diff options
author | Yanbo Liang <ybliang8@gmail.com> | 2015-11-09 08:57:29 -0800 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-11-09 08:57:29 -0800 |
commit | d50a66cc04bfa1c483f04daffe465322316c745e (patch) | |
tree | bdb6bb63bd3ef2cea6a2f1da282163c457be4418 /examples/src | |
parent | 8c0e1b50e960d3e8e51d0618c462eed2bb4936f0 (diff) | |
download | spark-d50a66cc04bfa1c483f04daffe465322316c745e.tar.gz spark-d50a66cc04bfa1c483f04daffe465322316c745e.tar.bz2 spark-d50a66cc04bfa1c483f04daffe465322316c745e.zip |
[SPARK-10689][ML][DOC] User guide and example code for AFTSurvivalRegression
Add user guide and example code for ```AFTSurvivalRegression```.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes #9491 from yanboliang/spark-10689.
Diffstat (limited to 'examples/src')
3 files changed, 184 insertions, 0 deletions
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java new file mode 100644 index 0000000000..69a174562f --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java @@ -0,0 +1,71 @@ +/* + * 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 java.util.List; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.ml.regression.AFTSurvivalRegression; +import org.apache.spark.ml.regression.AFTSurvivalRegressionModel; +import org.apache.spark.mllib.linalg.*; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.SQLContext; +import org.apache.spark.sql.types.*; +// $example off$ + +public class JavaAFTSurvivalRegressionExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("JavaAFTSurvivalRegressionExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + SQLContext jsql = new SQLContext(jsc); + + // $example on$ + List<Row> data = Arrays.asList( + RowFactory.create(1.218, 1.0, Vectors.dense(1.560, -0.605)), + RowFactory.create(2.949, 0.0, Vectors.dense(0.346, 2.158)), + RowFactory.create(3.627, 0.0, Vectors.dense(1.380, 0.231)), + RowFactory.create(0.273, 1.0, Vectors.dense(0.520, 1.151)), + RowFactory.create(4.199, 0.0, Vectors.dense(0.795, -0.226)) + ); + StructType schema = new StructType(new StructField[]{ + new StructField("label", DataTypes.DoubleType, false, Metadata.empty()), + new StructField("censor", DataTypes.DoubleType, false, Metadata.empty()), + new StructField("features", new VectorUDT(), false, Metadata.empty()) + }); + DataFrame training = jsql.createDataFrame(data, schema); + double[] quantileProbabilities = new double[]{0.3, 0.6}; + AFTSurvivalRegression aft = new AFTSurvivalRegression() + .setQuantileProbabilities(quantileProbabilities) + .setQuantilesCol("quantiles"); + + AFTSurvivalRegressionModel model = aft.fit(training); + + // Print the coefficients, intercept and scale parameter for AFT survival regression + System.out.println("Coefficients: " + model.coefficients() + " Intercept: " + + model.intercept() + " Scale: " + model.scale()); + model.transform(training).show(false); + // $example off$ + + jsc.stop(); + } +} diff --git a/examples/src/main/python/ml/aft_survival_regression.py b/examples/src/main/python/ml/aft_survival_regression.py new file mode 100644 index 0000000000..0ee01fd825 --- /dev/null +++ b/examples/src/main/python/ml/aft_survival_regression.py @@ -0,0 +1,51 @@ +# +# 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 import SparkContext +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.regression import AFTSurvivalRegression +from pyspark.mllib.linalg import Vectors +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="AFTSurvivalRegressionExample") + sqlContext = SQLContext(sc) + + # $example on$ + training = sqlContext.createDataFrame([ + (1.218, 1.0, Vectors.dense(1.560, -0.605)), + (2.949, 0.0, Vectors.dense(0.346, 2.158)), + (3.627, 0.0, Vectors.dense(1.380, 0.231)), + (0.273, 1.0, Vectors.dense(0.520, 1.151)), + (4.199, 0.0, Vectors.dense(0.795, -0.226))], ["label", "censor", "features"]) + quantileProbabilities = [0.3, 0.6] + aft = AFTSurvivalRegression(quantileProbabilities=quantileProbabilities, + quantilesCol="quantiles") + + model = aft.fit(training) + + # Print the coefficients, intercept and scale parameter for AFT survival regression + print("Coefficients: " + str(model.coefficients)) + print("Intercept: " + str(model.intercept)) + print("Scale: " + str(model.scale)) + model.transform(training).show(truncate=False) + # $example off$ + + sc.stop() diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/AFTSurvivalRegressionExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/AFTSurvivalRegressionExample.scala new file mode 100644 index 0000000000..5da285e836 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/AFTSurvivalRegressionExample.scala @@ -0,0 +1,62 @@ +/* + * 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 + +import org.apache.spark.sql.SQLContext +import org.apache.spark.{SparkContext, SparkConf} +// $example on$ +import org.apache.spark.ml.regression.AFTSurvivalRegression +import org.apache.spark.mllib.linalg.Vectors +// $example off$ + +/** + * An example for AFTSurvivalRegression. + */ +object AFTSurvivalRegressionExample { + + def main(args: Array[String]): Unit = { + val conf = new SparkConf().setAppName("AFTSurvivalRegressionExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + // $example on$ + val training = sqlContext.createDataFrame(Seq( + (1.218, 1.0, Vectors.dense(1.560, -0.605)), + (2.949, 0.0, Vectors.dense(0.346, 2.158)), + (3.627, 0.0, Vectors.dense(1.380, 0.231)), + (0.273, 1.0, Vectors.dense(0.520, 1.151)), + (4.199, 0.0, Vectors.dense(0.795, -0.226)) + )).toDF("label", "censor", "features") + val quantileProbabilities = Array(0.3, 0.6) + val aft = new AFTSurvivalRegression() + .setQuantileProbabilities(quantileProbabilities) + .setQuantilesCol("quantiles") + + val model = aft.fit(training) + + // Print the coefficients, intercept and scale parameter for AFT survival regression + println(s"Coefficients: ${model.coefficients} Intercept: " + + s"${model.intercept} Scale: ${model.scale}") + model.transform(training).show(false) + // $example off$ + + sc.stop() + } +} +// scalastyle:off println |