Github user liancheng commented on a diff in the pull request:
https://github.com/apache/spark/pull/7465#discussion_r34957816
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/SQLTransformer.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.Experimental
+import org.apache.spark.ml.param.{ParamMap, Param}
+import org.apache.spark.ml.Transformer
+import org.apache.spark.ml.util.Identifiable
+import org.apache.spark.sql.DataFrame
+import org.apache.spark.sql.Row
+import org.apache.spark.sql.types.StructType
+
+/**
+ * :: Experimental ::
+ * Implements the transforms which are defined by SQL statement.
+ * Currently we only support SQL syntax like 'SELECT ... FROM __THIS__'
+ * where '__THIS__' represents the underlying table of the input dataset.
+ */
+@Experimental
+class SQLTransformer (override val uid: String) extends Transformer {
+
+ def this() = this(Identifiable.randomUID("sql"))
+
+ /**
+ * SQL statement parameter. The statement is provided in string form.
+ * @group param
+ */
+ final val statement: Param[String] = new Param[String](this,
"statement", "SQL statement")
+
+ /** @group setParam */
+ def setStatement(value: String): this.type = set(statement, value)
+
+ /** @group getParam */
+ def getStatement(): String = $(statement)
+
+ private val tableIdentifier: String = "__THIS__"
+
+ /**
+ * The output schema of this transformer.
+ * It is only valid after transform function has been called.
+ */
+ private var outputSchema: StructType = null
+
+ override def transform(dataset: DataFrame): DataFrame = {
+ val tableName = uid
+ val realStatement = $(statement).replace(tableIdentifier, tableName)
+ dataset.registerTempTable(tableName)
+ val originalSchema = dataset.schema
+ val additiveDF = dataset.sqlContext.sql(realStatement)
+ val additiveSchema = additiveDF.schema
+ outputSchema = StructType(Array.concat(originalSchema.fields,
additiveSchema.fields))
+ additiveSchema.fieldNames.foreach {
+ case name =>
+ require(!originalSchema.fieldNames.contains(name), s"Output column
$name already exists.")
+ }
+ val rdd = dataset.rdd.zip(additiveDF.rdd).map {
+ case (r1, r2) => Row.merge(r1, r2)
+ }
+ dataset.sqlContext.createDataFrame(rdd, outputSchema)
+ }
+
+ override def transformSchema(schema: StructType): StructType = {
--- End diff --
We probably need an instance of `SQLContext` here to go through the whole
analysis phase to determine the output schema. I think we can construct an
empty `RDD[Row]`, apply the input schema to it to create an empty DataFrame,
and register it as a placeholder temporary table to perform the analysis phase.
---
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]
