Github user hhbyyh commented on a diff in the pull request:
https://github.com/apache/spark/pull/17583#discussion_r121183230
--- Diff: mllib/src/main/scala/org/apache/spark/ml/FuncTransformer.scala ---
@@ -0,0 +1,113 @@
+/*
+ * 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
+
+import java.io.{ByteArrayInputStream, ByteArrayOutputStream,
ObjectInputStream, ObjectOutputStream}
+
+import scala.reflect.runtime.universe.{typeOf, TypeTag}
+
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.annotation.{DeveloperApi, Since}
+import org.apache.spark.ml.FuncTransformer.FuncTransformerWriter
+import org.apache.spark.ml.util._
+import org.apache.spark.sql.Row
+import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
+import org.apache.spark.sql.types.DataType
+
+/**
+ * :: DeveloperApi ::
+ * A wrapper to allow easily creation of simple data manipulation for
DataFrame.
+ * Note that FuncTransformer supports serialization via scala
ObjectOutputStream and may not
+ * guarantee save/load compatibility between different scala version.
+ */
+@DeveloperApi
+@Since("2.3.0")
+class FuncTransformer [IN, OUT: TypeTag] @Since("2.3.0") (
+ @Since("2.3.0") override val uid: String,
+ @Since("2.3.0") val func: IN => OUT,
+ @Since("2.3.0") val outputDataType: DataType
+ ) extends UnaryTransformer[IN, OUT, FuncTransformer[IN, OUT]] with
DefaultParamsWritable {
+
+ @Since("2.3.0")
+ def this(fx: IN => OUT, outputDataType: DataType) =
+ this(Identifiable.randomUID("FuncTransformer"), fx, outputDataType)
+
+ @Since("2.3.0")
+ def this(fx: IN => OUT) =
+ this(Identifiable.randomUID("FuncTransformer"), fx,
+
CatalystSqlParser.parseDataType(typeOf[OUT].typeSymbol.name.decodedName.toString))
--- End diff --
Thanks for looking into it. I'll try with more test cases but I know this
will not work in all the cases.
I'm hesitating about whether we should keep the interface, it's really
convenient though. I think maybe adding some check and then throws friendly
exception if the output Type cannot be inferred directly.
I'll send out the unit tests that I already tried.
---
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]
