2616d5cc1d
### What changes were proposed in this pull request? Sets up the `mypy` configuration to enable `disallow_untyped_defs` check for pandas APIs on Spark module. ### Why are the changes needed? Currently many functions in the main codes in pandas APIs on Spark module are still missing type annotations and disabled `mypy` check `disallow_untyped_defs`. We should add more type annotations and enable the mypy check. ### Does this PR introduce _any_ user-facing change? Yes. This PR adds more type annotations in pandas APIs on Spark module, which can impact interaction with development tools for users. ### How was this patch tested? The mypy check with a new configuration and existing tests should pass. Closes #32614 from ueshin/issues/SPARK-35465/disallow_untyped_defs. Authored-by: Takuya UESHIN <ueshin@databricks.com> Signed-off-by: Takuya UESHIN <ueshin@databricks.com>
46 lines
1.7 KiB
Python
46 lines
1.7 KiB
Python
#
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
# this work for additional information regarding copyright ownership.
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
# (the "License"); you may not use this file except in compliance with
|
|
# the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
"""
|
|
Additional Spark functions used in pandas-on-Spark.
|
|
"""
|
|
from typing import Union, no_type_check
|
|
|
|
from pyspark import SparkContext
|
|
from pyspark.sql.column import Column, _to_java_column, _create_column_from_literal # type: ignore
|
|
|
|
|
|
def repeat(col: Column, n: Union[int, Column]) -> Column:
|
|
"""
|
|
Repeats a string column n times, and returns it as a new string column.
|
|
"""
|
|
sc = SparkContext._active_spark_context # type: ignore
|
|
n = _to_java_column(n) if isinstance(n, Column) else _create_column_from_literal(n)
|
|
return _call_udf(sc, "repeat", _to_java_column(col), n)
|
|
|
|
|
|
@no_type_check
|
|
def _call_udf(sc, name, *cols):
|
|
return Column(sc._jvm.functions.callUDF(name, _make_arguments(sc, *cols)))
|
|
|
|
|
|
@no_type_check
|
|
def _make_arguments(sc, *cols):
|
|
java_arr = sc._gateway.new_array(sc._jvm.Column, len(cols))
|
|
for i, col in enumerate(cols):
|
|
java_arr[i] = col
|
|
return java_arr
|