[SPARK-13019][DOCS] Replace example code in mllib-statistics.md using include_example

https://issues.apache.org/jira/browse/SPARK-13019

The example code in the user guide is embedded in the markdown and hence it is not easy to test. It would be nice to automatically test them. This JIRA is to discuss options to automate example code testing and see what we can do in Spark 1.6.

Goal is to move actual example code to spark/examples and test compilation in Jenkins builds. Then in the markdown, we can reference part of the code to show in the user guide. This requires adding a Jekyll tag that is similar to https://github.com/jekyll/jekyll/blob/master/lib/jekyll/tags/include.rb, e.g., called include_example.
`{% include_example scala/org/apache/spark/examples/mllib/SummaryStatisticsExample.scala %}`
Jekyll will find `examples/src/main/scala/org/apache/spark/examples/mllib/SummaryStatisticsExample.scala` and pick code blocks marked "example" and replace code block in
`{% highlight %}`
 in the markdown.

See more sub-tasks in parent ticket: https://issues.apache.org/jira/browse/SPARK-11337

Author: Xin Ren <iamshrek@126.com>

Closes #11108 from keypointt/SPARK-13019.

6 files changed, 387 insertions, 0 deletions

diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaCorrelationsExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaCorrelationsExample.java
new file mode 100644
index 0000000000..fd19b43504
--- /dev/null
+++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaCorrelationsExample.java
@@ -0,0 +1,70 @@
+/*
+ * 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 org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+// $example on$
+import java.util.Arrays;
+
+import org.apache.spark.api.java.JavaDoubleRDD;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.mllib.linalg.Matrix;
+import org.apache.spark.mllib.linalg.Vector;
+import org.apache.spark.mllib.linalg.Vectors;
+import org.apache.spark.mllib.stat.Statistics;
+// $example off$
+
+public class JavaCorrelationsExample {
+  public static void main(String[] args) {
+
+    SparkConf conf = new SparkConf().setAppName("JavaCorrelationsExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+
+    // $example on$
+    JavaDoubleRDD seriesX = jsc.parallelizeDoubles(
+      Arrays.asList(1.0, 2.0, 3.0, 3.0, 5.0));  // a series
+
+    // must have the same number of partitions and cardinality as seriesX
+    JavaDoubleRDD seriesY = jsc.parallelizeDoubles(
+      Arrays.asList(11.0, 22.0, 33.0, 33.0, 555.0));
+
+    // compute the correlation using Pearson's method. Enter "spearman" for Spearman's method.
+    // If a method is not specified, Pearson's method will be used by default.
+    Double correlation = Statistics.corr(seriesX.srdd(), seriesY.srdd(), "pearson");
+    System.out.println("Correlation is: " + correlation);
+
+    // note that each Vector is a row and not a column
+    JavaRDD<Vector> data = jsc.parallelize(
+      Arrays.asList(
+        Vectors.dense(1.0, 10.0, 100.0),
+        Vectors.dense(2.0, 20.0, 200.0),
+        Vectors.dense(5.0, 33.0, 366.0)
+      )
+    );
+
+    // calculate the correlation matrix using Pearson's method. Use "spearman" for Spearman's method.
+    // If a method is not specified, Pearson's method will be used by default.
+    Matrix correlMatrix = Statistics.corr(data.rdd(), "pearson");
+    System.out.println(correlMatrix.toString());
+    // $example off$
+
+    jsc.stop();
+  }
+}
+
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingExample.java
new file mode 100644
index 0000000000..b48b95ff1d
--- /dev/null
+++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingExample.java
@@ -0,0 +1,84 @@
+/*
+ * 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 org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+
+// $example on$
+import java.util.Arrays;
+
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.mllib.linalg.Matrices;
+import org.apache.spark.mllib.linalg.Matrix;
+import org.apache.spark.mllib.linalg.Vector;
+import org.apache.spark.mllib.linalg.Vectors;
+import org.apache.spark.mllib.regression.LabeledPoint;
+import org.apache.spark.mllib.stat.Statistics;
+import org.apache.spark.mllib.stat.test.ChiSqTestResult;
+// $example off$
+
+public class JavaHypothesisTestingExample {
+  public static void main(String[] args) {
+
