diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 5cc8b63cdfad..f37777e13ee1 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -1988,10 +1988,11 @@ def toPandas(self): if self.sql_ctx.getConf("spark.sql.execution.arrow.enabled", "false").lower() == "true": try: from pyspark.sql.types import _check_dataframe_convert_date, \ - _check_dataframe_localize_timestamps + _check_dataframe_localize_timestamps, to_arrow_schema from pyspark.sql.utils import require_minimum_pyarrow_version - import pyarrow require_minimum_pyarrow_version() + import pyarrow + to_arrow_schema(self.schema) tables = self._collectAsArrow() if tables: table = pyarrow.concat_tables(tables) @@ -2000,10 +2001,12 @@ def toPandas(self): return _check_dataframe_localize_timestamps(pdf, timezone) else: return pd.DataFrame.from_records([], columns=self.columns) - except ImportError as e: - msg = "note: pyarrow must be installed and available on calling Python process " \ - "if using spark.sql.execution.arrow.enabled=true" - raise ImportError("%s\n%s" % (_exception_message(e), msg)) + except Exception as e: + msg = ( + "Note: toPandas attempted Arrow optimization because " + "'spark.sql.execution.arrow.enabled' is set to true. Please set it to false " + "to disable this.") + raise RuntimeError("%s\n%s" % (_exception_message(e), msg)) else: pdf = pd.DataFrame.from_records(self.collect(), columns=self.columns) diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index 2af218a69102..19653072ea31 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -3497,7 +3497,14 @@ def test_unsupported_datatype(self): schema = StructType([StructField("map", MapType(StringType(), IntegerType()), True)]) df = self.spark.createDataFrame([(None,)], schema=schema) with QuietTest(self.sc): - with self.assertRaisesRegexp(Exception, 'Unsupported data type'): + with self.assertRaisesRegexp(Exception, 'Unsupported type'): + df.toPandas() + + df = self.spark.createDataFrame([(None,)], schema="a binary") + with QuietTest(self.sc): + with self.assertRaisesRegexp( + Exception, + 'Unsupported type.*\nNote: toPandas attempted Arrow optimization because'): df.toPandas() def test_null_conversion(self):