[SPARK-11975][ML] Remove duplicate mllib example (DT/RF/GBT in Java/Python)

Remove duplicate mllib example (DT/RF/GBT in Java/Python).
Since we have tutorial code for DT/RF/GBT classification/regression in Scala/Java/Python and example applications for DT/RF/GBT in Scala, so we mark these as duplicated and remove them.
mengxr

Author: Yanbo Liang <ybliang8@gmail.com>

Closes #9954 from yanboliang/SPARK-11975.

3 files changed, 0 insertions, 381 deletions

diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTree.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTree.java
deleted file mode 100644
index 1f82e3f4cb..0000000000
--- a/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTree.java
+++ /dev/null
@@ -1,116 +0,0 @@
-/*
- * 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.mllib;
-
-import java.util.HashMap;
-
-import scala.Tuple2;
-
-import org.apache.spark.api.java.function.Function2;
-import org.apache.spark.api.java.JavaPairRDD;
-import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.api.java.function.Function;
-import org.apache.spark.api.java.function.PairFunction;
-import org.apache.spark.mllib.regression.LabeledPoint;
-import org.apache.spark.mllib.tree.DecisionTree;
-import org.apache.spark.mllib.tree.model.DecisionTreeModel;
-import org.apache.spark.mllib.util.MLUtils;
-import org.apache.spark.SparkConf;
-
-/**
- * Classification and regression using decision trees.
- */
-public final class JavaDecisionTree {
-
-  public static void main(String[] args) {
-    String datapath = "data/mllib/sample_libsvm_data.txt";
-    if (args.length == 1) {
-      datapath = args[0];
-    } else if (args.length > 1) {
-      System.err.println("Usage: JavaDecisionTree <libsvm format data file>");
-      System.exit(1);
-    }
-    SparkConf sparkConf = new SparkConf().setAppName("JavaDecisionTree");
-    JavaSparkContext sc = new JavaSparkContext(sparkConf);
-
-    JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD().cache();
-
-    // Compute the number of classes from the data.
-    Integer numClasses = data.map(new Function<LabeledPoint, Double>() {
-      @Override public Double call(LabeledPoint p) {
-        return p.label();
-      }
-    }).countByValue().size();
-
-    // Set parameters.
-    //  Empty categoricalFeaturesInfo indicates all features are continuous.
-    HashMap<Integer, Integer> categoricalFeaturesInfo = new HashMap<Integer, Integer>();
-    String impurity = "gini";
-    Integer maxDepth = 5;
-    Integer maxBins = 32;
-
-    // Train a DecisionTree model for classification.
-    final DecisionTreeModel model = DecisionTree.trainClassifier(data, numClasses,
-      categoricalFeaturesInfo, impurity, maxDepth, maxBins);
-
-    // Evaluate model on training instances and compute training error
-    JavaPairRDD<Double, Double> predictionAndLabel =
-      data.mapToPair(new PairFunction<LabeledPoint, Double, Double>() {
-        @Override public Tuple2<Double, Double> call(LabeledPoint p) {
-          return new Tuple2<Double, Double>(model.predict(p.features()), p.label());
-        }
-      });
-    Double trainErr =
-      1.0 * predictionAndLabel.filter(new Function<Tuple2<Double, Double>, Boolean>() {
-        @Override public Boolean call(Tuple2<Double, Double> pl) {
-          return !pl._1().equals(pl._2());
-        }
-      }).count() / data.count();
-    System.out.println("Training error: " + trainErr);
-    System.out.println("Learned classification tree model:\n" + model);
-
-    // Train a DecisionTree model for regression.
-    impurity = "variance";
-    final DecisionTreeModel regressionModel = DecisionTree.trainRegressor(data,
-        categoricalFeaturesInfo, impurity, maxDepth, maxBins);
-
-    // Evaluate model on training instances and compute training error
-    JavaPairRDD<Double, Double> regressorPredictionAndLabel =
-      data.mapToPair(new PairFunction<LabeledPoint, Double, Double>() {
-        @Override public Tuple2<Double, Double> call(LabeledPoint p) {
-          return new Tuple2<Double, Double>(regressionModel.predict(p.features()), p.label());
-        }
-      });
-    Double trainMSE =
-      regressorPredictionAndLabel.map(new Function<Tuple2<Double, Double>, Double>() {
-        @Override public Double call(Tuple2<Double, Double> pl) {
-          Double diff = pl._1() - pl._2();
-          return diff * diff;
-        }
-      }).reduce(new Function2<Double, Double, Double>() {
-        @Override public Double call(Double a, Double b) {
-          return a + b;
-        }
-      }) / data.count();
-    System.out.println("Training Mean Squared Error: " + trainMSE);
-    System.out.println("Learned regression tree model:\n" + regressionModel);
-
-    sc.stop();
-  }
-}
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostedTreesRunner.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostedTreesRunner.java
deleted file mode 100644
index a1844d5d07..0000000000
--- a/examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostedTreesRunner.java
