diff options
author | sethah <seth.hendrickson16@gmail.com> | 2016-10-05 18:28:21 +0000 |
---|---|---|
committer | DB Tsai <dbtsai@dbtsai.com> | 2016-10-05 18:28:21 +0000 |
commit | 9df54f5325c2942bb77008ff1810e2fb5f6d848b (patch) | |
tree | b178ea4d0033a44e37902426104586be1a2ddf56 /examples/src | |
parent | 6a05eb24d043aa93390f353850d56efa6124e063 (diff) | |
download | spark-9df54f5325c2942bb77008ff1810e2fb5f6d848b.tar.gz spark-9df54f5325c2942bb77008ff1810e2fb5f6d848b.tar.bz2 spark-9df54f5325c2942bb77008ff1810e2fb5f6d848b.zip |
[SPARK-17239][ML][DOC] Update user guide for multiclass logistic regression
## What changes were proposed in this pull request?
Updates user guide to reflect that LogisticRegression now supports multiclass. Also adds new examples to show multiclass training.
## How was this patch tested?
Ran locally using spark-submit, run-example, and copy/paste from user guide into shells. Generated docs and verified correct output.
Author: sethah <seth.hendrickson16@gmail.com>
Closes #15349 from sethah/SPARK-17239.
Diffstat (limited to 'examples/src')
6 files changed, 197 insertions, 0 deletions
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaLogisticRegressionWithElasticNetExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaLogisticRegressionWithElasticNetExample.java index 6101c79fb0..b8fb5972ea 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaLogisticRegressionWithElasticNetExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaLogisticRegressionWithElasticNetExample.java @@ -48,6 +48,20 @@ public class JavaLogisticRegressionWithElasticNetExample { // Print the coefficients and intercept for logistic regression System.out.println("Coefficients: " + lrModel.coefficients() + " Intercept: " + lrModel.intercept()); + + // We can also use the multinomial family for binary classification + LogisticRegression mlr = new LogisticRegression() + .setMaxIter(10) + .setRegParam(0.3) + .setElasticNetParam(0.8) + .setFamily("multinomial"); + + // Fit the model + LogisticRegressionModel mlrModel = mlr.fit(training); + + // Print the coefficients and intercepts for logistic regression with multinomial family + System.out.println("Multinomial coefficients: " + + lrModel.coefficientMatrix() + "\nMultinomial intercepts: " + mlrModel.interceptVector()); // $example off$ spark.stop(); diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaMulticlassLogisticRegressionWithElasticNetExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaMulticlassLogisticRegressionWithElasticNetExample.java new file mode 100644 index 0000000000..da410cba2b --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaMulticlassLogisticRegressionWithElasticNetExample.java @@ -0,0 +1,55 @@ +/* + * 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 org.apache.spark.ml.classification.LogisticRegression; +import org.apache.spark.ml.classification.LogisticRegressionModel; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +// $example off$ + +public class JavaMulticlassLogisticRegressionWithElasticNetExample { + public static void main(String[] args) { + SparkSession spark = SparkSession + .builder() + .appName("JavaMulticlassLogisticRegressionWithElasticNetExample") + .getOrCreate(); + + // $example on$ + // Load training data + Dataset<Row> training = spark.read().format("libsvm") + .load("data/mllib/sample_multiclass_classification_data.txt"); + + LogisticRegression lr = new LogisticRegression() + .setMaxIter(10) + .setRegParam(0.3) + .setElasticNetParam(0.8); + + // Fit the model + LogisticRegressionModel lrModel = lr.fit(training); + + // Print the coefficients and intercept for multinomial logistic regression + System.out.println("Coefficients: \n" + + lrModel.coefficientMatrix() + " \nIntercept: " + lrModel.interceptVector()); + // $example off$ + + spark.stop(); + } +} diff --git a/examples/src/main/python/ml/logistic_regression_with_elastic_net.py b/examples/src/main/python/ml/logistic_regression_with_elastic_net.py index 33d0689f75..d095fbd373 100644 --- a/examples/src/main/python/ml/logistic_regression_with_elastic_net.py +++ b/examples/src/main/python/ml/logistic_regression_with_elastic_net.py @@ -40,6 +40,16 @@ if __name__ == "__main__": # Print