zhengruifeng commented on code in PR #38016: URL: https://github.com/apache/spark/pull/38016#discussion_r980911416
########## python/pyspark/pandas/tests/indexes/test_base.py: ########## @@ -203,9 +203,35 @@ def test_to_frame(self): # non-string names self.assert_eq(psidx.to_frame(name=[10, 20]), pidx.to_frame(name=[10, 20])) self.assert_eq(psidx.to_frame(name=("x", 10)), pidx.to_frame(name=("x", 10))) - self.assert_eq( - psidx.to_frame(name=[("x", 10), ("y", 20)]), pidx.to_frame(name=[("x", 10), ("y", 20)]) - ) + if LooseVersion(pd.__version__) < LooseVersion("1.5.0"): + self.assert_eq( + psidx.to_frame(name=[("x", 10), ("y", 20)]), + pidx.to_frame(name=[("x", 10), ("y", 20)]), + ) + else: + # Since pandas 1.5.0, the result is changed as below: + # (x, 10) (y, 20) + # b + # 0 4 0 4 + # 1 5 1 5 + # 3 6 3 6 + # 5 3 5 3 + # 6 2 6 2 + # 8 1 8 1 + # 9 0 9 0 + # 0 9 0 + # 0 9 0 + # + # pandas API on Spark doesn't support mixed type for Index, Review Comment: `mixed type` means a `MultiIndex` with different atomic Index type on each level? -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org