doc

README.rst

@@ -12,7 +12,7 @@ Documentation
 
 The **documentation** including installation instructions, API documentation
 and examples is
-`available online <http://dev.pages.lis-lab.fr/multimodal>`_.
+`available online <http://dev.pages.lis-lab.fr/scikit-multimodallearn>`_.
 
 
 Installation
@@ -31,7 +31,7 @@ Installation using pip
 ~~~~~~~~~~~~~~~~~~~~~~
 
 **scikit-multimodallearn** is
-`available on PyPI <https://pypi.org/project/multiconfusion/>`_
+`available on PyPI <https://pypi.org/project/scikit-multimodallearn/>`_
 and can be installed using **pip**::
 
   pip install scikit-multimodallearn
@@ -105,6 +105,22 @@ following paper::
             supervised learning},
  }
 
+ @InProceedings{Huu:2019:BAMCC,
+  author={Huusari, Riika, Kadri Hachem and Capponi, C{\'e}cile},
+  editor={},
+  title={Multi-view Metric Learning in Vector-valued Kernel Spaces},
+  booktitle={arXiv:1803.07821v1},
+  year={2018},
+  location={Athens, Greece},
+  publisher={},
+  address={},
+  pages={209--228},
+  numpages = {12}
+  isbn={978-3-642-23783-6}
+  url={https://link.springer.com/chapter/10.1007/978-3-642-23783-6_14},
+  keywords={boosting, classification, multiview learning,
+            merric learning, vector-valued, kernel spaces},
+ }
 
 References
 ~~~~~~~~~~
@@ -113,7 +129,6 @@ References
   Linking and mining heterogeneous an multi-view data, Unsupervised and
   semi-supervised learning Series Editor M. Emre Celeri, pp 161-182, Springer
 
-
 * Sokol Koço, Cécile Capponi,
   `"A boosting approach to multiview classification with cooperation"
   <https://link.springer.com/chapter/10.1007/978-3-642-23783-6_14>`_,

doc/conf.py

@@ -3,12 +3,14 @@
 from datetime import date
 import os
 import sys
-sys.path.insert(0, os.path.abspath('../metriclearning'))
+sys.path.insert(0, os.path.abspath('../multimodal'))
 sys.path.insert(0, os.path.abspath('../..'))
+sys.path.insert(0, os.path.abspath('../../multimodal'))
 sys.path.insert(0, os.path.abspath("."))
 sys.path.append(os.path.join(os.path.dirname(__name__), '..')) 
 sys.path.append(os.path.join(os.path.abspath(os.path.dirname(__file__)), 'sphinxext'))
-import metriclearning
+
+import multimodal
 
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
@@ -28,6 +30,9 @@ extensions = [
     'sphinx.ext.doctest',
     'sphinx.ext.imgmath',
     'numpydoc',
+    'sphinx.ext.napoleon',
+    'sphinx_gallery.gen_gallery'
+ #              'm2r',
  #     'sphinx_gallery.gen_gallery'
 ]
 
@@ -44,18 +49,18 @@ source_encoding = 'utf-8'
 master_doc = 'index'
 
 # General information about the project.
-project = 'metriclearning'
+project = 'scikit-multimodallearn'
 author = 'Dominique Benielli'
-copyright = '2017-{}, LIS UMR 7020'.format(date.today().year)
+copyright = '2020-{}, LIS UMR 7020'.format(date.today().year)
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
 # built documents.
 #
 # The short X.Y version.
-version = metriclearning.__version__
+version = multimodal.__version__
 # The full version, including alpha/beta/rc tags.
-release = metriclearning.__version__
+release = multimodal.__version__
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
@@ -69,7 +74,7 @@ release = metriclearning.__version__
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
-exclude_patterns = []
+exclude_patterns = ['_build']
 
 # The reST default role (used for this markup: `text`) to use for all
 # documents.
@@ -243,7 +248,7 @@ man_pages = [
 #  dir menu entry, description, category)
 texinfo_documents = [
   (master_doc, project, '{} Documentation'.format(project), author, project,
-   'Multi-View Metric Learning in Vector-Valued Kernel Spaces for machine learning.',
+   'Multimodal Multi-View Learning with kernels and boosting algorithms.',
    'Miscellaneous')]
 
