Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/1484#discussion_r23876952
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala ---
@@ -0,0 +1,86 @@
+/*
+ * 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.mllib.feature
+
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.mllib.linalg
+import org.apache.spark.mllib.linalg.{Vectors, Vector}
+import org.apache.spark.mllib.regression.LabeledPoint
+import org.apache.spark.mllib.stat.Statistics
+import org.apache.spark.rdd.RDD
+
+/**
+ * :: Experimental ::
+ * Chi Squared selector model.
+ *
+ * @param indices list of indices to select (filter)
+ */
+@Experimental
+class ChiSqSelectorModel(indices: IndexedSeq[Int]) extends
VectorTransformer {
+ /**
+ * Applies transformation on a vector.
+ *
+ * @param vector vector to be transformed.
+ * @return transformed vector.
+ */
+ override def transform(vector: linalg.Vector): linalg.Vector = {
+ Compress(vector, indices)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Creates a ChiSquared feature selector.
+ */
+@Experimental
+object ChiSqSelector {
--- End diff --
For this one, the static method is convenient. But others may take many
parameters, where a static method becomes hard to maintain. To be consistent
across MLlib, we use this Estimator/Model style. We can also embed statistics
in the model later, which is also helpful.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
