python/ml/logistic_regression_summary_example.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 """
0019 An example demonstrating Logistic Regression Summary.
0020 Run with:
0021   bin/spark-submit examples/src/main/python/ml/logistic_regression_summary_example.py
0022 """
0023 from __future__ import print_function
0024
0025 # $example on$
0026 from pyspark.ml.classification import LogisticRegression
0027 # $example off$
0028 from pyspark.sql import SparkSession
0029
0030 if __name__ == "__main__":
0031     spark = SparkSession \
0032         .builder \
0033         .appName("LogisticRegressionSummary") \
0034         .getOrCreate()
0035
0036     # Load training data
0037     training = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
0038
0039     lr = LogisticRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8)
0040
0041     # Fit the model
0042     lrModel = lr.fit(training)
0043
0044     # $example on$
0045     # Extract the summary from the returned LogisticRegressionModel instance trained
0046     # in the earlier example
0047     trainingSummary = lrModel.summary
0048
0049     # Obtain the objective per iteration
0050     objectiveHistory = trainingSummary.objectiveHistory
0051     print("objectiveHistory:")
0052     for objective in objectiveHistory:
0053         print(objective)
0054
0055     # Obtain the receiver-operating characteristic as a dataframe and areaUnderROC.
0056     trainingSummary.roc.show()
0057     print("areaUnderROC: " + str(trainingSummary.areaUnderROC))
0058
0059     # Set the model threshold to maximize F-Measure
0060     fMeasure = trainingSummary.fMeasureByThreshold
0061     maxFMeasure = fMeasure.groupBy().max('F-Measure').select('max(F-Measure)').head()
0062     bestThreshold = fMeasure.where(fMeasure['F-Measure'] == maxFMeasure['max(F-Measure)']) \
0063         .select('threshold').head()['threshold']
0064     lr.setThreshold(bestThreshold)
0065     # $example off$
0066
0067     spark.stop()