[SPARK-15162][SPARK-15164][PySpark][DOCS][ML] update some pydocs

mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala

@@ -72,10 +72,9 @@ private[classification] trait LogisticRegressionParams extends ProbabilisticClas
   /**
    * Get threshold for binary classification.
    *
-   * If [[threshold]] is set, returns that value.
-   * Otherwise, if [[thresholds]] is set with length 2 (i.e., binary classification),
+   * If [[thresholds]] is set with length 2 (i.e., binary classification),
    * this returns the equivalent threshold: {{{1 / (1 + thresholds(0) / thresholds(1))}}}.
-   * Otherwise, returns [[threshold]] default value.
+   * Otherwise, returns [[threshold]] if set, or its default value if unset.
    *
    * @group getParam
    * @throws IllegalArgumentException if [[thresholds]] is set to an array of length other than 2.

python/docs/conf.py

@@ -32,6 +32,7 @@
     'sphinx.ext.autodoc',
     'sphinx.ext.viewcode',
     'epytext',
+    'sphinx.ext.mathjax',
 ]
 
 # Add any paths that contain templates here, relative to this directory.

python/pyspark/ml/classification.py

@@ -49,6 +49,8 @@ class LogisticRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredicti
                          HasElasticNetParam, HasFitIntercept, HasStandardization, HasThresholds,
                          HasWeightCol, JavaMLWritable, JavaMLReadable):
     """
+    .. note:: Experimental
+
     Logistic regression.
     Currently, this class only supports binary classification.
 
@@ -96,7 +98,8 @@ class LogisticRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredicti
 
     threshold = Param(Params._dummy(), "threshold",
                       "Threshold in binary classification prediction, in range [0, 1]." +
-                      " If threshold and thresholds are both set, they must match.",
+                      " If threshold and thresholds are both set, they must match." +
+                      "e.g. if threshold is p, then thresholds must be equal to [1-p, p].",
                       typeConverter=TypeConverters.toFloat)
 
     @keyword_only
@@ -154,7 +157,12 @@ def setThreshold(self, value):
     @since("1.4.0")
     def getThreshold(self):
         """
-        Gets the value of threshold or its default value.
+        Get threshold for binary classification.
+
+        If :py:attr:`thresholds` is set with length 2 (i.e., binary classification),
+        this returns the equivalent threshold:
+        :math:`\\frac{1}{1 + \\frac{thresholds(0)}{thresholds(1)}}`.
+        Otherwise, returns :py:attr:`threshold` if set or its default value if unset.
         """
         self._checkThresholdConsistency()
         if self.isSet(self.thresholds):
@@ -208,6 +216,8 @@ def _checkThresholdConsistency(self):
 
 class LogisticRegressionModel(JavaModel, JavaMLWritable, JavaMLReadable):
     """
+    .. note:: Experimental
+
     Model fitted by LogisticRegression.
 
     .. versionadded:: 1.3.0
@@ -491,6 +501,8 @@ class DecisionTreeClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
                              TreeClassifierParams, HasCheckpointInterval, HasSeed, JavaMLWritable,
                              JavaMLReadable):
     """
+    .. note:: Experimental
+
     `Decision tree <http://en.wikipedia.org/wiki/Decision_tree_learning>`_
     learning algorithm for classification.
     It supports both binary and multiclass labels, as well as both continuous and categorical
@@ -587,6 +599,8 @@ def _create_model(self, java_model):
 @inherit_doc
 class DecisionTreeClassificationModel(DecisionTreeModel, JavaMLWritable, JavaMLReadable):
     """
+    .. note:: Experimental
+
     Model fitted by DecisionTreeClassifier.
 
     .. versionadded:: 1.4.0
@@ -620,6 +634,8 @@ class RandomForestClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
                              RandomForestParams, TreeClassifierParams, HasCheckpointInterval,
                              JavaMLWritable, JavaMLReadable):
     """
+    .. note:: Experimental
+
     `Random Forest <http://en.wikipedia.org/wiki/Random_forest>`_
     learning algorithm for classification.
     It supports both binary and multiclass labels, as well as both continuous and categorical
@@ -714,6 +730,8 @@ def _create_model(self, java_model):
 
 class RandomForestClassificationModel(TreeEnsembleModels, JavaMLWritable, JavaMLReadable):
     """
+    .. note:: Experimental
+
     Model fitted by RandomForestClassifier.
 
     .. versionadded:: 1.4.0
@@ -746,6 +764,8 @@ class GBTClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol
                     GBTParams, HasCheckpointInterval, HasStepSize, HasSeed, JavaMLWritable,
                     JavaMLReadable):
     """
+    .. note:: Experimental
+
     `Gradient-Boosted Trees (GBTs) <http://en.wikipedia.org/wiki/Gradient_boosting>`_
     learning algorithm for classification.
     It supports binary labels, as well as both continuous and categorical features.
@@ -863,6 +883,8 @@ def getLossType(self):
 
 class GBTClassificationModel(TreeEnsembleModels, JavaMLWritable, JavaMLReadable):
     """
+    .. note:: Experimental
+
     Model fitted by GBTClassifier.
 
     .. versionadded:: 1.4.0
@@ -894,6 +916,8 @@ def trees(self):
 class NaiveBayes(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol, HasProbabilityCol,
                  HasRawPredictionCol, HasThresholds, JavaMLWritable, JavaMLReadable):
     """
+    .. note:: Experimental
+
     Naive Bayes Classifiers.
     It supports both Multinomial and Bernoulli NB. `Multinomial NB
     <http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html>`_
@@ -1017,6 +1041,8 @@ def getModelType(self):
 
 class NaiveBayesModel(JavaModel, JavaMLWritable, JavaMLReadable):
     """
+    .. note:: Experimental
+
     Model fitted by NaiveBayes.
 
     .. versionadded:: 1.5.0
@@ -1044,6 +1070,8 @@ class MultilayerPerceptronClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol,
                                      HasMaxIter, HasTol, HasSeed, HasStepSize, JavaMLWritable,
                                      JavaMLReadable):
     """
+    .. note:: Experimental
+
     Classifier trainer based on the Multilayer Perceptron.
     Each layer has sigmoid activation function, output layer has softmax.
     Number of inputs has to be equal to the size of feature vectors.
@@ -1214,6 +1242,8 @@ def getInitialWeights(self):
 
 class MultilayerPerceptronClassificationModel(JavaModel, JavaMLWritable, JavaMLReadable):
     """
+    .. note:: Experimental
+
     Model fitted by MultilayerPerceptronClassifier.
 
     .. versionadded:: 1.6.0
@@ -1263,6 +1293,8 @@ def getClassifier(self):
 @inherit_doc
 class OneVsRest(Estimator, OneVsRestParams, MLReadable, MLWritable):
     """
+    .. note:: Experimental
+
     Reduction of Multiclass Classification to Binary Classification.
     Performs reduction using one against all strategy.
     For a multiclass classification with k classes, train k models (one per class).
@@ -1417,6 +1449,8 @@ def _to_java(self):
 
 class OneVsRestModel(Model, OneVsRestParams, MLReadable, MLWritable):
     """
+    .. note:: Experimental
+
     Model fitted by OneVsRest.
     This stores the models resulting from training k binary classifiers: one for each class.
     Each example is scored against all k models, and the model with the highest score