This is an automated email from the ASF dual-hosted git repository.
gurwls223 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 2b07d778620 [SPARK-46076][PYTHON][TESTS] Remove `unittest` deprecated
alias usage for Python 3.12
2b07d778620 is described below
commit 2b07d778620841fbd27f5bfdd10bed61a61ff2e1
Author: Dongjoon Hyun <dh...@apple.com>
AuthorDate: Fri Nov 24 08:17:35 2023 +0900
[SPARK-46076][PYTHON][TESTS] Remove `unittest` deprecated alias usage for
Python 3.12
### What changes were proposed in this pull request?
This PR aims to remove `unittest` alias usage for Python 3.12.
Currently, it fails like the following.
- https://github.com/apache/spark/actions/runs/6971394284/job/18971420822
```
======================================================================
ERROR [0.554s]: test_find_spark_home
(pyspark.tests.test_util.UtilTests.test_find_spark_home)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/__w/spark/spark/python/pyspark/tests/test_util.py", line 83, in
test_find_spark_home
self.assertEquals(origin, _find_spark_home())
^^^^^^^^^^^^^^^^^
AttributeError: 'UtilTests' object has no attribute 'assertEquals'. Did you
mean: 'assertEqual'?
```
### Why are the changes needed?
Python 3.12 removes the following deprecated aliases.
- https://docs.python.org/3/whatsnew/3.12.html#id3
<img width="802" alt="Screenshot 2023-11-23 at 12 52 33 PM"
src="https://github.com/apache/spark/assets/9700541/0158c1a4-fcfc-4a02-85c5-7fcbd6c6a034";>
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Pass the CIs with Python 3.9.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #43986 from dongjoon-hyun/SPARK-46076.
Authored-by: Dongjoon Hyun <dh...@apple.com>
Signed-off-by: Hyukjin Kwon <gurwls...@apache.org>
---
python/pyspark/ml/tests/test_linalg.py | 2 +-
python/pyspark/pandas/tests/indexes/test_base.py | 6 ++---
.../pyspark/pandas/tests/indexes/test_category.py | 4 +--
.../pyspark/pandas/tests/indexes/test_datetime.py | 4 +--
.../pyspark/pandas/tests/indexes/test_timedelta.py | 4 +--
.../sql/tests/connect/test_connect_basic.py | 6 ++---
.../sql/tests/connect/test_connect_column.py | 2 +-
python/pyspark/sql/tests/pandas/test_pandas_map.py | 2 +-
.../sql/tests/pandas/test_pandas_udf_scalar.py | 12 ++++-----
.../pyspark/sql/tests/streaming/test_streaming.py | 2 +-
.../sql/tests/streaming/test_streaming_listener.py | 20 +++++++--------
python/pyspark/sql/tests/test_arrow.py | 2 +-
python/pyspark/sql/tests/test_arrow_python_udf.py | 30 +++++++++++-----------
python/pyspark/sql/tests/test_functions.py | 2 +-
python/pyspark/sql/tests/test_udf.py | 20 +++++++--------
python/pyspark/sql/tests/test_utils.py | 4 +--
python/pyspark/tests/test_util.py | 2 +-
17 files changed, 61 insertions(+), 63 deletions(-)
diff --git a/python/pyspark/ml/tests/test_linalg.py
b/python/pyspark/ml/tests/test_linalg.py
index 66ba373b12f..08fa529087f 100644
--- a/python/pyspark/ml/tests/test_linalg.py
+++ b/python/pyspark/ml/tests/test_linalg.py
@@ -362,7 +362,7 @@ class VectorUDTTests(MLlibTestCase):
Row(v2=unwrapped_vec(1, None, None, [1.0, 2.0, 3.0])),
