Create v0.2.1 (#392)

* Add twine check to CI, attempt fix in README (#379)

* Tests for plotting functions and methods, other increases in test coverage (#384)

* Vectorization2 (#378)

* Fix azure on windows (#388)

* Allow more general input to ripser when metric='precomputed', improve/refactor check_point_clouds and add tests (#386)

* Add citing entry to README.rst and doc/faq.rst (#389)

* Fix markdown subsection formatting (#390)

* Prepare release 0.2.1 (#391)

Co-authored-by: Anibal M. Medina-Mardones <ammedmar@gmail.com>
Co-authored-by: REDS institute <reds-heig@users.noreply.github.com>
Co-authored-by: Guillaume Tauzin <guillaumetauzin.ut@gmail.com>

.azure-ci/docker_scripts.sh

@@ -39,7 +39,7 @@ cd /io
 pip install -e ".[dev]"
 
 # Test dev install with pytest
-pytest gtda --cov --cov-report xml
+pytest gtda --no-cov --no-coverage-upload
 
 # Uninstall giotto-tda/giotto-tda-nightly dev
 pip uninstall -y giotto-tda

.azure-ci/install_boost.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python
+
+import os
+from pathlib import Path
+import urllib.request
+import shutil
+import zipfile
+
+
+url = "https://dl.bintray.com/boostorg/release/1.72.0/source/boost_1_72_0.zip"
+boost_folder = r"C:\local"
+
+Path(boost_folder).mkdir(parents=True, exist_ok=True)
+zip_file = os.path.join(boost_folder, "1_72_0.zip")
+
+with urllib.request.urlopen(url) as response, \
+        open(zip_file, 'wb') as out_file:
+    shutil.copyfileobj(response, out_file)
+
+with zipfile.ZipFile(zip_file, 'r') as zip_ref:
+    zip_ref.extractall(boost_folder)
+
+os.remove(zip_file)

.coveragerc

@@ -1,14 +1,12 @@
 [run]
 omit =
     */gtda/externals/*
-    **/setup.py
 
-    */gtda/compose/*
-    */gtda/datasets/*
-    */gtda/images/*
-    */gtda/neural_network/*
-    */gtda/model_selection/*
+    *tests*
 
+    **/gtda/utils/intervals.py
+    **/gtda/utils/_docs.py
     **/base.py
     **/pipeline.py
-    **/_version.py
+    **/setup.py
+    **/_version.py

CMakeLists.txt

@@ -5,7 +5,7 @@ add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/gtda/externals/pybind11)
 set(BINDINGS_DIR "gtda/externals/bindings")
 
 include(cmake/HelperBoost.cmake)
-include_directories(${Boost_INCLUDE_DIR})
+include_directories(${Boost_INCLUDE_DIRS})
 
 find_package(OpenMP)
 

README.rst

@@ -120,12 +120,33 @@ source directory   ::
     pytest gtda
 
 Important links
----------------
+===============
 
 - Official source code repo: https://github.com/giotto-ai/giotto-tda
 - Download releases: https://pypi.org/project/giotto-tda/
 - Issue tracker: https://github.com/giotto-ai/giotto-tda/issues
 
+
+Citing giotto-tda
+=================
+
+If you use ``giotto-tda`` in a scientific publication, we would appreciate citations to the following paper:
+
+   `giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration <https://arxiv.org/abs/2004.02551>`_, Tauzin *et al*, arXiv:2004.02551, 2020.
+
+You can use the following BibTeX entry:
+
+.. code:: RST
+
+    @misc{tauzin2020giottotda,
+          title={giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration},
+          author={Guillaume Tauzin and Umberto Lupo and Lewis Tunstall and Julian Burella Pérez and Matteo Caorsi and Anibal Medina-Mardones and Alberto Dassatti and Kathryn Hess},
+          year={2020},
+          eprint={2004.02551},
+          archivePrefix={arXiv},
+          primaryClass={cs.LG}
+    }
+
 Community
 =========
 

azure-pipelines.yml

@@ -38,7 +38,7 @@ jobs:
 
   - task: Cache@2
     inputs:
-      key: '"ccache-wheels-v2020.03.23" | $(Agent.OS) | "$(python.version)"'
+      key: '"ccache-wheels-v2020.04.07" | $(Agent.OS) | "$(python.version)"'
       path: $(CCACHE_DIR)
     displayName: ccache
 
@@ -133,7 +133,7 @@ jobs:
 
   - task: Cache@2
     inputs:
-      key: '"ccache-v2020.03.23" | $(Agent.OS) | "$(python.version)"'
+      key: '"ccache-v2020.04.07" | $(Agent.OS) | "$(python.version)"'
       path: $(CCACHE_DIR)
     displayName: ccache
 
