[GitHub] [spark] viirya commented on a change in pull request #27895: [SPARK-31138][ML] Add ANOVA Selector for continuous features and categorical labels

[GitBox <gi...@apache.org>]

viirya commented on a change in pull request #27895: [SPARK-31138][ML] Add ANOVA Selector for continuous features and categorical labels
URL: https://github.com/apache/spark/pull/27895#discussion_r392729458
 
 

 ##########
 File path: mllib/src/main/scala/org/apache/spark/ml/feature/ANOVASelector.scala
 ##########
 @@ -0,0 +1,314 @@
+/*
+ * 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.ml.feature
+
+import scala.collection.mutable.ArrayBuilder
+
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.annotation.Since
+import org.apache.spark.ml._
+import org.apache.spark.ml.attribute._
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.stat.{ANOVATest, SelectionTestResult}
+import org.apache.spark.ml.util._
+import org.apache.spark.sql._
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.types.{DoubleType, StructField, StructType}
+
+
+/**
+ * ANOVA F-value Classification selector, which selects continuous features to use for predicting a
+ * categorical label.
+ * The selector supports different selection methods: `numTopFeatures`, `percentile`, `fpr`,
+ * `fdr`, `fwe`.
+ *  - `numTopFeatures` chooses a fixed number of top features according to a F value classification
+ *     test.
+ *  - `percentile` is similar but chooses a fraction of all features instead of a fixed number.
+ *  - `fpr` chooses all features whose p-value are below a threshold, thus controlling the false
+ *    positive rate of selection.
+ *  - `fdr` uses the [Benjamini-Hochberg procedure]
+ *    (https://en.wikipedia.org/wiki/False_discovery_rate#Benjamini.E2.80.93Hochberg_procedure)
+ *    to choose all features whose false discovery rate is below a threshold.
+ *  - `fwe` chooses all features whose p-values are below a threshold. The threshold is scaled by
+ *    1/numFeatures, thus controlling the family-wise error rate of selection.
+ * By default, the selection method is `numTopFeatures`, with the default number of top features
+ * set to 50.
+ */
+@Since("3.1.0")
+final class ANOVASelector @Since("3.1.0")(@Since("3.1.0") override val uid: String)
+  extends Estimator[ANOVASelectorModel] with FValueSelectorParams
+    with DefaultParamsWritable {
+
+  @Since("3.1.0")
+  def this() = this(Identifiable.randomUID("ANOVASelector"))
+
+  /** @group setParam */
+  @Since("3.1.0")
+  def setNumTopFeatures(value: Int): this.type = set(numTopFeatures, value)
+
+  /** @group setParam */
+  @Since("3.1.0")
+  def setPercentile(value: Double): this.type = set(percentile, value)
+
+  /** @group setParam */
+  @Since("3.1.0")
+  def setFpr(value: Double): this.type = set(fpr, value)
+
+  /** @group setParam */
+  @Since("3.1.0")
+  def setFdr(value: Double): this.type = set(fdr, value)
+
+  /** @group setParam */
+  @Since("3.1.0")
+  def setFwe(value: Double): this.type = set(fwe, value)
+
+  /** @group setParam */
+  @Since("3.1.0")
+  def setSelectorType(value: String): this.type = set(selectorType, value)
+
+  /** @group setParam */
+  @Since("3.1.0")
+  def setFeaturesCol(value: String): this.type = set(featuresCol, value)
+
+  /** @group setParam */
+  @Since("3.1.0")
+  def setOutputCol(value: String): this.type = set(outputCol, value)
+
+  /** @group setParam */
+  @Since("3.1.0")
+  def setLabelCol(value: String): this.type = set(labelCol, value)
+
+  @Since("3.1.0")
+  override def fit(dataset: Dataset[_]): ANOVASelectorModel = {
+    transformSchema(dataset.schema, logging = true)
+    dataset.select(col($(labelCol)).cast(DoubleType), col($(featuresCol))).rdd.map {
+      case Row(label: Double, features: Vector) =>
+        LabeledPoint(label, features)
+    }
 
 Review comment:
   I saw you did wrapping in `testClassification`, why you did here too?

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org