Github user feynmanliang commented on a diff in the pull request:
https://github.com/apache/spark/pull/7388#discussion_r34737611
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizerModel.scala ---
@@ -19,45 +19,135 @@ 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}
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared.{HasInputCol, HasOutputCol}
+import org.apache.spark.ml.util.{Identifiable, SchemaUtils}
+import org.apache.spark.ml.{Estimator, Model}
+import org.apache.spark.mllib.linalg.{VectorUDT, Vectors}
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.types._
+import org.apache.spark.sql.DataFrame
+
+/**
+ * Params for [[CountVectorizer]] and [[CountVectorizerModel]].
+ */
+private[feature] trait CountVectorizerParams extends Params with
HasInputCol with HasOutputCol {
+
+ /**
+ * size of the vocabulary.
+ * If using Estimator, CountVectorizer will build a vocabulary that only
consider the top
+ * vocabSize terms ordered by term frequency across the corpus.
+ * Default: 10000
+ * @group param
+ */
+ val vocabSize: IntParam = new IntParam(this, "vocabSize", "size of the
vocabulary")
+
+ /** @group getParam */
+ def getVocabSize: Int = $(vocabSize)
+
+ /** Validates and transforms the input schema. */
+ protected def validateAndTransformSchema(schema: StructType): StructType
= {
+ SchemaUtils.checkColumnType(schema, $(inputCol), new
ArrayType(StringType, true))
+ SchemaUtils.appendColumn(schema, $(outputCol), new VectorUDT)
+ }
+
+ override def validateParams(): Unit = {
+ require($(vocabSize) > 0, s"The vocabulary size (${$(vocabSize)}) must
be above 0.")
+ }
+}
/**
* :: 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.
+ * Extracts a vocabulary from document collections and generates a
CountVectorizerModel.
--- End diff --
"[[CountVectorizerModel]]"
---
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]
