[SPARK-11958][SPARK-11957][ML][DOC] SQLTransformer user guide and example code

Add ```SQLTransformer``` user guide, example code and make Scala API doc more clear.

Author: Yanbo Liang <ybliang8@gmail.com>

Closes #10006 from yanboliang/spark-11958.

3 files changed, 144 insertions, 0 deletions

diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaSQLTransformerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaSQLTransformerExample.java
new file mode 100644
index 0000000000..d55c70796a
--- /dev/null
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaSQLTransformerExample.java
@@ -0,0 +1,59 @@
+/*
+ * 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;
+
+// $example on$
+import java.util.Arrays;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.ml.feature.SQLTransformer;
+import org.apache.spark.sql.DataFrame;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.RowFactory;
+import org.apache.spark.sql.SQLContext;
+import org.apache.spark.sql.types.*;
+// $example off$
+
+public class JavaSQLTransformerExample {
+  public static void main(String[] args) {
+
+    SparkConf conf = new SparkConf().setAppName("JavaSQLTransformerExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+    SQLContext sqlContext = new SQLContext(jsc);
+
+    // $example on$
+    JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList(
+      RowFactory.create(0, 1.0, 3.0),
+      RowFactory.create(2, 2.0, 5.0)
+    ));
+    StructType schema = new StructType(new StructField [] {
+      new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
+      new StructField("v1", DataTypes.DoubleType, false, Metadata.empty()),
+      new StructField("v2", DataTypes.DoubleType, false, Metadata.empty())
+    });
+    DataFrame df = sqlContext.createDataFrame(jrdd, schema);
+
+    SQLTransformer sqlTrans = new SQLTransformer().setStatement(
+      "SELECT *, (v1 + v2) AS v3, (v1 * v2) AS v4 FROM __THIS__");
+
+    sqlTrans.transform(df).show();
+    // $example off$
+  }
+}
diff --git a/examples/src/main/python/ml/sql_transformer.py b/examples/src/main/python/ml/sql_transformer.py
new file mode 100644
index 0000000000..9575d728d8
--- /dev/null
+++ b/examples/src/main/python/ml/sql_transformer.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.ml.feature import SQLTransformer
+# $example off$
+from pyspark.sql import SQLContext
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="SQLTransformerExample")
+    sqlContext = SQLContext(sc)
+
+    # $example on$
+    df = sqlContext.createDataFrame([
+        (0, 1.0, 3.0),
+        (2, 2.0, 5.0)
+    ], ["id", "v1", "v2"])
+    sqlTrans = SQLTransformer(
+        statement="SELECT *, (v1 + v2) AS v3, (v1 * v2) AS v4 FROM __THIS__")
+    sqlTrans.transform(df).show()
+    # $example off$
+
+    sc.stop()
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/SQLTransformerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/SQLTransformerExample.scala
new file mode 100644
index 0000000000..014abd1fdb
--- /dev/null
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/SQLTransformerExample.scala
@@ -0,0 +1,45 @@
+/*
+ * 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.
+ */
+
+// scalastyle:off println
+package org.apache.spark.examples.ml
+
+// $example on$
+import org.apache.spark.ml.feature.SQLTransformer
+// $example off$
+import org.apache.spark.sql.SQLContext
+import org.apache.spark.{SparkConf, SparkContext}
+
+
+object SQLTransformerExample {
+  def main(args: Array[String]) {
+    val conf = new SparkConf().setAppName("SQLTransformerExample")
+    val sc = new SparkContext(conf)
+    val sqlContext = new SQLContext(sc)
+
+    // $example on$
+    val df = sqlContext.createDataFrame(
+      Seq((0, 1.0, 3.0), (2, 2.0, 5.0))).toDF("id", "v1", "v2")
+
+    val sqlTrans = new SQLTransformer().setStatement(
+      "SELECT *, (v1 + v2) AS v3, (v1 * v2) AS v4 FROM __THIS__")
+
+    sqlTrans.transform(df).show()
+    // $example off$
+  }
+}
+// scalastyle:on println