the coefficients and intercept for logistic regression print("Coefficients: " + str(lrModel.coefficients)) print("Intercept: " + str(lrModel.intercept)) + + # We can also use the multinomial family for binary classification + mlr = LogisticRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8, family="multinomial") + + # Fit the model + mlrModel = mlr.fit(training) + + # Print the coefficients and intercepts for logistic regression with multinomial family + print("Multinomial coefficients: " + str(mlrModel.coefficientMatrix)) + print("Multinomial intercepts: " + str(mlrModel.interceptVector)) # $example off$ spark.stop() diff --git a/examples/src/main/python/ml/multiclass_logistic_regression_with_elastic_net.py b/examples/src/main/python/ml/multiclass_logistic_regression_with_elastic_net.py new file mode 100644 index 0000000000..bb9cd82d6b --- /dev/null +++ b/examples/src/main/python/ml/multiclass_logistic_regression_with_elastic_net.py @@ -0,0 +1,48 @@ +# +# 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 + +# $example on$ +from pyspark.ml.classification import LogisticRegression +# $example off$ +from pyspark.sql import SparkSession + +if __name__ == "__main__": + spark = SparkSession \ + .builder \ + .appName("MulticlassLogisticRegressionWithElasticNet") \ + .getOrCreate() + + # $example on$ + # Load training data + training = spark \ + .read \ + .format("libsvm") \ + .load("data/mllib/sample_multiclass_classification_data.txt") + + lr = LogisticRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8) + + # Fit the model + lrModel = lr.fit(training) + + # Print the coefficients and intercept for multinomial logistic regression + print("Coefficients: \n" + str(lrModel.coefficientMatrix)) + print("Intercept: " + str(lrModel.interceptVector)) + # $example off$ + + spark.stop() diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionWithElasticNetExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionWithElasticNetExample.scala index 616263b8e9..1847104908 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionWithElasticNetExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionWithElasticNetExample.scala @@ -45,6 +45,19 @@ object LogisticRegressionWithElasticNetExample { // Print the coefficients and intercept for logistic regression println(s"Coefficients: ${lrModel.coefficients} Intercept: ${lrModel.intercept}") + + // We can also use the multinomial family for binary classification + val mlr = new LogisticRegression() + .setMaxIter(10) + .setRegParam(0.3) + .setElasticNetParam(0.8) + .setFamily("multinomial") + + val mlrModel = mlr.fit(training) + + // Print the coefficients and intercepts for logistic regression with multinomial family + println(s"Multinomial coefficients: ${mlrModel.coefficientMatrix}") + println(s"Multinomial intercepts: ${mlrModel.interceptVector}") // $example off$ spark.stop() diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/MulticlassLogisticRegressionWithElasticNetExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/MulticlassLogisticRegressionWithElasticNetExample.scala new file mode 100644 index 0000000000..42f0ace7a3 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/MulticlassLogisticRegressionWithElasticNetExample.scala @@ -0,0 +1,57 @@ +/* + * 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.classification.LogisticRegression +// $example off$ +import org.apache.spark.sql.SparkSession + +object MulticlassLogisticRegressionWithElasticNetExample { + + def main(args: Array[String]): Unit = { + val spark = SparkSession + .builder + .appName("MulticlassLogisticRegressionWithElasticNetExample") + .getOrCreate() + + // $example on$ + // Load training data + val training = spark + .read + .format("libsvm") + .load("data/mllib/sample_multiclass_classification_data.txt") + + val lr = new LogisticRegression() + .setMaxIter(10) + .setRegParam(0.3) + .setElasticNetParam(0.8) + + // Fit the model + val lrModel = lr.fit(training) + + // Print the coefficients and intercept for multinomial logistic regression + println(s"Coefficients: \n${lrModel.coefficientMatrix}") + println(s"Intercepts: ${lrModel.interceptVector}") + // $example off$ + + spark.stop() + } +} +// scalastyle:on println |