Coverage for pyspark/ml/tree.py : 90%
Hot-keys on this page
r m x p toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
|
# # Licensed to the Apache Software Foundation (ASF) under one or more # contributor license agreements. See the NOTICE file distributed with # this work for additional information regarding copyright ownership. # The ASF licenses this file to You under the Apache License, Version 2.0 # (the "License"); you may not use this file except in compliance with # the License. You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. #
TypeConverters, HasMaxIter, HasStepSize, HasValidationIndicatorCol
""" Abstraction for Decision Tree models.
.. versionadded:: 1.5.0 """
def numNodes(self): """Return number of nodes of the decision tree."""
def depth(self): """Return depth of the decision tree."""
def toDebugString(self): """Full description of model."""
def predictLeaf(self, value): """ Predict the indices of the leaves corresponding to the feature vector. """
""" Mixin for Decision Tree parameters. """
"index of each instance in each tree by preorder.", typeConverter=TypeConverters.toString)
"depth 0 means 1 leaf node; depth 1 means 1 internal node + 2 leaf nodes. " + "Must be in range [0, 30].", typeConverter=TypeConverters.toInt)
"features. Must be >=2 and >= number of categories for any categorical " + "feature.", typeConverter=TypeConverters.toInt)
"instances each child must have after split. If a split causes " + "the left or right child to have fewer than " + "minInstancesPerNode, the split will be discarded as invalid. " + "Should be >= 1.", typeConverter=TypeConverters.toInt)
"fraction of the weighted sample count that each child " "must have after split. If a split causes the fraction " "of the total weight in the left or right child to be " "less than minWeightFractionPerNode, the split will be " "discarded as invalid. Should be in interval [0.0, 0.5).", typeConverter=TypeConverters.toFloat)
"to be considered at a tree node.", typeConverter=TypeConverters.toFloat)
"histogram aggregation. If too small, then 1 node will be split per " + "iteration, and its aggregates may exceed this size.", typeConverter=TypeConverters.toInt)
"trees to executors to match instances with nodes. If true, the " + "algorithm will cache node IDs for each instance. Caching can speed " + "up training of deeper trees. Users can set how often should the cache " + "be checkpointed or disable it by setting checkpointInterval.", typeConverter=TypeConverters.toBoolean)
""" Sets the value of :py:attr:`leafCol`. """
""" Gets the value of leafCol or its default value. """ return self.getOrDefault(self.leafCol)
""" Gets the value of maxDepth or its default value. """
""" Gets the value of maxBins or its default value. """ return self.getOrDefault(self.maxBins)
""" Gets the value of minInstancesPerNode or its default value. """ return self.getOrDefault(self.minInstancesPerNode)
""" Gets the value of minWeightFractionPerNode or its default value. """
""" Gets the value of minInfoGain or its default value. """ return self.getOrDefault(self.minInfoGain)
""" Gets the value of maxMemoryInMB or its default value. """ return self.getOrDefault(self.maxMemoryInMB)
""" Gets the value of cacheNodeIds or its default value. """ return self.getOrDefault(self.cacheNodeIds)
""" (private abstraction) Represents a tree ensemble model. """
def trees(self): """Trees in this ensemble. Warning: These have null parent Estimators.""" return [_DecisionTreeModel(m) for m in list(self._call_java("trees"))]
def getNumTrees(self): """Number of trees in ensemble."""
def treeWeights(self): """Return the weights for each tree"""
def totalNumNodes(self): """Total number of nodes, summed over all trees in the ensemble."""
def toDebugString(self): """Full description of model."""
def predictLeaf(self, value): """ Predict the indices of the leaves corresponding to the feature vector. """
""" Mixin for Decision Tree-based ensemble algorithms parameters. """
"used for learning each decision tree, in range (0, 1].", typeConverter=TypeConverters.toFloat)
Param(Params._dummy(), "featureSubsetStrategy", "The number of features to consider for splits at each tree node. Supported " + "options: 'auto' (choose automatically for task: If numTrees == 1, set to " + "'all'. If numTrees > 1 (forest), set to 'sqrt' for classification and to " + "'onethird' for regression), 'all' (use all features), 'onethird' (use " + "1/3 of the features), 'sqrt' (use sqrt(number of features)), 'log2' (use " + "log2(number of features)), 'n' (when n is in the range (0, 1.0], use " + "n * number of features. When n is in the range (1, number of features), use" + " n features). default = 'auto'", typeConverter=TypeConverters.toString)
def getSubsamplingRate(self): """ Gets the value of subsamplingRate or its default value. """ return self.getOrDefault(self.subsamplingRate)
def getFeatureSubsetStrategy(self): """ Gets the value of featureSubsetStrategy or its default value. """
""" Private class to track supported random forest parameters. """
typeConverter=TypeConverters.toInt)
"when building trees.", typeConverter=TypeConverters.toBoolean)
def getNumTrees(self): """ Gets the value of numTrees or its default value. """
def getBootstrap(self): """ Gets the value of bootstrap or its default value. """
""" Private class to track supported GBT params. """
"Step size (a.k.a. learning rate) in interval (0, 1] for shrinking " + "the contribution of each estimator.", typeConverter=TypeConverters.toFloat)
"Threshold for stopping early when fit with validation is used. " + "If the error rate on the validation input changes by less than the " + "validationTol, then learning will stop early (before `maxIter`). " + "This parameter is ignored when fit without validation is used.", typeConverter=TypeConverters.toFloat)
def getValidationTol(self): """ Gets the value of validationTol or its default value. """
""" Private class to track supported impurity measures. """
"Criterion used for information gain calculation (case-insensitive). " + "Supported options: " + ", ".join(supportedImpurities), typeConverter=TypeConverters.toString)
def getImpurity(self): """ Gets the value of impurity or its default value. """
""" Private class to track supported impurity measures.
.. versionadded:: 1.4.0 """
"Criterion used for information gain calculation (case-insensitive). " + "Supported options: " + ", ".join(supportedImpurities), typeConverter=TypeConverters.toString)
def getImpurity(self): """ Gets the value of impurity or its default value. """ return self.getOrDefault(self.impurity)
""" Private class to track supported impurity measures. """ |