[SPARK-11551][DOC][EXAMPLE] Replace example code in ml-features.md us…

…ing include_example Made new patch contaning only markdown examples moved to exmaple/folder. Ony three java code were not shfted since they were contaning compliation error ,these classes are 1)StandardScale 2)NormalizerExample 3)VectorIndexer Author: Xusen Yin <[email protected]> Author: somideshmukh <[email protected]> Closes apache#10002 from somideshmukh/SomilBranch1.33.
markhamstra · Dec 8, 2015 · 78209b0 · 78209b0
1 parent 3e7e05f
commit 78209b0
Show file tree

Hide file tree

Showing 52 changed files with 2,806 additions and 1,058 deletions.
diff --git a/docs/ml-features.md b/docs/ml-features.md
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java
@@ -0,0 +1,68 @@
+/*
+ * 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;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SQLContext;
+
+// $example on$
+import java.util.Arrays;
+
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.ml.feature.Binarizer;
+import org.apache.spark.sql.DataFrame;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.RowFactory;
+import org.apache.spark.sql.types.DataTypes;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+// $example off$
+
+public class JavaBinarizerExample {
+  public static void main(String[] args) {
+    SparkConf conf = new SparkConf().setAppName("JavaBinarizerExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+    SQLContext jsql = new SQLContext(jsc);
+
+    // $example on$
+    JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList(
+      RowFactory.create(0, 0.1),
+      RowFactory.create(1, 0.8),
+      RowFactory.create(2, 0.2)
+    ));
+    StructType schema = new StructType(new StructField[]{
+      new StructField("label", DataTypes.DoubleType, false, Metadata.empty()),
+      new StructField("feature", DataTypes.DoubleType, false, Metadata.empty())
+    });
+    DataFrame continuousDataFrame = jsql.createDataFrame(jrdd, schema);
+    Binarizer binarizer = new Binarizer()
+      .setInputCol("feature")
+      .setOutputCol("binarized_feature")
+      .setThreshold(0.5);
+    DataFrame binarizedDataFrame = binarizer.transform(continuousDataFrame);
+    DataFrame binarizedFeatures = binarizedDataFrame.select("binarized_feature");
+    for (Row r : binarizedFeatures.collect()) {
+    Double binarized_value = r.getDouble(0);
+      System.out.println(binarized_value);
+    }
+    // $example off$
+    jsc.stop();
+  }
+}
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.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.ml;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SQLContext;
+
+// $example on$
+import java.util.Arrays;
+
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.ml.feature.Bucketizer;
+import org.apache.spark.sql.DataFrame;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.RowFactory;
+import org.apache.spark.sql.types.DataTypes;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+// $example off$
+
+public class JavaBucketizerExample {
+  public static void main(String[] args) {
+    SparkConf conf = new SparkConf().setAppName("JavaBucketizerExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+    SQLContext jsql = new SQLContext(jsc);
+
+    // $example on$
+    double[] splits = {Double.NEGATIVE_INFINITY, -0.5, 0.0, 0.5, Double.POSITIVE_INFINITY};
+
+    JavaRDD<Row> data = jsc.parallelize(Arrays.asList(
+      RowFactory.create(-0.5),
+      RowFactory.create(-0.3),
+      RowFactory.create(0.0),
+      RowFactory.create(0.2)
+    ));
+    StructType schema = new StructType(new StructField[]{
+      new StructField("features", DataTypes.DoubleType, false, Metadata.empty())
+    });
+    DataFrame dataFrame = jsql.createDataFrame(data, schema);
+
+    Bucketizer bucketizer = new Bucketizer()
+      .setInputCol("features")
+      .setOutputCol("bucketedFeatures")
+      .setSplits(splits);
+
+    // Transform original data into its bucket index.
+    DataFrame bucketedData = bucketizer.transform(dataFrame);
+    // $example off$
+    jsc.stop();
+  }
+}
+
+
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java
@@ -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.
+ */
+
+package org.apache.spark.examples.ml;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SQLContext;
+
+// $example on$
+import java.util.Arrays;
+
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.ml.feature.DCT;
