diagrams_[i][j,:]) for j in range(self.diagrams_[i].shape[0])]) for i in range(len(self.diagrams_)) ] + if self.kernel_approx is not None: + self.approx_ = np.concatenate([np.sum(np.multiply(self.ws_[i][:,np.newaxis], self.kernel_approx.transform(self.diagrams_[i])), axis=0)[np.newaxis,:] for i in range(len(self.diagrams_))]) + return self + + def transform(self, X): + """ + Compute all persistence weighted Gaussian kernel values between the persistence diagrams that were stored after calling the fit() method, and a given list of (possibly different) persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise persistence weighted Gaussian kernel values. + """ + Xp = list(X) + Xfit = np.zeros((len(Xp), len(self.diagrams_))) + if len(self.diagrams_) == len(Xp) and np.all([np.array_equal(self.diagrams_[i], Xp[i]) for i in range(len(Xp))]): + if self.kernel_approx is not None: + Xfit = (1./(np.sqrt(2*np.pi)*self.bandwidth)) * np.matmul(self.approx_, self.approx_.T) + else: + for i in range(len(self.diagrams_)): + for j in range(i+1, len(self.diagrams_)): + W = np.matmul(self.ws_[i][:,np.newaxis], self.ws_[j][np.newaxis,:]) + E = (1./(np.sqrt(2*np.pi)*self.bandwidth)) * np.exp(-np.square(pairwise_distances(self.diagrams_[i], self.diagrams_[j]))/(2*np.square(self.bandwidth))) + Xfit[i,j] = np.sum(np.multiply(W, E)) + Xfit[j,i] = Xfit[i,j] + else: + ws = [ np.array([self.weight(Xp[i][j,:]) for j in range(Xp[i].shape[0])]) for i in range(len(Xp)) ] + if self.kernel_approx is not None: + approx = np.concatenate([np.sum(np.multiply(ws[i][:,np.newaxis], self.kernel_approx.transform(Xp[i])), axis=0)[np.newaxis,:] for i in range(len(Xp))]) + Xfit = (1./(np.sqrt(2*np.pi)*self.bandwidth)) * np.matmul(approx, self.approx_.T) + else: + for i in range(len(Xp)): + for j in range(len(self.diagrams_)): + W = np.matmul(ws[i][:,np.newaxis], self.ws_[j][np.newaxis,:]) + E = (1./(np.sqrt(2*np.pi)*self.bandwidth)) * np.exp(-np.square(pairwise_distances(Xp[i], self.diagrams_[j]))/(2*np.square(self.bandwidth))) + Xfit[i,j] = np.sum(np.multiply(W, E)) + + return Xfit + +class PersistenceScaleSpaceKernel(BaseEstimator, TransformerMixin): + """ + This is a class for computing the persistence scale space kernel matrix from a list of persistence diagrams. The persistence scale space kernel is computed by adding the symmetric to the diagonal of each point in each persistence diagram, with negative weight, and then convolving the points with a Gaussian kernel. See https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Reininghaus_A_Stable_Multi-Scale_2015_CVPR_paper.pdf for more details. + """ + def __init__(self, bandwidth=1., kernel_approx=None): + """ + Constructor for the PersistenceScaleSpaceKernel class. + + Parameters: + bandwidth (double): bandwidth of the Gaussian kernel with which persistence diagrams will be convolved (default 1.) + kernel_approx (class): kernel approximation class used to speed up computation (default None). Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). + """ + self.pwg_ = PersistenceWeightedGaussianKernel(bandwidth=bandwidth, weight=lambda x: 1 if x[1] >= x[0] else -1, kernel_approx=kernel_approx) + + def fit(self, X, y=None): + """ + Fit the PersistenceScaleSpaceKernel class on a list of persistence diagrams: symmetric to the diagonal of all points are computed and an instance of the PersistenceWeightedGaussianKernel class is fitted on the diagrams and then stored. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + self.diagrams_ = list(X) + for i in range(len(self.diagrams_)): + op_D = self.diagrams_[i][:,[1,0]] + self.diagrams_[i] = np.concatenate([self.diagrams_[i], op_D], axis=0) + self.pwg_.fit(X) + return self + + def transform(self, X): + """ + Compute all persistence scale space kernel values between the persistence diagrams that were stored after calling the fit() method, and a given list of (possibly different) persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise persistence scale space kernel values. + """ + Xp = list(X) + for i in range(len(Xp)): + op_X = Xp[i][:,[1,0]] + Xp[i] = np.concatenate([Xp[i], op_X], axis=0) + return self.pwg_.transform(Xp) + +class PersistenceFisherKernel(BaseEstimator, TransformerMixin): + """ + This is a class for computing the persistence Fisher kernel matrix from a list of persistence diagrams. The persistence Fisher kernel is computed by exponentiating the corresponding persistence Fisher distance with a Gaussian kernel. See papers.nips.cc/paper/8205-persistence-fisher-kernel-a-riemannian-manifold-kernel-for-persistence-diagrams for more details. + """ + def __init__(self, bandwidth_fisher=1., bandwidth=1., kernel_approx=None): + """ + Constructor for the PersistenceFisherKernel class. + + Parameters: + bandwidth (double): bandwidth of the Gaussian kernel applied to the persistence Fisher distance (default 1.). + bandwidth_fisher (double): bandwidth of the Gaussian kernel used to turn persistence diagrams into probability distributions by PersistenceFisherDistance class (default 1.). + kernel_approx (class): kernel approximation class used to speed up computation (default None). Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). + """ + self.bandwidth = bandwidth + self.pf_ = PersistenceFisherDistance(bandwidth=bandwidth_fisher, kernel_approx=kernel_approx) + + def fit(self, X, y=None): + """ + Fit the PersistenceFisherKernel class on a list of persistence diagrams: an instance of the PersistenceFisherDistance class is fitted on the diagrams and then stored. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + self.pf_.fit(X, y) + return self + + def transform(self, X): + """ + Compute all persistence Fisher kernel values between the persistence diagrams that were stored after calling the fit() method, and a given list of (possibly different) persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise persistence Fisher kernel values. + """ + return np.exp(-self.pf_.transform(X)/self.bandwidth) + diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py new file mode 100644 index 00000000..5f9ec6ab --- /dev/null +++ b/src/python/gudhi/representations/metrics.py @@ -0,0 +1,244 @@ +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Mathieu Carrière +# +# Copyright (C) 2018-2019 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification + +import numpy as np +from sklearn.base import BaseEstimator, TransformerMixin +from sklearn.metrics import pairwise_distances +try: + from .. import bottleneck_distance + USE_GUDHI = True +except ImportError: + USE_GUDHI = False + print("Gudhi built without CGAL: BottleneckDistance will return a null matrix") + +############################################# +# Metrics ################################### +############################################# + +class SlicedWassersteinDistance(BaseEstimator, TransformerMixin): + """ + This is a class for computing the sliced Wasserstein distance matrix from a list of persistence diagrams. The Sliced Wasserstein distance is computed by projecting the persistence diagrams onto lines, comparing the projections with the 1-norm, and finally integrating over all possible lines. See http://proceedings.mlr.press/v70/carriere17a.html for more details. + """ + def __init__(self, num_directions=10): + """ + Constructor for the SlicedWassersteinDistance class. + + Parameters: + num_directions (int): number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the distance computation (default 10). + """ + self.num_directions = num_directions + thetas = np.linspace(-np.pi/2, np.pi/2, num=self.num_directions+1)[np.newaxis,:-1] + self.lines_ = np.concatenate([np.cos(thetas), np.sin(thetas)], axis=0) + + def fit(self, X, y=None): + """ + Fit the SlicedWassersteinDistance class on a list of persistence diagrams: persistence diagrams are projected onto the different lines. The diagrams themselves and their projections are then stored in numpy arrays, called **diagrams_** and **approx_diag_**. