Merge branch 'release/0.7'

.github/workflows/tests.yml

@@ -27,7 +27,9 @@ jobs:
 
     - name: Run tests
       run: |
-        pip3 install .
+        pip3 debug --verbose .
+        pip3 install numba==0.53
+        pip3 install --upgrade-strategy eager -v .
         coverage run --source=skfda/ setup.py test;
 
     - name: Upload coverage to Codecov

.zenodo.json

@@ -1,47 +1,47 @@
 {
-    'creators': [
+    "creators": [
         {
-            'affiliation': 'Universidad Autónoma de Madrid',
-            'name': 'Ramos-Carreño, Carlos',
-            'orcid': '0000-0003-2566-7058'
+            "affiliation": "Universidad Autónoma de Madrid",
+            "name": "Ramos-Carreño, Carlos",
+            "orcid": "0000-0003-2566-7058"
         },
         {
-            'affiliation': 'Universidad Autónoma de Madrid',
-            'name': 'Suárez, Alberto',
-            'orcid': '0000-0003-4534-0909'
+            "affiliation": "Universidad Autónoma de Madrid",
+            "name": "Suárez, Alberto",
+            "orcid": "0000-0003-4534-0909"
         },
         {
-            'affiliation': 'Universidad Autónoma de Madrid',
-            'name': 'Torrecilla, José Luis',
-            'orcid': '0000-0003-3719-5190'
+            "affiliation": "Universidad Autónoma de Madrid",
+            "name": "Torrecilla, José Luis",
+            "orcid": "0000-0003-3719-5190"
         },
         {
-            'name': 'Carbajo Berrocal, Miguel'
+            "name": "Carbajo Berrocal, Miguel"
         },
         {
-            'name': 'Marcos Manchón, Pablo'
+            "name": "Marcos Manchón, Pablo"
         },
         {
-            'name': 'Pérez Manso, Pablo'
+            "name": "Pérez Manso, Pablo"
         },
         {
-            'name': 'Hernando Bernabé, Amanda'
+            "name": "Hernando Bernabé, Amanda"
         },
         {
-            'name': 'García Fernández, David'
+            "name": "García Fernández, David"
         },
         {
-            'name': 'Hong, Yujian'
+            "name": "Hong, Yujian"
         },
         {
-            'name': 'Rodríguez-Ponga Eyriès, Pedro Martín'
+            "name": "Rodríguez-Ponga Eyriès, Pedro Martín"
         },
         {
-            'name': 'Sánchez Romero, Álvaro'
+            "name": "Sánchez Romero, Álvaro"
         },
         {
-            'name': 'Petrunina, Elena'
+            "name": "Petrunina, Elena"
         }
     ],
-    'license': 'BSD 3-Clause License',
+    "license": "BSD 3-Clause License"
 }

VERSION

@@ -1 +1 @@
-0.6.1
+0.7

docs/modules/exploratory/stats.rst

@@ -32,4 +32,13 @@ statistics can be used.
    skfda.exploratory.stats.cov
    skfda.exploratory.stats.var
 
+Additional statistics
+---------------------
+
+The following statistics can be used to estimate additional properties of the data.
+
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.exploratory.stats.modified_epigraph_index
 

docs/modules/exploratory/visualization.rst

@@ -1,14 +1,131 @@
 Visualization
 =============
 
-The visualization package provides tools to show different views of
-the functional data, that highlight several important aspects of it.
+Visualization methods are one of the most important tools for exploratory analysis.
+They can provide intuition over particular data that is very difficult to obtain otherwise.
+As functional data is infinite dimensional, good visualization tools capable to summarize
+and illustrate the main features of the data are of particular importance.
+The visualization module provides a thorough collection of these tools.
+Each of them highlights different characteristics of the data and thus they complement each other.
 
-.. toctree::
-   :maxdepth: 4
-   :caption: Modules:
+Basic representation
+--------------------
+
+Functional data with :term:`domain` dimension of 1 or 2 can be represented directly as function
+graphs, which will be curves or surfaces respectively. Each :term:`codomain` dimension will be plotted
+separately.
+Additionally, for discretized data, the discretization points can be plotted as a scatter plot.
+The following classes implement these plotting methods.
+
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.exploratory.visualization.representation.GraphPlot
+   skfda.exploratory.visualization.representation.ScatterPlot
 