@@ -154,7 +154,7 @@ jobs:
   - script: |
       set -e
       pytest gtda --cov --cov-report xml
-    displayName: 'Test dev install with pytest'
+    displayName: 'Test dev install with pytest, upload coverage report'
 
   - script: |
       set -e
@@ -246,13 +246,17 @@ jobs:
     condition: eq(variables['nightly_check'], 'true')
     displayName: 'Change name to giotto-tda-nightly'
 
+  - script: |
+      python .azure-ci/install_boost.py || exit /b
+    displayName: 'Install boost'
+
   - script: |
       python -m pip install --upgrade pip setuptools
       python -m pip install -e ".[dev]"
     displayName: 'Install dev environment'
 
   - script: |
-      pytest gtda --cov --cov-report xml || exit /b
+      pytest gtda --no-cov --no-coverage-upload || exit /b
     displayName: 'Test dev install with pytest'
 
   - script: |

doc/faq.rst

@@ -10,6 +10,25 @@ I am a researcher. Can I use ``giotto-tda`` in my project?
 Of course! The `license <https://github.com/giotto-ai/giotto-tda/blob/master/LICENSE>`_ is very permissive.
 For more information, please contact the `L2F team`_.
 
+How do I cite ``giotto-tda``?
+-----------------------------
+We would appreciate citations to the following paper:
+
+   `giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration <https://arxiv.org/abs/2004.02551>`_, Tauzin *et al*, arXiv:2004.02551, 2020.
+
+You can use the following BibTeX entry:
+
+.. code:: RST
+
+    @misc{tauzin2020giottotda,
+          title={giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration},
+          author={Guillaume Tauzin and Umberto Lupo and Lewis Tunstall and Julian Burella Pérez and Matteo Caorsi and Anibal Medina-Mardones and Alberto Dassatti and Kathryn Hess},
+          year={2020},
+          eprint={2004.02551},
+          archivePrefix={arXiv},
+          primaryClass={cs.LG}
+    }
+
 I cannot install ``giotto-tda``
 -------------------------------
 
@@ -26,4 +45,4 @@ There are many TDA libraries available. How is ``giotto-tda`` different?
 ``giotto-tda`` is oriented towards machine learning (for details, see the :ref:`guiding principles <guiding_principles>`).
 This philosophy is in contrast with other reference libraries, like `GUDHI <https://gudhi.inria.fr/doc/latest/index.html>`_,
 which provide more low-level functionality at the expense of being less adapted to e.g. batch processing, or of
-being tightly integrated with ``scikit-learn``.
+being tightly integrated with ``scikit-learn``.

doc/library.rst

@@ -114,5 +114,5 @@ What's new
 
 .. include::
    release.rst
-   :start-after: Release 0.2.0
-   :end-before: Release 0.1.4
+   :start-after: Release 0.2.1
+   :end-before: Release 0.2.0

doc/release.rst

@@ -5,6 +5,45 @@ Release Notes
 
 .. _stable:
 
+*************
+Release 0.2.1
+*************
+
+Major Features and Improvements
+===============================
+
+-  The theory glossary has been improved to include the notions of vectorization, kernel and amplitude for persistence diagrams.
+-  The ``ripser`` function in ``gtda.externals.python.ripser_interface`` no longer uses scikit-learn's ``pairwise_distances`` when
+   ``metric`` is ``'precomputed'``, thus allowing square arrays with negative entries or infinities to be passed.
+-  ``check_point_clouds`` in ``gtda.utils.validation`` now checks for square array input when the input should be a collection of
+   distance-type matrices. Warnings guide the user to correctly setting the ``distance_matrices`` parameter. ``force_all_finite=False``
+   no longer means accepting NaN input (only infinite input is accepted).
+-  ``VietorisRipsPersistence`` in ``gtda.homology.simplicial`` no longer masks out infinite entries in the input to be fed to
+   ``ripser``.
+-  The docstrings for ``check_point_clouds`` and ``VietorisRipsPersistence`` have been improved to reflect these changes and the
+   extra level of generality for ``ripser``.
+
+Bug Fixes
+=========
+
+-  The variable used to indicate the location of Boost headers has been renamed from ``Boost_INCLUDE_DIR`` to ``Boost_INCLUDE_DIRS``
+   to address developer installation issues in some Linux systems.
+
+Backwards-Incompatible Changes
+==============================
+
+-  The keyword parameter ``distance_matrix`` in ``check_point_clouds`` has been renamed to ``distance_matrices``.
+
+Thanks to our Contributors
+==========================
+
+This release contains contributions from many people:
+
+Umberto Lupo, Anibal Medina-Mardones, Julian Burella Pérez, Guillaume Tauzin, and Wojciech Reise.
+
+We are also grateful to all who filed issues or helped resolve them, asked and answered questions, and were part of
+inspiring discussions.
+
 *************
 Release 0.2.0
 *************