ueshin commented on a change in pull request #34040:
URL: https://github.com/apache/spark/pull/34040#discussion_r712527043
##########
File path: python/pyspark/pandas/tests/test_dataframe.py
##########
@@ -1954,6 +1954,41 @@ def test_isin(self):
with self.assertRaisesRegex(TypeError, msg):
psdf.isin(1)
+ pdf = pd.DataFrame(
+ {
+ "a": [4, 2, 3, 4, 8, 6],
+ "b": [1, None, 9, 4, None, 4],
+ "c": [None, 5, None, 3, 2, 1],
+ },
+ )
+ psdf = ps.from_pandas(pdf)
+
+ if LooseVersion(pd.__version__) >= LooseVersion("1.2"):
+ self.assert_eq(psdf.isin([4, 3, 1, 1, None]), pdf.isin([4, 3, 1,
1, None]))
+ else:
+ expected = pd.DataFrame(
+ {
+ "a": [True, False, True, True, False, False],
+ "b": [True, True, False, True, True, True],
+ "c": [True, False, True, True, False, True],
+ }
+ )
+ self.assert_eq(psdf.isin([4, 3, 1, 1, None]), expected)
+
+ if LooseVersion(pd.__version__) >= LooseVersion("1.2"):
+ self.assert_eq(
+ psdf.isin({"b": [4, 3, 1, 1, None]}), pdf.isin({"b": [4, 3, 1,
1, None]})
+ )
+ else:
+ expected = pd.DataFrame(
+ {
+ "a": [False, False, False, False, False, False],
+ "b": [True, True, False, True, True, True],
+ "c": [False, False, False, False, False, False],
+ }
+ )
+ self.assert_eq(psdf.isin([4, 3, 1, 1, None]), expected)
Review comment:
I guess you meant:
```suggestion
self.assert_eq(psdf.isin({"b": [4, 3, 1, 1, None]}), expected)
```
##########
File path: python/pyspark/pandas/tests/test_dataframe.py
##########
@@ -1954,6 +1954,41 @@ def test_isin(self):
with self.assertRaisesRegex(TypeError, msg):
psdf.isin(1)
+ pdf = pd.DataFrame(
+ {
+ "a": [4, 2, 3, 4, 8, 6],
+ "b": [1, None, 9, 4, None, 4],
+ "c": [None, 5, None, 3, 2, 1],
+ },
+ )
+ psdf = ps.from_pandas(pdf)
+
+ if LooseVersion(pd.__version__) >= LooseVersion("1.2"):
+ self.assert_eq(psdf.isin([4, 3, 1, 1, None]), pdf.isin([4, 3, 1,
1, None]))
+ else:
+ expected = pd.DataFrame(
+ {
+ "a": [True, False, True, True, False, False],
+ "b": [True, True, False, True, True, True],
+ "c": [True, False, True, True, False, True],
Review comment:
This fails with pandas <1.2.
Should be:
```suggestion
"a": [True, False, True, True, False, False],
"b": [True, False, False, True, False, True],
"c": [False, False, False, True, False, True],
```
?
##########
File path: python/pyspark/pandas/tests/test_dataframe.py
##########
@@ -1954,6 +1954,41 @@ def test_isin(self):
with self.assertRaisesRegex(TypeError, msg):
psdf.isin(1)
+ pdf = pd.DataFrame(
+ {
+ "a": [4, 2, 3, 4, 8, 6],
+ "b": [1, None, 9, 4, None, 4],
+ "c": [None, 5, None, 3, 2, 1],
+ },
+ )
+ psdf = ps.from_pandas(pdf)
+
+ if LooseVersion(pd.__version__) >= LooseVersion("1.2"):
+ self.assert_eq(psdf.isin([4, 3, 1, 1, None]), pdf.isin([4, 3, 1,
1, None]))
+ else:
+ expected = pd.DataFrame(
+ {
+ "a": [True, False, True, True, False, False],
+ "b": [True, True, False, True, True, True],
+ "c": [True, False, True, True, False, True],
+ }
+ )
+ self.assert_eq(psdf.isin([4, 3, 1, 1, None]), expected)
+
+ if LooseVersion(pd.__version__) >= LooseVersion("1.2"):
+ self.assert_eq(
+ psdf.isin({"b": [4, 3, 1, 1, None]}), pdf.isin({"b": [4, 3, 1,
1, None]})
+ )
+ else:
+ expected = pd.DataFrame(
+ {
+ "a": [False, False, False, False, False, False],
+ "b": [True, True, False, True, True, True],
+ "c": [False, False, False, False, False, False],
Review comment:
And the result should be:
```suggestion
"a": [False, False, False, False, False, False],
"b": [True, False, False, True, False, True],
"c": [False, False, False, False, False, False],
```
--
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]
