diff options
Diffstat (limited to 'python/pyspark/mllib/tree.py')
-rw-r--r-- | python/pyspark/mllib/tree.py | 156 |
1 files changed, 94 insertions, 62 deletions
diff --git a/python/pyspark/mllib/tree.py b/python/pyspark/mllib/tree.py index 02d551b87d..73618f0449 100644 --- a/python/pyspark/mllib/tree.py +++ b/python/pyspark/mllib/tree.py @@ -33,6 +33,10 @@ class TreeEnsembleModel(JavaModelWrapper): """ Predict values for a single data point or an RDD of points using the model trained. + + Note: In Python, predict cannot currently be used within an RDD + transformation or action. + Call predict directly on the RDD instead. """ if isinstance(x, RDD): return self.call("predict", x.map(_convert_to_vector)) @@ -48,7 +52,8 @@ class TreeEnsembleModel(JavaModelWrapper): def totalNumNodes(self): """ - Get total number of nodes, summed over all trees in the ensemble. + Get total number of nodes, summed over all trees in the + ensemble. """ return self.call("totalNumNodes") @@ -71,6 +76,10 @@ class DecisionTreeModel(JavaModelWrapper): """ Predict the label of one or more examples. + Note: In Python, predict cannot currently be used within an RDD + transformation or action. + Call predict directly on the RDD instead. + :param x: Data point (feature vector), or an RDD of data points (feature vectors). """ @@ -99,7 +108,8 @@ class DecisionTree(object): """ .. note:: Experimental - Learning algorithm for a decision tree model for classification or regression. + Learning algorithm for a decision tree model for classification or + regression. """ @classmethod @@ -176,17 +186,17 @@ class DecisionTree(object): :param data: Training data: RDD of LabeledPoint. Labels are real numbers. - :param categoricalFeaturesInfo: Map from categorical feature index - to number of categories. - Any feature not in this map - is treated as continuous. + :param categoricalFeaturesInfo: Map from categorical feature + index to number of categories. + Any feature not in this map is treated as continuous. :param impurity: Supported values: "variance" :param maxDepth: Max depth of tree. - E.g., depth 0 means 1 leaf node. - Depth 1 means 1 internal node + 2 leaf nodes. - :param maxBins: Number of bins used for finding splits at each node. - :param minInstancesPerNode: Min number of instances required at child - nodes to create the parent split + E.g., depth 0 means 1 leaf node. + Depth 1 means 1 internal node + 2 leaf nodes. + :param maxBins: Number of bins used for finding splits at each + node. + :param minInstancesPerNode: Min number of instances required at + child nodes to create the parent split :param minInfoGain: Min info gain required to create a split :return: DecisionTreeModel @@ -229,7 +239,8 @@ class RandomForest(object): """ .. note:: Experimental - Learning algorithm for a random forest model for classification or regression. + Learning algorithm for a random forest model for classification or + regression. """ supportedFeatureSubsetStrategies = ("auto", "all", "sqrt", "log2", "onethird") @@ -256,26 +267,33 @@ class RandomForest(object): 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 data: Training dataset: RDD of LabeledPoint. Labels + should take values {0, 1, ..., numClasses-1}. :param numClasses: 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 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. + :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 + :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. + :param seed: Random seed for bootstrapping and choosing feature + subsets. :return: RandomForestModel that can be used for prediction Example usage: @@ -337,19 +355,24 @@ class RandomForest(object): {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" for regression. - :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. + 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" for + regression. + :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 Example usage: @@ -395,7 +418,8 @@ class GradientBoostedTrees(object): """ .. note:: Experimental - Learning algorithm for a gradient boosted trees model for classification or regression. + Learning algorithm for a gradient boosted trees model for + classification or regression. """ @classmethod @@ -411,24 +435,29 @@ class GradientBoostedTrees(object): def trainClassifier(cls, data, categoricalFeaturesInfo, loss="logLoss", numIterations=100, learningRate=0.1, maxDepth=3): """ - Method to train a gradient-boosted trees model for classification. + Method to train a gradient-boosted trees model for + classification. - :param data: Training dataset: RDD of LabeledPoint. Labels should take values {0, 1}. + :param data: Training dataset: RDD of LabeledPoint. + Labels should take values {0, 1}. :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 loss: Loss function used for minimization during gradient boosting. - Supported: {"logLoss" (default), "leastSquaresError", "leastAbsoluteError"}. + :param loss: Loss function used for minimization during gradient + boosting. Supported: {"logLoss" (default), + "leastSquaresError", "leastAbsoluteError"}. :param numIterations: Number of iterations of boosting. (default: 100) - :param learningRate: Learning rate for shrinking the contribution of each estimator. - The learning rate should be between in the interval (0, 1] - (default: 0.1) - :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: 3) - :return: GradientBoostedTreesModel that can be used for prediction + :param learningRate: Learning rate for shrinking the + contribution of each estimator. The learning rate + should be between in the interval (0, 1]. + (default: 0.1) + :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: 3) + :return: GradientBoostedTreesModel that can be used for + prediction Example usage: @@ -472,17 +501,20 @@ class GradientBoostedTrees(object): features. E.g., an entry (n -> k) indicates that feature n is categorical with k categories indexed from 0: {0, 1, ..., k-1}. - :param loss: Loss function used for minimization during gradient boosting. - Supported: {"logLoss" (default), "leastSquaresError", "leastAbsoluteError"}. + :param loss: Loss function used for minimization during gradient + boosting. Supported: {"logLoss" (default), + "leastSquaresError", "leastAbsoluteError"}. :param numIterations: Number of iterations of boosting. (default: 100) - :param learningRate: Learning rate for shrinking the contribution of each estimator. - The learning rate should be between in the interval (0, 1] - (default: 0.1) - :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: 3) - :return: GradientBoostedTreesModel that can be used for prediction + :param learningRate: Learning rate for shrinking the + contribution of each estimator. The learning rate + should be between in the interval (0, 1]. + (default: 0.1) + :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: 3) + :return: GradientBoostedTreesModel that can be used for + prediction Example usage: |