itholic commented on code in PR #37768:
URL: https://github.com/apache/spark/pull/37768#discussion_r962549104
##########
python/pyspark/pandas/tests/test_dataframe.py:
##########
@@ -343,6 +343,80 @@ def test_creation_index(self):
data=ps.DataFrame([1, 2]),
index=ps.MultiIndex.from_tuples([(1, 3), (2, 4)])
)
+ def test_creation_index_same_anchor(self):
+ pdf = pd.DataFrame(
+ {
+ "a": [1, 2, None, 4],
+ "b": [1, None, None, 4],
+ "c": [1, 2, None, None],
+ "d": [None, 2, None, 4],
+ }
+ )
+ psdf = ps.from_pandas(pdf)
+
+ self.assert_eq(
+ ps.DataFrame(data=psdf, index=psdf.index),
+ pd.DataFrame(data=pdf, index=pdf.index),
+ )
+ self.assert_eq(
+ ps.DataFrame(data=psdf + 1, index=psdf.index),
+ pd.DataFrame(data=pdf + 1, index=pdf.index),
+ )
+ self.assert_eq(
+ ps.DataFrame(data=psdf[["a", "c"]] * 2, index=psdf.index),
+ pd.DataFrame(data=pdf[["a", "c"]] * 2, index=pdf.index),
+ )
+
+ # test String Index
+ pdf = pd.DataFrame(
+ data={"s": ["Hello", "World", "Databricks"], "x": [2002, 2003,
2004], "y": [4, 5, 6]}
+ )
+ pdf = pdf.set_index("s")
+ pdf.index.name = None
+ psdf = ps.from_pandas(pdf)
+
+ self.assert_eq(
+ ps.DataFrame(data=psdf, index=psdf.index),
+ pd.DataFrame(data=pdf, index=pdf.index),
+ )
+ self.assert_eq(
+ ps.DataFrame(data=psdf + 1, index=psdf.index),
+ pd.DataFrame(data=pdf + 1, index=pdf.index),
+ )
+ self.assert_eq(
+ ps.DataFrame(data=psdf[["y"]] * 2, index=psdf.index),
+ pd.DataFrame(data=pdf[["y"]] * 2, index=pdf.index),
+ )
+
+ # test DatetimeIndex
+ pdf = pd.DataFrame(
+ data={
+ "t": [
+ datetime(2022, 9, 1, 0, 0, 0, 0),
+ datetime(2022, 9, 2, 0, 0, 0, 0),
+ datetime(2022, 9, 3, 0, 0, 0, 0),
+ ],
+ "x": [2002, 2003, 2004],
+ "y": [4, 5, 6],
+ }
+ )
+ pdf = pdf.set_index("t")
+ pdf.index.name = None
+ psdf = ps.from_pandas(pdf)
+
+ self.assert_eq(
+ ps.DataFrame(data=psdf, index=psdf.index),
+ pd.DataFrame(data=pdf, index=pdf.index),
+ )
+ self.assert_eq(
+ ps.DataFrame(data=psdf + 1, index=psdf.index),
+ pd.DataFrame(data=pdf + 1, index=pdf.index),
+ )
+ self.assert_eq(
+ ps.DataFrame(data=psdf[["y"]] * 2, index=psdf.index),
+ pd.DataFrame(data=pdf[["y"]] * 2, index=pdf.index),
+ )
Review Comment:
Can we test it with the `MultiIndex` and other index types such as
`CategoricalIndex` and `TimedeltaIndex` ?
--
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]