Row(v2=unwrapped_vec(0, 3, [1, 2], [1.0, 5.5])),
]
- self.assertEquals(results, expected)
+ self.assertEqual(results, expected)
class MatrixUDTTests(MLlibTestCase):
diff --git a/python/pyspark/pandas/tests/indexes/test_base.py
b/python/pyspark/pandas/tests/indexes/test_base.py
index e84ab60f121..79570440c79 100644
--- a/python/pyspark/pandas/tests/indexes/test_base.py
+++ b/python/pyspark/pandas/tests/indexes/test_base.py
@@ -62,11 +62,11 @@ class IndexesTestsMixin:
self.assert_eq(psdf.index.dtype, pdf.index.dtype)
self.assert_eq(ps.Index([])._summary(), "Index: 0 entries")
- with self.assertRaisesRegexp(ValueError, "The truth value of a Index
is ambiguous."):
+ with self.assertRaisesRegex(ValueError, "The truth value of a Index is
ambiguous."):
bool(ps.Index([1]))
- with self.assertRaisesRegexp(TypeError, "Index.name must be a hashable
type"):
+ with self.assertRaisesRegex(TypeError, "Index.name must be a hashable
type"):
ps.Index([1, 2, 3], name=[(1, 2, 3)])
- with self.assertRaisesRegexp(TypeError, "Index.name must be a hashable
type"):
+ with self.assertRaisesRegex(TypeError, "Index.name must be a hashable
type"):
ps.Index([1.0, 2.0, 3.0], name=[(1, 2, 3)])
def test_index_from_series(self):
diff --git a/python/pyspark/pandas/tests/indexes/test_category.py
b/python/pyspark/pandas/tests/indexes/test_category.py
index 0cd89711bee..761e1100d8a 100644
--- a/python/pyspark/pandas/tests/indexes/test_category.py
+++ b/python/pyspark/pandas/tests/indexes/test_category.py
@@ -68,9 +68,9 @@ class CategoricalIndexTestsMixin:
self.assert_eq(psidx.codes, pd.Index(pidx.codes))
self.assert_eq(psidx.ordered, pidx.ordered)
- with self.assertRaisesRegexp(TypeError, "Index.name must be a hashable
type"):
+ with self.assertRaisesRegex(TypeError, "Index.name must be a hashable
type"):
ps.CategoricalIndex([1, 2, 3], name=[(1, 2, 3)])
- with self.assertRaisesRegexp(
+ with self.assertRaisesRegex(
TypeError, "Cannot perform 'all' with this index type:
CategoricalIndex"
):
ps.CategoricalIndex([1, 2, 3]).all()
diff --git a/python/pyspark/pandas/tests/indexes/test_datetime.py
b/python/pyspark/pandas/tests/indexes/test_datetime.py
index d89e448dd4f..92f60762307 100644
--- a/python/pyspark/pandas/tests/indexes/test_datetime.py
+++ b/python/pyspark/pandas/tests/indexes/test_datetime.py
@@ -64,9 +64,9 @@ class DatetimeIndexTestsMixin:
self.assertRaises(ValueError, lambda: f(freq="N"))
def test_datetime_index(self):
- with self.assertRaisesRegexp(TypeError, "Index.name must be a hashable
type"):
+ with self.assertRaisesRegex(TypeError, "Index.name must be a hashable
type"):
ps.DatetimeIndex(["2004-01-01", "2002-12-31", "2000-04-01"],
name=[(1, 2)])
- with self.assertRaisesRegexp(
+ with self.assertRaisesRegex(
TypeError, "Cannot perform 'all' with this index type:
DatetimeIndex"
):
ps.DatetimeIndex(["2004-01-01", "2002-12-31", "2000-04-01"]).all()
diff --git a/python/pyspark/pandas/tests/indexes/test_timedelta.py
b/python/pyspark/pandas/tests/indexes/test_timedelta.py
index 6bab794f3ab..46b30d9b460 100644
--- a/python/pyspark/pandas/tests/indexes/test_timedelta.py
