Version 0.6.

Merge branch 'release/0.6'

.github/workflows/tests.yml

@@ -11,7 +11,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ['3.6', '3.7', '3.8']
+        python-version: ['3.7', '3.8']
 
     steps:
     - uses: actions/checkout@v2

.gitignore

@@ -110,3 +110,5 @@ pip-wheel-metadata/
 
 # macOS DS_Store
 .DS_Store
+.gitignore
+.vscode/settings.json

MANIFEST.in

@@ -1,6 +1,7 @@
 include README.rst
 include MANIFEST.in
 include VERSION
+include skfda/py.typed
 include pyproject.toml
 include *.txt
 recursive-include deps *

README.rst

@@ -65,7 +65,6 @@ Requirements
 * `fdasrsf <https://github.com/jdtuck/fdasrsf_python>`_ - SRSF framework
 * `findiff <https://github.com/maroba/findiff>`_ - Finite differences
 * `matplotlib <https://github.com/matplotlib/matplotlib>`_ - Plotting with Python
-* `mpldatacursor <https://github.com/joferkington/mpldatacursor/>`_ - Interactive data cursors for matplotlib
 * `multimethod <https://github.com/coady/multimethod>`_ - Multiple dispatch
 * `numpy <https://github.com/numpy/numpy>`_ - The fundamental package for scientific computing with Python
 * `pandas <https://github.com/pandas-dev/pandas>`_ - Powerful Python data analysis toolkit

THANKS.txt

@@ -5,4 +5,10 @@ Carlos Ramos Carreño for the design, reviews and supervision, and for contribut
 Pablo Marcos Manchón for the registration functions, including integration with fdasrsf.
 Amanda Hernando Bernabé for visualization and clustering functions.
 Pablo Pérez Manso for regression and related utilities.
-Sergio Ruiz Lozano for the design of the logo.
+Yujian Hong for the Principal Component Analysis functionalities.
+David García Fernandez for implementing Anova and Hotelling tests.
+Pedro Martín Rodríguez-Ponga Eyriès for implementing several classification methods.
+Álvaro Sánchez Romero for improving the visualization methods and adding interactive visualizations.
+Elena Petrunina for improving the documentation, and regression functions.
+Luis Alberto Rodriguez Ramirez for providing mathematical support.
+Sergio Ruiz Lozano for the design of the logo.

VERSION

@@ -1 +1 @@
-0.5
+0.6

docs/.gitignore

@@ -1,3 +1,4 @@
 /auto_examples/
+/auto_tutorial/
 /backreferences/
 **/autosummary/

docs/Makefile

@@ -51,6 +51,7 @@ help:
 clean:
 	rm -rf $(BUILDDIR)/*
 	rm -rf auto_examples
+	rm -rf auto_tutorial
 	rm -rf modules/autosummary
 	rm -rf modules/exploratory/visualization/autosummary
 	rm -rf modules/exploratory/autosummary

docs/_templates/autosummary/class.rst

@@ -14,18 +14,9 @@
    {%- endfor %}
    {% endif %}
 
-   .. automethod:: __init__
-   {% endblock %}
-
-   {% block attributes %}
-   {% if attributes %}
-   .. rubric:: Attributes
-
-   .. autosummary::
-   {% for item in attributes %}
-      ~{{ name }}.{{ item }}
+   {% for item in methods %}
+   .. automethod:: {{ item }}
    {%- endfor %}
-   {% endif %}
    {% endblock %}
 
 .. include:: {{package}}/backreferences/{{fullname}}.examples

docs/conf.py

@@ -22,6 +22,9 @@
 import sys
 
 import pkg_resources
+# -- Extensions to the  Napoleon GoogleDocstring class ---------------------
+from sphinx.ext.napoleon.docstring import GoogleDocstring
+
 try:
     release = pkg_resources.get_distribution('scikit-fda').version
 except pkg_resources.DistributionNotFound:
@@ -54,7 +57,10 @@
               'sphinx.ext.intersphinx',
               'sphinx.ext.doctest',
               'jupyter_sphinx',
-              'sphinx.ext.autodoc.typehints']
+              'sphinx.ext.autodoc.typehints',
+              'sphinxcontrib.bibtex']
+
+bibtex_bibfiles = ['refs.bib']
 
 autodoc_default_flags = ['members', 'inherited-members']
 
@@ -221,32 +227,66 @@
     'sklearn': ('https://scikit-learn.org/stable', None),
     'matplotlib': ('https://matplotlib.org/', None),
     'pandas': ('https://pandas.pydata.org/pandas-docs/stable/', None),
-    'mpldatacursor': ('https://pypi.org/project/mpldatacursor/', None),
 }
 
