Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix lack of support for new TimestampNTZType in Spark 3.4 datatypes #1385

Merged
merged 3 commits into from
Oct 19, 2023
Merged

Fix lack of support for new TimestampNTZType in Spark 3.4 datatypes #1385

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
32f8c41
add TimestampNTZType as equivalents and add parameters to test case
filipeo2-mck Oct 18, 2023
9817197
Merge branch 'main' of github.com:unionai-oss/pandera into pyspark_ti…
filipeo2-mck Oct 18, 2023
0dce486
parse version to improve robustness
filipeo2-mck Oct 18, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 12 additions & 3 deletions pandera/engines/pyspark_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,9 @@
import warnings
from typing import Any, Iterable, Union, Optional
import sys
from packaging import version

import pyspark
import pyspark.sql.types as pst

from pandera import dtypes, errors
Expand All @@ -32,6 +34,8 @@
DEFAULT_PYSPARK_PREC = pst.DecimalType().precision
DEFAULT_PYSPARK_SCALE = pst.DecimalType().scale

CURRENT_PYSPARK_VERSION = version.parse(pyspark.__version__)


@immutable(init=True)
class DataType(dtypes.DataType):
Expand Down Expand Up @@ -341,10 +345,15 @@ class Date(DataType, dtypes.Date): # type: ignore
# timestamp
###############################################################################

# Default timestamp equivalents
filipeo2-mck marked this conversation as resolved.
Show resolved Hide resolved
equivalents = ["datetime", "timestamp", "TimestampType", "TimestampType()", pst.TimestampType(), pst.TimestampType] # type: ignore

@Engine.register_dtype(
equivalents=["datetime", "timestamp", "TimestampType", "TimestampType()", pst.TimestampType(), pst.TimestampType], # type: ignore
)
# Include new Spark 3.4 TimestampNTZType as equivalents
if CURRENT_PYSPARK_VERSION >= version.parse("3.4"):
equivalents += ["TimestampNTZType", "TimestampNTZType()", pst.TimestampNTZType, pst.TimestampNTZType()] # type: ignore


@Engine.register_dtype(equivalents=equivalents) # type: ignore
@immutable
class Timestamp(DataType, dtypes.Timestamp): # type: ignore
"""Semantic representation of a :class:`pyspark.sql.types.TimestampType`."""
Expand Down
16 changes: 15 additions & 1 deletion tests/pyspark/test_pyspark_dtypes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
"""Unit tests for pyspark container."""

from typing import Any
import pyspark
import pyspark.sql.types as T
from pyspark.sql import DataFrame

Expand Down Expand Up @@ -239,6 +240,18 @@ def test_pyspark_all_bytetint_types(
class TestAllDatetimeTestClass(BaseClass):
"""This class is to test all the datetime types"""

# Include new Spark 3.4 TimestampNTZType as equivalents
ntz_equivalents = (
[
{"pandera_equivalent": "TimestampNTZType"},
{"pandera_equivalent": "TimestampNTZType()"},
{"pandera_equivalent": T.TimestampNTZType},
{"pandera_equivalent": T.TimestampNTZType()},
]
if pyspark.__version__ >= "3.4"
else []
)

# a map specifying multiple argument sets for a test method
params = {
"test_pyspark_all_date_types": [
Expand All @@ -253,7 +266,8 @@ class TestAllDatetimeTestClass(BaseClass):
{"pandera_equivalent": T.TimestampType()},
{"pandera_equivalent": "datetime"},
{"pandera_equivalent": "timestamp"},
],
]
+ ntz_equivalents,
}

def test_pyspark_all_date_types(
Expand Down