 # Documents to append as an appendix to all manuals.
@@ -267,11 +272,11 @@ numpydoc_show_class_members = False
 
 sphinx_gallery_conf = {
     'doc_module': (project,),
-    'backreferences_dir': 'backreferences',
+    'backreferences_dir': 'tutorial/backreferences',
     # path to your examples scripts
     'examples_dirs': '../examples',
     # path where to save gallery generated examples
-    'gallery_dirs': 'auto_examples'}
+    'gallery_dirs': 'tutorial/auto_examples'}
 
 # Generate the plots for the gallery
 plot_gallery = 'True'

doc/docmumbo/install_devel.rst

-Installation and development
-============================
-
-Dependencies
-------------
-
-**multimodalboost** works with **Python 3.5 or later**.
-
-**multimodalboost** depends on **scikit-learn** (version >= 0.19).
-
-Optionally, **matplotlib** is required when running the examples.
-
-Installation
-------------
-
-**multimodalboost** is
-`available on PyPI <https://pypi.org/project/multimodalboost/>`_
-and can be installed using **pip**::
-
-  pip install multimodalboost
-
-If you prefer to install directly from the **source code**, clone the **Git**
-repository of the project and run the **setup.py** file with the following
-commands::
-
-  git clone git@gitlab.lis-lab.fr:dev/multimodalboost.git
-  cd multimodalboost
-  python setup.py install
-
-or alternatively use **pip**::
-
-  pip install git+https://gitlab.lis-lab.fr/dev/multimodalboost.git
-
-Development
------------
-
-The development of multimodalboost follows the guidelines provided by the
-scikit-learn community.
-
-Refer to the `Developer's Guide <http://scikit-learn.org/stable/developers>`_
-of the scikit-learn project for more details.
-
-Source code
------------
-
-You can get the **source code** from the **Git** repository of the project::
-
-  git clone git@gitlab.lis-lab.fr:dev/multimodalboost.git
-
-
-Testing
--------
-
-**pytest** and **pytest-cov** are required to run the **test suite** with::
-
-  cd multimodalboost
-  pytest
-
-A code coverage report is displayed in the terminal when running the tests.
-An HTML version of the report is also stored in the directory **htmlcov**.
-
-Generating the documentation
-----------------------------
-
-The generation of the documentation requires **sphinx**, **sphinx-gallery**,
-**numpydoc** and **matplotlib** and can be run with::
-
-  python setup.py build_sphinx
-
-The resulting files are stored in the directory **build/sphinx/html**.

doc/index.rst

-.. metriclearning documentation master file, created by
-   sphinx-quickstart on Mon Sep  2 12:12:08 2019.
-   You can adapt this file completely to your liking, but it should at least
-   contain the root `toctree` directive.
+
 
 Welcome to scikit-multimodallearn's documentation!
 ==================================================
@@ -15,8 +12,11 @@ package for machine learning in Python.
 Documentation
 -------------
 
+:Release: |version|
+:Date: |today|
+
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 3
    :caption: Contents:
 
 
@@ -27,21 +27,6 @@ Documentation
 
 
 
-Documentation
--------------
-
-:Release: |version|
-:Date: |today|
-
-.. toctree::
-   :maxdepth: 1
-
-   install_devel
-   api
-   auto_examples/index
-   credits
-
-
 Indices and tables
 ------------------
 

doc/reference/api.rst

 API Documentation
 =================
 
+datasets
+--------
+
+.. automodule:: multimodal.datasets.data_sample
+   :members:
+   :inherited-members:
+
+
+Boosting
+--------
 
 multimodal.boosting.mumbo
--------------------------
++++++++++++++++++++++++++
 
 .. automodule:: multimodal.boosting.mumbo
    :members:
@@ -11,7 +21,7 @@ multimodal.boosting.mumbo
 