+
+tutorial_list = [
+    "plot_introduction.py",
+    "plot_getting_data.py",
+    "plot_basis_representation.py",
+    "plot_skfda_sklearn.py",
+]
+
+
+class SkfdaExplicitSubOrder(object):
+    """
+    Class for use within the 'within_subsection_order' key.
+
+    Inspired by Matplotlib gallery.
+
+    """
+
+    def __init__(self, src_dir: str) -> None:
+        self.src_dir = src_dir  # src_dir is unused here
+        self.ordered_list = tutorial_list
+
+    def __call__(self, filename: str) -> str:
+        """Return a string determining the sort order."""
+        if filename in self.ordered_list:
+            ind = self.ordered_list.index(filename)
+            return f"{ind:04d}"
+
+        # ensure not explicitly listed items come last.
+        return f"zzz{filename}"
+
+
 sphinx_gallery_conf = {
     # path to your examples scripts
-    'examples_dirs': '../examples',
+    'examples_dirs': ['../examples', '../tutorial'],
     # path where to save gallery generated examples
-    'gallery_dirs': 'auto_examples',
+    'gallery_dirs': ['auto_examples', 'auto_tutorial'],
     'reference_url': {
         # The module you locally document uses None
         'skfda': None,
     },
     'backreferences_dir': 'backreferences',
     'doc_module': 'skfda',
+    'within_subsection_order': SkfdaExplicitSubOrder,
 }
 
 autosummary_generate = True
 autodoc_typehints = "description"
 napoleon_use_rtype = True
 
+autodoc_type_aliases = {
+    "ArrayLike": "ArrayLike",
+    "GridPointsLike": "Union[ArrayLike, Sequence[ArrayLike]]",
+}
+
 # Napoleon fix for attributes
 # Taken from
 # https://michaelgoerz.net/notes/extending-sphinx-napoleon-docstring-sections.html
 
-# -- Extensions to the  Napoleon GoogleDocstring class ---------------------
-from sphinx.ext.napoleon.docstring import GoogleDocstring
 
 # first, we define new methods for any new sections and add them to the class
 

docs/glossary.rst

@@ -29,6 +29,12 @@ General Concepts
     domain
         The set of possible input values of a function.
 
+    domain range
+    	The valid range where a function can be evaluated. It is a Python
+    	sequence that contains, for each dimension of the domain, a tuple with
+    	the minimum and maximum values for that dimension. Usually used in
+    	plotting functions and as the domain of integration for this function.
+
     FDA
     Functional Data Analysis
     	The branch of statistics that deals with curves, surfaces or other

docs/index.rst

@@ -14,21 +14,27 @@ or clustering of functional data.
 In the `project page <https://github.com/GAA-UAM/scikit-fda>`_ hosted by
 Github you can find more information related to the development of the package.
 
+.. toctree::
+   :caption: Using scikit-fda
+   :hidden:
+
+   auto_tutorial/index
 
 .. toctree::
-   :maxdepth: 2
-   :caption: Contents:
+   :maxdepth: 1
    :titlesonly:
+   :hidden:
 
-   apilist
-   glossary
-
+   auto_examples/index
 
 .. toctree::
-   :maxdepth: 1
+   :maxdepth: 2
    :titlesonly:
+   :hidden:
+   :caption: More documentation
 
-   auto_examples/index
+   apilist
+   glossary
 
 An exhaustive list of all the contents of the package can be found in the
 :ref:`genindex`.
@@ -58,6 +64,14 @@ In this type of installation make sure that your default Python version is
 currently supported, or change the python and pip commands by specifying a
 version, such as python3.6.
 
+How do I start?
+---------------
+
+If you want a quick overview of the package, we recommend you to try the
+new :doc:`tutorial <auto_tutorial/index>`. For articles about specific
+topics, feel free to explore the :doc:`examples <auto_examples/index>`. Want
+to check the documentation of a particular class or function? Try searching
+for it in the :doc:`API list <apilist>`.
 
 Contributions
 -------------

docs/modules/exploratory/visualization/clustering.rst

@@ -2,14 +2,14 @@ Clustering Plots
 ================
 In order to show the results of the cluster algorithms in a visual way,
 :mod:`this module <skfda.exploratory.visualization.clustering_plots>` is
-implemented. It contains the following methods:
+implemented. It contains the following classes:
 
 .. autosummary::
    :toctree: autosummary
 
-   skfda.exploratory.visualization.clustering.plot_clusters
-   skfda.exploratory.visualization.clustering.plot_cluster_lines
-   skfda.exploratory.visualization.clustering.plot_cluster_bars
+   skfda.exploratory.visualization.clustering.ClusterPlot
+   skfda.exploratory.visualization.clustering.ClusterMembershipLinesPlot
+   skfda.exploratory.visualization.clustering.ClusterMembershipPlot
 
