2a335f2d7d
### What changes were proposed in this pull request? Fixes `mypy` errors and enables `mypy` check for pandas-on-Spark. ### Why are the changes needed? The `mypy` check for pandas-on-Spark was disabled when the initial porting. It should be enabled again; otherwise we will miss type checking errors. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? The enabled `mypy` check and existing unit tests should pass. Closes #32540 from ueshin/issues/SPARK-34941/pandas_mypy. Authored-by: Takuya UESHIN <ueshin@databricks.com> Signed-off-by: Takuya UESHIN <ueshin@databricks.com>
43 lines
1.5 KiB
Python
43 lines
1.5 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 pyspark import SparkContext
|
|
from pyspark.sql.column import Column, _to_java_column, _create_column_from_literal # type: ignore
|
|
|
|
|
|
def repeat(col, n):
|
|
"""
|
|
Repeats a string column n times, and returns it as a new string column.
|
|
"""
|
|
sc = SparkContext._active_spark_context
|
|
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)
|
|
|
|
|
|
def _call_udf(sc, name, *cols):
|
|
return Column(sc._jvm.functions.callUDF(name, _make_arguments(sc, *cols)))
|
|
|
|
|
|
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
|