 
 multimodal.boosting.cumbo
--------------------------
++++++++++++++++++++++++++
 
 .. automodule:: multimodal.boosting.cumbo
    :members:
@@ -19,8 +29,35 @@ multimodal.boosting.cumbo
 
 
 multimodal.boosting.boost
--------------------------
++++++++++++++++++++++++++
 
 .. automodule:: multimodal.boosting.boost
    :members:
    :inherited-members:
+
+
+Kernels
+-------
+
+multimodal.kernels.mvml
++++++++++++++++++++++++
+
+.. automodule:: multimodal.kernels.mvml
+   :members:
+   :inherited-members:
+
+
+multimodal.kernels.lpMKL
+++++++++++++++++++++++++
+
+.. automodule:: multimodal.kernels.lpMKL
+   :members:
+   :inherited-members:
+
+
+multimodal.kernels.mkernel
+++++++++++++++++++++++++++
+
+.. automodule:: multimodal.kernels.mkernel
+   :members:
+   :inherited-members:

examples/README.txt

+.. _examples:
+
+Examples
+========
+
+MuMBo Examples
+--------------
+
+The following toy examples illustrate how the MuMBo algorithm exploits
+cooperation between views for classification.
+

examples/cumbo_plot_2_views_2_classes.py

+# -*- coding: utf-8 -*-
+"""
+==========================
+2 views, 2 classes example
+==========================
+
+In this toy example, we generate data from two classes, split between two
+two-dimensional views.
+
+For each view, the data are generated so that half of the points of each class
+are well separated in the plane, while the other half of the points are not
+separated and placed in the same area. We also insure that the points that are
+not separated in one view are well separated in the other view.
+
+Thus, in the figure representing the data, the points represented by crosses
+(x) are well separated in view 0 while they are not separated in view 1, while
+the points represented by dots (.) are well separated in view 1 while they are
+not separated in view 0. In this figure, the blue symbols represent points
+of class 0, while red symbols represent points of class 1.
+
+The MuMBo algorithm take adavantage of the complementarity of the two views to
+rightly classify the points.
+"""
+
+import numpy as np
+from multimodal.boosting.cumbo import MuCumboClassifier
+from matplotlib import pyplot as plt
+
+
+def generate_data(n_samples, lim):
+    """Generate random data in a rectangle"""
+    lim = np.array(lim)
+    n_features = lim.shape[0]
+    data = np.random.random((n_samples, n_features))
+    data = (lim[:, 1]-lim[:, 0]) * data + lim[:, 0]
+    return data
+
+
+seed = 12
+np.random.seed(seed)
+
+n_samples = 100
+
+view_0 = np.concatenate((generate_data(n_samples, [[0., 1.], [0., 1.]]),
+                         generate_data(n_samples, [[1., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [1., 2.]])))
+
+view_1 = np.concatenate((generate_data(n_samples, [[1., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [1., 2.]]),
+                         generate_data(n_samples, [[0., 1.], [0., 1.]])))
+
+X = np.concatenate((view_0, view_1), axis=1)
