Github user mateiz commented on a diff in the pull request:
https://github.com/apache/spark/pull/1671#discussion_r15618551
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/feature/text/HashingTF.scala ---
@@ -0,0 +1,61 @@
+/*
+ * 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.text
+
+import scala.collection.mutable
+
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.mllib.linalg.{Vector, Vectors}
+import org.apache.spark.rdd.RDD
+import org.apache.spark.util.Utils
+
+/**
+ * :: Experimental ::
+ * Maps a sequence of terms to their term frequencies using the hashing
trick.
+ *
+ * @param numFeatures number of features (default: 1000000)
+ */
+@Experimental
+class HashingTF(val numFeatures: Int) extends Serializable {
+
+ def this() = this(1000000)
+
+ /**
+ * Returns the index of the input term.
+ */
+ def indexOf(term: Any): Int = Utils.nonNegativeMod(term.##, numFeatures)
+
+ /**
+ * Transforms the input document into a sparse term frequency vector.
+ */
+ def transform(document: Iterable[_]): Vector = {
+ val termFrequencies = mutable.HashMap.empty[Int, Double]
+ document.foreach { term =>
+ val i = indexOf(term)
+ termFrequencies.put(i, termFrequencies.getOrElse(i, 0.0) + 1.0)
+ }
+ Vectors.sparse(numFeatures, termFrequencies.toSeq)
+ }
+
+ /**
+ * Transforms the input document to term frequency vectors.
+ */
+ def transform[D <: Iterable[_]](dataset: RDD[D]): RDD[Vector] = {
+ dataset.map(this.transform)
+ }
--- End diff --
Can you add a Java-friendly version of these tool? This looks like
`scala.Iterable`. For the Java one you will probably have to make it take
`JavaRDD` since we can't have methods that differ on the element type of RDD.
Once you add it, please add a Java test that uses it as well so we make
sure it compiles in Java with no surprises.
---
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.
---