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + self.diagrams_ = X + self.approx_ = [np.matmul(X[i], self.lines_) for i in range(len(X))] + diag_proj = (1./2) * np.ones((2,2)) + self.approx_diag_ = [np.matmul(np.matmul(X[i], diag_proj), self.lines_) for i in range(len(X))] + return self + + def transform(self, X): + """ + Compute all sliced Wasserstein distances between the persistence diagrams that were stored after calling the fit() method, and a given list of (possibly different) persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise sliced Wasserstein distances. + """ + Xfit = np.zeros((len(X), len(self.approx_))) + if len(self.diagrams_) == len(X) and np.all([np.array_equal(self.diagrams_[i], X[i]) for i in range(len(X))]): + for i in range(len(self.approx_)): + for j in range(i+1, len(self.approx_)): + A = np.sort(np.concatenate([self.approx_[i], self.approx_diag_[j]], axis=0), axis=0) + B = np.sort(np.concatenate([self.approx_[j], self.approx_diag_[i]], axis=0), axis=0) + L1 = np.sum(np.abs(A-B), axis=0) + Xfit[i,j] = np.mean(L1) + Xfit[j,i] = Xfit[i,j] + else: + diag_proj = (1./2) * np.ones((2,2)) + approx = [np.matmul(X[i], self.lines_) for i in range(len(X))] + approx_diag = [np.matmul(np.matmul(X[i], diag_proj), self.lines_) for i in range(len(X))] + for i in range(len(approx)): + for j in range(len(self.approx_)): + A = np.sort(np.concatenate([approx[i], self.approx_diag_[j]], axis=0), axis=0) + B = np.sort(np.concatenate([self.approx_[j], approx_diag[i]], axis=0), axis=0) + L1 = np.sum(np.abs(A-B), axis=0) + Xfit[i,j] = np.mean(L1) + + return Xfit + +class BottleneckDistance(BaseEstimator, TransformerMixin): + """ + This is a class for computing the bottleneck distance matrix from a list of persistence diagrams. + """ + def __init__(self, epsilon=None): + """ + Constructor for the BottleneckDistance class. + + Parameters: + epsilon (double): absolute (additive) error tolerated on the distance (default is the smallest positive float), see :func:`gudhi.bottleneck_distance`. + """ + self.epsilon = epsilon + + def fit(self, X, y=None): + """ + Fit the BottleneckDistance class on a list of persistence diagrams: persistence diagrams are stored in a numpy array called **diagrams**. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + self.diagrams_ = X + return self + + def transform(self, X): + """ + Compute all bottleneck distances between the persistence diagrams that were stored after calling the fit() method, and a given list of (possibly different) persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise bottleneck distances. + """ + num_diag1 = len(X) + + #if len(self.diagrams_) == len(X) and np.all([np.array_equal(self.diagrams_[i], X[i]) for i in range(len(X))]): + if X is self.diagrams_: + matrix = np.zeros((num_diag1, num_diag1)) + + if USE_GUDHI: + for i in range(num_diag1): + for j in range(i+1, num_diag1): + matrix[i,j] = bottleneck_distance(X[i], X[j], self.epsilon) + matrix[j,i] = matrix[i,j] + else: + print("Gudhi built without CGAL: returning a null matrix") + + else: + num_diag2 = len(self.diagrams_) + matrix = np.zeros((num_diag1, num_diag2)) + + if USE_GUDHI: + for i in range(num_diag1): + for j in range(num_diag2): + matrix[i,j] = bottleneck_distance(X[i], self.diagrams_[j], self.epsilon) + else: + print("Gudhi built without CGAL: returning a null matrix") + + Xfit = matrix + + return Xfit + +class PersistenceFisherDistance(BaseEstimator, TransformerMixin): + """ + This is a class for computing the persistence Fisher distance matrix from a list of persistence diagrams. The persistence Fisher distance is obtained by computing the original Fisher distance between the probability distributions associated to the persistence diagrams given by convolving them with a Gaussian kernel. See http://papers.nips.cc/paper/8205-persistence-fisher-kernel-a-riemannian-manifold-kernel-for-persistence-diagrams for more details. + """ + def __init__(self, bandwidth=1., kernel_approx=None): + """ + Constructor for the PersistenceFisherDistance class. + + Parameters: + bandwidth (double): bandwidth of the Gaussian kernel used to turn persistence diagrams into probability distributions (default 1.). + kernel_approx (class): kernel approximation class used to speed up computation (default None). Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). + """ + self.bandwidth, self.kernel_approx = bandwidth, kernel_approx + + def fit(self, X, y=None): + """ + Fit the PersistenceFisherDistance class on a list of persistence diagrams: persistence diagrams are stored in a numpy array called **diagrams** and the kernel approximation class (if not None) is applied on them. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + self.diagrams_ = X + projection = (1./2) * np.ones((2,2)) + self.diagonal_projections_ = [np.matmul(X[i], projection) for i in range(len(X))] + if self.kernel_approx is not None: + self.approx_ = [self.kernel_approx.transform(X[i]) for i in range(len(X))] + self.approx_diagonal_ = [self.kernel_approx.transform(self.diagonal_projections_[i]) for i in range(len(X))] + return self + + def transform(self, X): + """ + Compute all persistence Fisher distances between the persistence diagrams that were stored after calling the fit() method, and a given list of (possibly different) persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise persistence Fisher distances. + """ + Xfit = np.zeros((len(X), len(self.diagrams_))) + if len(self.diagrams_) == len(X) and np.all([np.array_equal(self.diagrams_[i], X[i]) for i in range(len(X))]): + for i in range(len(self.diagrams_)): + for j in range(i+1, len(self.diagrams_)): + if self.kernel_approx is not None: + Z = np.concatenate([self.approx_[i], self.approx_diagonal_[i], self.approx_[j], self.approx_diagonal_[j]], axis=0) + U, V = np.sum(np.concatenate([self.approx_[i], self.approx_diagonal_[j]], axis=0), axis=0), np.sum(np.concatenate([self.approx_[j], self.approx_diagonal_[i]], axis=0), axis=0) + vectori, vectorj = np.abs(np.matmul(Z, U.T)), np.abs(np.matmul(Z, V.T)) + vectori_sum, vectorj_sum = np.sum(vectori), np.sum(vectorj) + if vectori_sum != 0: + vectori = vectori/vectori_sum + if vectorj_sum != 0: + vectorj = vectorj/vectorj_sum + Xfit[i,j] = np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) + Xfit[j,i] = Xfit[i,j] + else: + Z = np.concatenate([self.diagrams_[i], self.diagonal_projections_[i], self.diagrams_[j], self.diagonal_projections_[j]], axis=0) + U, V = np.concatenate([self.diagrams_[i], self.diagonal_projections_[j]], axis=0), np.concatenate([self.diagrams_[j], self.diagonal_projections_[i]], axis=0) + vectori = np.sum(np.exp(-np.square(pairwise_distances(Z,U))/(2 * np.square(self.bandwidth)))/(self.bandwidth * np.sqrt(2*np.pi)), axis=1) + vectorj = np.sum(np.exp(-np.square(pairwise_distances(Z,V))/(2 * np.square(self.bandwidth)))/(self.bandwidth * np.sqrt(2*np.pi)), axis=1) + vectori_sum, vectorj_sum = np.sum(vectori), np.sum(vectorj) + if vectori_sum != 0: + vectori = vectori/vectori_sum + if vectorj_sum != 0: + vectorj = vectorj/vectorj_sum + Xfit[i,j] = np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) + Xfit[j,i] = Xfit[i,j] + else: + projection = (1./2) * np.ones((2,2)) + diagonal_projections = [np.matmul(X[i], projection) for i in range(len(X))] + if self.kernel_approx is not None: + approx = [self.kernel_approx.transform(X[i]) for i in range(len(X))] + approx_diagonal = [self.kernel_approx.transform(diagonal_projections[i]) for i in range(len(X))] + for i in range(len(X)): + for j in range(len(self.diagrams_)): + if self.kernel_approx is not None: + Z = np.concatenate([approx[i], approx_diagonal[i], self.approx_[j], self.approx_diagonal_[j]], axis=0) + U, V = np.sum(np.concatenate([approx[i], self.approx_diagonal_[j]], axis=0), axis=0), np.sum(np.concatenate([self.approx_[j], approx_diagonal[i]], axis=0), axis=0) + vectori, vectorj = np.abs(np.matmul(Z, U.T)), np.abs(np.matmul(Z, V.T)) + vectori_sum, vectorj_sum = np.sum(vectori), np.sum(vectorj) + if vectori_sum != 0: + vectori = vectori/vectori_sum + if vectorj_sum != 0: + vectorj = vectorj/vectorj_sum + Xfit[i,j] = np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) + else: + Z = np.concatenate([X[i], diagonal_projections[i], self.diagrams_[j], self.diagonal_projections_[j]], axis=0) + U, V = np.concatenate([X[i], self.diagonal_projections_[j]], axis=0), np.concatenate([self.diagrams_[j], diagonal_projections[i]], axis=0) + vectori = np.sum(np.exp(-np.square(pairwise_distances(Z,U))/(2 * np.square(self.bandwidth)))/(self.bandwidth * np.sqrt(2*np.pi)), axis=1) + vectorj = np.sum(np.exp(-np.square(pairwise_distances(Z,V))/(2 * np.square(self.bandwidth)))/(self.bandwidth * np.sqrt(2*np.pi)), axis=1) + vectori_sum, vectorj_sum = np.sum(vectori), np.sum(vectorj) + if vectori_sum != 0: + vectori = vectori/vectori_sum + if vectorj_sum != 0: + vectorj = vectorj/vectorj_sum + Xfit[i,j] = np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) + return Xfit diff --git a/src/python/gudhi/representations/preprocessing.py b/src/python/gudhi/representations/preprocessing.py new file mode 100644 index 00000000..a39b00e4 --- /dev/null +++ b/src/python/gudhi/representations/preprocessing.py @@ -0,0 +1,305 @@ +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Mathieu Carrière +# +# Copyright (C) 2018-2019 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification + +import numpy as np +from sklearn.base import BaseEstimator, TransformerMixin +from sklearn.preprocessing import StandardScaler + +############################################# +# Preprocessing ############################# +############################################# + +class BirthPersistenceTransform(BaseEstimator, TransformerMixin): + """ + This is a class for the affine transformation (x,y) -> (x,y-x) to be applied on persistence diagrams. + """ + def __init__(self): + """ + Constructor for BirthPersistenceTransform class. + """ + return None + + def fit(self, X, y=None): + """ + Fit the BirthPersistenceTransform class on a list of persistence diagrams (this function actually does nothing but is useful when BirthPersistenceTransform is included in a scikit-learn Pipeline). + + Parameters: + X (list of n x 2 numpy array): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + return self + + def transform(self, X): + """ + Apply the BirthPersistenceTransform function on the persistence diagrams. + + Parameters: + X (list of n x 2 numpy array): input persistence diagrams. + + Returns: + list of n x 2 numpy array: transformed persistence diagrams. + """ + Xfit = [] + for diag in X: + #new_diag = np.empty(diag.shape) + #np.copyto(new_diag, diag) + new_diag = np.copy(diag) + new_diag[:,1] = new_diag[:,1] - new_diag[:,0] + Xfit.append(new_diag) + return Xfit + +class Clamping(BaseEstimator, TransformerMixin): + """ + This is a class for clamping values. It can be used as a parameter for the DiagramScaler class, for instance if you want to clamp abscissae or ordinates of persistence diagrams. + """ + def __init__(self, minimum=-np.inf, maximum=np.inf): + """ + Constructor for the Clamping class. + + Parameters: + limit (double): clamping value (default np.inf). + """ + self.minimum = minimum + self.maximum = maximum + + def fit(self, X, y=None): + """ + Fit the Clamping class on a list of values (this function actually does nothing but is useful when Clamping is included in a scikit-learn Pipeline). + + Parameters: + X (numpy array of size n): input values. + y (n x 1 array): value labels (unused). + """ + return self + + def transform(self, X): + """ + Clamp list of values. + + Parameters: + X (numpy array of size n): input list of values. + + Returns: + numpy array of size n: output list of values. + """ + Xfit = np.clip(X, self.minimum, self.maximum) + return Xfit + +class DiagramScaler(BaseEstimator, TransformerMixin): + """ + This is a class for preprocessing persistence diagrams with a given list of scalers, such as those included in scikit-learn. + """ + def __init__(self, use=False, scalers=[]): + """ + Constructor for the DiagramScaler class. + + Parameters: + use (bool): whether to use the class or not (default False). + scalers (list of classes): list of scalers to be fit on the persistence diagrams (default []). Each element of the list is a tuple with two elements: the first one is a list of coordinates, and the second one is a scaler (i.e. a class with fit() and transform() methods) that is going to be applied to these coordinates. Common scalers can be found in the scikit-learn library (such as MinMaxScaler for instance). + """ + self.scalers = scalers + self.use = use + + def fit(self, X, y=None): + """ + Fit the DiagramScaler class on a list of persistence diagrams: persistence diagrams are concatenated in a big numpy array, and scalers are fit (by calling their fit() method) on their corresponding coordinates in this big array. + + Parameters: + X (list of n x 2 or n x 1 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + if self.use: + if len(X) == 1: + P = X[0] + else: + P = np.concatenate(X,0) + for (indices, scaler) in self.scalers: + scaler.fit(np.reshape(P[:,indices], [-1, 1])) + return self + + def transform(self, X): + """ + Apply the DiagramScaler function on the persistence diagrams. The fitted scalers are applied (by calling their transform() method) to their corresponding coordinates in each persistence diagram individually. + + Parameters: + X (list of n x 2 or n x 1 numpy arrays): input persistence diagrams. + + Returns: + list of n x 2 or n x 1 numpy arrays: transformed persistence diagrams. + """ + Xfit = [np.copy(d) for d in X] + if self.use: + for i in range(len(Xfit)): + if Xfit[i].shape[0] > 0: + for (indices, scaler) in self.scalers: + for I in indices: + Xfit[i][:,I] = np.squeeze(scaler.transform(np.reshape(Xfit[i][:,I], [-1,1]))) + return Xfit + +class Padding(BaseEstimator, TransformerMixin): + """ + This is a class for padding a list of persistence diagrams with dummy points, so that all persistence diagrams end up with the same number of points. + """ + def __init__(self, use=False): + """ + Constructor for the Padding class. + + Parameters: + use (bool): whether to use the class or not (default False). + """ + self.use = use + + def fit(self, X, y=None): + """ + Fit the Padding class on a list of persistence diagrams (this function actually does nothing but is useful when Padding is included in a scikit-learn Pipeline). + + Parameters: + X (list of n x 2 or n x 1 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + self.max_pts = max([len(diag) for diag in X]) + return self + + def transform(self, X): + """ + Add dummy points to each persistence diagram so that they all have the same cardinality. All points are given an additional coordinate indicating if the point was added after padding (0) or already present before (1). + + Parameters: + X (list of n x 2 or n x 1 numpy arrays): input persistence diagrams. + + Returns: + list of n x 3 or n x 2 numpy arrays: padded persistence diagrams. + """ + if self.use: + Xfit, num_diag = [], len(X) + for diag in X: + diag_pad = np.pad(diag, ((0,max(0, self.max_pts - diag.shape[0])), (0,1)), "constant", constant_values=((0,0),(0,0))) + diag_pad[:diag.shape[0],2] = np.ones(diag.shape[0]) + Xfit.append(diag_pad) + else: + Xfit = X + return Xfit + +class ProminentPoints(BaseEstimator, TransformerMixin): + """ + This is a class for removing points that are close or far from the diagonal in persistence diagrams. If persistence diagrams are n x 2 numpy arrays (i.e. persistence diagrams with ordinary features), points are ordered and thresholded by distance-to-diagonal. If persistence diagrams are n x 1 numpy arrays (i.e. persistence diagrams with essential features), points are not ordered and thresholded by first coordinate. + """ + def __init__(self, use=False, num_pts=10, threshold=-1, location="upper"): + """ + Constructor for the ProminentPoints class. + + Parameters: + use (bool): whether to use the class or not (default False). + location (string): either "upper" or "lower" (default "upper"). Whether to keep the points that are far away ("upper") or close ("lower") to the diagonal. + num_pts (int): cardinality threshold (default 10). If location == "upper", keep the top **num_pts** points that are the farthest away from the diagonal. If location == "lower", keep the top **num_pts** points that are the closest to the diagonal. + threshold (double): distance-to-diagonal threshold (default -1). If location == "upper", keep the points that are at least at a distance **threshold** from the diagonal. If location == "lower", keep the points that are at most at a distance **threshold** from the diagonal. + """ + self.num_pts = num_pts + self.threshold = threshold + self.use = use + self.location = location + + def