+
+y = np.zeros(4*n_samples, dtype=np.int64)
+y[2*n_samples:] = 1
+
+views_ind = np.array([0, 2, 4])
+
+n_estimators = 3
+clf = MuCumboClassifier(n_estimators=n_estimators)
+clf.fit(X, y, views_ind)
+
+print('\nAfter 3 iterations, the MuMBo classifier reaches exact '
+      'classification for the\nlearning samples:')
+for ind, score in enumerate(clf.staged_score(X, y)):
+    print('  - iteration {}, score: {}'.format(ind + 1, score))
+
+
+print('\nThe resulting MuCuMBo classifier uses three sub-classifiers that are '
+      'wheighted\nusing the following weights:\n'
+      '  estimator weights: {}'.format(clf.estimator_weights_alpha_))
+
+# print('\nThe two first sub-classifiers use the data of view 0 to compute '
+#       'their\nclassification results, while the third one uses the data of '
+#       'view 1:\n'
+#       '  best views: {}'. format(clf.best_views_))
+
+print('\nThe first figure displays the data, splitting the representation '
+      'between the\ntwo views.')
+
+fig = plt.figure(figsize=(10., 8.))
+fig.suptitle('Representation of the data', size=16)
+for ind_view in range(2):
+    ax = plt.subplot(2, 1, ind_view + 1)
+    ax.set_title('View {}'.format(ind_view))
+    ind_feature = ind_view * 2
+    styles = ('.b', 'xb', '.r', 'xr')
+    labels = ('non-separated', 'separated')
+    for ind in range(4):
+        ind_class = ind // 2
+        label = labels[(ind + ind_view) % 2]
+        ax.plot(X[n_samples*ind:n_samples*(ind+1), ind_feature],
+                X[n_samples*ind:n_samples*(ind+1), ind_feature + 1],
+                styles[ind],
+                label='Class {} ({})'.format(ind_class, label))
+    ax.legend()
+
+print('\nThe second figure displays the classification results for the '
+      'sub-classifiers\non the learning sample data.\n')
+
+styles = ('.b', '.r')
+# fig = plt.figure(figsize=(12., 7.))
+# fig.suptitle('Classification results on the learning data for the '
+#              'sub-classifiers', size=16)
+# for ind_estimator in range(n_estimators):
+#     best_view = clf.best_views_[ind_estimator]
+#     y_pred = clf.estimators_[ind_estimator].predict(
+#         X[:, 2*best_view:2*best_view+2])
+#     background_color = (1.0, 1.0, 0.9)
+#     for ind_view in range(2):
+#         ax = plt.subplot(2, 3, ind_estimator + 3*ind_view + 1)
+#         if ind_view == best_view:
+#             ax.set_facecolor(background_color)
+#         ax.set_title(
+#             'Sub-classifier {} - View {}'.format(ind_estimator, ind_view))
+#         ind_feature = ind_view * 2
+#         for ind_class in range(2):
+#             ind_samples = (y_pred == ind_class)
+#             ax.plot(X[ind_samples, ind_feature],
+#                     X[ind_samples, ind_feature + 1],
+#                     styles[ind_class],
+#                     label='Class {}'.format(ind_class))
+#         ax.legend(title='Predicted class:')
+
+plt.show()

