itamarst commented on a change in pull request #7169:
URL: https://github.com/apache/arrow/pull/7169#discussion_r438967894
##########
File path: python/pyarrow/tests/test_pandas.py
##########
@@ -3941,3 +3946,63 @@ def test_metadata_compat_missing_field_name():
result = table.to_pandas()
# on python 3.5 the column order can differ -> adding check_like=True
tm.assert_frame_equal(result, expected, check_like=True)
+
+
+def make_df_with_timestamps():
+ # Some of the milliseconds timestamps deliberately don't fit in the range
+ # that is possible with nanosecond timestamps.
+ df = pd.DataFrame({
+ 'dateTimeMs': [
+ np.datetime64('0001-01-01 00:00', 'ms'),
+ np.datetime64('2012-05-02 12:35', 'ms'),
+ np.datetime64('2012-05-03 15:42', 'ms'),
+ np.datetime64('3000-05-03 15:42', 'ms'),
+ ],
+ 'dateTimeNs': [
+ np.datetime64('1991-01-01 00:00', 'ns'),
+ np.datetime64('2012-05-02 12:35', 'ns'),
+ np.datetime64('2012-05-03 15:42', 'ns'),
+ np.datetime64('2050-05-03 15:42', 'ns'),
+ ],
+ })
+ # Not part of what we're testing, just ensuring that the inputs are what we
+ # expect.
+ assert (df.dateTimeMs.dtype, df.dateTimeNs.dtype) == (
+ # O == object, <M8[ns] == timestamp64[ns]
+ np.dtype("O"), np.dtype("<M8[ns]")
+ )
+ return df
+
+
+@pytest.mark.parquet
+def test_timestamp_as_object_parquet(tempdir):
+ # Timestamps can be stored as Parquet and reloaded into Pandas with no loss
+ # of information if the timestamp_as_object option is True.
+ df = make_df_with_timestamps()
+ table = pa.Table.from_pandas(df)
+ filename = tempdir / "timestamps_from_pandas.parquet"
+ pq.write_table(table, filename, version="2.0")
+ result = pq.read_table(filename)
+ df2 = result.to_pandas(timestamp_as_object=True)
+ tm.assert_frame_equal(df, df2, check_like=True)
Review comment:
Fixed locally, will push with other fixes.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