+    SparkConf conf = new SparkConf().setAppName("JavaHypothesisTestingExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+
+    // $example on$
+    // a vector composed of the frequencies of events
+    Vector vec = Vectors.dense(0.1, 0.15, 0.2, 0.3, 0.25);
+
+    // compute the goodness of fit. If a second vector to test against is not supplied
+    // as a parameter, the test runs against a uniform distribution.
+    ChiSqTestResult goodnessOfFitTestResult = Statistics.chiSqTest(vec);
+    // summary of the test including the p-value, degrees of freedom, test statistic,
+    // the method used, and the null hypothesis.
+    System.out.println(goodnessOfFitTestResult + "\n");
+
+    // Create a contingency matrix ((1.0, 2.0), (3.0, 4.0), (5.0, 6.0))
+    Matrix mat = Matrices.dense(3, 2, new double[]{1.0, 3.0, 5.0, 2.0, 4.0, 6.0});
+
+    // conduct Pearson's independence test on the input contingency matrix
+    ChiSqTestResult independenceTestResult = Statistics.chiSqTest(mat);
+    // summary of the test including the p-value, degrees of freedom...
+    System.out.println(independenceTestResult + "\n");
+
+    // an RDD of labeled points
+    JavaRDD<LabeledPoint> obs = jsc.parallelize(
+      Arrays.asList(
+        new LabeledPoint(1.0, Vectors.dense(1.0, 0.0, 3.0)),
+        new LabeledPoint(1.0, Vectors.dense(1.0, 2.0, 0.0)),
+        new LabeledPoint(-1.0, Vectors.dense(-1.0, 0.0, -0.5))
+      )
+    );
+
+    // The contingency table is constructed from the raw (feature, label) pairs and used to conduct
+    // the independence test. Returns an array containing the ChiSquaredTestResult for every feature
+    // against the label.
+    ChiSqTestResult[] featureTestResults = Statistics.chiSqTest(obs.rdd());
+    int i = 1;
+    for (ChiSqTestResult result : featureTestResults) {
+      System.out.println("Column " + i + ":");
+      System.out.println(result + "\n");  // summary of the test
+      i++;
+    }
+    // $example off$
+
+    jsc.stop();
+  }
+}
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingKolmogorovSmirnovTestExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingKolmogorovSmirnovTestExample.java
new file mode 100644
index 0000000000..fe611c9ae6
--- /dev/null
+++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingKolmogorovSmirnovTestExample.java
@@ -0,0 +1,49 @@
+/*
+ * 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 org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+// $example on$
+import java.util.Arrays;
+
+import org.apache.spark.api.java.JavaDoubleRDD;
+import org.apache.spark.mllib.stat.Statistics;
+import org.apache.spark.mllib.stat.test.KolmogorovSmirnovTestResult;
+// $example off$
+
+public class JavaHypothesisTestingKolmogorovSmirnovTestExample {
+  public static void main(String[] args) {
+
+    SparkConf conf =
+      new SparkConf().setAppName("JavaHypothesisTestingKolmogorovSmirnovTestExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+
+    // $example on$
+    JavaDoubleRDD data = jsc.parallelizeDoubles(Arrays.asList(0.1, 0.15, 0.2, 0.3, 0.25));
+    KolmogorovSmirnovTestResult testResult =
+      Statistics.kolmogorovSmirnovTest(data, "norm", 0.0, 1.0);
+    // summary of the test including the p-value, test statistic, and null hypothesis
+    // if our p-value indicates significance, we can reject the null hypothesis
+    System.out.println(testResult);
+    // $example off$
+
+    jsc.stop();
+  }
+}
+
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaKernelDensityEstimationExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaKernelDensityEstimationExample.java
new file mode 100644
index 0000000000..41de0d90ec
--- /dev/null
+++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaKernelDensityEstimationExample.java
@@ -0,0 +1,53 @@
+/*
+ * 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 org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+// $example on$
+import java.util.Arrays;
+
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.mllib.stat.KernelDensity;
+// $example off$
+
+public class JavaKernelDensityEstimationExample {
+  public static void main(String[] args) {
+
+    SparkConf conf = new SparkConf().setAppName("JavaKernelDensityEstimationExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+
+    // $example on$
+    // an RDD of sample data
+    JavaRDD<Double> data = jsc.parallelize(