examples/cumbo_plot_3_views_3_classes.py

+# -*- coding: utf-8 -*-
+"""
+==========================
+3 views, 3 classes example
+==========================
+
+In this toy example, we generate data from three classes, split between three
+two-dimensional views.
+
+For each view, the data are generated so that the points for two classes are
+well seperated, while the points for the third class are not seperated with
+the two other classes. That means that, taken separately, none of the single
+views allows for a good classification of the data.
+
+Nevertheless, the MuMBo algorithm take adavantage of the complementarity of
+the views to rightly classify the points.
+"""
+
+import numpy as np
+from multimodal.boosting.cumbo import MuCumboClassifier
+from matplotlib import pyplot as plt
+
+
+def generate_data(n_samples, lim):
+    """Generate random data in a rectangle"""
+    lim = np.array(lim)
+    n_features = lim.shape[0]
+    data = np.random.random((n_samples, n_features))
+    data = (lim[:, 1]-lim[:, 0]) * data + lim[:, 0]
+    return data
+
+
+seed = 12
+np.random.seed(seed)
+
+n_samples = 300
+
+view_0 = np.concatenate((generate_data(n_samples, [[0., 1.], [0., 1.]]),
+                         generate_data(n_samples, [[1., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 2.], [0., 1.]])))
+
+view_1 = np.concatenate((generate_data(n_samples, [[1., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [0., 1.]])))
+
+view_2 = np.concatenate((generate_data(n_samples, [[0., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [0., 1.]]),
+                         generate_data(n_samples, [[1., 2.], [0., 1.]])))
+
+X = np.concatenate((view_0, view_1, view_2), axis=1)
+
+y = np.zeros(3*n_samples, dtype=np.int64)
+y[n_samples:2*n_samples] = 1
+y[2*n_samples:] = 2
+
+views_ind = np.array([0, 2, 4, 6])
+
+n_estimators = 4
+clf = MuCumboClassifier(n_estimators=n_estimators)
+clf.fit(X, y, views_ind)
+
+print('\nAfter 4 iterations, the MuCuMBo classifier reaches exact '
+      'classification for the\nlearning samples:')
+for ind, score in enumerate(clf.staged_score(X, y)):
+    print('  - iteration {}, score: {}'.format(ind + 1, score))
+
+print('\nThe resulting MuCuMBo classifier uses four sub-classifiers that are '
+      'wheighted\nusing the following weights:\n'
+      '  estimator weights alpha: {}'.format(clf.estimator_weights_alpha_))
+
+# print('\nThe first sub-classifier uses the data of view 0 to compute '
+#       'its classification\nresults, the second and third sub-classifiers use '
+#       'the data of view 1, while the\nfourth one uses the data of '
+#       'view 2:\n'
+#       '  best views: {}'. format(clf.best_views_))
+
+print('\nThe first figure displays the data, splitting the representation '
+      'between the\nthree views.')
+
+styles = ('.b', '.r', '.g')
+fig = plt.figure(figsize=(12., 11.))
+fig.suptitle('Representation of the data', size=16)
+for ind_view in range(3):
+    ax = plt.subplot(3, 1, ind_view + 1)
+    ax.set_title('View {}'.format(ind_view))
+    ind_feature = ind_view * 2
+    for ind_class in range(3):
+        ind_samples = (y == ind_class)
+        ax.plot(X[ind_samples, ind_feature],
+                X[ind_samples, ind_feature + 1],
+                styles[ind_class],
+                label='Class {}'.format(ind_class))
+    ax.legend(loc='upper left', framealpha=0.9)
+
+print('\nThe second figure displays the classification results for the '
+      'sub-classifiers\non the learning sample data.\n')
+
+# fig = plt.figure(figsize=(14., 11.))
+# fig.suptitle('Classification results on the learning data for the '
+#              'sub-classifiers', size=16)
+# for ind_estimator in range(n_estimators):
+#     best_view = clf.best_views_[ind_estimator]
+#     y_pred = clf.estimators_[ind_estimator].predict(
+#         X[:, 2*best_view:2*best_view+2])
+#     background_color = (1.0, 1.0, 0.9)
+#     for ind_view in range(3):
+#         ax = plt.subplot(3, 4, ind_estimator + 4*ind_view + 1)
+#         if ind_view == best_view:
+#             ax.set_facecolor(background_color)
+#         ax.set_title(
+#             'Sub-classifier {} - View {}'.format(ind_estimator, ind_view))
+#         ind_feature = ind_view * 2
+#         for ind_class in range(3):
+#             ind_samples = (y_pred == ind_class)
+#             ax.plot(X[ind_samples, ind_feature],
+#                     X[ind_samples, ind_feature + 1],
+#                     styles[ind_class],
+#                     label='Class {}'.format(ind_class))
+#         ax.legend(title='Predicted class:', loc='upper left', framealpha=0.9)
+
+plt.show()