+++ b/python/pyspark/pandas/tests/indexes/test_timedelta.py
@@ -90,9 +90,9 @@ class TimedeltaIndexTestsMixin:
)
# ps.TimedeltaIndex(ps.Index([1, 2, 3]))
- with self.assertRaisesRegexp(TypeError, "Index.name must be a hashable
type"):
+ with self.assertRaisesRegex(TypeError, "Index.name must be a hashable
type"):
ps.TimedeltaIndex([timedelta(1), timedelta(microseconds=2)],
name=[(1, 2)])
- with self.assertRaisesRegexp(
+ with self.assertRaisesRegex(
TypeError, "Cannot perform 'all' with this index type:
TimedeltaIndex"
):
psidx.all()
diff --git a/python/pyspark/sql/tests/connect/test_connect_basic.py
b/python/pyspark/sql/tests/connect/test_connect_basic.py
index d4fb2d92fbb..856bcbead19 100755
--- a/python/pyspark/sql/tests/connect/test_connect_basic.py
+++ b/python/pyspark/sql/tests/connect/test_connect_basic.py
@@ -1824,7 +1824,7 @@ class SparkConnectBasicTests(SparkConnectSQLTestCase):
self.assert_eq(cdf, df)
- self.assertEquals(cobservation.get, observation.get)
+ self.assertEqual(cobservation.get, observation.get)
observed_metrics = cdf.attrs["observed_metrics"]
self.assert_eq(len(observed_metrics), 1)
@@ -3449,11 +3449,11 @@ class SparkConnectSessionTests(ReusedConnectTestCase):
self.assertIsNotNone(self.spark._client)
# Creates a new remote session.
other =
PySparkSession.builder.remote("sc://other.remote:114/").create()
- self.assertNotEquals(self.spark, other)
+ self.assertNotEqual(self.spark, other)
# Gets currently active session.
same =
PySparkSession.builder.remote("sc://other.remote.host:114/").getOrCreate()
- self.assertEquals(other, same)
+ self.assertEqual(other, same)
same.release_session_on_close = False # avoid sending release to
dummy connection
same.stop()
diff --git a/python/pyspark/sql/tests/connect/test_connect_column.py
b/python/pyspark/sql/tests/connect/test_connect_column.py
index d838260a26f..f9a9fa95a37 100644
--- a/python/pyspark/sql/tests/connect/test_connect_column.py
+++ b/python/pyspark/sql/tests/connect/test_connect_column.py
@@ -379,7 +379,7 @@ class SparkConnectColumnTests(SparkConnectSQLTestCase):
self.assertEqual(len(pdf.index), 4)
res = pd.DataFrame(data={"id": [0, 30, 60, 90]})
- self.assert_(pdf.equals(res), f"{pdf.to_string()} !=
{res.to_string()}")
+ self.assertTrue(pdf.equals(res), f"{pdf.to_string()} !=
{res.to_string()}")
def test_literal_with_acceptable_type(self):
for value, dataType in [
diff --git a/python/pyspark/sql/tests/pandas/test_pandas_map.py
b/python/pyspark/sql/tests/pandas/test_pandas_map.py
index fb2f9214c5d..304b78049b2 100644
--- a/python/pyspark/sql/tests/pandas/test_pandas_map.py
+++ b/python/pyspark/sql/tests/pandas/test_pandas_map.py
@@ -394,7 +394,7 @@ class MapInPandasTestsMixin:
for offheap in ["true", "false"]:
with self.sql_conf({"spark.sql.columnVector.offheap.enabled":
offheap}):
- self.assertEquals(
+ self.assertEqual(
self.spark.read.parquet(path).mapInPandas(func, "id
long").head(), Row(0)
)
finally:
diff --git a/python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py
b/python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py
