[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user WeichenXu123 commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165578020 --- Diff: examples/src/main/scala/org/apache/spark/examples/ml/SummarizerExample.scala --- @@ -0,0 +1,60 @@ +/* + * 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.linalg.{Vector, Vectors} +import org.apache.spark.ml.stat.Summarizer +// $example off$ +import org.apache.spark.sql.SparkSession + +object SummarizerExample { + def main(args: Array[String]): Unit = { +val spark = SparkSession + .builder + .appName("SummarizerExample") + .getOrCreate() + +import spark.implicits._ +import Summarizer._ + +// $example on$ +val data = Seq( + (Vectors.dense(2.0, 3.0, 5.0), 1.0), + (Vectors.dense(4.0, 6.0, 7.0), 2.0) +) + +val df = data.toDF("features", "weight") + +val Tuple1((meanVal, varianceVal)) = df.select(metrics("mean", "variance") + .summary($"features", $"weight")) + .as[Tuple1[(Vector, Vector)]].first() --- End diff -- Good idea. This way make code easier to read. Done. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165575680 --- Diff: examples/src/main/scala/org/apache/spark/examples/ml/SummarizerExample.scala --- @@ -0,0 +1,60 @@ +/* + * 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.linalg.{Vector, Vectors} +import org.apache.spark.ml.stat.Summarizer +// $example off$ +import org.apache.spark.sql.SparkSession + +object SummarizerExample { + def main(args: Array[String]): Unit = { +val spark = SparkSession + .builder + .appName("SummarizerExample") + .getOrCreate() + +import spark.implicits._ +import Summarizer._ + +// $example on$ +val data = Seq( + (Vectors.dense(2.0, 3.0, 5.0), 1.0), + (Vectors.dense(4.0, 6.0, 7.0), 2.0) +) + +val df = data.toDF("features", "weight") + +val Tuple1((meanVal, varianceVal)) = df.select(metrics("mean", "variance") + .summary($"features", $"weight")) + .as[Tuple1[(Vector, Vector)]].first() --- End diff -- oh ok - perhaps `select("summary.mean", "summary.variance")` would work to extract into two columns? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user WeichenXu123 commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165573866 --- Diff: examples/src/main/scala/org/apache/spark/examples/ml/SummarizerExample.scala --- @@ -0,0 +1,60 @@ +/* + * 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.linalg.{Vector, Vectors} +import org.apache.spark.ml.stat.Summarizer +// $example off$ +import org.apache.spark.sql.SparkSession + +object SummarizerExample { + def main(args: Array[String]): Unit = { +val spark = SparkSession + .builder + .appName("SummarizerExample") + .getOrCreate() + +import spark.implicits._ +import Summarizer._ + +// $example on$ +val data = Seq( + (Vectors.dense(2.0, 3.0, 5.0), 1.0), + (Vectors.dense(4.0, 6.0, 7.0), 2.0) +) + +val df = data.toDF("features", "weight") + +val Tuple1((meanVal, varianceVal)) = df.select(metrics("mean", "variance") + .summary($"features", $"weight")) + .as[Tuple1[(Vector, Vector)]].first() --- End diff -- Do you mean us `.as[((Vector, Vector))]` ? It compile fails.. or Do you mean change to ``` val (meanVal, varianceVal) = df.select(metrics("mean", "variance") .summary($"features", $"weight")) .as[(Vector, Vector)].first() ``` ? Seems also do not work because it is a "struct type" value in the returned row. So the first row format should match Row(Row(mean, variance)) --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165568368 --- Diff: docs/ml-statistics.md --- @@ -89,4 +89,26 @@ Refer to the [`ChiSquareTest` Python docs](api/python/index.html#pyspark.ml.stat {% include_example python/ml/chi_square_test_example.py %} + + +## Summarizer + +We provide vector column summary statistics for `Dataframe` through `Summarizer`. +Available metrics are the column-wise max, min, mean, variance, and number of nonzeros, as well as the total count. + + + +The following example demonstrates using [`Summarizer`](api/scala/index.html#org.apache.spark.ml.stat.Summarizer$) +to compute the mean and variance for the input dataframe, with and without a weight column. --- End diff -- sorry, one more comment here I think perhaps "... to compute the mean and variance for a vector column of the input dataframe ..." (and same below) --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165568014 --- Diff: examples/src/main/java/org/apache/spark/examples/ml/JavaSummarizerExample.java --- @@ -0,0 +1,71 @@ +/* + * 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.sql.