examples/mumbo_plot_2_views_2_classes.py

+# -*- coding: utf-8 -*-
+"""
+==========================
+2 views, 2 classes example
+==========================
+
+In this toy example, we generate data from two classes, split between two
+two-dimensional views.
+
+For each view, the data are generated so that half of the points of each class
+are well separated in the plane, while the other half of the points are not
+separated and placed in the same area. We also insure that the points that are
+not separated in one view are well separated in the other view.
+
+Thus, in the figure representing the data, the points represented by crosses
+(x) are well separated in view 0 while they are not separated in view 1, while
+the points represented by dots (.) are well separated in view 1 while they are
+not separated in view 0. In this figure, the blue symbols represent points
+of class 0, while red symbols represent points of class 1.
+
+The MuMBo algorithm take adavantage of the complementarity of the two views to
+rightly classify the points.
+"""
+
+import numpy as np
+from multimodal.boosting.mumbo import MumboClassifier
+from matplotlib import pyplot as plt
+
+
+def generate_data(n_samples, lim):
+    """Generate random data in a rectangle"""
+    lim = np.array(lim)
+    n_features = lim.shape[0]
+    data = np.random.random((n_samples, n_features))
+    data = (lim[:, 1]-lim[:, 0]) * data + lim[:, 0]
+    return data
+
+
+seed = 12
+np.random.seed(seed)
+
+n_samples = 100
+
+view_0 = np.concatenate((generate_data(n_samples, [[0., 1.], [0., 1.]]),
+                         generate_data(n_samples, [[1., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [1., 2.]])))
+
+view_1 = np.concatenate((generate_data(n_samples, [[1., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [1., 2.]]),
+                         generate_data(n_samples, [[0., 1.], [0., 1.]])))
+
+X = np.concatenate((view_0, view_1), axis=1)
+
+y = np.zeros(4*n_samples, dtype=np.int64)
+y[2*n_samples:] = 1
+
+views_ind = np.array([0, 2, 4])
+
+n_estimators = 3
+clf = MumboClassifier(n_estimators=n_estimators)
+clf.fit(X, y, views_ind)
+
+print('\nAfter 3 iterations, the MuMBo classifier reaches exact '
+      'classification for the\nlearning samples:')
+for ind, score in enumerate(clf.staged_score(X, y)):
+    print('  - iteration {}, score: {}'.format(ind + 1, score))
+
+
+print('\nThe resulting MuMBo classifier uses three sub-classifiers that are '
+      'wheighted\nusing the following weights:\n'
+      '  estimator weights: {}'.format(clf.estimator_weights_))
+
+print('\nThe two first sub-classifiers use the data of view 0 to compute '
+      'their\nclassification results, while the third one uses the data of '
+      'view 1:\n'
+      '  best views: {}'. format(clf.best_views_))
+
+print('\nThe first figure displays the data, splitting the representation '
+      'between the\ntwo views.')
+
+fig = plt.figure(figsize=(10., 8.))
+fig.suptitle('Representation of the data', size=16)
+for ind_view in range(2):
+    ax = plt.subplot(2, 1, ind_view + 1)
+    ax.set_title('View {}'.format(ind_view))
+    ind_feature = ind_view * 2
+    styles = ('.b', 'xb', '.r', 'xr')
+    labels = ('non-separated', 'separated')
+    for ind in range(4):
+        ind_class = ind // 2
+        label = labels[(ind + ind_view) % 2]
+        ax.plot(X[n_samples*ind:n_samples*(ind+1), ind_feature],
+                X[n_samples*ind:n_samples*(ind+1), ind_feature + 1],
+                styles[ind],
+                label='Class {} ({})'.format(ind_class, label))
+    ax.legend()
+
+print('\nThe second figure displays the classification results for the '
+      'sub-classifiers\non the learning sample data.\n')
+
+styles = ('.b', '.r')
+fig = plt.figure(figsize=(12., 7.))
+fig.suptitle('Classification results on the learning data for the '
+             'sub-classifiers', size=16)
+for ind_estimator in range(n_estimators):
+    best_view = clf.best_views_[ind_estimator]
+    y_pred = clf.estimators_[ind_estimator].predict(
+        X[:, 2*best_view:2*best_view+2])
+    background_color = (1.0, 1.0, 0.9)
+    for ind_view in range(2):
+        ax = plt.subplot(2, 3, ind_estimator + 3*ind_view + 1)
+        if ind_view == best_view:
+            ax.set_facecolor(background_color)
+        ax.set_title(
+            'Sub-classifier {} - View {}'.format(ind_estimator, ind_view))
+        ind_feature = ind_view * 2
+        for ind_class in range(2):
+            ind_samples = (y_pred == ind_class)
+            ax.plot(X[ind_samples, ind_feature],
+                    X[ind_samples, ind_feature + 1],
+                    styles[ind_class],
+                    label='Class {}'.format(ind_class))
+        ax.legend(title='Predicted class:')
+
+plt.show()

