Rebuild dev docs at master=425407b

Author: sklearn-ci

dev/_sources/modules/outlier_detection.txt

@@ -128,9 +128,53 @@ This strategy is illustrated below.
 
     ..  [RD1999] Rousseeuw, P.J., Van Driessen, K. "A fast algorithm for the minimum
         covariance determinant estimator" Technometrics 41(3), 212 (1999)
+
+
+Isolation Forest
+----------------------------
+
+One efficient way of performing outlier detection in high-dimensional datasets
+is to use random forests.
+The :class:`ensemble.IsolationForest` 'isolates' observations by randomly selecting
+a feature and then randomly selecting a split value between the maximum and
+minimum values of the selected feature.
+
+Since recursive partitioning can be represented by a tree structure, the
+number of splittings required to isolate a sample is equivalent to the path
+length from the root node to the terminating node.
+
+This path length, averaged over a forest of such random trees, is a
+measure of abnormality and our decision function.
+
+Random partitioning produces noticeably shorter paths for anomalies.
+Hence, when a forest of random trees collectively produce shorter path
+lengths for particular samples, they are highly likely to be anomalies.
+
+This strategy is illustrated below.
+
+.. figure:: ../auto_examples/ensemble/images/plot_isolation_forest_001.png
+   :target: ../auto_examples/ensemble/plot_isolation_forest.html
+   :align: center
+   :scale: 75%
+
+.. topic:: Examples:
+
+   * See :ref:`example_ensemble_plot_isolation_forest.py` for
+     an illustration of the use of IsolationForest.
+
+   * See :ref:`example_covariance_plot_outlier_detection.py` for a
+     comparison of :class:`ensemble.IsolationForest` with
+     :class:`svm.OneClassSVM` (tuned to perform like an outlier detection
+     method) and a covariance-based outlier detection with
+     :class:`covariance.MinCovDet`.
+
+.. topic:: References:
+    .. [LTZ2008] Liu, Fei Tony, Ting, Kai Ming and Zhou, Zhi-Hua. "Isolation forest."
+           Data Mining, 2008. ICDM'08. Eighth IEEE International Conference on.
+
 
-One-class SVM versus elliptic envelope
---------------------------------------
+One-class SVM versus Elliptic Envelope versus Isolation Forest
+--------------------------------------------------------------
 
 Strictly-speaking, the One-class SVM is not an outlier-detection method,
 but a novelty-detection method: its training set should not be
@@ -141,8 +185,8 @@ results in these situations.
 
 The examples below illustrate how the performance of the
 :class:`covariance.EllipticEnvelope` degrades as the data is less and
-less unimodal.  :class:`svm.OneClassSVM` works better on data with
-multiple modes.
+less unimodal. The :class:`svm.OneClassSVM` works better on data with
+multiple modes and :class:`ensemble.IsolationForest` performs well in every cases.
 
 .. |outlier1| image:: ../auto_examples/covariance/images/plot_outlier_detection_001.png
    :target: ../auto_examples/covariance/plot_outlier_detection.html
@@ -166,70 +210,32 @@ multiple modes.
         fits a bit the outliers present in the training set. On the
         opposite, the decision rule based on fitting an
         :class:`covariance.EllipticEnvelope` learns an ellipse, which
-        fits well the inlier distribution.
+        fits well the inlier distribution. The :class:`ensemble.IsolationForest`
+	performs as well.
       - |outlier1| 
 
    * 
       - As the inlier distribution becomes bimodal, the
         :class:`covariance.EllipticEnvelope` does not fit well the
-        inliers. However, we can see that the :class:`svm.OneClassSVM`
+        inliers. However, we can see that both :class:`ensemble.IsolationForest`
+	and :class:`svm.OneClassSVM` have difficulties to detect the two modes,
+	and that the :class:`svm.OneClassSVM`
         tends to overfit: because it has not model of inliers, it
         interprets a region where, by chance some outliers are
-        clustered, as inliers.
+        clustered, as inliers. 
       - |outlier2| 
 
