zhengruifeng commented on code in PR #42956:
URL: https://github.com/apache/spark/pull/42956#discussion_r1328212481
##########
python/pyspark/pandas/tests/connect/test_parity_internal.py:
##########
@@ -15,18 +15,86 @@
# limitations under the License.
#
import unittest
+import pandas as pd
from pyspark.pandas.tests.test_internal import InternalFrameTestsMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
+from pyspark.pandas.internal import (
+ InternalFrame,
+ SPARK_DEFAULT_INDEX_NAME,
+ SPARK_INDEX_NAME_FORMAT,
+)
+from pyspark.pandas.utils import spark_column_equals
class InternalFrameParityTests(
InternalFrameTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
):
- @unittest.skip("TODO(SPARK-43654): Enable
InternalFrameParityTests.test_from_pandas.")
def test_from_pandas(self):
- super().test_from_pandas()
+ pdf = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
Review Comment:
Instead of compare the columns, what about simplify the tests by comparing
the column string representations?
Otherwise, you may have to add `__eq__` for Column and all the Expressions
in Connect, but I am not sure whether it works in case 'resolved column' vs
'unresolved column'
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