index d37e6b0130f..dfbab5c8b3c 100644
--- a/python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py
+++ b/python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py
@@ -181,7 +181,7 @@ class ScalarPandasUDFTestsMixin:
mirror = pandas_udf(lambda s: s, df.dtypes[0][1])
- self.assertEquals(
+ self.assertEqual(
df.select(mirror(df.struct).alias("res")).first(),
Row(
res=Row(
@@ -194,13 +194,13 @@ class ScalarPandasUDFTestsMixin:
df = self.df_with_nested_maps
str_repr = pandas_udf(lambda s: s.astype(str), StringType())
- self.assertEquals(
+ self.assertEqual(
df.select(str_repr(df.attributes).alias("res")).first(),
Row(res="{'personal': {'name': 'John', 'city': 'New York'}}"),
)
extract_name = pandas_udf(lambda s: s.apply(lambda x:
x["personal"]["name"]), StringType())
- self.assertEquals(
+ self.assertEqual(
df.select(extract_name(df.attributes).alias("res")).first(),
Row(res="John"),
)
@@ -209,7 +209,7 @@ class ScalarPandasUDFTestsMixin:
df = self.df_with_nested_arrays
str_repr = pandas_udf(lambda s: s.astype(str), StringType())
- self.assertEquals(
+ self.assertEqual(
df.select(str_repr(df.nested_array).alias("res")).first(),
Row(res="[array([1, 2, 3], dtype=int32) array([4, 5],
dtype=int32)]"),
)
@@ -1450,9 +1450,7 @@ class ScalarPandasUDFTestsMixin:
for offheap in ["true", "false"]:
with self.sql_conf({"spark.sql.columnVector.offheap.enabled":
offheap}):
- self.assertEquals(
-
self.spark.read.parquet(path).select(udf("id")).head(), Row(0)
- )
+
self.assertEqual(self.spark.read.parquet(path).select(udf("id")).head(), Row(0))
finally:
shutil.rmtree(path)
diff --git a/python/pyspark/sql/tests/streaming/test_streaming.py
b/python/pyspark/sql/tests/streaming/test_streaming.py
index b51b058ca97..a905a87a3b4 100644
--- a/python/pyspark/sql/tests/streaming/test_streaming.py
+++ b/python/pyspark/sql/tests/streaming/test_streaming.py
@@ -36,7 +36,7 @@ class StreamingTestsMixin:
.start()
)
try:
- self.assertEquals(query.name,
"test_streaming_query_functions_basic")
+ self.assertEqual(query.name,
"test_streaming_query_functions_basic")
self.assertTrue(isinstance(query.id, str))
self.assertTrue(isinstance(query.runId, str))
self.assertTrue(query.isActive)
diff --git a/python/pyspark/sql/tests/streaming/test_streaming_listener.py
b/python/pyspark/sql/tests/streaming/test_streaming_listener.py
index b2200efb0e7..243ad2dca07 100644
--- a/python/pyspark/sql/tests/streaming/test_streaming_listener.py
+++ b/python/pyspark/sql/tests/streaming/test_streaming_listener.py
@@ -58,19 +58,19 @@ class StreamingListenerTestsMixin:
if exception:
self.assertTrue(exception in event.exception)
else:
- self.assertEquals(event.exception, None)
+ self.assertEqual(event.exception, None)
if error_class:
self.assertTrue(error_class in event.errorClassOnException)
else:
- self.assertEquals(event.errorClassOnException, None)
+ self.assertEqual(event.errorClassOnException, None)
def check_streaming_query_progress(self, progress):
"""Check StreamingQueryProgress"""
self.assertTrue(isinstance(progress, StreamingQueryProgress))