    * 
       - If the inlier distribution is strongly non Gaussian, the
         :class:`svm.OneClassSVM` is able to recover a reasonable
-        approximation, whereas the :class:`covariance.EllipticEnvelope`
-        completely fails.
+        approximation as well as :class:`ensemble.IsolationForest`,
+	whereas the :class:`covariance.EllipticEnvelope` completely fails.
       - |outlier3|
 
 .. topic:: Examples:
 
    * See :ref:`example_covariance_plot_outlier_detection.py` for a
      comparison of the :class:`svm.OneClassSVM` (tuned to perform like
-     an outlier detection method) and a covariance-based outlier
+     an outlier detection method), the :class:`ensemble.IsolationForest`
+     and a covariance-based outlier
      detection with :class:`covariance.MinCovDet`.
-
-Isolation Forest
-----------------------------
-
-One efficient way of performing outlier detection in high-dimensional datasets
-is to use random forests.
-The :class:`ensemble.IsolationForest` 'isolates' observations by randomly selecting
-a feature and then randomly selecting a split value between the maximum and
-minimum values of the selected feature.
-
-Since recursive partitioning can be represented by a tree structure, the
-number of splittings required to isolate a sample is equivalent to the path
-length from the root node to the terminating node.
-
-This path length, averaged over a forest of such random trees, is a
-measure of abnormality and our decision function.
-
-Random partitioning produces noticeably shorter paths for anomalies.
-Hence, when a forest of random trees collectively produce shorter path
-lengths for particular samples, they are highly likely to be anomalies.
-
-This strategy is illustrated below.
-
-.. figure:: ../auto_examples/ensemble/images/plot_isolation_forest_001.png
-   :target: ../auto_examples/ensemble/plot_isolation_forest.html
-   :align: center
-   :scale: 75%
-
-.. topic:: Examples:
-
-   * See :ref:`example_ensemble_plot_isolation_forest.py` for
-     an illustration of the use of IsolationForest.
-
-   * See :ref:`example_covariance_plot_outlier_detection.py` for a
-     comparison of :class:`ensemble.IsolationForest` with
-     :class:`svm.OneClassSVM` (tuned to perform like an outlier detection
-     method) and a covariance-based outlier detection with
-     :class:`covariance.MinCovDet`.
-
-.. topic:: References:
-    .. [LTZ2008] Liu, Fei Tony, Ting, Kai Ming and Zhou, Zhi-Hua. "Isolation forest."
-           Data Mining, 2008. ICDM'08. Eighth IEEE International Conference on.

dev/modules/generated/sklearn.base.BaseEstimator.html

@@ -172,7 +172,7 @@
 <h1><a class="reference internal" href="../classes.html#module-sklearn.base" title="sklearn.base"><tt class="xref py py-mod docutils literal"><span class="pre">sklearn.base</span></tt></a>.BaseEstimator<a class="headerlink" href="#sklearn-base-baseestimator" title="Permalink to this headline">¶</a></h1>
 <dl class="class">
 <dt id="sklearn.base.BaseEstimator">
-<em class="property">class </em><tt class="descclassname">sklearn.base.</tt><tt class="descname">BaseEstimator</tt><a class="reference external" href="https://github.com/scikit-learn/scikit-learn/blob/e3a95bf/sklearn/base.py#L169"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#sklearn.base.BaseEstimator" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><tt class="descclassname">sklearn.base.</tt><tt class="descname">BaseEstimator</tt><a class="reference external" href="https://github.com/scikit-learn/scikit-learn/blob/425407b/sklearn/base.py#L169"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#sklearn.base.BaseEstimator" title="Permalink to this definition">¶</a></dt>
 <dd><p>Base class for all estimators in scikit-learn</p>
 <p class="rubric">Notes</p>
 <p>All estimators should specify all the parameters that can be set
@@ -201,7 +201,7 @@ <h1><a class="reference internal" href="../classes.html#module-sklearn.base" tit
 
