python/ml/linear_regression_with_elastic_net.py

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 from __future__ import print_function
0019
0020 # $example on$
0021 from pyspark.ml.regression import LinearRegression
0022 # $example off$
0023 from pyspark.sql import SparkSession
0024
0025 if __name__ == "__main__":
0026     spark = SparkSession\
0027         .builder\
0028         .appName("LinearRegressionWithElasticNet")\
0029         .getOrCreate()
0030
0031     # $example on$
0032     # Load training data
0033     training = spark.read.format("libsvm")\
0034         .load("data/mllib/sample_linear_regression_data.txt")
0035
0036     lr = LinearRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8)
0037
0038     # Fit the model
0039     lrModel = lr.fit(training)
0040
0041     # Print the coefficients and intercept for linear regression
0042     print("Coefficients: %s" % str(lrModel.coefficients))
0043     print("Intercept: %s" % str(lrModel.intercept))
0044
0045     # Summarize the model over the training set and print out some metrics
0046     trainingSummary = lrModel.summary
0047     print("numIterations: %d" % trainingSummary.totalIterations)
0048     print("objectiveHistory: %s" % str(trainingSummary.objectiveHistory))
0049     trainingSummary.residuals.show()
0050     print("RMSE: %f" % trainingSummary.rootMeanSquaredError)
0051     print("r2: %f" % trainingSummary.r2)
0052     # $example off$
0053
0054     spark.stop()