*; + +// $example on$ +import java.util.Arrays; +import java.util.List; + +import org.apache.spark.ml.linalg.Vector; +import org.apache.spark.ml.linalg.Vectors; +import org.apache.spark.ml.linalg.VectorUDT; +import org.apache.spark.ml.stat.Summarizer; +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 JavaSummarizerExample { + public static void main(String[] args) { +SparkSession spark = SparkSession + .builder() + .appName("JavaSummarizerExample") + .getOrCreate(); + +// $example on$ +List data = Arrays.asList( + RowFactory.create(Vectors.dense(2.0, 3.0, 5.0), 1.0), + RowFactory.create(Vectors.dense(4.0, 6.0, 7.0), 2.0) +); + +StructType schema = new StructType(new StructField[]{ + new StructField("features", new VectorUDT(), false, Metadata.empty()), + new StructField("weight", DataTypes.DoubleType, false, Metadata.empty()) +}); + +Dataset df = spark.createDataFrame(data, schema); + +Row result1 = df.select(Summarizer.metrics("mean", "variance") +.summary(new Column("features"), new Column("weight"))) +.first().getStruct(0); +System.out.println("with weight: mean = " + result1.getAs(0).toString() + --- End diff -- ok fair enough --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165567614 --- Diff: examples/src/main/scala/org/apache/spark/examples/ml/SummarizerExample.scala --- @@ -0,0 +1,60 @@ +/* + * 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.linalg.{Vector, Vectors} +import org.apache.spark.ml.stat.Summarizer +// $example off$ +import org.apache.spark.sql.SparkSession + +object SummarizerExample { + def main(args: Array[String]): Unit = { +val spark = SparkSession + .builder + .appName("SummarizerExample") + .getOrCreate() + +import spark.implicits._ +import Summarizer._ + +// $example on$ +val data = Seq( + (Vectors.dense(2.0, 3.0, 5.0), 1.0), + (Vectors.dense(4.0, 6.0, 7.0), 2.0) +) + +val df = data.toDF("features", "weight") + +val Tuple1((meanVal, varianceVal)) = df.select(metrics("mean", "variance") + .summary($"features", $"weight")) + .as[Tuple1[(Vector, Vector)]].first() --- End diff -- nit, but `Tuple1` not required here? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user WeichenXu123 commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165565121 --- Diff: examples/src/main/java/org/apache/spark/examples/ml/JavaSummarizerExample.java --- @@ -0,0 +1,71 @@ +/* + * 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.sql.*; + +// $example on$ +import java.util.Arrays; +import java.util.List; + +import org.apache.spark.ml.linalg.Vector; +import org.apache.spark.ml.linalg.Vectors; +import org.apache.spark.ml.linalg.VectorUDT; +import org.apache.spark.ml.stat.Summarizer; +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 JavaSummarizerExample { + public static void main(String[] args) { +SparkSession spark = SparkSession + .builder() + .appName("JavaSummarizerExample") + .getOrCreate(); + +// $example on$ +List data = Arrays.asList( + RowFactory.create(Vectors.dense(2.0, 3.0, 5.0), 1.0), + RowFactory.create(Vectors.dense(4.0, 6.0, 7.0), 2.0) +); + +StructType schema = new StructType(new StructField[]{ + new StructField("features", new VectorUDT(), false, Metadata.empty()), + new StructField("weight", DataTypes.DoubleType, false, Metadata.empty()) +}); + +Dataset df = spark.createDataFrame(data, schema); + +Row result1 = df.select(Summarizer.metrics("mean", "variance") +.summary(new Column("features"), new Column("weight"))) +.first().getStruct(0); +System.out.println("with weight: mean = " + result1.getAs(0).toString() + --- End diff -- Because spark user will usually want to get the summary result (multiple vectors), I want to show the simple way to extract these results from the returned dataframe which contains only one row. I think some user is possible to get stuck here. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165362568 --- Diff: examples/src/main/scala/org/apache/spark/examples/ml/SummarizerExample.scala --- @@ -0,0 +1,60 @@ +/* + * 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.linalg.{Vector, Vectors} +import org.apache.spark.ml.stat.Summarizer +// $example off$ +import org.apache.spark.sql.SparkSession + +object SummarizerExample { + def main(args: Array[String]): Unit = { +val spark = SparkSession + .builder + .appName("SummarizerExample") + .getOrCreate() + +import spark.implicits._ +import Summarizer._ + +// $example on$ +val data = Seq( + (Vectors.dense(2.0, 3.0, 5.0), 1.0), + (Vectors.dense(4.0, 6.0, 7.0), 2.0) +) + +val df = data.toDF("features", "weight") + +val Tuple1((meanVal, varianceVal)) = df.select(metrics("mean", "variance") + .summary($"features", $"weight")) + .as[Tuple1[(Vector, Vector)]].first() + +println(s"with weight: mean = ${meanVal}, variance = ${varianceVal}") + +val (meanVal2, varianceVal2) = df.select(mean($"features"), variance($"features")) + .as[(Vector, Vector)].first() + +println(s"without weight: mean = ${meanVal2}, sum = ${varianceVal2}") --- End diff -- Same applies here, why not just `df.select(...).show()`? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165362364 --- Diff: examples/src/main/java/org/apache/spark/examples/ml/JavaSummarizerExample.java --- @@ -0,0 +1,71 @@ +/* + * 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.sql.*; + +// $example on$ +import java.util.Arrays; +import java.util.List; + +import org.apache.spark.ml.linalg.Vector; +import org.apache.spark.ml.linalg.Vectors; +import org.apache.spark.ml.linalg.VectorUDT; +import org.apache.spark.ml.stat.Summarizer; +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 JavaSummarizerExample { + public static void main(String[] args) { +SparkSession spark = SparkSession + .builder() + .appName("JavaSummarizerExample") + .getOrCreate(); + +// $example on$ +List data = Arrays.asList( + RowFactory.create(Vectors.dense(2.0, 3.0, 5.0), 1.0), + RowFactory.create(Vectors.dense(4.0, 6.0, 7.0), 2.0) +); + +StructType schema = new StructType(new StructField[]{ + new StructField("features", new VectorUDT(), false, Metadata.empty()), + new StructField("weight", DataTypes.DoubleType, false, Metadata.empty()) +}); + +Dataset df = spark.createDataFrame(data, schema); + +Row result1 = df.select(Summarizer.metrics("mean", "variance") +.summary(new Column("features"), new Column("weight"))) +.first().getStruct(0); +System.out.println("with weight: mean = " + result1.getAs(0).toString() + --- End diff -- Why not just `df.select(...).show()`? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165360692 --- Diff: docs/ml-statistics.md --- @@ -89,4 +89,26 @@ Refer to the [`ChiSquareTest` Python docs](api/python/index.html#pyspark.ml.stat {% include_example python/ml/chi_square_test_example.py %} + + +## Summarizer + +We provide vector column summary statistics for `Dataframe` through `Summarizer`. +Available metrics contain the column-wise max, min, mean, variance, and number of nonzeros, as well as the total count. --- End diff -- Perhaps "contain" -> "are" or "include"? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165362533 --- Diff: examples/src/main/scala/org/apache/spark/examples/ml/SummarizerExample.scala --- @@ -0,0 +1,60 @@ +/* + * 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.linalg.{Vector, Vectors} +import org.apache.spark.ml.stat.Summarizer +// $example off$ +import org.apache.spark.sql.SparkSession + +object SummarizerExample { + def main(args: Array[String]): Unit = { +val spark = SparkSession + .builder + .appName("SummarizerExample") + .getOrCreate() + +import spark.implicits._ +import Summarizer._ + +// $example on$ +val data = Seq( + (Vectors.dense(2.0, 3.0, 5.0), 1.0), + (Vectors.dense(4.0, 6.0, 7.0), 2.0) +) + +val df = data.toDF("features", "weight") + +val Tuple1((meanVal, varianceVal)) = df.select(metrics("mean", "variance") + .summary($"features", $"weight")) + .as[Tuple1[(Vector, Vector)]].first() + +println(s"with weight: mean = ${meanVal}, variance = ${varianceVal}") --- End diff -- Same applies here, why not just `df.select(...).show()`? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165362148 --- Diff: docs/ml-statistics.md --- @@ -89,4 +89,26 @@ Refer to the [`ChiSquareTest` Python docs](api/python/index.html#pyspark.ml.stat {% include_example python/ml/chi_square_test_example.py %} + + +## Summarizer + +We provide vector column summary statistics for `Dataframe` through `Summarizer`. +Available metrics contain the column-wise max, min, mean, variance, and number of nonzeros, as well as the total count. + + + +[`Summarizer`](api/scala/index.html#org.apache.spark.ml.stat.Summarizer$) --- End diff -- Perhaps "The following example demonstrates using `Summarizer`(...) to compute the mean and variance for the input dataframe, with and without a weight column"? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165362440 --- Diff: examples/src/main/java/org/apache/spark/examples/ml/JavaSummarizerExample.java --- @@ -0,0 +1,71 @@ +/* + * 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.sql.*; + +// $example on$ +import java.util.Arrays; +import java.util.List; + +import org.apache.spark.ml.linalg.Vector; +import org.apache.spark.ml.linalg.Vectors; +import org.apache.spark.ml.linalg.VectorUDT; +import org.apache.spark.ml.stat.Summarizer; +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 JavaSummarizerExample { + public static void main(String[] args) { +SparkSession spark = SparkSession + .builder() + .appName("JavaSummarizerExample") + .getOrCreate(); + +// $example on$ +List data = Arrays.asList( + RowFactory.create(Vectors.dense(2.0, 3.0, 5.0), 1.0), + RowFactory.create(Vectors.dense(4.0, 6.0, 7.0), 2.0) +); + +StructType schema = new StructType(new StructField[]{ + new StructField("features", new VectorUDT(), false, Metadata.empty()), + new StructField("weight", DataTypes.DoubleType, false, Metadata.empty()) +}); + +Dataset df = spark.createDataFrame(data, schema); + +Row result1 = df.select(Summarizer.metrics("mean", "variance") +.summary(new Column("features"), new Column("weight"))) +.first().getStruct(0); +System.out.println("with weight: mean = " + result1.getAs(0).toString() + + ", variance = " + result1.getAs(1).toString()); + +Row result2 = df.select( + Summarizer.mean(new Column("features")), + Summarizer.variance(new Column("features")) +).first(); +System.out.println("without weight: mean = " + result2.getAs(0).toString() + --- End diff -- Why not just `df.select(...).show()`? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #20446: [SPARK-23254][ML] Add user guide entry for DataFr...
GitHub user WeichenXu123 opened a pull request: https://github.com/apache/spark/pull/20446 [SPARK-23254][ML] Add user guide entry for DataFrame multivariate summary ## What changes were proposed in this pull request? Add user guide and scala/java examples for `ml.stat.Summarizer` ## How was this patch tested? Doc generated snapshot: ![image](https://user-images.githubusercontent.com/19235986/35600897-2bb9c102-05e5-11e8-849f-e327f125.png) ![image](https://user-images.githubusercontent.com/19235986/35600910-3b022f28-05e5-11e8-823e-ae61009317a0.png) ![image](https://user-images.githubusercontent.com/19235986/35600918-43c24f3a-05e5-11e8-847d-446452838e05.png) You can merge this pull request into a Git repository by running: $ git pull https://github.com/WeichenXu123/spark summ_guide Alternatively you can review and apply these changes as the patch at: https://github.com/apache/spark/pull/20446.patch To close this pull request, make a commit to your master/trunk branch with (at least) the following in the commit message: This closes #20446 commit 307f75f4990049f78978364af4541cd20e4d5bd7 Author: WeichenXu Date: 2018-01-31T01:41:48Z init pr --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org