diff --git a/doc/modules/classes.rst b/doc/modules/classes.rst index 497a7acb2d3ed1507c88f1d874747aaffe922753..61f6535ec0b6fbc4507b844b6be73e4e746c6389 100644 --- a/doc/modules/classes.rst +++ b/doc/modules/classes.rst @@ -169,3 +169,34 @@ Feature Selection feature_selection.rfe.RFE feature_selection.rfe.RFECV + +.. _feature_extraction_ref: + +Feature Extraction +================== + +.. autosummary:: + :toctree: generated/ + :template: function.rst + + feature_extraction.image.img_to_graph + +.. autosummary:: + :toctree: generated/ + :template: class.rst + + feature_extraction.text.WordNGramAnalyzer + feature_extraction.text.CharNGramAnalyzer + feature_extraction.text.TermCountVectorizer + feature_extraction.text.TfidfTransformer + feature_extraction.text.TfidfVectorizer + feature_extraction.text.SparseHashingVectorizer + +Pipeline +======== + +.. autosummary:: + :toctree: generated/ + :template: class.rst + + pipeline.Pipeline diff --git a/doc/modules/feature_selection.rst b/doc/modules/feature_selection.rst index dcd8e9a44ef5e6315ad6de46341b41bd8ba0e9b9..13d5c2a929b8283e3f579c72e88df926e9c277c4 100644 --- a/doc/modules/feature_selection.rst +++ b/doc/modules/feature_selection.rst @@ -1,4 +1,6 @@ +.. _feature_selection_doc: + ======================= Feature selection ======================= diff --git a/doc/whats_new.rst b/doc/whats_new.rst index 2764b0447d9d2ebe103343a58a449d7a4253555f..1417b7a6841d6ae064463eb7904c9007e2a80e64 100644 --- a/doc/whats_new.rst +++ b/doc/whats_new.rst @@ -9,34 +9,45 @@ Changelog --------- -New modules -~~~~~~~~~~~ +New classes +~~~~~~~~~~~~ - - New Hidden Markov Models module (:ref:`scikits.learn.hmm`) + - Support for sparse matrices in some classifiers of modules + ``svm`` and ``glm`` (see :class:`svm.sparse.SVC`, + :class:`svm.sparse.SVR`, :class:`svm.sparse.LinearSVC`, + :class:`glm.sparse.ElasticNet`, :class:`glm.sparse.Lasso`) - - Support for sparse matrices in modules ``svm`` and ``glm``. - - - Add a Pipeline object to compose different estimators. + - New :class:`pipeline.Pipeline` object to compose different estimators. - Recursive Feature Elimination routines in module - :ref:`modules/feature_selection`. + :ref:`feature_selection_doc`. - Addition of various classes capable of cross validation in the glm module (:class:`glm.LassoCV`, :class:`glm.ElasticNetCV`, etc.). - - New pure-python LARS algorithm implementation - (scikits.learn.glm.lars). + - New, more efficient LARS algorithm implementation. The Lasso + variant of the algorithm is also implemented. See + :class:`glm.lars_path`, :class:`glm.LARS` and + :class:`glm.LassoLARS`. + - New Hidden Markov Models module (see classes + :class:`hmm.GaussianHMM`, :class:`hmm.MultinomialHMM`, + :class:`hmm.GMMHMM`) -Examples -~~~~~~~~ + - New module feature_extraction (see :ref:`class reference + <feature_extraction_ref>`) - - new examples using some of the mlcomp datasets: - :ref:`example_mlcomp_sparse_document_classification.py`, - :ref:`example_mlcomp_document_classification.py` - - Many more examaples. +Documentation +~~~~~~~~~~~~~ + + - Improved documentation for many modules, now separating + narrative documentation from the class reference. As an example, + see `documentation for the SVM module + <http://scikit-learn.sourceforge.net/modules/svm.html>`_ and the + complete `class reference + <http://scikit-learn.sourceforge.net/modules/classes.html>`_. Fixes ~~~~~ @@ -44,6 +55,22 @@ Fixes - API changes: adhere variable names to PEP-8, give more meaningful names. + - Fixes for svm module to run on a shared memory context + (multiprocessing). + + - It is again possible to generate latex (and thus PDF) from the + sphinx docs. + +Examples +~~~~~~~~ + + - new examples using some of the mlcomp datasets: + :ref:`example_mlcomp_sparse_document_classification.py`, + :ref:`example_mlcomp_document_classification.py` + + - Many more examaples. `See here + <http://scikit-learn.sourceforge.net/auto_examples/index.html>`_ + the full list of examples. External dependencies @@ -59,6 +86,11 @@ Removed modules the distribution. Users wanting this sort of algorithms should take a look into pybrain. +Misc +~~~~ + + - New sphinx theme for the web page. + 0.4 ===