You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by xi...@apache.org on 2023/07/17 18:43:23 UTC
[spark] branch master updated: [SPARK-44446][PYTHON] Add checks for expected list type special cases
This is an automated email from the ASF dual-hosted git repository.
xinrong 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 e578d466d4e [SPARK-44446][PYTHON] Add checks for expected list type special cases
e578d466d4e is described below
commit e578d466d4eae808a8ad5e42681b9e3e87fe6ca7
Author: Amanda Liu <am...@databricks.com>
AuthorDate: Mon Jul 17 11:43:05 2023 -0700
[SPARK-44446][PYTHON] Add checks for expected list type special cases
### What changes were proposed in this pull request?
This PR adds handling for special cases when `expected` is type list.
### Why are the changes needed?
The change is needed to handle all cases for when `expected` is type list.
### Does this PR introduce _any_ user-facing change?
Yes, the PR makes modifications to the user-facing function `assertDataFrameEqual`
### How was this patch tested?
Added tests to `runtime/python/pyspark/sql/tests/test_utils.py` and `runtime/python/pyspark/sql/tests/connect/test_utils.py`
Closes #42023 from asl3/fix-list-support.
Authored-by: Amanda Liu <am...@databricks.com>
Signed-off-by: Xinrong Meng <xi...@apache.org>
---
python/pyspark/sql/tests/test_utils.py | 24 ++++++++++++++++++++++++
python/pyspark/testing/utils.py | 15 +++++++++++++--
2 files changed, 37 insertions(+), 2 deletions(-)
diff --git a/python/pyspark/sql/tests/test_utils.py b/python/pyspark/sql/tests/test_utils.py
index 5b859ad15a5..eae3f528504 100644
--- a/python/pyspark/sql/tests/test_utils.py
+++ b/python/pyspark/sql/tests/test_utils.py
@@ -1119,6 +1119,30 @@ class UtilsTestsMixin:
assertDataFrameEqual(df1, df2, checkRowOrder=False)
assertDataFrameEqual(df1, df2, checkRowOrder=True)
+ def test_empty_expected_list(self):
+ df1 = self.spark.range(0, 10).drop("id")
+
+ df2 = []
+
+ assertDataFrameEqual(df1, df2, checkRowOrder=False)
+ assertDataFrameEqual(df1, df2, checkRowOrder=True)
+
+ def test_no_column_expected_list(self):
+ df1 = self.spark.range(0, 10).limit(0)
+
+ df2 = []
+
+ assertDataFrameEqual(df1, df2, checkRowOrder=False)
+ assertDataFrameEqual(df1, df2, checkRowOrder=True)
+
+ def test_empty_no_column_expected_list(self):
+ df1 = self.spark.range(0, 10).drop("id").limit(0)
+
+ df2 = []
+
+ assertDataFrameEqual(df1, df2, checkRowOrder=False)
+ assertDataFrameEqual(df1, df2, checkRowOrder=True)
+
def test_special_vals(self):
df1 = self.spark.createDataFrame(
data=[
diff --git a/python/pyspark/testing/utils.py b/python/pyspark/testing/utils.py
index 21c7b7e4dcd..14db9264209 100644
--- a/python/pyspark/testing/utils.py
+++ b/python/pyspark/testing/utils.py
@@ -349,6 +349,8 @@ def assertDataFrameEqual(
For checkRowOrder, note that PySpark DataFrame ordering is non-deterministic, unless
explicitly sorted.
+ Note that schema equality is checked only when `expected` is a DataFrame (not a list of Rows).
+
For DataFrames with float values, assertDataFrame asserts approximate equality.
Two float values a and b are approximately equal if the following equation is True:
@@ -362,6 +364,9 @@ def assertDataFrameEqual(
>>> df1 = spark.createDataFrame(data=[("1", 0.1), ("2", 3.23)], schema=["id", "amount"])
>>> df2 = spark.createDataFrame(data=[("1", 0.109), ("2", 3.23)], schema=["id", "amount"])
>>> assertDataFrameEqual(df1, df2, rtol=1e-1) # pass, DataFrames are approx equal by rtol
+ >>> df1 = spark.createDataFrame(data=[(1, 1000), (2, 3000)], schema=["id", "amount"])
+ >>> list_of_rows = [Row(1, 1000), Row(2, 3000)]
+ >>> assertDataFrameEqual(df1, list_of_rows) # pass, actual and expected are equal
>>> df1 = spark.createDataFrame(
... data=[("1", 1000.00), ("2", 3000.00), ("3", 2000.00)], schema=["id", "amount"])
>>> df2 = spark.createDataFrame(
@@ -415,8 +420,14 @@ def assertDataFrameEqual(
)
# special cases: empty datasets, datasets with 0 columns
- if (actual.first() is None and expected.first() is None) or (
- len(actual.columns) == 0 and len(expected.columns) == 0
+ if (
+ isinstance(expected, DataFrame)
+ and (
+ (actual.first() is None and expected.first() is None)
+ or (len(actual.columns) == 0 and len(expected.columns) == 0)
+ )
+ or isinstance(expected, list)
+ and ((actual.first() is None or len(actual.columns) == 0) and len(expected) == 0)
):
return True
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org