You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by jk...@apache.org on 2015/12/02 00:21:57 UTC
spark git commit: [SPARK-11961][DOC] Add docs of ChiSqSelector
Repository: spark
Updated Branches:
refs/heads/master 328b757d5 -> e76431f88
[SPARK-11961][DOC] Add docs of ChiSqSelector
https://issues.apache.org/jira/browse/SPARK-11961
Author: Xusen Yin <yi...@gmail.com>
Closes #9965 from yinxusen/SPARK-11961.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/e76431f8
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/e76431f8
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/e76431f8
Branch: refs/heads/master
Commit: e76431f886ae8061545b3216e8e2fb38c4db1f43
Parents: 328b757
Author: Xusen Yin <yi...@gmail.com>
Authored: Tue Dec 1 15:21:53 2015 -0800
Committer: Joseph K. Bradley <jo...@databricks.com>
Committed: Tue Dec 1 15:21:53 2015 -0800
----------------------------------------------------------------------
docs/ml-features.md | 50 ++++++++++++++
.../examples/ml/JavaChiSqSelectorExample.java | 71 ++++++++++++++++++++
.../examples/ml/ChiSqSelectorExample.scala | 57 ++++++++++++++++
3 files changed, 178 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/e76431f8/docs/ml-features.md
----------------------------------------------------------------------
diff --git a/docs/ml-features.md b/docs/ml-features.md
index cd1838d..5f88877 100644
--- a/docs/ml-features.md
+++ b/docs/ml-features.md
@@ -1949,3 +1949,53 @@ output.select("features", "label").show()
{% endhighlight %}
</div>
</div>
+
+## ChiSqSelector
+
+`ChiSqSelector` stands for Chi-Squared feature selection. It operates on labeled data with
+categorical features. ChiSqSelector orders features based on a
+[Chi-Squared test of independence](https://en.wikipedia.org/wiki/Chi-squared_test)
+from the class, and then filters (selects) the top features which the class label depends on the
+most. This is akin to yielding the features with the most predictive power.
+
+**Examples**
+
+Assume that we have a DataFrame with the columns `id`, `features`, and `clicked`, which is used as
+our target to be predicted:
+
+~~~
+id | features | clicked
+---|-----------------------|---------
+ 7 | [0.0, 0.0, 18.0, 1.0] | 1.0
+ 8 | [0.0, 1.0, 12.0, 0.0] | 0.0
+ 9 | [1.0, 0.0, 15.0, 0.1] | 0.0
+~~~
+
+If we use `ChiSqSelector` with a `numTopFeatures = 1`, then according to our label `clicked` the
+last column in our `features` chosen as the most useful feature:
+
+~~~
+id | features | clicked | selectedFeatures
+---|-----------------------|---------|------------------
+ 7 | [0.0, 0.0, 18.0, 1.0] | 1.0 | [1.0]
+ 8 | [0.0, 1.0, 12.0, 0.0] | 0.0 | [0.0]
+ 9 | [1.0, 0.0, 15.0, 0.1] | 0.0 | [0.1]
+~~~
+
+<div class="codetabs">
+<div data-lang="scala" markdown="1">
+
+Refer to the [ChiSqSelector Scala docs](api/scala/index.html#org.apache.spark.ml.feature.ChiSqSelector)
+for more details on the API.
+
+{% include_example scala/org/apache/spark/examples/ml/ChiSqSelectorExample.scala %}
+</div>
+
+<div data-lang="java" markdown="1">
+
+Refer to the [ChiSqSelector Java docs](api/java/org/apache/spark/ml/feature/ChiSqSelector.html)
+for more details on the API.
+
+{% include_example java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java %}
+</div>
+</div>
http://git-wip-us.apache.org/repos/asf/spark/blob/e76431f8/examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java
----------------------------------------------------------------------
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java
new file mode 100644
index 0000000..ede05d6
--- /dev/null
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.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.SparkConf;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SQLContext;
+
+// $example on$
+import java.util.Arrays;
+
+import org.apache.spark.ml.feature.ChiSqSelector;
+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.Metadata;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+// $example off$
+
+public class JavaChiSqSelectorExample {
+ public static void main(String[] args) {
+ SparkConf conf = new SparkConf().setAppName("JavaChiSqSelectorExample");
+ JavaSparkContext jsc = new JavaSparkContext(conf);
+ SQLContext sqlContext = new SQLContext(jsc);
+
+ // $example on$
+ JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList(
+ RowFactory.create(7, Vectors.dense(0.0, 0.0, 18.0, 1.0), 1.0),
+ RowFactory.create(8, Vectors.dense(0.0, 1.0, 12.0, 0.0), 0.0),
+ RowFactory.create(9, Vectors.dense(1.0, 0.0, 15.0, 0.1), 0.0)
+ ));
+ StructType schema = new StructType(new StructField[]{
+ new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
+ new StructField("features", new VectorUDT(), false, Metadata.empty()),
+ new StructField("clicked", DataTypes.DoubleType, false, Metadata.empty())
+ });
+
+ DataFrame df = sqlContext.createDataFrame(jrdd, schema);
+
+ ChiSqSelector selector = new ChiSqSelector()
+ .setNumTopFeatures(1)
+ .setFeaturesCol("features")
+ .setLabelCol("clicked")
+ .setOutputCol("selectedFeatures");
+
+ DataFrame result = selector.fit(df).transform(df);
+ result.show();
+ // $example off$
+ jsc.stop();
+ }
+}
http://git-wip-us.apache.org/repos/asf/spark/blob/e76431f8/examples/src/main/scala/org/apache/spark/examples/ml/ChiSqSelectorExample.scala
----------------------------------------------------------------------
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/ChiSqSelectorExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/ChiSqSelectorExample.scala
new file mode 100644
index 0000000..a8d2bc4
--- /dev/null
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/ChiSqSelectorExample.scala
@@ -0,0 +1,57 @@
+/*
+ * 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.ChiSqSelector
+import org.apache.spark.mllib.linalg.Vectors
+// $example off$
+import org.apache.spark.sql.SQLContext
+import org.apache.spark.{SparkConf, SparkContext}
+
+object ChiSqSelectorExample {
+ def main(args: Array[String]) {
+ val conf = new SparkConf().setAppName("ChiSqSelectorExample")
+ val sc = new SparkContext(conf)
+
+ val sqlContext = SQLContext.getOrCreate(sc)
+ import sqlContext.implicits._
+
+ // $example on$
+ val data = Seq(
+ (7, Vectors.dense(0.0, 0.0, 18.0, 1.0), 1.0),
+ (8, Vectors.dense(0.0, 1.0, 12.0, 0.0), 0.0),
+ (9, Vectors.dense(1.0, 0.0, 15.0, 0.1), 0.0)
+ )
+
+ val df = sc.parallelize(data).toDF("id", "features", "clicked")
+
+ val selector = new ChiSqSelector()
+ .setNumTopFeatures(1)
+ .setFeaturesCol("features")
+ .setLabelCol("clicked")
+ .setOutputCol("selectedFeatures")
+
+ val result = selector.fit(df).transform(df)
+ result.show()
+ // $example off$
+ sc.stop()
+ }
+}
+// scalastyle:on println
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org