 <dl class="method">
 <dt id="sklearn.base.BaseEstimator.get_params">
-<tt class="descname">get_params</tt><big>(</big><em>deep=True</em><big>)</big><a class="reference external" href="https://github.com/scikit-learn/scikit-learn/blob/e3a95bf/sklearn/base.py#L206"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#sklearn.base.BaseEstimator.get_params" title="Permalink to this definition">¶</a></dt>
+<tt class="descname">get_params</tt><big>(</big><em>deep=True</em><big>)</big><a class="reference external" href="https://github.com/scikit-learn/scikit-learn/blob/425407b/sklearn/base.py#L206"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#sklearn.base.BaseEstimator.get_params" title="Permalink to this definition">¶</a></dt>
 <dd><p>Get parameters for this estimator.</p>
 <table class="docutils field-list" frame="void" rules="none">
 <col class="field-name" />
@@ -226,7 +226,7 @@ <h1><a class="reference internal" href="../classes.html#module-sklearn.base" tit
 
 <dl class="method">
 <dt id="sklearn.base.BaseEstimator.set_params">
-<tt class="descname">set_params</tt><big>(</big><em>**params</em><big>)</big><a class="reference external" href="https://github.com/scikit-learn/scikit-learn/blob/e3a95bf/sklearn/base.py#L243"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#sklearn.base.BaseEstimator.set_params" title="Permalink to this definition">¶</a></dt>
+<tt class="descname">set_params</tt><big>(</big><em>**params</em><big>)</big><a class="reference external" href="https://github.com/scikit-learn/scikit-learn/blob/425407b/sklearn/base.py#L243"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#sklearn.base.BaseEstimator.set_params" title="Permalink to this definition">¶</a></dt>
 <dd><p>Set the parameters of this estimator.</p>
 <p>The method works on simple estimators as well as on nested objects
 (such as pipelines). The former have parameters of the form

dev/modules/generated/sklearn.base.TransformerMixin.html

@@ -172,7 +172,7 @@
 <h1><a class="reference internal" href="../classes.html#module-sklearn.base" title="sklearn.base"><tt class="xref py py-mod docutils literal"><span class="pre">sklearn.base</span></tt></a>.TransformerMixin<a class="headerlink" href="#sklearn-base-transformermixin" title="Permalink to this headline">¶</a></h1>
 <dl class="class">
 <dt id="sklearn.base.TransformerMixin">
-<em class="property">class </em><tt class="descclassname">sklearn.base.</tt><tt class="descname">TransformerMixin</tt><a class="reference external" href="https://github.com/scikit-learn/scikit-learn/blob/e3a95bf/sklearn/base.py#L435"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#sklearn.base.TransformerMixin" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><tt class="descclassname">sklearn.base.</tt><tt class="descname">TransformerMixin</tt><a class="reference external" href="https://github.com/scikit-learn/scikit-learn/blob/425407b/sklearn/base.py#L435"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#sklearn.base.TransformerMixin" title="Permalink to this definition">¶</a></dt>
 <dd><p>Mixin class for all transformers in scikit-learn.</p>
 <p class="rubric">Methods</p>
 <table border="1" class="longtable docutils">
@@ -194,7 +194,7 @@ <h1><a class="reference internal" href="../classes.html#module-sklearn.base" tit
 
 <dl class="method">
 <dt id="sklearn.base.TransformerMixin.fit_transform">
-<tt class="descname">fit_transform</tt><big>(</big><em>X</em>, <em>y=None</em>, <em>**fit_params</em><big>)</big><a class="reference external" href="https://github.com/scikit-learn/scikit-learn/blob/e3a95bf/sklearn/base.py#L438"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#sklearn.base.TransformerMixin.fit_transform" title="Permalink to this definition">¶</a></dt>
+<tt class="descname">fit_transform</tt><big>(</big><em>X</em>, <em>y=None</em>, <em>**fit_params</em><big>)</big><a class="reference external" href="https://github.com/scikit-learn/scikit-learn/blob/425407b/sklearn/base.py#L438"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#sklearn.base.TransformerMixin.fit_transform" title="Permalink to this definition">¶</a></dt>
 <dd><p>Fit to data, then transform it.</p>
 <p>Fits transformer to X and y with optional parameters fit_params
 and returns a transformed version of X.</p>