[SPARK-11728] Replace example code in ml-ensembles.md using include_example

JIRA issue https://issues.apache.org/jira/browse/SPARK-11728.

The ml-ensembles.md file contains `OneVsRestExample`. Instead of writing new code files of two `OneVsRestExample`s, I use two existing files in the examples directory, they are `OneVsRestExample.scala` and `JavaOneVsRestExample.scala`.

Author: Xusen Yin <yinxusen@gmail.com>

Closes #9716 from yinxusen/SPARK-11728.

4 files changed, 302 insertions, 0 deletions

diff --git a/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py b/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py
new file mode 100644
index 0000000000..028497651f
--- /dev/null
+++ b/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py
@@ -0,0 +1,77 @@
+#
+# 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.
+#
+
+"""
+Gradient Boosted Tree Classifier Example.
+"""
+from __future__ import print_function
+
+import sys
+
+from pyspark import SparkContext, SQLContext
+# $example on$
+from pyspark.ml import Pipeline
+from pyspark.ml.classification import GBTClassifier
+from pyspark.ml.feature import StringIndexer, VectorIndexer
+from pyspark.ml.evaluation import MulticlassClassificationEvaluator
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="gradient_boosted_tree_classifier_example")
+    sqlContext = SQLContext(sc)
+
+    # $example on$
+    # Load and parse the data file, converting it to a DataFrame.
+    data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
+
+    # Index labels, adding metadata to the label column.
+    # Fit on whole dataset to include all labels in index.
+    labelIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel").fit(data)
+    # Automatically identify categorical features, and index them.
+    # Set maxCategories so features with > 4 distinct values are treated as continuous.
+    featureIndexer =\
+        VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)
+
+    # Split the data into training and test sets (30% held out for testing)
+    (trainingData, testData) = data.randomSplit([0.7, 0.3])
+
+    # Train a GBT model.
+    gbt = GBTClassifier(labelCol="indexedLabel", featuresCol="indexedFeatures", maxIter=10)
+
+    # Chain indexers and GBT in a Pipeline
+    pipeline = Pipeline(stages=[labelIndexer, featureIndexer, gbt])
+
+    # Train model.  This also runs the indexers.
+    model = pipeline.fit(trainingData)
+
+    # Make predictions.
+    predictions = model.transform(testData)
+
+    # Select example rows to display.
+    predictions.select("prediction", "indexedLabel", "features").show(5)
+
+    # Select (prediction, true label) and compute test error
+    evaluator = MulticlassClassificationEvaluator(
+        labelCol="indexedLabel", predictionCol="prediction", metricName="precision")
+    accuracy = evaluator.evaluate(predictions)
+    print("Test Error = %g" % (1.0 - accuracy))
+
+    gbtModel = model.stages[2]
+    print(gbtModel)  # summary only
+    # $example off$
+
+    sc.stop()
diff --git a/examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py b/examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py
new file mode 100644
index 0000000000..4246e133a9
--- /dev/null
+++ b/examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py
@@ -0,0 +1,74 @@
+#
+# 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.
+#
+
+"""
+Gradient Boosted Tree Regressor Example.
+"""
+from __future__ import print_function
+
+import sys
+
+from pyspark import SparkContext, SQLContext
+# $example on$
+from pyspark.ml import Pipeline
+from pyspark.ml.regression import GBTRegressor
+from pyspark.ml.feature import VectorIndexer
+from pyspark.ml.evaluation import RegressionEvaluator
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="gradient_boosted_tree_regressor_example")
+    sqlContext = SQLContext(sc)
+
+    # $example on$
+    # Load and parse the data file, converting it to a DataFrame.
+    data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
+
+    # Automatically identify categorical features, and index them.
+    # Set maxCategories so features with > 4 distinct values are treated as continuous.
+    featureIndexer =\
+        VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)
+
+    # Split the data into training and test sets (30% held out for testing)
+    (trainingData, testData) = data.randomSplit([0.7, 0.3])
+
+    # Train a GBT model.
+    gbt = GBTRegressor(featuresCol="indexedFeatures", maxIter=10)
+
+    # Chain indexer and GBT in a Pipeline
+    pipeline = Pipeline(stages=[featureIndexer, gbt])
+
+    # Train model.  This also runs the indexer.
+    model = pipeline.fit(trainingData)
+
+    # Make predictions.
+    predictions = model.transform(testData)
+
+    # Select example rows to display.
+    predictions.select("prediction", "label", "features").show(5)
+
+    # Select (prediction, true label) and compute test error
+    evaluator = RegressionEvaluator(
+        labelCol="label", predictionCol="prediction", metricName="rmse")
