diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 09647ff6d0749f658d5fe8908b49715378617d46..da742d7ce7d1373542bfcce7399a1f62ff99c852 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -722,8 +722,6 @@ class DataFrame(object): [Row(age=5, name=u'Bob')] """ if isinstance(item, basestring): - if item not in self.columns: - raise IndexError("no such column: %s" % item) jc = self._jdf.apply(item) return Column(jc) elif isinstance(item, Column): diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index 9b748101b5e53994ebdbf8b68dd41c025404704f..13cf647b66da8339be9dc1723256e67208623df9 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -770,7 +770,7 @@ class SQLTests(ReusedPySparkTestCase): self.assertTrue(isinstance(df['key'], Column)) self.assertTrue(isinstance(df[0], Column)) self.assertRaises(IndexError, lambda: df[2]) - self.assertRaises(IndexError, lambda: df["bad_key"]) + self.assertRaises(AnalysisException, lambda: df["bad_key"]) self.assertRaises(TypeError, lambda: df[{}]) def test_column_name_with_non_ascii(self): @@ -794,7 +794,9 @@ class SQLTests(ReusedPySparkTestCase): df = self.sc.parallelize([Row(l=[1], r=Row(a=1, b="b"), d={"k": "v"})]).toDF() self.assertEqual(1, df.select(df.l[0]).first()[0]) self.assertEqual(1, df.select(df.r["a"]).first()[0]) + self.assertEqual(1, df.select(df["r.a"]).first()[0]) self.assertEqual("b", df.select(df.r["b"]).first()[0]) + self.assertEqual("b", df.select(df["r.b"]).first()[0]) self.assertEqual("v", df.select(df.d["k"]).first()[0]) def test_infer_long_type(self): diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala index cf75e64e884b4f1df12092809cf3a8036b4f01d3..fd0ead4401193a5297bad56e0b9948a441ad1574 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala @@ -634,6 +634,7 @@ class DataFrame private[sql]( /** * Selects column based on the column name and return it as a [[Column]]. + * Note that the column name can also reference to a nested column like `a.b`. * @group dfops * @since 1.3.0 */ @@ -641,6 +642,7 @@ class DataFrame private[sql]( /** * Selects column based on the column name and return it as a [[Column]]. + * Note that the column name can also reference to a nested column like `a.b`. * @group dfops * @since 1.3.0 */