Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/5500#discussion_r28827831
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala ---
@@ -0,0 +1,109 @@
+/*
+ * 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.UnaryTransformer
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.mllib.linalg.{Vector, Vectors, VectorUDT}
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared.{HasInputCol, HasOutputCol}
+import org.apache.spark.ml.util.SchemaUtils
+import org.apache.spark.sql.types.{DataType, DoubleType, StructType}
+
+/**
+ * A one-hot encoder that maps a column of label indices to a column of
binary vectors, with
+ * at most a single one-value. By default, the binary vector has an
element for each category, so
+ * with 5 categories, an input value of 2.0 would map to an output vector
of
+ * (0.0, 0.0, 1.0, 0.0, 0.0). If includeFirst is set to false, the first
category is omitted, so the
+ * output vector for the previous example would be (0.0, 1.0, 0.0, 0.0)
and an input value
+ * of 0.0 would map to a vector of all zeros. Omitting the first category
enables the vector
+ * columns to be independent.
+ */
+@AlphaComponent
+class OneHotEncoder extends UnaryTransformer[Double, Vector, OneHotEncoder]
+ with HasInputCol with HasOutputCol {
+
+ /**
+ * Whether to include a component in the encoded vectors for the first
category, defaults to true.
+ * @group param
+ */
+ final val includeFirst: Param[Boolean] =
+ new Param[Boolean](this, "includeFirst", "include first category")
+ setDefault(includeFirst -> true)
+
+ /**
+ * The names of the categories. Used to identify them in the attributes
of the output column.
+ * This is a required parameter.
+ * @group param
+ */
+ final val labelNames: Param[Array[String]] =
--- End diff --
Label names should be extracted from the metadata, e.g., generated by
`StringIndexer`.
---
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]
