Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/5699#discussion_r29373343
--- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
---
@@ -0,0 +1,82 @@
+/*
+ * 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 org.apache.spark.annotation.AlphaComponent
+import org.apache.spark.ml.Transformer
+import org.apache.spark.ml.attribute.BinaryAttribute
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util.SchemaUtils
+import org.apache.spark.sql._
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.types.{DoubleType, StructType}
+
+/**
+ * :: AlphaComponent ::
+ * Binarize a column of continuous features given a threshold.
+ */
+@AlphaComponent
+final class Binarizer extends Transformer with HasInputCol with
HasOutputCol {
+
+ /**
+ * Param for threshold used to binarize continuous features.
+ * The features greater than the threshold, will be binarized to 1.0.
+ * The features equal to or less than the threshold, will be binarized
to 0.0.
+ * @group param
+ */
+ val threshold: DoubleParam =
+ new DoubleParam(this, "threshold", "threshold used to binarize
continuous features")
+
+ /** @group getParam */
+ def getThreshold: Double = getOrDefault(threshold)
+
+ /** @group setParam */
+ def setThreshold(value: Double): this.type = set(threshold, value)
+
+ setDefault(threshold -> 0.0)
+
+ /** @group setParam */
+ def setInputCol(value: String): this.type = set(inputCol, value)
+
+ /** @group setParam */
+ def setOutputCol(value: String): this.type = set(outputCol, value)
+
+ override def transform(dataset: DataFrame, paramMap: ParamMap):
DataFrame = {
+ transformSchema(dataset.schema, paramMap, logging = true)
+ val map = extractParamMap(paramMap)
+ val td = map(threshold)
+ val binarizer = udf { in: Double => if (in > td) 1.0 else 0.0 }
+ dataset.withColumn(map(outputCol), binarizer(col(map(inputCol))))
--- End diff --
Need to add Attribute. See:
https://github.com/apache/spark/blob/master/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala#L129
---
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]