+++ /dev/null
@@ -1,126 +0,0 @@
-/*
- * 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.mllib;
-
-import scala.Tuple2;
-
-import org.apache.spark.SparkConf;
-import org.apache.spark.api.java.JavaPairRDD;
-import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.api.java.function.Function;
-import org.apache.spark.api.java.function.Function2;
-import org.apache.spark.api.java.function.PairFunction;
-import org.apache.spark.mllib.regression.LabeledPoint;
-import org.apache.spark.mllib.tree.GradientBoostedTrees;
-import org.apache.spark.mllib.tree.configuration.BoostingStrategy;
-import org.apache.spark.mllib.tree.model.GradientBoostedTreesModel;
-import org.apache.spark.mllib.util.MLUtils;
-
-/**
- * Classification and regression using gradient-boosted decision trees.
- */
-public final class JavaGradientBoostedTreesRunner {
-
-  private static void usage() {
-    System.err.println("Usage: JavaGradientBoostedTreesRunner <libsvm format data file>" +
-        " <Classification/Regression>");
-    System.exit(-1);
-  }
-
-  public static void main(String[] args) {
-    String datapath = "data/mllib/sample_libsvm_data.txt";
-    String algo = "Classification";
-    if (args.length >= 1) {
-      datapath = args[0];
-    }
-    if (args.length >= 2) {
-      algo = args[1];
-    }
-    if (args.length > 2) {
-      usage();
-    }
-    SparkConf sparkConf = new SparkConf().setAppName("JavaGradientBoostedTreesRunner");
-    JavaSparkContext sc = new JavaSparkContext(sparkConf);
-
-    JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD().cache();
-
-    // Set parameters.
-    //  Note: All features are treated as continuous.
-    BoostingStrategy boostingStrategy = BoostingStrategy.defaultParams(algo);
-    boostingStrategy.setNumIterations(10);
-    boostingStrategy.treeStrategy().setMaxDepth(5);
-
-    if (algo.equals("Classification")) {
-      // Compute the number of classes from the data.
-      Integer numClasses = data.map(new Function<LabeledPoint, Double>() {
-        @Override public Double call(LabeledPoint p) {
-          return p.label();
-        }
-      }).countByValue().size();
-      boostingStrategy.treeStrategy().setNumClasses(numClasses);
-
-      // Train a GradientBoosting model for classification.
-      final GradientBoostedTreesModel model = GradientBoostedTrees.train(data, boostingStrategy);
-
-      // Evaluate model on training instances and compute training error
-      JavaPairRDD<Double, Double> predictionAndLabel =
-          data.mapToPair(new PairFunction<LabeledPoint, Double, Double>() {
-            @Override public Tuple2<Double, Double> call(LabeledPoint p) {
-              return new Tuple2<Double, Double>(model.predict(p.features()), p.label());
-            }
-          });
-      Double trainErr =
-          1.0 * predictionAndLabel.filter(new Function<Tuple2<Double, Double>, Boolean>() {
-            @Override public Boolean call(Tuple2<Double, Double> pl) {
-              return !pl._1().equals(pl._2());
-            }
-          }).count() / data.count();
-      System.out.println("Training error: " + trainErr);
-      System.out.println("Learned classification tree model:\n" + model);
-    } else if (algo.equals("Regression")) {
-      // Train a GradientBoosting model for classification.
-      final GradientBoostedTreesModel model = GradientBoostedTrees.train(data, boostingStrategy);
-
-      // Evaluate model on training instances and compute training error
-      JavaPairRDD<Double, Double> predictionAndLabel =
-          data.mapToPair(new PairFunction<LabeledPoint, Double, Double>() {
-            @Override public Tuple2<Double, Double> call(LabeledPoint p) {
-              return new Tuple2<Double, Double>(model.predict(p.features()), p.label());
-            }
-          });
-      Double trainMSE =
-          predictionAndLabel.map(new Function<Tuple2<Double, Double>, Double>() {
-            @Override public Double call(Tuple2<Double, Double> pl) {
-              Double diff = pl._1() - pl._2();
-              return diff * diff;
-            }
-          }).reduce(new Function2<Double, Double, Double>() {
-            @Override public Double call(Double a, Double b) {
-              return a + b;
-            }
-          }) / data.count();
-      System.out.println("Training Mean Squared Error: " + trainMSE);
-      System.out.println("Learned regression tree model:\n" + model);
-    } else {
-      usage();
-    }
-
-    sc.stop();
-  }
-}
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestExample.java
deleted file mode 100644
index 89a4e092a5..0000000000
--- a/examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestExample.java
+++ /dev/null
@@ -1,139 +0,0 @@
-/*
- * 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.mllib;
-
-import scala.Tuple2;
-
-import java.util.HashMap;
-
-import org.apache.spark.SparkConf;
-import org.apache.spark.api.java.JavaPairRDD;