+    rmse = evaluator.evaluate(predictions)
+    print("Root Mean Squared Error (RMSE) on test data = %g" % rmse)
+
+    gbtModel = model.stages[1]
+    print(gbtModel)  # summary only
+    # $example off$
+
+    sc.stop()
diff --git a/examples/src/main/python/ml/random_forest_classifier_example.py b/examples/src/main/python/ml/random_forest_classifier_example.py
new file mode 100644
index 0000000000..b3530d4f41
--- /dev/null
+++ b/examples/src/main/python/ml/random_forest_classifier_example.py
@@ -0,0 +1,77 @@
+#
+# 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.
+#
+
+"""
+Random Forest Classifier Example.
+"""
+from __future__ import print_function
+
+import sys
+
+from pyspark import SparkContext, SQLContext
+# $example on$
+from pyspark.ml import Pipeline
+from pyspark.ml.classification import RandomForestClassifier
+from pyspark.ml.feature import StringIndexer, VectorIndexer
+from pyspark.ml.evaluation import MulticlassClassificationEvaluator
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="random_forest_classifier_example")
+    sqlContext = SQLContext(sc)
+
+    # $example on$
+    # Load and parse the data file, converting it to a DataFrame.
+    data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
+
+    # Index labels, adding metadata to the label column.
+    # Fit on whole dataset to include all labels in index.
+    labelIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel").fit(data)
+    # Automatically identify categorical features, and index them.
+    # Set maxCategories so features with > 4 distinct values are treated as continuous.
+    featureIndexer =\
+        VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)
+
+    # Split the data into training and test sets (30% held out for testing)
+    (trainingData, testData) = data.randomSplit([0.7, 0.3])
+
+    # Train a RandomForest model.
+    rf = RandomForestClassifier(labelCol="indexedLabel", featuresCol="indexedFeatures")
+
+    # Chain indexers and forest in a Pipeline
+    pipeline = Pipeline(stages=[labelIndexer, featureIndexer, rf])
+
+    # Train model.  This also runs the indexers.
+    model = pipeline.fit(trainingData)
+
+    # Make predictions.
+    predictions = model.transform(testData)
+
+    # Select example rows to display.
+    predictions.select("prediction", "indexedLabel", "features").show(5)
+
+    # Select (prediction, true label) and compute test error
+    evaluator = MulticlassClassificationEvaluator(
+        labelCol="indexedLabel", predictionCol="prediction", metricName="precision")
+    accuracy = evaluator.evaluate(predictions)
+    print("Test Error = %g" % (1.0 - accuracy))
+
+    rfModel = model.stages[2]
+    print(rfModel)  # summary only
+    # $example off$
+
+    sc.stop()
diff --git a/examples/src/main/python/ml/random_forest_regressor_example.py b/examples/src/main/python/ml/random_forest_regressor_example.py
new file mode 100644
index 0000000000..b59c7c9414
--- /dev/null
+++ b/examples/src/main/python/ml/random_forest_regressor_example.py
@@ -0,0 +1,74 @@
+#
+# 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.
+#
+
+"""
+Random Forest Regressor Example.
+"""
+from __future__ import print_function
+
+import sys
+
+from pyspark import SparkContext, SQLContext
+# $example on$
+from pyspark.ml import Pipeline
+from pyspark.ml.regression import RandomForestRegressor
+from pyspark.ml.feature import VectorIndexer
+from pyspark.ml.evaluation import RegressionEvaluator
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="random_forest_regressor_example")
+    sqlContext = SQLContext(sc)
+
+    # $example on$
+    # Load and parse the data file, converting it to a DataFrame.
+    data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
+
+    # Automatically identify categorical features, and index them.
+    # Set maxCategories so features with > 4 distinct values are treated as continuous.
+    featureIndexer =\
+        VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)
+
+    # Split the data into training and test sets (30% held out for testing)
+    (trainingData, testData) = data.randomSplit([0.7, 0.3])
+
+    # Train a RandomForest model.
+    rf = RandomForestRegressor(featuresCol="indexedFeatures")
+
+    # Chain indexer and forest in a Pipeline
+    pipeline = Pipeline(stages=[featureIndexer, rf])
+
+    # Train model.  This also runs the indexer.
+    model = pipeline.fit(trainingData)
+
+    # Make predictions.
+    predictions = model.transform(testData)
+
+    # Select example rows to display.
+    predictions.select("prediction", "label", "features").show(5)
+
+    # Select (prediction, true label) and compute test error
+    evaluator = RegressionEvaluator(
+        labelCol="label", predictionCol="prediction", metricName="rmse")
+    rmse = evaluator.evaluate(predictions)
+    print("Root Mean Squared Error (RMSE) on test data = %g" % rmse)
+
+    rfModel = model.stages[1]
+    print(rfModel)  # summary only
+    # $example off$
+
+    sc.stop()