This is an automated email from the ASF dual-hosted git repository.
zhengruifeng pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 0993d4345969 [SPARK-57314][PS][TEST] Add tests for Index.equals in
pandas-on-Spark
0993d4345969 is described below
commit 0993d4345969dfe16b334598dc80a452e4a270f7
Author: tonghuaroot (童话) <[email protected]>
AuthorDate: Tue Jun 9 08:54:05 2026 +0800
[SPARK-57314][PS][TEST] Add tests for Index.equals in pandas-on-Spark
### What changes were proposed in this pull request?
This PR adds positive parity tests for `Index.equals` in pandas-on-Spark
(`IndexBasicMixin` in `python/pyspark/pandas/tests/indexes/test_basic.py`).
The tests compare the `True`/`False` result of `Index.equals` against pandas
for single `Index` and `MultiIndex`: equal and unequal element sets,
reordered elements, and the fact that `equals` ignores the index name.
### Why are the changes needed?
`Index.equals` currently has no positive test coverage. The only existing
test exercises the error path when `compute.ops_on_diff_frames` is disabled
and never checks the actual `True`/`False` result, so the common behavior is
untested. These tests close that gap.
### Does this PR introduce _any_ user-facing change?
No. This PR only adds tests.
### How was this patch tested?
Ran the new test against a local SparkSession
(`IndexBasicTests.test_equals`); it passes.
### Was this patch authored or co-authored using generative AI tooling?
Yes, this patch was co-authored with generative AI tooling (Claude,
Anthropic Opus 4.8). The contributor selected the under-tested method,
required that the asserted cases first be verified to match pandas on a
real SparkSession (excluding inputs where pandas-on-Spark intentionally
differs, e.g. NaN comparison under Spark equality), and reviewed the result.
Closes #56362 from tonghuaroot/ps-tests-identical-equals.
Authored-by: tonghuaroot (童话) <[email protected]>
Signed-off-by: Ruifeng Zheng <[email protected]>
---
python/pyspark/pandas/tests/indexes/test_basic.py | 40 +++++++++++++++++++++++
1 file changed, 40 insertions(+)
diff --git a/python/pyspark/pandas/tests/indexes/test_basic.py
b/python/pyspark/pandas/tests/indexes/test_basic.py
index 7255522c6e78..5d8a62fa6a56 100644
--- a/python/pyspark/pandas/tests/indexes/test_basic.py
+++ b/python/pyspark/pandas/tests/indexes/test_basic.py
@@ -22,6 +22,7 @@ import pandas as pd
import pyspark.pandas as ps
from pyspark.loose_version import LooseVersion
+from pyspark.pandas.config import option_context
from pyspark.pandas.exceptions import PandasNotImplementedError
from pyspark.testing.pandasutils import PandasOnSparkTestCase, TestUtils
@@ -193,6 +194,45 @@ class IndexBasicMixin:
self.assertRaises(PandasNotImplementedError, lambda:
psmidx.factorize())
+ def test_equals(self):
+ # Single Index
+ pidx = pd.Index(["a", "b", "c"])
+ psidx = ps.from_pandas(pidx)
+ self.assert_eq(pidx.equals(pidx), psidx.equals(psidx))
+
+ with option_context("compute.ops_on_diff_frames", True):
+ self.assert_eq(
+ pidx.equals(pd.Index(["a", "b", "c"])),
+ psidx.equals(ps.Index(["a", "b", "c"])),
+ )
+ self.assert_eq(
+ pidx.equals(pd.Index(["b", "b", "a"])),
+ psidx.equals(ps.Index(["b", "b", "a"])),
+ )
+ # equals ignores the name (unlike identical)
+ self.assert_eq(
+ pd.Index([1, 2, 3], name="x").equals(pd.Index([1, 2, 3],
name="y")),
+ ps.Index([1, 2, 3], name="x").equals(ps.Index([1, 2, 3],
name="y")),
+ )
+
+ # MultiIndex
+ pmidx = pd.MultiIndex.from_tuples([("a", "x"), ("b", "y"), ("c", "z")])
+ psmidx = ps.from_pandas(pmidx)
+ self.assert_eq(pmidx.equals(pmidx), psmidx.equals(psmidx))
+
+ with option_context("compute.ops_on_diff_frames", True):
+ self.assert_eq(
+ pmidx.equals(pd.MultiIndex.from_tuples([("a", "x"), ("b",
"y"), ("c", "z")])),
+ psmidx.equals(ps.MultiIndex.from_tuples([("a", "x"), ("b",
"y"), ("c", "z")])),
+ )
+ self.assert_eq(
+ pmidx.equals(pd.MultiIndex.from_tuples([("c", "z"), ("b",
"y"), ("a", "x")])),
+ psmidx.equals(ps.MultiIndex.from_tuples([("c", "z"), ("b",
"y"), ("a", "x")])),
+ )
+
+ # Index vs MultiIndex (different type) -> not equal
+ self.assert_eq(pidx.equals(pmidx), psidx.equals(psmidx))
+
class IndexBasicTests(
IndexBasicMixin,
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