self.assertTrue(isinstance(progress.id, uuid.UUID))
self.assertTrue(isinstance(progress.runId, uuid.UUID))
- self.assertEquals(progress.name, "test")
+ self.assertEqual(progress.name, "test")
try:
json.loads(progress.json)
except Exception:
@@ -208,41 +208,41 @@ class StreamingListenerTests(StreamingListenerTestsMixin,
ReusedSQLTestCase):
).getMethods()
)
- self.assertEquals(
+ self.assertEqual(
get_number_of_public_methods(
"org.apache.spark.sql.streaming.StreamingQueryListener$QueryStartedEvent"
),
15,
msg,
)
- self.assertEquals(
+ self.assertEqual(
get_number_of_public_methods(
"org.apache.spark.sql.streaming.StreamingQueryListener$QueryProgressEvent"
),
12,
msg,
)
- self.assertEquals(
+ self.assertEqual(
get_number_of_public_methods(
"org.apache.spark.sql.streaming.StreamingQueryListener$QueryTerminatedEvent"
),
15,
msg,
)
- self.assertEquals(
+ self.assertEqual(
get_number_of_public_methods("org.apache.spark.sql.streaming.StreamingQueryProgress"),
38,
msg,
)
- self.assertEquals(
+ self.assertEqual(
get_number_of_public_methods("org.apache.spark.sql.streaming.StateOperatorProgress"),
27,
msg,
)
- self.assertEquals(
+ self.assertEqual(
get_number_of_public_methods("org.apache.spark.sql.streaming.SourceProgress"),
21, msg
)
- self.assertEquals(
+ self.assertEqual(
get_number_of_public_methods("org.apache.spark.sql.streaming.SinkProgress"),
19, msg
)
diff --git a/python/pyspark/sql/tests/test_arrow.py
b/python/pyspark/sql/tests/test_arrow.py
index 28244b14385..fc979c9e8b7 100644
--- a/python/pyspark/sql/tests/test_arrow.py
+++ b/python/pyspark/sql/tests/test_arrow.py
@@ -877,7 +877,7 @@ class ArrowTestsMixin:
}
):
if arrow_enabled and struct_in_pandas == "legacy":
- with self.assertRaisesRegexp(
+ with self.assertRaisesRegex(
UnsupportedOperationException,
"DUPLICATED_FIELD_NAME_IN_ARROW_STRUCT"
):
df.toPandas()
diff --git a/python/pyspark/sql/tests/test_arrow_python_udf.py
b/python/pyspark/sql/tests/test_arrow_python_udf.py
index f48f07666e1..f853b15ce6f 100644
--- a/python/pyspark/sql/tests/test_arrow_python_udf.py
+++ b/python/pyspark/sql/tests/test_arrow_python_udf.py
@@ -59,9 +59,9 @@ class PythonUDFArrowTestsMixin(BaseUDFTestsMixin):
.first()
)
- self.assertEquals(row[0], "[1, 2, 3]")
- self.assertEquals(row[1], "{'a': 'b'}")
- self.assertEquals(row[2], "Row(col1=1, col2=2)")
+ self.assertEqual(row[0], "[1, 2, 3]")
+ self.assertEqual(row[1], "{'a': 'b'}")
+ self.assertEqual(row[2], "Row(col1=1, col2=2)")
def test_use_arrow(self):
# useArrow=True
@@ -88,7 +88,7 @@ class PythonUDFArrowTestsMixin(BaseUDFTestsMixin):
.first()
)
- self.assertEquals(row_true[0], row_none[0]) # "[1, 2, 3]"
+ self.assertEqual(row_true[0], row_none[0]) # "[1, 2, 3]"
# useArrow=False
row_false = (
@@ -101,13 +101,13 @@ class PythonUDFArrowTestsMixin(BaseUDFTestsMixin):
)
.first()
)
- self.assertEquals(row_false[0], "[1, 2, 3]")
+ self.assertEqual(row_false[0], "[1, 2, 3]")
def test_eval_type(self):
- self.assertEquals(
+ self.assertEqual(
udf(lambda x: str(x), useArrow=True).evalType,
PythonEvalType.SQL_ARROW_BATCHED_UDF
)
- self.assertEquals(
+ self.assertEqual(