fit(self, X, y=None): + """ + Fit the ProminentPoints class on a list of persistence diagrams (this function actually does nothing but is useful when ProminentPoints is included in a scikit-learn Pipeline). + + Parameters: + X (list of n x 2 or n x 1 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + return self + + def transform(self, X): + """ + If location == "upper", first select the top **num_pts** points that are the farthest away from the diagonal, then select and return from these points the ones that are at least at distance **threshold** from the diagonal for each persistence diagram individually. If location == "lower", first select the top **num_pts** points that are the closest to the diagonal, then select and return from these points the ones that are at most at distance **threshold** from the diagonal for each persistence diagram individually. + + Parameters: + X (list of n x 2 or n x 1 numpy arrays): input persistence diagrams. + + Returns: + list of n x 2 or n x 1 numpy arrays: thresholded persistence diagrams. + """ + if self.use: + Xfit, num_diag = [], len(X) + for i in range(num_diag): + diag = X[i] + if diag.shape[1] >= 2: + if diag.shape[0] > 0: + pers = np.abs(diag[:,1] - diag[:,0]) + idx_thresh = pers >= self.threshold + thresh_diag, thresh_pers = diag[idx_thresh], pers[idx_thresh] + sort_index = np.flip(np.argsort(thresh_pers, axis=None), 0) + if self.location == "upper": + new_diag = thresh_diag[sort_index[:min(self.num_pts, thresh_diag.shape[0])],:] + if self.location == "lower": + new_diag = np.concatenate( [ thresh_diag[sort_index[min(self.num_pts, thresh_diag.shape[0]):],:], diag[~idx_thresh] ], axis=0) + else: + new_diag = diag + + else: + if diag.shape[0] > 0: + birth = diag[:,:1] + idx_thresh = birth >= self.threshold + thresh_diag, thresh_birth = diag[idx_thresh], birth[idx_thresh] + if self.location == "upper": + new_diag = thresh_diag[:min(self.num_pts, thresh_diag.shape[0]),:] + if self.location == "lower": + new_diag = np.concatenate( [ thresh_diag[min(self.num_pts, thresh_diag.shape[0]):,:], diag[~idx_thresh] ], axis=0) + else: + new_diag = diag + + Xfit.append(new_diag) + else: + Xfit = X + return Xfit + +class DiagramSelector(BaseEstimator, TransformerMixin): + """ + This is a class for extracting finite or essential points in persistence diagrams. + """ + def __init__(self, use=False, limit=np.inf, point_type="finite"): + """ + Constructor for the DiagramSelector class. + + Parameters: + use (bool): whether to use the class or not (default False). + limit (double): second coordinate value that is the criterion for being an essential point (default numpy.inf). + point_type (string): either "finite" or "essential". The type of the points that are going to be extracted. + """ + self.use, self.limit, self.point_type = use, limit, point_type + + def fit(self, X, y=None): + """ + Fit the DiagramSelector class on a list of persistence diagrams (this function actually does nothing but is useful when DiagramSelector is included in a scikit-learn Pipeline). + + Parameters: + X (list of n x 2 or n x 1 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + return self + + def transform(self, X): + """ + Extract and return the finite or essential points of each persistence diagram individually. + + Parameters: + X (list of n x 2 or n x 1 numpy arrays): input persistence diagrams. + + Returns: + list of n x 2 or n x 1 numpy arrays: extracted persistence diagrams. + """ + if self.use: + Xfit, num_diag = [], len(X) + if self.point_type == "finite": + Xfit = [ diag[diag[:,1] < self.limit] if diag.shape[0] != 0 else diag for diag in X] + else: + Xfit = [ diag[diag[:,1] >= self.limit, 0:1] if diag.shape[0] != 0 else diag for diag in X] + else: + Xfit = X + return Xfit diff --git a/src/python/gudhi/representations/vector_methods.py b/src/python/gudhi/representations/vector_methods.py new file mode 100644 index 00000000..fe26dbe2 --- /dev/null +++ b/src/python/gudhi/representations/vector_methods.py @@ -0,0 +1,492 @@ +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Mathieu Carrière +# +# Copyright (C) 2018-2019 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification + +import numpy as np +from sklearn.base import BaseEstimator, TransformerMixin +from sklearn.preprocessing import MinMaxScaler, MaxAbsScaler +from sklearn.neighbors import DistanceMetric + +from .preprocessing import DiagramScaler, BirthPersistenceTransform + +############################################# +# Finite Vectorization methods ############## +############################################# + +class PersistenceImage(BaseEstimator, TransformerMixin): + """ + This is a class for computing persistence images from a list of persistence diagrams. A persistence image is a 2D function computed from a persistence diagram by convolving the diagram points with a weighted Gaussian kernel. The plane is then discretized into an image with pixels, which is flattened and returned as a vector. See http://jmlr.org/papers/v18/16-337.html for more details. + """ + def __init__(self, bandwidth=1., weight=lambda x: 1, resolution=[20,20], im_range=[np.nan, np.nan, np.nan, np.nan]): + """ + Constructor for the PersistenceImage class. + + Parameters: + bandwidth (double): bandwidth of the Gaussian kernel (default 1.). + weight (function): weight function for the persistence diagram points (default constant function, ie lambda x: 1). This function must be defined on 2D points, ie lists or numpy arrays of the form [p_x,p_y]. + resolution ([int,int]): size (in pixels) of the persistence image (default [20,20]). + im_range ([double,double,double,double]): minimum and maximum of each axis of the persistence image, of the form [x_min, x_max, y_min, y_max] (default [numpy.nan, numpy.nan, numpy.nan, numpyp.nan]). If one of the values is numpy.nan, it can be computed from the persistence diagrams with the fit() method. + """ + self.bandwidth, self.weight = bandwidth, weight + self.resolution, self.im_range = resolution, im_range + + def fit(self, X, y=None): + """ + Fit the PersistenceImage class on a list of persistence diagrams: if any of the values in **im_range** is numpy.nan, replace it with the corresponding value computed on the given list of persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + if np.isnan(np.array(self.im_range)).any(): + new_X = BirthPersistenceTransform().fit_transform(X) + pre = DiagramScaler(use=True, scalers=[([0], MinMaxScaler()), ([1], MinMaxScaler())]).fit(new_X,y) + [mx,my],[Mx,My] = [pre.scalers[0][1].data_min_[0], pre.scalers[1][1].data_min_[0]], [pre.scalers[0][1].data_max_[0], pre.scalers[1][1].data_max_[0]] + self.im_range = np.where(np.isnan(np.array(self.im_range)), np.array([mx, Mx, my, My]), np.array(self.im_range)) + return self + + def transform(self, X): + """ + Compute the persistence image for each persistence diagram individually and store the results in a single numpy array. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array with shape (number of diagrams) x (number of pixels = **resolution[0]** x **resolution[1]**): output persistence images. + """ + num_diag, Xfit = len(X), [] + new_X = BirthPersistenceTransform().fit_transform(X) + + for i in range(num_diag): + + diagram, num_pts_in_diag = new_X[i], X[i].shape[0] + + w = np.empty(num_pts_in_diag) + for j in range(num_pts_in_diag): + w[j] = self.weight(diagram[j,:]) + + x_values, y_values = np.linspace(self.im_range[0], self.im_range[1], self.resolution[0]), np.linspace(self.im_range[2], self.im_range[3], self.resolution[1]) + Xs, Ys = np.tile((diagram[:,0][:,np.newaxis,np.newaxis]-x_values[np.newaxis,np.newaxis,:]),[1,self.resolution[1],1]), np.tile(diagram[:,1][:,np.newaxis,np.newaxis]-y_values[np.newaxis,:,np.newaxis],[1,1,self.resolution[0]]) + image = np.tensordot(w, np.exp((-np.square(Xs)-np.square(Ys))/(2*np.square(self.bandwidth)))/(np.square(self.bandwidth)*2*np.pi), 1) + + Xfit.append(image.flatten()[np.newaxis,:]) + + Xfit = np.concatenate(Xfit,0) + + return Xfit + +class Landscape(BaseEstimator, TransformerMixin): + """ + This is a class for computing persistence landscapes from a list of persistence diagrams. A persistence landscape is a collection of 1D piecewise-linear functions computed from the rank function