examples/mumbo_plot_3_views_3_classes.py

+# -*- coding: utf-8 -*-
+"""
+==========================
+3 views, 3 classes example
+==========================
+
+In this toy example, we generate data from three classes, split between three
+two-dimensional views.
+
+For each view, the data are generated so that the points for two classes are
+well seperated, while the points for the third class are not seperated with
+the two other classes. That means that, taken separately, none of the single
+views allows for a good classification of the data.
+
+Nevertheless, the MuMBo algorithm take adavantage of the complementarity of
+the views to rightly classify the points.
+"""
+
+import numpy as np
+from multimodal.boosting.mumbo import MumboClassifier
+from matplotlib import pyplot as plt
+
+
+def generate_data(n_samples, lim):
+    """Generate random data in a rectangle"""
+    lim = np.array(lim)
+    n_features = lim.shape[0]
+    data = np.random.random((n_samples, n_features))
+    data = (lim[:, 1]-lim[:, 0]) * data + lim[:, 0]
+    return data
+
+
+seed = 12
+np.random.seed(seed)
+
+n_samples = 300
+
+view_0 = np.concatenate((generate_data(n_samples, [[0., 1.], [0., 1.]]),
+                         generate_data(n_samples, [[1., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 2.], [0., 1.]])))
+
+view_1 = np.concatenate((generate_data(n_samples, [[1., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [0., 1.]])))
+
+view_2 = np.concatenate((generate_data(n_samples, [[0., 2.], [0., 1.]]),
+                         generate_data(n_samples, [[0., 1.], [0., 1.]]),
+                         generate_data(n_samples, [[1., 2.], [0., 1.]])))
+
+X = np.concatenate((view_0, view_1, view_2), axis=1)
+
+y = np.zeros(3*n_samples, dtype=np.int64)
+y[n_samples:2*n_samples] = 1
+y[2*n_samples:] = 2
+
+views_ind = np.array([0, 2, 4, 6])
+
+n_estimators = 4
+clf = MumboClassifier(n_estimators=n_estimators)
+clf.fit(X, y, views_ind)
+
+print('\nAfter 4 iterations, the MuMBo classifier reaches exact '
+      'classification for the\nlearning samples:')
+for ind, score in enumerate(clf.staged_score(X, y)):
+    print('  - iteration {}, score: {}'.format(ind + 1, score))
+
+print('\nThe resulting MuMBo classifier uses four sub-classifiers that are '
+      'wheighted\nusing the following weights:\n'
+      '  estimator weights: {}'.format(clf.estimator_weights_))
+
+print('\nThe first sub-classifier uses the data of view 0 to compute '
+      'its classification\nresults, the second and third sub-classifiers use '
+      'the data of view 1, while the\nfourth one uses the data of '
+      'view 2:\n'
+      '  best views: {}'. format(clf.best_views_))
+
+print('\nThe first figure displays the data, splitting the representation '
+      'between the\nthree views.')
+
+styles = ('.b', '.r', '.g')
+fig = plt.figure(figsize=(12., 11.))
+fig.suptitle('Representation of the data', size=16)
+for ind_view in range(3):
+    ax = plt.subplot(3, 1, ind_view + 1)
+    ax.set_title('View {}'.format(ind_view))
+    ind_feature = ind_view * 2
+    for ind_class in range(3):
+        ind_samples = (y == ind_class)
+        ax.plot(X[ind_samples, ind_feature],
+                X[ind_samples, ind_feature + 1],
+                styles[ind_class],
+                label='Class {}'.format(ind_class))
+    ax.legend(loc='upper left', framealpha=0.9)
+
+print('\nThe second figure displays the classification results for the '
+      'sub-classifiers\non the learning sample data.\n')
+
+fig = plt.figure(figsize=(14., 11.))
+fig.suptitle('Classification results on the learning data for the '
+             'sub-classifiers', size=16)
+for ind_estimator in range(n_estimators):
+    best_view = clf.best_views_[ind_estimator]
+    y_pred = clf.estimators_[ind_estimator].predict(
+        X[:, 2*best_view:2*best_view+2])
+    background_color = (1.0, 1.0, 0.9)
+    for ind_view in range(3):
+        ax = plt.subplot(3, 4, ind_estimator + 4*ind_view + 1)
+        if ind_view == best_view:
+            ax.set_facecolor(background_color)
+        ax.set_title(
+            'Sub-classifier {} - View {}'.format(ind_estimator, ind_view))
+        ind_feature = ind_view * 2
+        for ind_class in range(3):
+            ind_samples = (y_pred == ind_class)
+            ax.plot(X[ind_samples, ind_feature],
+                    X[ind_samples, ind_feature + 1],
+                    styles[ind_class],
+                    label='Class {}'.format(ind_class))
+        ax.legend(title='Predicted class:', loc='upper left', framealpha=0.9)
+
+plt.show()