udf(lambda x: str(x), useArrow=False).evalType,
PythonEvalType.SQL_BATCHED_UDF
)
@@ -118,7 +118,7 @@ class PythonUDFArrowTestsMixin(BaseUDFTestsMixin):
str_repr_func = self.spark.udf.register("str_repr", udf(lambda x:
str(x), useArrow=True))
# To verify that Arrow optimization is on
- self.assertEquals(
+ self.assertEqual(
df.selectExpr("str_repr(array) AS str_id").first()[0],
"[1, 2, 3]", # The input is a NumPy array when the Arrow
optimization is on
)
@@ -131,7 +131,7 @@ class PythonUDFArrowTestsMixin(BaseUDFTestsMixin):
def test_nested_array_input(self):
df = self.spark.range(1).selectExpr("array(array(1, 2), array(3, 4))
as nested_array")
- self.assertEquals(
+ self.assertEqual(
df.select(
udf(lambda x: str(x), returnType="string",
useArrow=True)("nested_array")
).first()[0],
@@ -148,8 +148,8 @@ class PythonUDFArrowTestsMixin(BaseUDFTestsMixin):
for ddl_type in int_ddl_types:
# df_int_value
res = df_int_value.select(udf(lambda x: x,
ddl_type)("value").alias("res"))
- self.assertEquals(res.collect(), [Row(res=1), Row(res=2)])
- self.assertEquals(res.dtypes[0][1], ddl_type)
+ self.assertEqual(res.collect(), [Row(res=1), Row(res=2)])
+ self.assertEqual(res.dtypes[0][1], ddl_type)
floating_results = [
[Row(res=1.1), Row(res=2.2)],
@@ -158,12 +158,12 @@ class PythonUDFArrowTestsMixin(BaseUDFTestsMixin):
for ddl_type, floating_res in zip(floating_ddl_types,
floating_results):
# df_int_value
res = df_int_value.select(udf(lambda x: x,
ddl_type)("value").alias("res"))
- self.assertEquals(res.collect(), [Row(res=1.0), Row(res=2.0)])
- self.assertEquals(res.dtypes[0][1], ddl_type)
+ self.assertEqual(res.collect(), [Row(res=1.0), Row(res=2.0)])
+ self.assertEqual(res.dtypes[0][1], ddl_type)
# df_floating_value
res = df_floating_value.select(udf(lambda x: x,
ddl_type)("value").alias("res"))
- self.assertEquals(res.collect(), floating_res)
- self.assertEquals(res.dtypes[0][1], ddl_type)
+ self.assertEqual(res.collect(), floating_res)
+ self.assertEqual(res.dtypes[0][1], ddl_type)
# invalid
with self.assertRaises(PythonException):
diff --git a/python/pyspark/sql/tests/test_functions.py
b/python/pyspark/sql/tests/test_functions.py
index b04127b3d5c..7d8acbb2b18 100644
--- a/python/pyspark/sql/tests/test_functions.py
+++ b/python/pyspark/sql/tests/test_functions.py
@@ -903,7 +903,7 @@ class FunctionsTestsMixin:
(3, "c"),
]
- self.assertEquals(actual, expected)
+ self.assertEqual(actual, expected)
def test_window_functions(self):
df = self.spark.createDataFrame([(1, "1"), (2, "2"), (1, "2"), (1,
"2")], ["key", "value"])
diff --git a/python/pyspark/sql/tests/test_udf.py
b/python/pyspark/sql/tests/test_udf.py
index 8b82f591ffc..b070124cb45 100644
--- a/python/pyspark/sql/tests/test_udf.py
+++ b/python/pyspark/sql/tests/test_udf.py
@@ -825,7 +825,7 @@ class BaseUDFTestsMixin(object):
for offheap in ["true", "false"]:
with self.sql_conf({"spark.sql.columnVector.offheap.enabled":
offheap}):
- self.assertEquals(
+ self.assertEqual(
self.spark.read.parquet(path).select(fUdf("id")).head(), Row(0)
)
finally:
@@ -843,12 +843,12 @@ class BaseUDFTestsMixin(object):