+      Arrays.asList(1.0, 1.0, 1.0, 2.0, 3.0, 4.0, 5.0, 5.0, 6.0, 7.0, 8.0, 9.0, 9.0));
+
+    // Construct the density estimator with the sample data
+    // and a standard deviation for the Gaussian kernels
+    KernelDensity kd = new KernelDensity().setSample(data).setBandwidth(3.0);
+
+    // Find density estimates for the given values
+    double[] densities = kd.estimate(new double[]{-1.0, 2.0, 5.0});
+
+    System.out.println(Arrays.toString(densities));
+    // $example off$
+
+    jsc.stop();
+  }
+}
+
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaStratifiedSamplingExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaStratifiedSamplingExample.java
new file mode 100644
index 0000000000..f5a451019b
--- /dev/null
+++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaStratifiedSamplingExample.java
@@ -0,0 +1,75 @@
+/*
+ * 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 com.google.common.collect.ImmutableMap;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+
+// $example on$
+import java.util.*;
+
+import scala.Tuple2;
+
+import org.apache.spark.api.java.JavaPairRDD;
+import org.apache.spark.api.java.function.VoidFunction;
+// $example off$
+
+public class JavaStratifiedSamplingExample {
+  public static void main(String[] args) {
+
+    SparkConf conf = new SparkConf().setAppName("JavaStratifiedSamplingExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+
+    // $example on$
+    List<Tuple2<Integer, Character>> list = new ArrayList<Tuple2<Integer, Character>>(
+      Arrays.<Tuple2<Integer, Character>>asList(
+        new Tuple2(1, 'a'),
+        new Tuple2(1, 'b'),
+        new Tuple2(2, 'c'),
+        new Tuple2(2, 'd'),
+        new Tuple2(2, 'e'),
+        new Tuple2(3, 'f')
+      )
+    );
+
+    JavaPairRDD<Integer, Character> data = jsc.parallelizePairs(list);
+
+    // specify the exact fraction desired from each key Map<K, Object>
+    ImmutableMap<Integer, Object> fractions =
+      ImmutableMap.of(1, (Object)0.1, 2, (Object) 0.6, 3, (Object) 0.3);
+
+    // Get an approximate sample from each stratum
+    JavaPairRDD<Integer, Character> approxSample = data.sampleByKey(false, fractions);
+    // Get an exact sample from each stratum
+    JavaPairRDD<Integer, Character> exactSample = data.sampleByKeyExact(false, fractions);
+    // $example off$
+
+    System.out.println("approxSample size is " + approxSample.collect().size());
+    for (Tuple2<Integer, Character> t : approxSample.collect()) {
+      System.out.println(t._1() + " " + t._2());
+    }
+
+    System.out.println("exactSample size is " + exactSample.collect().size());
+    for (Tuple2<Integer, Character> t : exactSample.collect()) {
+      System.out.println(t._1() + " " + t._2());
+    }
+
+    jsc.stop();
+  }
+}
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaSummaryStatisticsExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaSummaryStatisticsExample.java
new file mode 100644
index 0000000000..278706bc8f
--- /dev/null
+++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaSummaryStatisticsExample.java
@@ -0,0 +1,56 @@
+/*
+ * 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 org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+// $example on$
+import java.util.Arrays;
+
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.mllib.linalg.Vector;
+import org.apache.spark.mllib.linalg.Vectors;
+import org.apache.spark.mllib.stat.MultivariateStatisticalSummary;
+import org.apache.spark.mllib.stat.Statistics;
+// $example off$
+
+public class JavaSummaryStatisticsExample {
+  public static void main(String[] args) {
+
+    SparkConf conf = new SparkConf().setAppName("JavaSummaryStatisticsExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+
+    // $example on$
+    JavaRDD<Vector> mat = jsc.parallelize(
+      Arrays.asList(
+        Vectors.dense(1.0, 10.0, 100.0),
+        Vectors.dense(2.0, 20.0, 200.0),
+        Vectors.dense(3.0, 30.0, 300.0)
+      )
+    ); // an RDD of Vectors
+
+    // Compute column summary statistics.
+    MultivariateStatisticalSummary summary = Statistics.colStats(mat.rdd());
+    System.out.println(summary.mean());  // a dense vector containing the mean value for each column
+    System.out.println(summary.variance());  // column-wise variance
+    System.out.println(summary.numNonzeros());  // number of nonzeros in each column
+    // $example off$
+
+    jsc.stop();
+  }
+}