-   visualization/boxplot
-   visualization/magnitude_shape_plot
-   visualization/clustering
-   visualization/fpca
+Note that the :func:`~skfda.representation.FData.plot` and
+:func:`~skfda.representation.grid.FDataGrid.plot` methods simply instantiate and plot an object
+of one of these classes.
+
+Parametric plot
+---------------
+
+Parametric plots are used to plot one function versus another when they have the same :term:`domain`.
+This is used for example in phase plane plots, showing the relation between two derivatives
+of different order.
+It is also useful to plot observations corresponding to curves in 2D, as it shows both dimensions
+of the :term:`codomain` in the same plot.
+
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.exploratory.visualization.ParametricPlot
+
+Functional Data Boxplot
+-----------------------
+
+The functional data boxplot is an extension of the univariate boxplot to the functional data domain.
+As such, it is a very useful tool to detect outliers and check the magnitude of the variation of the data.
+There are two variants of this plot, depending on the number of dimensions (1 or 2) of the :term:`domain`.
+
+If the dimension of the :term:`domain` is 1, the following class must be used.
+See the :ref:`sphx_glr_auto_examples_plot_boxplot.py` example for detailed explanation.
+
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.exploratory.visualization.Boxplot
+
+If the dimension of the :term:`domain` is 2, this one. See the
+:ref:`sphx_glr_auto_examples_plot_surface_boxplot.py`
+example for detailed explanation.
+
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.exploratory.visualization.SurfaceBoxplot
+
+Outliergram
+-----------
+
+The outliergram represents each functional observation as a point whose coordinates are its
+:class:`modified band depth<skfda.exploratory.depth.ModifiedBandDepth>` and its
+:func:`modified epigraph index<skfda.exploratory.stats.modified_epigraph_index>`.
+These quantities are related, and in absence of crossings between observations the points
+should lie on a parabola.
+Thus, substantial deviations from that behavior characterize observations that are shape
+outliers.
+
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.exploratory.visualization.Outliergram
+
+Magnitude-Shape Plot
+--------------------
+
+The Magnitude-Shape plot tries to summarize the shape and magnitude of an observation as real
+numbers, and plot them in a scatter plot.
+In addition it computes an ellipse, which serves as a decision boundary for detecting outliers.
+
+This is a very useful tool to detect shape and magnitude outliers and differentiate between them. 
+
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.exploratory.visualization.MagnitudeShapePlot
+
+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 classes:
+
+.. autosummary::
+   :toctree: autosummary
+
+   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
+class :class:`FuzzyKMeans <skfda.ml.clustering.base_kmeans.FuzzyKMeans>` to see
+the results graphically in the form of a parallel coordinates plot or a barplot
+respectively.
+
+See `Clustering Example <../auto_examples/plot_clustering.html>`_ for detailed
+explanation.
+
+Functional Principal Component Analysis plots
+---------------------------------------------
+In order to show the modes of variation that the principal components represent,
+the following class is implemented:
+
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.exploratory.visualization.fpca.FPCAPlot
+
+See the example :ref:`sphx_glr_auto_examples_plot_fpca.py` for detailed
+explanation.

docs/modules/misc/regularization.rst

@@ -17,11 +17,8 @@ When dealing with multivariate data, a common choice for the regularization
 is to penalize the squared Euclidean norm, or :math:`L_2` norm, of the vectors
 in order to obtain simpler solutions. This can be done in scikit-fda for
 both multivariate and functional data using the :class:`L2Regularization`
-class.
-
-A more flexible generalization of this approach is the so called Tikhonov
-regularization, available as :class:`TikhonovRegularization`, in which the
-squared :math:`L_2` norm is penalized after a particular linear operator is
+class. A more flexible generalization of this approach is to penalize the
+squared :math:`L_2` norm after a particular linear operator is
 applied. This for example allows to penalize the second derivative of a curve,
 which is a measure of its curvature, because the differential operator
 is linear. As arbitrary Python callables can be used as operators (provided
@@ -32,5 +29,4 @@ linear operations.
 .. autosummary::
    :toctree: autosummary
 
-   skfda.misc.regularization.L2Regularization
-   skfda.misc.regularization.TikhonovRegularization
+   skfda.misc.regularization.L2Regularization

docs/modules/ml/classification.rst

@@ -46,3 +46,12 @@ This module contains depth based estimators to perform classification.
    skfda.ml.classification.DDClassifier
    skfda.ml.classification.DDGClassifier
    skfda.ml.classification.MaximumDepthClassifier
+
+Logistic regression
+-----------------------
+Classifier based on logistic regression.
+
+.. autosummary::
+   :toctree: autosummary
+
+   skfda.ml.classification.LogisticRegression