-import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.api.java.function.Function;
-import org.apache.spark.api.java.function.Function2;
-import org.apache.spark.api.java.function.PairFunction;
-import org.apache.spark.mllib.regression.LabeledPoint;
-import org.apache.spark.mllib.tree.RandomForest;
-import org.apache.spark.mllib.tree.model.RandomForestModel;
-import org.apache.spark.mllib.util.MLUtils;
-
-public final class JavaRandomForestExample {
-
-  /**
-   * Note: This example illustrates binary classification.
-   * For information on multiclass classification, please refer to the JavaDecisionTree.java
-   * example.
-   */
-  private static void testClassification(JavaRDD<LabeledPoint> trainingData,
-                                         JavaRDD<LabeledPoint> testData) {
-    // Train a RandomForest model.
-    //  Empty categoricalFeaturesInfo indicates all features are continuous.
-    Integer numClasses = 2;
-    HashMap<Integer, Integer> categoricalFeaturesInfo = new HashMap<Integer, Integer>();
-    Integer numTrees = 3; // Use more in practice.
-    String featureSubsetStrategy = "auto"; // Let the algorithm choose.
-    String impurity = "gini";
-    Integer maxDepth = 4;
-    Integer maxBins = 32;
-    Integer seed = 12345;
-
-    final RandomForestModel model = RandomForest.trainClassifier(trainingData, numClasses,
-        categoricalFeaturesInfo, numTrees, featureSubsetStrategy, impurity, maxDepth, maxBins,
-        seed);
-
-    // Evaluate model on test instances and compute test error
-    JavaPairRDD<Double, Double> predictionAndLabel =
-        testData.mapToPair(new PairFunction<LabeledPoint, Double, Double>() {
-          @Override
-          public Tuple2<Double, Double> call(LabeledPoint p) {
-            return new Tuple2<Double, Double>(model.predict(p.features()), p.label());
-          }
-        });
-    Double testErr =
-        1.0 * predictionAndLabel.filter(new Function<Tuple2<Double, Double>, Boolean>() {
-          @Override
-          public Boolean call(Tuple2<Double, Double> pl) {
-            return !pl._1().equals(pl._2());
-          }
-        }).count() / testData.count();
-    System.out.println("Test Error: " + testErr);
-    System.out.println("Learned classification forest model:\n" + model.toDebugString());
-  }
-
-  private static void testRegression(JavaRDD<LabeledPoint> trainingData,
-                                     JavaRDD<LabeledPoint> testData) {
-    // Train a RandomForest model.
-    //  Empty categoricalFeaturesInfo indicates all features are continuous.
-    HashMap<Integer, Integer> categoricalFeaturesInfo = new HashMap<Integer, Integer>();
-    Integer numTrees = 3; // Use more in practice.
-    String featureSubsetStrategy = "auto"; // Let the algorithm choose.
-    String impurity = "variance";
-    Integer maxDepth = 4;
-    Integer maxBins = 32;
-    Integer seed = 12345;
-
-    final RandomForestModel model = RandomForest.trainRegressor(trainingData,
-        categoricalFeaturesInfo, numTrees, featureSubsetStrategy, impurity, maxDepth, maxBins,
-        seed);
-
-    // Evaluate model on test instances and compute test error
-    JavaPairRDD<Double, Double> predictionAndLabel =
-        testData.mapToPair(new PairFunction<LabeledPoint, Double, Double>() {
-          @Override
-          public Tuple2<Double, Double> call(LabeledPoint p) {
-            return new Tuple2<Double, Double>(model.predict(p.features()), p.label());
-          }
-        });
-    Double testMSE =
-        predictionAndLabel.map(new Function<Tuple2<Double, Double>, Double>() {
-          @Override
-          public Double call(Tuple2<Double, Double> pl) {
-            Double diff = pl._1() - pl._2();
-            return diff * diff;
-          }
-        }).reduce(new Function2<Double, Double, Double>() {
-          @Override
-          public Double call(Double a, Double b) {
-            return a + b;
-          }
-        }) / testData.count();
-    System.out.println("Test Mean Squared Error: " + testMSE);
-    System.out.println("Learned regression forest model:\n" + model.toDebugString());
-  }
-
-  public static void main(String[] args) {
-    SparkConf sparkConf = new SparkConf().setAppName("JavaRandomForestExample");
-    JavaSparkContext sc = new JavaSparkContext(sparkConf);
-
-    // Load and parse the data file.
-    String datapath = "data/mllib/sample_libsvm_data.txt";
-    JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD();
-    // Split the data into training and test sets (30% held out for testing)
-    JavaRDD<LabeledPoint>[] splits = data.randomSplit(new double[]{0.7, 0.3});
-    JavaRDD<LabeledPoint> trainingData = splits[0];
-    JavaRDD<LabeledPoint> testData = splits[1];
-
-    System.out.println("\nRunning example of classification using RandomForest\n");
-    testClassification(trainingData, testData);
-
-    System.out.println("\nRunning example of regression using RandomForest\n");
-    testRegression(trainingData, testData);
-    sc.stop();
-  }
-}