Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/3320#discussion_r20676263 --- Diff: python/pyspark/mllib/tree.py --- @@ -181,8 +182,206 @@ def trainRegressor(data, categoricalFeaturesInfo, >>> model.predict(rdd).collect() [1.0, 0.0] """ - return DecisionTree._train(data, "regression", 0, categoricalFeaturesInfo, - impurity, maxDepth, maxBins, minInstancesPerNode, minInfoGain) + return cls._train(data, "regression", 0, categoricalFeaturesInfo, + impurity, maxDepth, maxBins, minInstancesPerNode, minInfoGain) + + +class RandomForestModel(JavaModelWrapper): + """ + Represents a random forest model. + + EXPERIMENTAL: This is an experimental API. + It will probably be modified in future. + """ + def predict(self, x): + """ + Predict values for a single data point or an RDD of points using + the model trained. + """ + if isinstance(x, RDD): + return self.call("predict", x.map(_convert_to_vector)) + + else: + return self.call("predict", _convert_to_vector(x)) + + def numTrees(self): + """ + Get number of trees in forest. + """ + return self.call("numTrees") + + def totalNumNodes(self): + """ + Get total number of nodes, summed over all trees in the forest. + """ + return self.call("totalNumNodes") + + def __repr__(self): + """ Summary of model """ + return self._java_model.toString() + + def toDebugString(self): + """ Full model """ + return self._java_model.toDebugString() + + +class RandomForest(object): + """ + Learning algorithm for a random forest model for classification or regression. + + EXPERIMENTAL: This is an experimental API. + It will probably be modified in future. + """ + + supportedFeatureSubsetStrategies = ("auto", "all", "sqrt", "log2", "onethird") + + @classmethod + def _train(cls, data, type, numClasses, features, impurity, maxDepth, maxBins, + numTrees, featureSubsetStrategy, seed): + first = data.first() + assert isinstance(first, LabeledPoint), "the data should be RDD of LabeledPoint" + if featureSubsetStrategy not in cls.supportedFeatureSubsetStrategies: + raise ValueError("unsupported featureSubsetStrategy: %s" % featureSubsetStrategy) + if seed is None: + seed = random.randint(0, 1 << 30) + model = callMLlibFunc("trainRandomForestModel", data, type, numClasses, features, + impurity, maxDepth, maxBins, numTrees, featureSubsetStrategy, seed) + return RandomForestModel(model) + + @classmethod + def 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" for classification and to + "onethird" for regression. + :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 + + Example usage: + + >>> from pyspark.mllib.regression import LabeledPoint + >>> from pyspark.mllib.tree import RandomForest + >>> + >>> data = [ + ... LabeledPoint(0.0, [0.0]), + ... LabeledPoint(0.0, [1.0]), + ... LabeledPoint(1.0, [2.0]), + ... LabeledPoint(1.0, [3.0]) + ... ] + >>> model = RandomForest.trainClassifier(sc.parallelize(data), 2, {}, 3, seed=42) + >>> model.numTrees() + 3 + >>> model.totalNumNodes() + 7 + >>> print model, + TreeEnsembleModel classifier with 3 trees + >>> print model.toDebugString(), + TreeEnsembleModel classifier with 3 trees + <BLANKLINE> + Tree 0: + Predict: 1.0 + Tree 1: + If (feature 0 <= 1.0) + Predict: 0.0 + Else (feature 0 > 1.0) + Predict: 1.0 + Tree 2: + If (feature 0 <= 1.0) + Predict: 0.0 + Else (feature 0 > 1.0) + Predict: 1.0 + >>> model.predict([2.0]) + 1.0 + >>> model.predict([0.0]) + 0.0 + >>> rdd = sc.parallelize([[3.0], [1.0]]) + >>> model.predict(rdd).collect() + [1.0, 0.0] + """ + return cls._train(data, "classification", numClassesForClassification, + categoricalFeaturesInfo, impurity, maxDepth, maxBins, numTrees, + featureSubsetStrategy, seed) + + @classmethod + def 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 "sqrt" for classification and --- End diff -- could just state default for regression
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org