|
||||
0001 # 0002 # Licensed to the Apache Software Foundation (ASF) under one or more 0003 # contributor license agreements. See the NOTICE file distributed with 0004 # this work for additional information regarding copyright ownership. 0005 # The ASF licenses this file to You under the Apache License, Version 2.0 0006 # (the "License"); you may not use this file except in compliance with 0007 # the License. You may obtain a copy of the License at 0008 # 0009 # http://www.apache.org/licenses/LICENSE-2.0 0010 # 0011 # Unless required by applicable law or agreed to in writing, software 0012 # distributed under the License is distributed on an "AS IS" BASIS, 0013 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 0014 # See the License for the specific language governing permissions and 0015 # limitations under the License. 0016 # 0017 0018 """ 0019 Isotonic Regression Example. 0020 """ 0021 from __future__ import print_function 0022 0023 from pyspark import SparkContext 0024 # $example on$ 0025 import math 0026 from pyspark.mllib.regression import IsotonicRegression, IsotonicRegressionModel 0027 from pyspark.mllib.util import MLUtils 0028 # $example off$ 0029 0030 if __name__ == "__main__": 0031 0032 sc = SparkContext(appName="PythonIsotonicRegressionExample") 0033 0034 # $example on$ 0035 # Load and parse the data 0036 def parsePoint(labeledData): 0037 return (labeledData.label, labeledData.features[0], 1.0) 0038 0039 data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_isotonic_regression_libsvm_data.txt") 0040 0041 # Create label, feature, weight tuples from input data with weight set to default value 1.0. 0042 parsedData = data.map(parsePoint) 0043 0044 # Split data into training (60%) and test (40%) sets. 0045 training, test = parsedData.randomSplit([0.6, 0.4], 11) 0046 0047 # Create isotonic regression model from training data. 0048 # Isotonic parameter defaults to true so it is only shown for demonstration 0049 model = IsotonicRegression.train(training) 0050 0051 # Create tuples of predicted and real labels. 0052 predictionAndLabel = test.map(lambda p: (model.predict(p[1]), p[0])) 0053 0054 # Calculate mean squared error between predicted and real labels. 0055 meanSquaredError = predictionAndLabel.map(lambda pl: math.pow((pl[0] - pl[1]), 2)).mean() 0056 print("Mean Squared Error = " + str(meanSquaredError)) 0057 0058 # Save and load model 0059 model.save(sc, "target/tmp/myIsotonicRegressionModel") 0060 sameModel = IsotonicRegressionModel.load(sc, "target/tmp/myIsotonicRegressionModel") 0061 # $example off$
[ Source navigation ] | [ Diff markup ] | [ Identifier search ] | [ general search ] |
This page was automatically generated by the 2.1.0 LXR engine. The LXR team |