 In the first one, the samples of the FDataGrid are divided by clusters which
 are assigned different colors. The following functions, are only valid for the

docs/modules/exploratory/visualization/fpca.rst

@@ -1,12 +1,12 @@
 Functional Principal Component Analysis plots
 =============================================
 In order to show the modes of variation that the principal components represent,
-the following function is implemented
+the following class is implemented
 
 .. autosummary::
    :toctree: autosummary
 
-   skfda.exploratory.visualization.fpca.plot_fpca_perturbation_graphs
+   skfda.exploratory.visualization.fpca.FPCAPlot
 
 See the example :ref:`sphx_glr_auto_examples_plot_fpca.py` for detailed
 explanation.

docs/modules/misc/metrics.rst

@@ -7,15 +7,33 @@ This module contains multiple functional distances and norms.
 Lp Spaces
 ---------
 
-The following functions computes the norms and distances used in Lp spaces.
+The following classes compute the norms and metrics used in Lp spaces. One
+first has to create an instance for the class, specifying the desired value
+for ``p``, and use this instance to evaluate the norm or distance over
+:term:`functional data objects`.
 
 .. autosummary::
    :toctree: autosummary
 
-   skfda.misc.metrics.lp_norm
-   skfda.misc.metrics.lp_distance
+   skfda.misc.metrics.LpNorm
+   skfda.misc.metrics.LpDistance
+
+As the :math:`L_1`, :math:`L_2` and :math:`L_{\infty}` norms are very common
+in :term:`FDA`, instances for these have been created, called respectively
+``l1_norm``, ``l2_norm`` and ``linf_norm``. The same is true for metrics,
+having ``l1_distance``, ``l2_distance`` and ``linf_distance`` already
+created.
 
+The following functions are wrappers for convenience, in case that one
+only wants to evaluate the norm/metric for a value of ``p``. These functions
+cannot be used in objects or methods that require a norm or metric, as the
+value of ``p`` must be explicitly passed in each call.
 
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.misc.metrics.lp_norm
+   skfda.misc.metrics.lp_distance
 
 Elastic distances
 -----------------
@@ -32,11 +50,28 @@ analysis and registration of functional data.
     skfda.misc.metrics.warping_distance
 
 
-Utils
------
+Metric induced by a norm
+------------------------
+
+If a norm has been defined, it is possible to construct a metric between two
+elements simply subtracting one from the other and computing the norm of the
+result. Such a metric is called the metric induced by the norm, and the
+:math:`Lp` distance is an example of these. The following class can be used
+to construct a metric from a norm in this way:
+
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.misc.metrics.NormInducedMetric
+
+
+Pairwise metric
+---------------
+
+Some tasks require the computation of all possible distances between pairs
+of objets. The following class can compute that efficiently:
 
 .. autosummary::
    :toctree: autosummary
 
-   skfda.misc.metrics.distance_from_norm
-   skfda.misc.metrics.pairwise_distance
+   skfda.misc.metrics.PairwiseMetric

docs/modules/ml/classification.rst

@@ -22,3 +22,7 @@ it is explained the basic usage of these estimators.
    skfda.ml.classification.KNeighborsClassifier
    skfda.ml.classification.RadiusNeighborsClassifier
    skfda.ml.classification.NearestCentroid
+   skfda.ml.classification.DTMClassifier
+   skfda.ml.classification.DDClassifier
+   skfda.ml.classification.DDGClassifier
+   skfda.ml.classification.MaximumDepthClassifier

docs/modules/ml/clustering.rst

@@ -34,3 +34,18 @@ searches.
    :toctree: autosummary
 
    skfda.ml.clustering.NearestNeighbors
+
+Hierarchical clustering
+-----------------------
+
+Hierarchical clusterings are constructed by iteratively merging or splitting
+clusters given a metric between their elements, in order to cluster together
+elements that are close from each other. This is repeated until a desired
+number of clusters is obtained. The resulting hierarchy of clusters can be
+represented as a tree, called a dendogram. The following hierarchical
+clusterings are supported: 
+
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.ml.clustering.AgglomerativeClustering

docs/modules/ml/regression.rst

@@ -10,12 +10,14 @@ Linear regression
 
 A linear regression model is one in which the response variable can be
 expressed as a linear combination of the covariates (which could be
-multivariate or functional).
+multivariate or functional). The following linear models are available
+in scikit-fda:
 
 .. autosummary::
    :toctree: autosummary
 
    skfda.ml.regression.LinearRegression
+   skfda.ml.regression.HistoricalLinearRegression
 
 Nearest Neighbors
 -----------------