+import org.apache.spark.mllib.linalg.VectorUDT;
+import org.apache.spark.mllib.linalg.Vectors;
+import org.apache.spark.sql.DataFrame;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.RowFactory;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+// $example off$
+
+public class JavaDCTExample {
+  public static void main(String[] args) {
+    SparkConf conf = new SparkConf().setAppName("JavaDCTExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+    SQLContext jsql = new SQLContext(jsc);
+
+    // $example on$
+    JavaRDD<Row> data = jsc.parallelize(Arrays.asList(
+      RowFactory.create(Vectors.dense(0.0, 1.0, -2.0, 3.0)),
+      RowFactory.create(Vectors.dense(-1.0, 2.0, 4.0, -7.0)),
+      RowFactory.create(Vectors.dense(14.0, -2.0, -5.0, 1.0))
+    ));
+    StructType schema = new StructType(new StructField[]{
+      new StructField("features", new VectorUDT(), false, Metadata.empty()),
+    });
+    DataFrame df = jsql.createDataFrame(data, schema);
+    DCT dct = new DCT()
+      .setInputCol("features")
+      .setOutputCol("featuresDCT")
+      .setInverse(false);
+    DataFrame dctDf = dct.transform(df);
+    dctDf.select("featuresDCT").show(3);
+    // $example off$
+    jsc.stop();
+  }
+}
+
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.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.ml;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SQLContext;
+
+// $example on$
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.List;
+
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.ml.feature.ElementwiseProduct;
+import org.apache.spark.mllib.linalg.Vector;
+import org.apache.spark.mllib.linalg.VectorUDT;
+import org.apache.spark.mllib.linalg.Vectors;
+import org.apache.spark.sql.DataFrame;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.RowFactory;
+import org.apache.spark.sql.types.DataTypes;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+// $example off$
+
+public class JavaElementwiseProductExample {
+  public static void main(String[] args) {
+    SparkConf conf = new SparkConf().setAppName("JavaElementwiseProductExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+    SQLContext sqlContext = new SQLContext(jsc);
+
+    // $example on$
+    // Create some vector data; also works for sparse vectors
+    JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList(
+      RowFactory.create("a", Vectors.dense(1.0, 2.0, 3.0)),
+      RowFactory.create("b", Vectors.dense(4.0, 5.0, 6.0))
+    ));
+
+    List<StructField> fields = new ArrayList<StructField>(2);
+    fields.add(DataTypes.createStructField("id", DataTypes.StringType, false));
+    fields.add(DataTypes.createStructField("vector", new VectorUDT(), false));
+
+    StructType schema = DataTypes.createStructType(fields);
+
+    DataFrame dataFrame = sqlContext.createDataFrame(jrdd, schema);
+
+    Vector transformingVector = Vectors.dense(0.0, 1.0, 2.0);
+
+    ElementwiseProduct transformer = new ElementwiseProduct()
+      .setScalingVec(transformingVector)
+      .setInputCol("vector")
+      .setOutputCol("transformedVector");
+
+    // Batch transform the vectors to create new column:
+    transformer.transform(dataFrame).show();
+    // $example off$
+    jsc.stop();
+  }
+}
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java
@@ -0,0 +1,50 @@
+/*
+ * 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;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SQLContext;
+
+// $example on$
+import org.apache.spark.ml.feature.MinMaxScaler;
+import org.apache.spark.ml.feature.MinMaxScalerModel;
+import org.apache.spark.sql.DataFrame;
+// $example off$
+
+public class JavaMinMaxScalerExample {
+  public static void main(String[] args) {
+    SparkConf conf = new SparkConf().setAppName("JaveMinMaxScalerExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+    SQLContext jsql = new SQLContext(jsc);
+
+    // $example on$
+    DataFrame dataFrame = jsql.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
+    MinMaxScaler scaler = new MinMaxScaler()
+      .setInputCol("features")
+      .setOutputCol("scaledFeatures");
+
+    // Compute summary statistics and generate MinMaxScalerModel
+    MinMaxScalerModel scalerModel = scaler.fit(dataFrame);
+
+    // rescale each feature to range [min, max].
+    DataFrame scaledData = scalerModel.transform(dataFrame);
+    // $example off$
+    jsc.stop();
+  }
+}