From f116a84ef8bf8a201c1a67154fda6990e4222074 Mon Sep 17 00:00:00 2001 From: Yanbo Liang Date: Mon, 16 May 2016 09:55:35 +0200 Subject: [SPARK-14979][ML][PYSPARK] Add examples for GeneralizedLinearRegression ## What changes were proposed in this pull request? Add Scala/Java/Python examples for ```GeneralizedLinearRegression```. ## How was this patch tested? They are examples and have been tested offline. Author: Yanbo Liang Closes #12754 from yanboliang/spark-14979. --- .../ml/JavaGeneralizedLinearRegressionExample.java | 83 ++++++++++++++++++++++ .../ml/generalized_linear_regression_example.py | 66 +++++++++++++++++ .../ml/GeneralizedLinearRegressionExample.scala | 78 ++++++++++++++++++++ 3 files changed, 227 insertions(+) create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaGeneralizedLinearRegressionExample.java create mode 100644 examples/src/main/python/ml/generalized_linear_regression_example.py create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/GeneralizedLinearRegressionExample.scala (limited to 'examples/src') diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaGeneralizedLinearRegressionExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaGeneralizedLinearRegressionExample.java new file mode 100644 index 0000000000..3f072d1e50 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaGeneralizedLinearRegressionExample.java @@ -0,0 +1,83 @@ +/* + * 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. + */ + +package org.apache.spark.examples.ml; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.ml.regression.GeneralizedLinearRegression; +import org.apache.spark.ml.regression.GeneralizedLinearRegressionModel; +import org.apache.spark.ml.regression.GeneralizedLinearRegressionTrainingSummary; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +// $example off$ +import org.apache.spark.sql.SparkSession; + +/** + * An example demonstrating generalized linear regression. + * Run with + * 
+ * bin/run-example ml.JavaGeneralizedLinearRegressionExample
+ *
+ */ + +public class JavaGeneralizedLinearRegressionExample { + + public static void main(String[] args) { + SparkSession spark = SparkSession + .builder() + .appName("JavaGeneralizedLinearRegressionExample") + .getOrCreate(); + + // $example on$ + // Load training data + Dataset dataset = spark.read().format("libsvm") + .load("data/mllib/sample_linear_regression_data.txt"); + + GeneralizedLinearRegression glr = new GeneralizedLinearRegression() + .setFamily("gaussian") + .setLink("identity") + .setMaxIter(10) + .setRegParam(0.3); + + // Fit the model + GeneralizedLinearRegressionModel model = glr.fit(dataset); + + // Print the coefficients and intercept for generalized linear regression model + System.out.println("Coefficients: " + model.coefficients()); + System.out.println("Intercept: " + model.intercept()); + + // Summarize the model over the training set and print out some metrics + GeneralizedLinearRegressionTrainingSummary summary = model.summary(); + System.out.println("Coefficient Standard Errors: " + + Arrays.toString(summary.coefficientStandardErrors())); + System.out.println("T Values: " + Arrays.toString(summary.tValues())); + System.out.println("P Values: " + Arrays.toString(summary.pValues())); + System.out.println("Dispersion: " + summary.dispersion()); + System.out.println("Null Deviance: " + summary.nullDeviance()); + System.out.println("Residual Degree Of Freedom Null: " + summary.residualDegreeOfFreedomNull()); + System.out.println("Deviance: " + summary.deviance()); + System.out.println("Residual Degree Of Freedom: " + summary.residualDegreeOfFreedom()); + System.out.println("AIC: " + summary.aic()); + System.out.println("Deviance Residuals: "); + summary.residuals().show(); + // $example off$ + + spark.stop(); + } +} diff --git a/examples/src/main/python/ml/generalized_linear_regression_example.py b/examples/src/main/python/ml/generalized_linear_regression_example.py new file mode 100644 index 0000000000..796752a60f --- /dev/null +++ b/examples/src/main/python/ml/generalized_linear_regression_example.py @@ -0,0 +1,66 @@ +# +# 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. +# + +from __future__ import print_function + +from pyspark.sql import SparkSession +# $example on$ +from pyspark.ml.regression import GeneralizedLinearRegression +# $example off$ + +""" +An example demonstrating generalized linear regression. +Run with: + bin/spark-submit examples/src/main/python/ml/generalized_linear_regression_example.py +""" + +if __name__ == "__main__": + spark = SparkSession\ + .builder\ + .appName("GeneralizedLinearRegressionExample")\ + .getOrCreate() + + # $example on$ + # Load training data + dataset = spark.read.format("libsvm")\ + .load("data/mllib/sample_linear_regression_data.txt") + + glr = GeneralizedLinearRegression(family="gaussian", link="identity", maxIter=10, regParam=0.3) + + # Fit the model + model = glr.fit(dataset) + + # Print the coefficients and intercept for generalized linear regression model + print("Coefficients: " + str(model.coefficients)) + print("Intercept: " + str(model.intercept)) + + # Summarize the model over the training set and print out some metrics + summary = model.summary + print("Coefficient Standard Errors: " + str(summary.coefficientStandardErrors)) + print("T Values: " + str(summary.tValues)) + print("P Values: " + str(summary.pValues)) + print("Dispersion: " + str(summary.dispersion)) + print("Null Deviance: " + str(summary.nullDeviance)) + print("Residual Degree Of Freedom Null: " + str(summary.residualDegreeOfFreedomNull)) + print("Deviance: " + str(summary.deviance)) + print("Residual Degree Of Freedom: " + str(summary.residualDegreeOfFreedom)) + print("AIC: " + str(summary.aic)) + print("Deviance Residuals: ") + summary.residuals().show() + # $example off$ + + spark.stop() diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/GeneralizedLinearRegressionExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/GeneralizedLinearRegressionExample.scala new file mode 100644 index 0000000000..1b86d7cad0 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/GeneralizedLinearRegressionExample.scala @@ -0,0 +1,78 @@ +/* + * 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. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.regression.GeneralizedLinearRegression +// $example off$ +import org.apache.spark.sql.SparkSession + +/** + * An example demonstrating generalized linear regression. + * Run with + * {{{ + * bin/run-example ml.GeneralizedLinearRegressionExample + * }}} + */ + +object GeneralizedLinearRegressionExample { + + def main(args: Array[String]): Unit = { + val spark = SparkSession + .builder + .appName("GeneralizedLinearRegressionExample") + .getOrCreate() + + // $example on$ + // Load training data + val dataset = spark.read.format("libsvm") + .load("data/mllib/sample_linear_regression_data.txt") + + val glr = new GeneralizedLinearRegression() + .setFamily("gaussian") + .setLink("identity") + .setMaxIter(10) + .setRegParam(0.3) + + // Fit the model + val model = glr.fit(dataset) + + // Print the coefficients and intercept for generalized linear regression model + println(s"Coefficients: ${model.coefficients}") + println(s"Intercept: ${model.intercept}") + + // Summarize the model over the training set and print out some metrics + val summary = model.summary + println(s"Coefficient Standard Errors: ${summary.coefficientStandardErrors.mkString(",")}") + println(s"T Values: ${summary.tValues.mkString(",")}") + println(s"P Values: ${summary.pValues.mkString(",")}") + println(s"Dispersion: ${summary.dispersion}") + println(s"Null Deviance: ${summary.nullDeviance}") + println(s"Residual Degree Of Freedom Null: ${summary.residualDegreeOfFreedomNull}") + println(s"Deviance: ${summary.deviance}") + println(s"Residual Degree Of Freedom: ${summary.residualDegreeOfFreedom}") + println(s"AIC: ${summary.aic}") + println("Deviance Residuals: ") + summary.residuals().show() + // $example off$ + + spark.stop() + } +} +// scalastyle:on println -- cgit v1.2.3