我的spark python 決策樹執行個體

標籤：執行個體   lambda   contex   span   rom   example   res   logs   bug   

from numpy import arrayfrom pyspark.mllib.regression import LabeledPointfrom pyspark.mllib.tree import DecisionTree, DecisionTreeModelfrom pyspark import SparkContextsc = SparkContext(appName="PythonDecisionTreeClassificationExample")data = [     LabeledPoint(0.0, [0.0]),     LabeledPoint(1.0, [1.0]),     LabeledPoint(0.0, [-2.0]),     LabeledPoint(0.0, [-1.0]),     LabeledPoint(0.0, [-3.0]),     LabeledPoint(1.0, [4.0]),     LabeledPoint(1.0, [4.5]),     LabeledPoint(1.0, [4.9]),     LabeledPoint(1.0, [3.0]) ]all_data = sc.parallelize(data) (trainingData, testData) = all_data.randomSplit([0.8, 0.2])# model = DecisionTree.trainClassifier(sc.parallelize(data), 2, {})model = DecisionTree.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},                                         impurity=‘gini‘, maxDepth=5, maxBins=32)print(model)print(model.toDebugString())model.predict(array([1.0]))model.predict(array([0.0]))rdd = sc.parallelize([[1.0], [0.0]])model.predict(rdd).collect()predictions = model.predict(testData.map(lambda x: x.features))labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count())print(‘Test Error = ‘ + str(testErr))print(‘Learned classification tree model:‘)print(model.toDebugString())# Save and load modelmodel.save(sc, "./myDecisionTreeClassificationModel")sameModel = DecisionTreeModel.load(sc, "./myDecisionTreeClassificationModel")

 

我的spark python 決策樹執行個體