[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, 277 insertions, 0 deletions

diff --git a/examples/src/main/python/mllib/correlations_example.py b/examples/src/main/python/mllib/correlations_example.py
new file mode 100644
index 0000000000..66d18f6e5d
--- /dev/null
+++ b/examples/src/main/python/mllib/correlations_example.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
+
+import numpy as np
+
+from pyspark import SparkContext
+# $example on$
+from pyspark.mllib.stat import Statistics
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="CorrelationsExample")  # SparkContext
+
+    # $example on$
+    seriesX = sc.parallelize([1.0, 2.0, 3.0, 3.0, 5.0])  # a series
+    # seriesY must have the same number of partitions and cardinality as seriesX
+    seriesY = sc.parallelize([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.
+    print("Correlation is: " + str(Statistics.corr(seriesX, seriesY, method="pearson")))
+
+    data = sc.parallelize(
+        [np.array([1.0, 10.0, 100.0]), np.array([2.0, 20.0, 200.0]), np.array([5.0, 33.0, 366.0])]
+    )  # an RDD of Vectors
+
+    # 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.
+    print(Statistics.corr(data, method="pearson"))
+    # $example off$
+
+    sc.stop()
diff --git a/examples/src/main/python/mllib/hypothesis_testing_example.py b/examples/src/main/python/mllib/hypothesis_testing_example.py
new file mode 100644
index 0000000000..e566ead0d3
--- /dev/null
+++ b/examples/src/main/python/mllib/hypothesis_testing_example.py
@@ -0,0 +1,65 @@
+#
+# 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
+# $example on$
+from pyspark.mllib.linalg import Matrices, Vectors
+from pyspark.mllib.regression import LabeledPoint
+from pyspark.mllib.stat import Statistics
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="HypothesisTestingExample")
+
+    # $example on$
+    vec = Vectors.dense(0.1, 0.15, 0.2, 0.3, 0.25)  # a vector composed of the frequencies of events
+
+    # 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.
+    goodnessOfFitTestResult = Statistics.chiSqTest(vec)
+
+    # summary of the test including the p-value, degrees of freedom,
+    # test statistic, the method used, and the null hypothesis.
+    print("%s\n" % goodnessOfFitTestResult)
+
+    mat = Matrices.dense(3, 2, [1.0, 3.0, 5.0, 2.0, 4.0, 6.0])  # a contingency matrix
+
+    # conduct Pearson's independence test on the input contingency matrix
+    independenceTestResult = Statistics.chiSqTest(mat)
+
+    # summary of the test including the p-value, degrees of freedom,
+    # test statistic, the method used, and the null hypothesis.
+    print("%s\n" % independenceTestResult)
+
+    obs = sc.parallelize(
+        [LabeledPoint(1.0, [1.0, 0.0, 3.0]),
+         LabeledPoint(1.0, [1.0, 2.0, 0.0]),
+         LabeledPoint(1.0, [-1.0, 0.0, -0.5])]
+    )  # LabeledPoint(feature, label)
+
+    # The contingency table is constructed from an RDD of LabeledPoint and used to conduct
+    # the independence test. Returns an array containing the ChiSquaredTestResult for every feature
+    # against the label.
+    featureTestResults = Statistics.chiSqTest(obs)
+
+    for i, result in enumerate(featureTestResults):
+        print("Column %d:\n%s" % (i + 1, result))
+    # $example off$
+
+    sc.stop()
diff --git a/examples/src/main/python/mllib/hypothesis_testing_kolmogorov_smirnov_test_example.py b/examples/src/main/python/mllib/hypothesis_testing_kolmogorov_smirnov_test_example.py
new file mode 100644
index 0000000000..ef380dee79
--- /dev/null
+++ b/examples/src/main/python/mllib/hypothesis_testing_kolmogorov_smirnov_test_example.py
@@ -0,0 +1,40 @@
+#
+# 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
+# $example on$
+from pyspark.mllib.stat import Statistics
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="HypothesisTestingKolmogorovSmirnovTestExample")
+
+    # $example on$
+    parallelData = sc.parallelize([0.1, 0.15, 0.2, 0.3, 0.25])
+
+    # run a KS test for the sample versus a standard normal distribution
+    testResult = Statistics.kolmogorovSmirnovTest(parallelData, "norm", 0, 1)
+    # 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
+    # Note that the Scala functionality of calling Statistics.kolmogorovSmirnovTest with
+    # a lambda to calculate the CDF is not made available in the Python API
+    print(testResult)
+    # $example off$
+
+    sc.stop()
diff --git a/examples/src/main/python/mllib/kernel_density_estimation_example.py b/examples/src/main/python/mllib/kernel_density_estimation_example.py
new file mode 100644
index 0000000000..3e8f7241a4
--- /dev/null
+++ b/examples/src/main/python/mllib/kernel_density_estimation_example.py
@@ -0,0 +1,44 @@
+#
+# 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
+# $example on$
+from pyspark.mllib.stat import KernelDensity
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="KernelDensityEstimationExample")  # SparkContext
+
+    # $example on$
+    # an RDD of sample data
+    data = sc.parallelize([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
+    kd = KernelDensity()
+    kd.setSample(data)
+    kd.setBandwidth(3.0)
+
+    # Find density estimates for the given values
+    densities = kd.estimate([-1.0, 2.0, 5.0])
+    # $example off$
+
+    print(densities)
+
+    sc.stop()
diff --git a/examples/src/main/python/mllib/stratified_sampling_example.py b/examples/src/main/python/mllib/stratified_sampling_example.py
new file mode 100644
index 0000000000..a13f8f08dd
--- /dev/null
+++ b/examples/src/main/python/mllib/stratified_sampling_example.py
@@ -0,0 +1,38 @@
+#
+# 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
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="StratifiedSamplingExample")  # SparkContext
+
+    # $example on$
+    # an RDD of any key value pairs
+    data = sc.parallelize([(1, 'a'), (1, 'b'), (2, 'c'), (2, 'd'), (2, 'e'), (3, 'f')])
+
+    # specify the exact fraction desired from each key as a dictionary
+    fractions = {1: 0.1, 2: 0.6, 3: 0.3}
+
+    approxSample = data.sampleByKey(False, fractions)
+    # $example off$
+
+    for each in approxSample.collect():
+        print(each)
+
+    sc.stop()
diff --git a/examples/src/main/python/mllib/summary_statistics_example.py b/examples/src/main/python/mllib/summary_statistics_example.py
new file mode 100644
index 0000000000..d55d1a2c2d
--- /dev/null
+++ b/examples/src/main/python/mllib/summary_statistics_example.py
@@ -0,0 +1,42 @@
+#
+# 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
+# $example on$
+import numpy as np
+
+from pyspark.mllib.stat import Statistics
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="SummaryStatisticsExample")  # SparkContext
+
+    # $example on$
+    mat = sc.parallelize(
+        [np.array([1.0, 10.0, 100.0]), np.array([2.0, 20.0, 200.0]), np.array([3.0, 30.0, 300.0])]
+    )  # an RDD of Vectors
+
+    # Compute column summary statistics.
+    summary = Statistics.colStats(mat)
+    print(summary.mean())  # a dense vector containing the mean value for each column
+    print(summary.variance())  # column-wise variance
+    print(summary.numNonzeros())  # number of nonzeros in each column
+    # $example off$
+
+    sc.stop()