multimodal/boosting/cumbo.py

@@ -5,32 +5,6 @@ This module contains a **Mu**\ lti\ **C**\ onfusion **M**\ Matrix **B**\ osting
 estimator for classification implemented in the ``MuCumboClassifier`` class.
 """
 
-# Université d'Aix Marseille (AMU) -
-# Centre National de la Recherche Scientifique (CNRS) -
-# Université de Toulon (UTLN).
-# Copyright © 2017-2018 AMU, CNRS, UTLN
-#
-# This file is part of multimodalboost.
-#
-# multimodalboost is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Lesser General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# multimodalboost is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Lesser General Public License for more details.
-#
-# You should have received a copy of the GNU Lesser General Public License
-# along with multiconfusion. If not, see <http://www.gnu.org/licenses/>.
-#
-# Author: Dominique Benielli- Laboratoire d'Informatique et Systèmes - UMR 7020
-
-# The implementation of the MuCumboClassifier in this module used the code of
-# sklearn.ensemble.AdaBoostClassifier as a model and tried to use the same
-# structure, notations and behavior where possible.
-
 import numpy as np
 from sklearn.base import ClassifierMixin
 from sklearn.ensemble import BaseEnsemble

multimodal/datasets/data_sample.py

@@ -6,18 +6,29 @@ nbL and nbEx numbers,
 MultiModalArray class inherit from numpy ndarray and contains a 2d data ndarray
 with the shape (n_samples, n_view_i * n_features_i)
 
-0        1    2    3
-======== ==== ==== ====
-xxxxxxxx xxxx xxxx xxxx
-xxxxxxxx xxxx xxxx xxxx
-xxxxxxxx xxxx xxxx xxxx
-xxxxxxxx xxxx xxxx xxxx
-xxxxxxxx xxxx xxxx xxxx
-xxxxxxxx xxxx xxxx xxxx
-xxxxxxxx xxxx xxxx xxxx
-xxxxxxxx xxxx xxxx xxxx
-xxxxxxxx xxxx xxxx xxxx
-======== ==== ==== ====
+.. tabularcolumns::  |l|l|l|l|
+
++----------+------+------+------+
+| 0        | 1    | 2    | 3    |
++==========+======+======+======+
+| xxxxxxxx | xxxx | xxxx | xxxx |
++----------+------+------+------+
+| xxxxxxxx | xxxx | xxxx | xxxx |
++----------+------+------+------+
+| xxxxxxxx | xxxx | xxxx | xxxx |
++----------+------+------+------+
+| xxxxxxxx | xxxx | xxxx | xxxx |
++----------+------+------+------+
+| xxxxxxxx | xxxx | xxxx | xxxx |
++----------+------+------+------+
+| xxxxxxxx | xxxx | xxxx | xxxx |
++----------+------+------+------+
+| xxxxxxxx | xxxx | xxxx | xxxx |
++----------+------+------+------+
+| xxxxxxxx | xxxx | xxxx | xxxx |
++----------+------+------+------+
+| xxxxxxxx | xxxx | xxxx | xxxx |
++----------+------+------+------+
 
 MultiModalSparseArray inherit from scipy sparce matrix with the shape (n_samples, n_view_i * n_features_i)
 

multimodal/kernels/mvml.py

@@ -417,7 +417,7 @@ class MVML(MKernel, BaseEstimator, ClassifierMixin):
 
         Parameters
         ----------
-        test_kernels : `Metriclearn_array` of test kernels
+        test_kernels : `` of test kernels
 
         g : learning solution that is learned in learn_mvml