diff --git a/python/pyspark/ml/pipeline.py b/python/pyspark/ml/pipeline.py index 5233c5801e2e680e84cec8bf6833145591ee7d79..83880a5afcd1d9954a1d5cf254fa7f44720c7b06 100644 --- a/python/pyspark/ml/pipeline.py +++ b/python/pyspark/ml/pipeline.py @@ -39,7 +39,7 @@ class Estimator(Params): Fits a model to the input dataset with optional parameters. :param dataset: input dataset, which is an instance of - :py:class:`pyspark.sql.SchemaRDD` + :py:class:`pyspark.sql.DataFrame` :param params: an optional param map that overwrites embedded params :returns: fitted model @@ -62,7 +62,7 @@ class Transformer(Params): Transforms the input dataset with optional parameters. :param dataset: input dataset, which is an instance of - :py:class:`pyspark.sql.SchemaRDD` + :py:class:`pyspark.sql.DataFrame` :param params: an optional param map that overwrites embedded params :returns: transformed dataset diff --git a/python/pyspark/ml/wrapper.py b/python/pyspark/ml/wrapper.py index 4bae96f6783884c4688d22738b31da0c9c44c1ec..31a66b3d2f7305f32e00997d850f23ded9da74f4 100644 --- a/python/pyspark/ml/wrapper.py +++ b/python/pyspark/ml/wrapper.py @@ -102,7 +102,7 @@ class JavaEstimator(Estimator, JavaWrapper): """ Fits a Java model to the input dataset. :param dataset: input dataset, which is an instance of - :py:class:`pyspark.sql.SchemaRDD` + :py:class:`pyspark.sql.DataFrame` :param params: additional params (overwriting embedded values) :return: fitted Java model """ diff --git a/repl/scala-2.11/src/test/scala/org/apache/spark/repl/ReplSuite.scala b/repl/scala-2.11/src/test/scala/org/apache/spark/repl/ReplSuite.scala index f966f25c5a14ce1c6b13f316d7a2a4be77d97748..ed9b207a86a0bb767d2ce2c581e7b610cccd487d 100644 --- a/repl/scala-2.11/src/test/scala/org/apache/spark/repl/ReplSuite.scala +++ b/repl/scala-2.11/src/test/scala/org/apache/spark/repl/ReplSuite.scala @@ -263,14 +263,14 @@ class ReplSuite extends FunSuite { assertDoesNotContain("Exception", output) } - test("SPARK-2576 importing SQLContext.createSchemaRDD.") { + test("SPARK-2576 importing SQLContext.createDataFrame.") { // We need to use local-cluster to test this case. val output = runInterpreter("local-cluster[1,1,512]", """ |val sqlContext = new org.apache.spark.sql.SQLContext(sc) - |import sqlContext.createSchemaRDD + |import sqlContext.implicits._ |case class TestCaseClass(value: Int) - |sc.parallelize(1 to 10).map(x => TestCaseClass(x)).toSchemaRDD.collect + |sc.parallelize(1 to 10).map(x => TestCaseClass(x)).toDF.collect """.stripMargin) assertDoesNotContain("error:", output) assertDoesNotContain("Exception", output)