Github user yanboliang commented on a diff in the pull request:
https://github.com/apache/spark/pull/13461#discussion_r65666682
--- Diff:
examples/src/main/scala/org/apache/spark/examples/ml/UnaryTransformerExample.scala
---
@@ -0,0 +1,119 @@
+/*
+ * 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.
+ */
+
+// scalastyle:off println
+package org.apache.spark.examples.ml
+
+// $example on$
+import java.io.File
+
+import org.apache.spark.ml.UnaryTransformer
+import org.apache.spark.ml.param.DoubleParam
+import org.apache.spark.ml.util.{DefaultParamsReadable,
DefaultParamsWritable, Identifiable}
+import org.apache.spark.sql.functions.col
+// $example off$
+import org.apache.spark.sql.SparkSession
+// $example on$
+import org.apache.spark.sql.types.{DataType, DataTypes}
+import org.apache.spark.util.Utils
+// $example off$
+
+/**
+ * An example demonstrating creating a custom
[[org.apache.spark.ml.Transformer]] using
+ * the [[UnaryTransformer]] abstraction.
+ *
+ * Run with
+ * {{{
+ * bin/run-example ml.UnaryTransformerExample
+ * }}}
+ */
+object UnaryTransformerExample {
+
+ // $example on$
+ /**
+ * Simple Transformer which adds a constant value to input Doubles.
+ *
+ * [[UnaryTransformer]] handles schema validation and other elements
required by Pipelines.
+ * It also defines parameters for specifying input and output columns:
+ * [[UnaryTransformer.inputCol]] and [[UnaryTransformer.outputCol]].
+ *
+ * [[DefaultParamsWritable]] provides a default implementation for
persisting instances
+ * of this Transformer.
+ */
+ class MyTransformer(override val uid: String)
+ extends UnaryTransformer[Double, Double, MyTransformer] with
DefaultParamsWritable {
+
+ final val shift: DoubleParam = new DoubleParam(this, "shift", "Value
added to input")
+
+ def getShift: Double = $(shift)
+
+ def setShift(value: Double): this.type = set(shift, value)
+
+ def this() = this(Identifiable.randomUID("myT"))
+
+ override protected def createTransformFunc: Double => Double = (input:
Double) => {
+ input + $(shift)
+ }
+
+ override protected def outputDataType: DataType = DataTypes.DoubleType
+ }
--- End diff --
Minor: It's better we can implement ```validateInputType``` since the
default one do nothing and will not handles schema validation which is
mentioned in the annotation of this class.
---
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]