associated to the persistence diagram. These piecewise-linear functions are then sampled evenly on a given range and the corresponding vectors of samples are concatenated and returned. See http://jmlr.org/papers/v16/bubenik15a.html for more details. + """ + def __init__(self, num_landscapes=5, resolution=100, sample_range=[np.nan, np.nan]): + """ + Constructor for the Landscape class. + + Parameters: + num_landscapes (int): number of piecewise-linear functions to output (default 5). + resolution (int): number of sample for all piecewise-linear functions (default 100). + sample_range ([double, double]): minimum and maximum of all piecewise-linear function domains, of the form [x_min, x_max] (default [numpy.nan, numpy.nan]). It is the interval on which samples will be drawn evenly. If one of the values is numpy.nan, it can be computed from the persistence diagrams with the fit() method. + """ + self.num_landscapes, self.resolution, self.sample_range = num_landscapes, resolution, sample_range + self.nan_in_range = np.isnan(np.array(self.sample_range)) + self.new_resolution = self.resolution + self.nan_in_range.sum() + + def fit(self, X, y=None): + """ + Fit the Landscape class on a list of persistence diagrams: if any of the values in **sample_range** is numpy.nan, replace it with the corresponding value computed on the given list of persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + if self.nan_in_range.any(): + pre = DiagramScaler(use=True, scalers=[([0], MinMaxScaler()), ([1], MinMaxScaler())]).fit(X,y) + [mx,my],[Mx,My] = [pre.scalers[0][1].data_min_[0], pre.scalers[1][1].data_min_[0]], [pre.scalers[0][1].data_max_[0], pre.scalers[1][1].data_max_[0]] + self.sample_range = np.where(self.nan_in_range, np.array([mx, My]), np.array(self.sample_range)) + return self + + def transform(self, X): + """ + Compute the persistence landscape for each persistence diagram individually and concatenate the results. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array with shape (number of diagrams) x (number of samples = **num_landscapes** x **resolution**): output persistence landscapes. + """ + num_diag, Xfit = len(X), [] + x_values = np.linspace(self.sample_range[0], self.sample_range[1], self.new_resolution) + step_x = x_values[1] - x_values[0] + + for i in range(num_diag): + + diagram, num_pts_in_diag = X[i], X[i].shape[0] + + ls = np.zeros([self.num_landscapes, self.new_resolution]) + + events = [] + for j in range(self.new_resolution): + events.append([]) + + for j in range(num_pts_in_diag): + [px,py] = diagram[j,:2] + min_idx = np.clip(np.ceil((px - self.sample_range[0]) / step_x).astype(int), 0, self.new_resolution) + mid_idx = np.clip(np.ceil((0.5*(py+px) - self.sample_range[0]) / step_x).astype(int), 0, self.new_resolution) + max_idx = np.clip(np.ceil((py - self.sample_range[0]) / step_x).astype(int), 0, self.new_resolution) + + if min_idx < self.new_resolution and max_idx > 0: + + landscape_value = self.sample_range[0] + min_idx * step_x - px + for k in range(min_idx, mid_idx): + events[k].append(landscape_value) + landscape_value += step_x + + landscape_value = py - self.sample_range[0] - mid_idx * step_x + for k in range(mid_idx, max_idx): + events[k].append(landscape_value) + landscape_value -= step_x + + for j in range(self.new_resolution): + events[j].sort(reverse=True) + for k in range( min(self.num_landscapes, len(events[j])) ): + ls[k,j] = events[j][k] + + if self.nan_in_range[0]: + ls = ls[:,1:] + if self.nan_in_range[1]: + ls = ls[:,:-1] + ls = np.sqrt(2)*np.reshape(ls,[1,-1]) + Xfit.append(ls) + + Xfit = np.concatenate(Xfit,0) + + return Xfit + +class Silhouette(BaseEstimator, TransformerMixin): + """ + This is a class for computing persistence silhouettes from a list of persistence diagrams. A persistence silhouette is computed by taking a weighted average of the collection of 1D piecewise-linear functions given by the persistence landscapes, and then by evenly sampling this average on a given range. Finally, the corresponding vector of samples is returned. See https://arxiv.org/abs/1312.0308 for more details. + """ + def __init__(self, weight=lambda x: 1, resolution=100, sample_range=[np.nan, np.nan]): + """ + Constructor for the Silhouette class. + + Parameters: + weight (function): weight function for the persistence diagram points (default constant function, ie lambda x: 1). This function must be defined on 2D points, ie on lists or numpy arrays of the form [p_x,p_y]. + resolution (int): number of samples for the weighted average (default 100). + sample_range ([double, double]): minimum and maximum for the weighted average domain, of the form [x_min, x_max] (default [numpy.nan, numpy.nan]). It is the interval on which samples will be drawn evenly. If one of the values is numpy.nan, it can be computed from the persistence diagrams with the fit() method. + """ + self.weight, self.resolution, self.sample_range = weight, resolution, sample_range + + def fit(self, X, y=None): + """ + Fit the Silhouette class on a list of persistence diagrams: if any of the values in **sample_range** is numpy.nan, replace it with the corresponding value computed on the given list of persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + if np.isnan(np.array(self.sample_range)).any(): + pre = DiagramScaler(use=True, scalers=[([0], MinMaxScaler()), ([1], MinMaxScaler())]).fit(X,y) + [mx,my],[Mx,My] = [pre.scalers[0][1].data_min_[0], pre.scalers[1][1].data_min_[0]], [pre.scalers[0][1].data_max_[0], pre.scalers[1][1].data_max_[0]] + self.sample_range = np.where(np.isnan(np.array(self.sample_range)), np.array([mx, My]), np.array(self.sample_range)) + return self + + def transform(self, X): + """ + Compute the persistence silhouette for each persistence diagram individually and concatenate the results. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array with shape (number of diagrams) x (**resolution**): output persistence silhouettes. + """ + num_diag, Xfit = len(X), [] + x_values = np.linspace(self.sample_range[0], self.sample_range[1], self.resolution) + step_x = x_values[1] - x_values[0] + + for i in range(num_diag): + + diagram, num_pts_in_diag = X[i], X[i].shape[0] + + sh, weights = np.zeros(self.resolution), np.zeros(num_pts_in_diag) + for j in range(num_pts_in_diag): + weights[j] = self.weight(diagram[j,:]) + total_weight = np.sum(weights) + + for j in range(num_pts_in_diag): + + [px,py] = diagram[j,:2] + weight = weights[j] / total_weight + min_idx = np.clip(np.ceil((px - self.sample_range[0]) / step_x).astype(int), 0, self.resolution) + mid_idx = np.clip(np.ceil((0.5*(py+px) - self.sample_range[0]) / step_x).astype(int), 0, self.resolution) + max_idx = np.clip(np.ceil((py - self.sample_range[0]) / step_x).astype(int), 0, self.resolution) + + if min_idx < self.resolution and max_idx > 0: + + silhouette_value = self.sample_range[0] + min_idx * step_x - px + for k in range(min_idx, mid_idx): + sh[k] += weight * silhouette_value + silhouette_value += step_x + + silhouette_value = py - self.sample_range[0] - mid_idx * step_x + for k in range(mid_idx, max_idx): + sh[k] += weight * silhouette_value + silhouette_value -= step_x + + Xfit.append(np.reshape(np.sqrt(2) * sh, [1,-1])) + + Xfit = np.concatenate(Xfit, 0) + + return Xfit + +class BettiCurve(BaseEstimator, TransformerMixin): + """ + This is a class for computing Betti curves from a list of persistence diagrams. A Betti curve is a 1D piecewise-constant function obtained from the rank function. It is sampled evenly on a given range and the vector of samples is returned. See https://www.researchgate.net/publication/316604237_Time_Series_Classification_via_Topological_Data_Analysis for more details. + """ + def __init__(self, resolution=100, sample_range=[np.nan, np.nan]): + """ + Constructor for the BettiCurve class. + + Parameters: + resolution (int): number of sample for the piecewise-constant function (default 100). + sample_range ([double, double]): minimum and maximum of the piecewise-constant function domain, of the form [x_min, x_max] (default [numpy.nan, numpy.nan]). It is the interval on which samples will be drawn evenly. If one of the values is numpy.nan, it can be computed from the persistence diagrams with the fit() method. + """ + self.resolution, self.sample_range = resolution, sample_range + + def fit(self, X, y=None): + """ + Fit the BettiCurve class on a list of persistence diagrams: if any of the values in **sample_range** is numpy.nan, replace it with the corresponding value computed on the given list of persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + if np.isnan(np.array(self.sample_range)).any(): + pre = DiagramScaler(use=True, scalers=[([0], MinMaxScaler()), ([1], MinMaxScaler())]).fit(X,y) + [mx,my],[Mx,My] = [pre.scalers[0][1].data_min_[0], pre.scalers[1][1].data_min_[0]], [pre.scalers[0][1].data_max_[0], pre.scalers[1][1].data_max_[0]] + self.sample_range = np.where(np.isnan(np.array(self.sample_range)), np.array([mx, My]), np.array(self.sample_range)) + return self + + def transform(self, X): + """ + Compute the Betti curve for each persistence diagram individually and concatenate the results. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array with shape (number of diagrams) x (**resolution**): output Betti curves. + """ + num_diag, Xfit = len(X), [] + x_values = np.linspace(self.sample_range[0], self.sample_range[1], self.resolution) + step_x = x_values[1] - x_values[0] + + for i in range(num_diag): + + diagram, num_pts_in_diag = X[i], X[i].shape[0] + + bc = np.zeros(self.resolution) + for j in range(num_pts_in_diag): + [px,py] = diagram[j,:2] + min_idx = np.clip(np.ceil((px - self.sample_range[0]) / step_x).astype(int), 0, self.resolution) + max_idx = np.clip(np.ceil((py - self.sample_range[0]) / step_x).astype(int), 0, self.resolution) + for k in range(min_idx, max_idx): + bc[k] += 1 + + Xfit.append(np.reshape(bc,[1,-1])) + + Xfit = np.concatenate(Xfit, 0) + + return Xfit + +class Entropy(BaseEstimator, TransformerMixin): + """ + This is a class for computing persistence entropy. Persistence entropy is a statistic for persistence diagrams inspired from Shannon entropy. This statistic can also be used to compute a feature vector, called the entropy summary function. See https://arxiv.org/pdf/1803.08304.pdf for more details. Note that a previous implementation was contributed by Manuel Soriano-Trigueros. + """ + def __init__(self, mode="scalar", normalized=True, resolution=100, sample_range=[np.nan, np.nan]): + """ + Constructor for the Entropy class. + + Parameters: + mode (string): what entropy to compute: either "scalar" for computing the entropy statistics, or "vector" for computing the entropy summary functions (default "scalar"). + normalized (bool): whether to normalize the entropy summary function (default True). Used only if **mode** = "vector". + resolution (int): number of sample for the entropy summary function (default 100). Used only if **mode** = "vector". + sample_range ([double, double]): minimum and maximum of the entropy summary function domain, of the form [x_min, x_max] (default [numpy.nan, numpy.nan]). It is the interval on which samples will be drawn evenly. If one of the values is numpy.nan, it can be computed from the persistence diagrams with the fit() method. Used only if **mode** = "vector". + """ + self.mode, self.normalized, self.resolution, self.sample_range = mode, normalized, resolution, sample_range + + def fit(self, X, y=None): + """ + Fit the Entropy class on a list of persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + if np.isnan(np.array(self.sample_range)).any(): + pre = DiagramScaler(use=True, scalers=[([0], MinMaxScaler()), ([1], MinMaxScaler())]).fit(X,y) + [mx,my],[Mx,My] = [pre.scalers[0][1].data_min_[0], pre.scalers[1][1].data_min_[0]], [pre.scalers[0][1].data_max_[0], pre.scalers[1][1].data_max_[0]] + self.sample_range = np.where(np.isnan(np.array(self.sample_range)), np.array([mx, My]), np.array(self.sample_range)) + return self + + def transform(self, X): + """ + Compute the entropy for each persistence diagram individually and concatenate the results. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array with shape (number of diagrams) x (1 if **mode** = "scalar" else **resolution**): output entropy. + """ + num_diag, Xfit = len(X), [] + x_values = np.linspace(self.sample_range[0], self.sample_range[1], self.resolution) + step_x = x_values[1] - x_values[0] + new_X = BirthPersistenceTransform().fit_transform(X) + + for i in range(num_diag): + + orig_diagram, diagram, num_pts_in_diag = X[i], new_X[i], X[i].shape[0] + new_diagram = DiagramScaler(use=True, scalers=[([1], MaxAbsScaler())]).fit_transform([diagram])[0] + + if self.mode == "scalar": + ent = - np.sum( np.multiply(new_diagram[:,1], np.log(new_diagram[:,1])) ) + Xfit.append(np.array([[ent]])) + + else: + ent = np.zeros(self.resolution) + for j in range(num_pts_in_diag): + [px,py] = orig_diagram[j,:2] + min_idx = np.clip(np.ceil((px - self.sample_range[0]) / step_x).astype(int), 0, self.resolution) + max_idx = np.clip(np.ceil((py - self.sample_range[0]) / step_x).astype(int), 0, self.resolution) + for k in range(min_idx, max_idx): + ent[k] += (-1) * new_diagram[j,1] * np.log(new_diagram[j,1]) + if self.normalized: + ent = ent / np.linalg.norm(ent, ord=1) + Xfit.append(np.reshape(ent,[1,-1])) + + Xfit = np.concatenate(Xfit, 0) + + return Xfit + +class TopologicalVector(BaseEstimator, TransformerMixin): + """ + This is a class for computing topological vectors from a list of persistence diagrams. The topological vector associated to a persistence diagram is the sorted vector of a slight modification of the pairwise distances between the persistence diagram points. See https://diglib.eg.org/handle/10.1111/cgf12692 for more details. + """ + def __init__(self, threshold=10): + """ + Constructor for the TopologicalVector class. + + Parameters: + threshold (int): number of distances to keep (default 10). This is the dimension of the topological vector. If -1, this threshold is computed from the list of persistence diagrams by considering the one with the largest number of points and using the dimension of its corresponding topological vector as threshold. + """ + self.threshold = threshold + + def fit(self, X, y=None): + """ + Fit the TopologicalVector class on a list of persistence diagrams (this function actually does nothing but is useful when TopologicalVector is included in a scikit-learn Pipeline). + + Parameters: + X (list of n x 2 or n x 1 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + return self + + def transform(self, X): + """ + Compute the topological vector for each persistence diagram individually and concatenate the results. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array with shape (number of diagrams) x (**threshold**): output topological vectors. + """ + if self.threshold == -1: + thresh = np.array([X[i].shape[0] for i in range(len(X))]).max() + else: + thresh = self.threshold + + num_diag = len(X) + Xfit = np.zeros([num_diag, thresh]) + + for i in range(num_diag): + + diagram, num_pts_in_diag = X[i], X[i].shape[0] + pers = 0.5 * (diagram[:,1]-diagram[:,0]) + min_pers = np.minimum(pers,np.transpose(pers)) + distances = DistanceMetric.get_metric("chebyshev").pairwise(diagram) + vect = np.flip(np.sort(np.triu(np.minimum(distances, min_pers)), axis=None), 0) + dim = min(len(vect), thresh) + Xfit[i, :dim] = vect[:dim] + + return Xfit + +class ComplexPolynomial(BaseEstimator, TransformerMixin): + """ + This is a class for computing complex polynomials from a list of persistence diagrams. The persistence diagram points are seen as the roots of some complex polynomial, whose coefficients are returned in a complex vector. See https://link.springer.com/chapter/10.1007%2F978-3-319-23231-7_27 for more details. + """ + def __init__(self, polynomial_type="R", threshold=10): + """ + Constructor for the ComplexPolynomial class. + + Parameters: + polynomial_type (char): either "R", "S" or "T" (default "R"). Type of complex polynomial that is going to be computed (explained in https://link.springer.com/chapter/10.1007%2F978-3-319-23231-7_27). + threshold (int): number of coefficients (default 10). This is the dimension of the complex vector of coefficients, i.e. the number of coefficients corresponding to the largest degree terms of the polynomial. If -1, this threshold is computed from the list of persistence diagrams by considering the one with the largest number of points and using the dimension of its corresponding complex vector of coefficients as threshold. + """ + self.threshold, self.polynomial_type = threshold, polynomial_type + + def fit(self, X, y=None): + """ + Fit the ComplexPolynomial class on a list of persistence diagrams (this function actually does nothing but is useful when ComplexPolynomial is included in a scikit-learn Pipeline). + + Parameters: + X (list of n x 2 or n x 1 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + return self + + def transform(self, X): + """ + Compute the complex vector of coefficients for each persistence diagram individually and concatenate the results. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array with shape (number of diagrams) x (**threshold**): output complex vectors of coefficients. + """ + if self.threshold == -1: + thresh = np.array([X[i].shape[0] for i in range(len(X))]).max() + else: + thresh = self.threshold + + Xfit = np.zeros([len(X), thresh]) + 1j * np.zeros([len(X), thresh]) + for d in range(len(X)): + D, N = X[d], X[d].shape[0] + if self.polynomial_type == "R": + roots = D[:,0] + 1j * D[:,1] + elif self.polynomial_type == "S": + alpha = np.linalg.norm(D, axis=1) + alpha = np.where(alpha==0, np.ones(N), alpha) + roots = np.multiply( np.multiply( (D[:,0]+1j*D[:,1]), (D[:,1]-D[:,0]) ), 1./(np.sqrt(2)*alpha) ) + elif self.polynomial_type == "T": + alpha = np.linalg.norm(D, axis=1) + roots = np.multiply( (D[:,1]-D[:,0])/2, np.cos(alpha) - np.sin(alpha) + 1j * (np.cos(alpha) + np.sin(alpha)) ) + coeff = [0] * (N+1) + coeff[N] = 1 + for i in range(1, N+1): + for j in range(N-i-1, N): + coeff[j] += ((-1) * roots[i-1] * coeff[j+1]) + coeff = np.array(coeff[::-1])[1:] + Xfit[d, :min(thresh, coeff.shape[0])] = coeff[:min(thresh, coeff.shape[0])] + return Xfit diff --git a/src/python/gudhi/rips_complex.pyx b/src/python/gudhi/rips_complex.pyx index f2cd6a8d..cbbbab0d 100644 --- a/src/python/gudhi/rips_complex.pyx +++ b/src/python/gudhi/rips_complex.pyx @@ -8,15 +8,14 @@ from libc.stdint cimport intptr_t from gudhi.simplex_tree cimport * from gudhi.simplex_tree import SimplexTree -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 9f490271..4a3cd9bc 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -2,15 +2,14 @@ from libc.stdint cimport intptr_t from numpy import array as np_array cimport simplex_tree -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -75,13 +74,22 @@ cdef class SimplexTree: return self.get_ptr().simplex_filtration(simplex) def assign_filtration(self, simplex, filtration): - """This function assigns the simplicial complex filtration value for a + """This function assigns a new filtration value to a given N-simplex. :param simplex: The N-simplex, represented by a list of vertex. :type simplex: list of int. - :param filtration: The simplicial complex filtration value. + :param filtration: The new filtration value. :type filtration: float + + .. note:: + Beware that after this operation, the structure may not be a valid + filtration anymore, a simplex could have a lower filtration value + than one of its faces. Callers are responsible for fixing this + (with more :meth:`assign_filtration` or + :meth:`make_filtration_non_decreasing` for instance) before calling + any function that relies on the filtration property, like + :meth:`initialize_filtration`. """ self.get_ptr().assign_simplex_filtration(simplex, filtration) @@ -362,7 +370,7 @@ cdef class SimplexTree: value than its faces by increasing the filtration values. :returns: True if any filtration value was modified, - False if the filtration was already non-decreasing. + False if the filtration was already non-decreasing. :rtype: bool diff --git a/src/python/gudhi/strong_witness_complex.pyx b/src/python/gudhi/strong_witness_complex.pyx index e757abea..66d49b49 100644 --- a/src/python/gudhi/strong_witness_complex.pyx +++ b/src/python/gudhi/strong_witness_complex.pyx @@ -6,15 +6,14 @@ from libc.stdint cimport intptr_t from gudhi.simplex_tree cimport * from gudhi.simplex_tree import SimplexTree -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -69,7 +68,7 @@ cdef class StrongWitnessComplex: """ stree = SimplexTree() cdef intptr_t stree_int_ptr=stree.thisptr - if limit_dimension is not -1: + if limit_dimension != -1: self.thisptr.create_simplex_tree(<Simplex_tree_interface_full_featured*>stree_int_ptr, max_alpha_square, limit_dimension) else: diff --git a/src/python/gudhi/subsampling.pyx b/src/python/gudhi/subsampling.pyx index 1135c1fb..e0cd1348 100644 --- a/src/python/gudhi/subsampling.pyx +++ b/src/python/gudhi/subsampling.pyx @@ -4,15 +4,14 @@ from libcpp.string cimport string from libcpp cimport bool import os -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -44,15 +43,15 @@ def choose_n_farthest_points(points=None, off_file='', nb_points=0, starting_poi :param nb_points: Number of points of the subsample. :type nb_points: unsigned. :param starting_point: The iteration starts with the landmark `starting \ - point`,which is the index of the poit to start with. If not set, this \ - index is choosen randomly. + point`,which is the index of the point to start with. If not set, this \ + index is chosen randomly. :type starting_point: unsigned. :returns: The subsample point set. :rtype: vector[vector[double]] """ - if off_file is not '': + if off_file: if os.path.isfile(off_file): - if starting_point is '': + if starting_point == '': return subsampling_n_farthest_points_from_file(str.encode(off_file), nb_points) else: @@ -65,7 +64,7 @@ def choose_n_farthest_points(points=None, off_file='', nb_points=0, starting_poi if points is None: # Empty points points=[] - if starting_point is '': + if starting_point == '': return subsampling_n_farthest_points(points, nb_points) else: return subsampling_n_farthest_points(points, nb_points, @@ -87,7 +86,7 @@ def pick_n_random_points(points=None, off_file='', nb_points=0): :returns: The subsample point set. :rtype: vector[vector[double]] """ - if off_file is not '': + if off_file: if os.path.isfile(off_file): return subsampling_n_random_points_from_file(str.encode(off_file), nb_points) @@ -117,7 +116,7 @@ def sparsify_point_set(points=None, off_file='', min_squared_dist=0.0): :returns: The subsample point set. :rtype: vector[vector[double]] """ - if off_file is not '': + if off_file: if os.path.isfile(off_file): return subsampling_sparsify_points_from_file(str.encode(off_file), min_squared_dist) diff --git a/src/python/gudhi/tangential_complex.pyx b/src/python/gudhi/tangential_complex.pyx index 3a945fe2..f4c8b079 100644 --- a/src/python/gudhi/tangential_complex.pyx +++ b/src/python/gudhi/tangential_complex.pyx @@ -9,15 +9,14 @@ import os from gudhi.simplex_tree cimport * from gudhi.simplex_tree import SimplexTree -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -65,7 +64,7 @@ cdef class TangentialComplex: # The real cython constructor def __cinit__(self, intrisic_dim, points=None, off_file=''): - if off_file is not '': + if off_file: if os.path.isfile(off_file): self.thisptr = new Tangential_complex_interface(intrisic_dim, str.encode(off_file), True) else: @@ -92,7 +91,7 @@ cdef class TangentialComplex: Raises: ValueError: In debug mode, if the computed star dimension is too low. Try to set a bigger maximal edge length value with - :func:`~gudhi.Tangential_complex.set_max_squared_edge_length` + :meth:`set_max_squared_edge_length` if this happens. """ self.thisptr.compute_tangential_complex() @@ -167,7 +166,7 @@ cdef class TangentialComplex: :type max_squared_edge_length: double If the maximal edge length value is too low - :func:`~gudhi.Tangential_complex.compute_tangential_complex` + :meth:`compute_tangential_complex` will throw an exception in debug mode. """ self.thisptr.set_max_squared_edge_length(max_squared_edge_length) diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py new file mode 100644 index 00000000..d8a3104c --- /dev/null +++ b/src/python/gudhi/wasserstein.py @@ -0,0 +1,98 @@ +import numpy as np +import scipy.spatial.distance as sc +try: + import ot +except ImportError: + print("POT (Python Optimal Transport) package is not installed. Try to run $ conda install -c conda-forge pot ; or $ pip install POT") + +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Theo Lacombe +# +# Copyright (C) 2019 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification + +def _proj_on_diag(X): + ''' + :param X: (n x 2) array encoding the points of a persistent diagram. + :returns: (n x 2) array encoding the (respective orthogonal) projections of the points onto the diagonal + ''' + Z = (X[:,0] + X[:,1]) / 2. + return np.array([Z , Z]).T + + +def _build_dist_matrix(X, Y, p=2., q=2.): + ''' + :param X: (n x 2) numpy.array encoding the (points of the) first diagram. + :param Y: (m x 2) numpy.array encoding the second diagram. + :param q: Ground metric (i.e. norm l_q). + :param p: exponent for the Wasserstein metric. + :returns: (n+1) x (m+1) np.array encoding the cost matrix C. + For 1 <= i <= n, 1 <= j <= m, C[i,j] encodes the distance between X[i] and Y[j], while C[i, m+1] (resp. C[n+1, j]) encodes the distance (to the p) between X[i] (resp Y[j]) and its orthogonal proj onto the diagonal. + note also that C[n+1, m+1] = 0 (it costs nothing to move from the diagonal to the diagonal). + ''' + Xdiag = _proj_on_diag(X) + Ydiag = _proj_on_diag(Y) + if np.isinf(q): + C = sc.cdist(X,Y, metric='chebyshev')**p + Cxd = np.linalg.norm(X - Xdiag, ord=q, axis=1)**p + Cdy = np.linalg.norm(Y - Ydiag, ord=q, axis=1)**p + else: + C = sc.cdist(X,Y, metric='minkowski', p=q)**p + Cxd = np.linalg.norm(X - Xdiag, ord=q, axis=1)**p + Cdy = np.linalg.norm(Y - Ydiag, ord=q, axis=1)**p + Cf = np.hstack((C, Cxd[:,None])) + Cdy = np.append(Cdy, 0) + + Cf = np.vstack((Cf, Cdy[None,:])) + + return Cf + + +def _perstot(X, p, q): + ''' + :param X: (n x 2) numpy.array (points of a given diagram). + :param q: Ground metric on the (upper-half) plane (i.e. norm l_q in R^2); Default value is 2 (Euclidean norm). + :param p: exponent for Wasserstein; Default value is 2. + :returns: float, the total persistence of the diagram (that is, its distance to the empty diagram). + ''' + Xdiag = _proj_on_diag(X) + return (np.sum(np.linalg.norm(X - Xdiag, ord=q, axis=1)**p))**(1./p) + + +def wasserstein_distance(X, Y, p=2., q=2.): + ''' + :param X: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). + :param Y: (m x 2) numpy.array encoding the second diagram. + :param q: Ground metric on the (upper-half) plane (i.e. norm l_q in R^2); Default value is 2 (euclidean norm). + :param p: exponent for Wasserstein; Default value is 2. + :returns: the p-Wasserstein distance (1 <= p < infinity) with respect to the q-norm as ground metric. + :rtype: float + ''' + n = len(X) + m = len(Y) + + # handle empty diagrams + if X.size == 0: + if Y.size == 0: + return 0. + else: + return _perstot(Y, p, q) + elif Y.size == 0: + return _perstot(X, p, q) + + M = _build_dist_matrix(X, Y, p=p, q=q) + a = np.full(n+1, 1. / (n + m) ) # weight vector of the input diagram. Uniform here. + a[-1] = a[-1] * m # normalized so that we have a probability measure, required by POT + b = np.full(m+1, 1. / (n + m) ) # weight vector of the input diagram. Uniform here. + b[-1] = b[-1] * n # so that we have a probability measure, required by POT + + # Comptuation of the otcost using the ot.emd2 library. + # Note: it is the squared Wasserstein distance. + # The default numItermax=100000 is not sufficient for some examples with 5000 points, what is a good value? + ot_cost = (n+m) * ot.emd2(a, b, M, numItermax=2000000) + + return ot_cost ** (1./p) + diff --git a/src/python/gudhi/witness_complex.pyx b/src/python/gudhi/witness_complex.pyx index baa70b7a..153fc615 100644 --- a/src/python/gudhi/witness_complex.pyx +++ b/src/python/gudhi/witness_complex.pyx @@ -6,15 +6,14 @@ from libc.stdint cimport intptr_t from gudhi.simplex_tree cimport * from gudhi.simplex_tree import SimplexTree -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. - Author(s): Vincent Rouvreau - - Copyright (C) 2016 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Vincent Rouvreau +# +# Copyright (C) 2016 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -69,7 +68,7 @@ cdef class WitnessComplex: """ stree = SimplexTree() cdef intptr_t stree_int_ptr=stree.thisptr - if limit_dimension is not -1: + if limit_dimension != -1: self.thisptr.create_simplex_tree(<Simplex_tree_interface_full_featured*>stree_int_ptr, max_alpha_square, limit_dimension) else: diff --git a/src/python/include/Alpha_complex_interface.h b/src/python/include/Alpha_complex_interface.h index b3553d32..96353cc4 100644 --- a/src/python/include/Alpha_complex_interface.h +++ b/src/python/include/Alpha_complex_interface.h @@ -15,6 +15,8 @@ #include <gudhi/Alpha_complex.h> #include <CGAL/Epick_d.h> +#include <boost/range/adaptor/transformed.hpp> + #include "Simplex_tree_interface.h" #include <iostream> @@ -31,7 +33,10 @@ class Alpha_complex_interface { public: Alpha_complex_interface(const std::vector<std::vector<double>>& points) { - alpha_complex_ = new Alpha_complex<Dynamic_kernel>(points); + auto mkpt = [](std::vector<double> const& vec){ + return Point_d(vec.size(), vec.begin(), vec.end()); + }; + alpha_complex_ = new Alpha_complex<Dynamic_kernel>(boost::adaptors::transform(points, mkpt)); } Alpha_complex_interface(const std::string& off_file_name, bool from_file = true) { @@ -45,9 +50,9 @@ class Alpha_complex_interface { std::vector<double> get_point(int vh) { std::vector<double> vd; try { - Point_d ph = alpha_complex_->get_point(vh); + Point_d const& ph = alpha_complex_->get_point(vh); for (auto coord = ph.cartesian_begin(); coord < ph.cartesian_end(); coord++) - vd.push_back(*coord); + vd.push_back(CGAL::to_double(*coord)); } catch (std::out_of_range const&) { // std::out_of_range is thrown in case not found. Other exceptions must be re-thrown } diff --git a/src/python/test/test_representations.py b/src/python/test/test_representations.py new file mode 100755 index 00000000..4ff65f98 --- /dev/null +++ b/src/python/test/test_representations.py @@ -0,0 +1,11 @@ +import os +import sys +import matplotlib.pyplot as plt +# Disable graphics for testing purposes +plt.show = lambda:None +here = os.path.dirname(os.path.realpath(__file__)) +sys.path.append(here + "/../example") +import diagram_vectorizations_distances_kernels +# pytest is unhappy if there are 0 tests +def test_nothing(): + return None diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py new file mode 100755 index 00000000..a6bf9901 --- /dev/null +++ b/src/python/test/test_wasserstein_distance.py @@ -0,0 +1,48 @@ +from gudhi.wasserstein import wasserstein_distance +import numpy as np + +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. + Author(s): Theo Lacombe + + Copyright (C) 2019 Inria + + Modification(s): + - YYYY/MM Author: Description of the modification +""" + +__author__ = "Theo Lacombe" +__copyright__ = "Copyright (C) 2019 Inria" +__license__ = "MIT" + + +def test_basic_wasserstein(): + diag1 = np.array([[2.7, 3.7], [9.6, 14.0], [34.2, 34.974]]) + diag2 = np.array([[2.8, 4.45], [9.5, 14.1]]) + diag3 = np.array([[0, 2], [4, 6]]) + diag4 = np.array([[0, 3], [4, 8]]) + emptydiag = np.array([[]]) + + assert wasserstein_distance(emptydiag, emptydiag, q=2., p=1.) == 0. + assert wasserstein_distance(emptydiag, emptydiag, q=np.inf, p=1.) == 0. + assert wasserstein_distance(emptydiag, emptydiag, q=np.inf, p=2.) == 0. + assert wasserstein_distance(emptydiag, emptydiag, q=2., p=2.) == 0. + + assert wasserstein_distance(diag3, emptydiag, q=np.inf, p=1.) == 2. + assert wasserstein_distance(diag3, emptydiag, q=1., p=1.) == 4. + + assert wasserstein_distance(diag4, emptydiag, q=1., p=2.) == 5. # thank you Pythagorician triplets + assert wasserstein_distance(diag4, emptydiag, q=np.inf, p=2.) == 2.5 + assert wasserstein_distance(diag4, emptydiag, q=2., p=2.) == 3.5355339059327378 + + assert wasserstein_distance(diag1, diag2, q=2., p=1.) == 1.4453593023967701 + assert wasserstein_distance(diag1, diag2, q=2.35, p=1.74) == 0.9772734057168739 + + assert wasserstein_distance(diag1, emptydiag, q=2.35, p=1.7863) == 3.141592214572228 + + assert wasserstein_distance(diag3, diag4, q=1., p=1.) == 3. + assert wasserstein_distance(diag3, diag4, q=np.inf, p=1.) == 3. # no diag matching here + assert wasserstein_distance(diag3, diag4, q=np.inf, p=2.) == np.sqrt(5) + assert wasserstein_distance(diag3, diag4, q=1., p=2.) == np.sqrt(5) + assert wasserstein_distance(diag3, diag4, q=4.5, p=2.) == np.sqrt(5) + |
