From 1c53a5db993193122bfa79574d2540149fe2cc08 Mon Sep 17 00:00:00 2001
From: Davies Liu <davies@databricks.com>
Date: Thu, 20 Nov 2014 15:31:28 -0800
Subject: [SPARK-4439] [MLlib] add python api for random forest

```
    class RandomForestModel
     |  A model trained by RandomForest
     |
     |  numTrees(self)
     |      Get number of trees in forest.
     |
     |  predict(self, x)
     |      Predict values for a single data point or an RDD of points using the model trained.
     |
     |  toDebugString(self)
     |      Full model
     |
     |  totalNumNodes(self)
     |      Get total number of nodes, summed over all trees in the forest.
     |

    class RandomForest
     |  trainClassifier(cls, data, numClassesForClassification, categoricalFeaturesInfo, numTrees, featureSubsetStrategy='auto', impurity='gini', maxDepth=4, maxBins=32, seed=None):
     |      Method to train a decision tree model for binary or multiclass classification.
     |
     |      :param data: Training dataset: RDD of LabeledPoint.
     |                   Labels should take values {0, 1, ..., numClasses-1}.
     |      :param numClassesForClassification: number of classes for classification.
     |      :param categoricalFeaturesInfo: Map storing arity of categorical features.
     |                                  E.g., an entry (n -> k) indicates that feature n is categorical
     |                                  with k categories indexed from 0: {0, 1, ..., k-1}.
     |      :param numTrees: Number of trees in the random forest.
     |      :param featureSubsetStrategy: Number of features to consider for splits at each node.
     |                                Supported: "auto" (default), "all", "sqrt", "log2", "onethird".
     |                                If "auto" is set, this parameter is set based on numTrees:
     |                                  if numTrees == 1, set to "all";
     |                                  if numTrees > 1 (forest) set to "sqrt".
     |      :param impurity: Criterion used for information gain calculation.
     |                   Supported values: "gini" (recommended) or "entropy".
     |      :param maxDepth: Maximum depth of the tree. E.g., depth 0 means 1 leaf node; depth 1 means
     |                       1 internal node + 2 leaf nodes. (default: 4)
     |      :param maxBins: maximum number of bins used for splitting features (default: 100)
     |      :param seed:  Random seed for bootstrapping and choosing feature subsets.
     |      :return: RandomForestModel that can be used for prediction
     |
     |   trainRegressor(cls, data, categoricalFeaturesInfo, numTrees, featureSubsetStrategy='auto', impurity='variance', maxDepth=4, maxBins=32, seed=None):
     |      Method to train a decision tree model for regression.
     |
     |      :param data: Training dataset: RDD of LabeledPoint.
     |                   Labels are real numbers.
     |      :param categoricalFeaturesInfo: Map storing arity of categorical features.
     |                                   E.g., an entry (n -> k) indicates that feature n is categorical
     |                                   with k categories indexed from 0: {0, 1, ..., k-1}.
     |      :param numTrees: Number of trees in the random forest.
     |      :param featureSubsetStrategy: Number of features to consider for splits at each node.
     |                                 Supported: "auto" (default), "all", "sqrt", "log2", "onethird".
     |                                 If "auto" is set, this parameter is set based on numTrees:
     |                                 if numTrees == 1, set to "all";
     |                                 if numTrees > 1 (forest) set to "onethird".
     |      :param impurity: Criterion used for information gain calculation.
     |                       Supported values: "variance".
     |      :param maxDepth: Maximum depth of the tree. E.g., depth 0 means 1 leaf node; depth 1 means
     |                       1 internal node + 2 leaf nodes.(default: 4)
     |      :param maxBins: maximum number of bins used for splitting features (default: 100)
     |      :param seed:  Random seed for bootstrapping and choosing feature subsets.
     |      :return: RandomForestModel that can be used for prediction
     |
```

Author: Davies Liu <davies@databricks.com>

Closes #3320 from davies/forest and squashes the following commits:

8003dfc [Davies Liu] reorder
53cf510 [Davies Liu] fix docs
4ca593d [Davies Liu] fix docs
e0df852 [Davies Liu] fix docs
0431746 [Davies Liu] rebased
2b6f239 [Davies Liu] Merge branch 'master' of github.com:apache/spark into forest
885abee [Davies Liu] address comments
dae7fc0 [Davies Liu] address comments
89a000f [Davies Liu] fix docs
565d476 [Davies Liu] add python api for random forest
---
 python/docs/epytext.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'python/docs/epytext.py')

diff --git a/python/docs/epytext.py b/python/docs/epytext.py
index 19fefbfc05..e884d5e6b1 100644
--- a/python/docs/epytext.py
+++ b/python/docs/epytext.py
@@ -1,7 +1,7 @@
 import re
 
 RULES = (
-    (r"<[\w.]+>", r""),
+    (r"<(!BLANKLINE)[\w.]+>", r""),
     (r"L{([\w.()]+)}", r":class:`\1`"),
     (r"[LC]{(\w+\.\w+)\(\)}", r":func:`\1`"),
     (r"C{([\w.()]+)}", r":class:`\1`"),
-- 
cgit v1.2.3