)
# Input
row = df.select(udf(lambda x: str(x))("nested_struct")).first()
- self.assertEquals(
+ self.assertEqual(
row[0], "Row(col1=1, col2=Row(col1='John', col2=30,
col3=Row(col1='value', col2=10)))"
)
# Output
row = df.select(udf(lambda x: x,
returnType=df.dtypes[0][1])("nested_struct")).first()
- self.assertEquals(
+ self.assertEqual(
row[0], Row(col1=1, col2=Row(col1="John", col2=30,
col3=Row(col1="value", col2=10)))
)
@@ -856,7 +856,7 @@ class BaseUDFTestsMixin(object):
df = self.spark.range(1).selectExpr("map('a', map('b', 'c')) as
nested_map")
# Input
row = df.select(udf(lambda x: str(x))("nested_map")).first()
- self.assertEquals(row[0], "{'a': {'b': 'c'}}")
+ self.assertEqual(row[0], "{'a': {'b': 'c'}}")
# Output
@udf(returnType=df.dtypes[0][1])
@@ -865,13 +865,13 @@ class BaseUDFTestsMixin(object):
return x
row = df.select(f("nested_map")).first()
- self.assertEquals(row[0], {"a": {"b": "d"}})
+ self.assertEqual(row[0], {"a": {"b": "d"}})
def test_nested_array(self):
df = self.spark.range(1).selectExpr("array(array(1, 2), array(3, 4))
as nested_array")
# Input
row = df.select(udf(lambda x: str(x))("nested_array")).first()
- self.assertEquals(row[0], "[[1, 2], [3, 4]]")
+ self.assertEqual(row[0], "[[1, 2], [3, 4]]")
# Output
@udf(returnType=df.dtypes[0][1])
@@ -880,7 +880,7 @@ class BaseUDFTestsMixin(object):
return x
row = df.select(f("nested_array")).first()
- self.assertEquals(row[0], [[1, 2], [3, 4], [4, 5]])
+ self.assertEqual(row[0], [[1, 2], [3, 4], [4, 5]])
def test_complex_return_types(self):
row = (
@@ -894,9 +894,9 @@ class BaseUDFTestsMixin(object):
.first()
)
- self.assertEquals(row[0], [1, 2, 3])
- self.assertEquals(row[1], {"a": "b"})
- self.assertEquals(row[2], Row(col1=1, col2=2))
+ self.assertEqual(row[0], [1, 2, 3])
+ self.assertEqual(row[1], {"a": "b"})
+ self.assertEqual(row[2], Row(col1=1, col2=2))
def test_named_arguments(self):
@udf("int")
diff --git a/python/pyspark/sql/tests/test_utils.py
b/python/pyspark/sql/tests/test_utils.py
index ccfadf0b8db..b99ca41e84f 100644
--- a/python/pyspark/sql/tests/test_utils.py
+++ b/python/pyspark/sql/tests/test_utils.py
@@ -1747,8 +1747,8 @@ class UtilsTests(ReusedSQLTestCase, UtilsTestsMixin):
try:
self.spark.sql("""SELECT a""")
except AnalysisException as e:
- self.assertEquals(e.getErrorClass(),
"UNRESOLVED_COLUMN.WITHOUT_SUGGESTION")
- self.assertEquals(e.getSqlState(), "42703")
+ self.assertEqual(e.getErrorClass(),
"UNRESOLVED_COLUMN.WITHOUT_SUGGESTION")
+ self.assertEqual(e.getSqlState(), "42703")
if __name__ == "__main__":
diff --git a/python/pyspark/tests/test_util.py
b/python/pyspark/tests/test_util.py
index 26dc3db74de..af104d683aa 100644
--- a/python/pyspark/tests/test_util.py
+++ b/python/pyspark/tests/test_util.py
@@ -80,7 +80,7 @@ class UtilTests(PySparkTestCase):
origin = os.environ["SPARK_HOME"]
try:
del os.environ["SPARK_HOME"]
- self.assertEquals(origin, _find_spark_home())
+ self.assertEqual(origin, _find_spark_home())
finally:
os.environ["SPARK_HOME"] = origin
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
