Github user hhbyyh commented on a diff in the pull request:
https://github.com/apache/spark/pull/7084#discussion_r33902864
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala ---
@@ -0,0 +1,79 @@
+/*
+ * 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
+
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.ml.UnaryTransformer
+import org.apache.spark.ml.param.{ParamMap, ParamValidators, IntParam}
+import org.apache.spark.ml.util.Identifiable
+import org.apache.spark.mllib.linalg.{Vectors, VectorUDT, Vector}
+import org.apache.spark.sql.types.{StringType, ArrayType, DataType}
+
+/**
+ * :: Experimental ::
+ * Converts a text document to a sparse vector of token counts.
+ * @param vocabulary An Array over terms. Only the terms in the vocabulary
will be counted.
+ */
+@Experimental
+class CountVectorizer (override val uid: String, vocabulary: Array[String])
+ extends UnaryTransformer[Seq[String], Vector, CountVectorizer] {
+
+ def this(vocabulary: Array[String]) =
this(Identifiable.randomUID("countVectorizer"), vocabulary)
+
+ /**
+ * Corpus-specific stop words filter. Terms with count less than the
given threshold are ignored.
+ * Default: 1
+ * @group param
+ */
+ val minTermCounts: IntParam = new IntParam(this, "minTermCounts",
--- End diff --
Thanks for the careful consideration.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
