AlenkaF commented on code in PR #14804: URL: https://github.com/apache/arrow/pull/14804#discussion_r1049653747
########## python/pyarrow/interchange/column.py: ########## @@ -0,0 +1,507 @@ +# 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. + +from __future__ import annotations + +import enum +from typing import ( + Any, + Dict, + Iterable, + Optional, + Tuple, +) + +import sys +if sys.version_info >= (3, 8): + from typing import TypedDict +else: + from typing_extensions import TypedDict + +import pyarrow as pa +import pyarrow.compute as pc +from pyarrow.interchange.buffer import _PyArrowBuffer + + +class DtypeKind(enum.IntEnum): + """ + Integer enum for data types. + Attributes + ---------- + INT : int + Matches to signed integer data type. + UINT : int + Matches to unsigned integer data type. + FLOAT : int + Matches to floating point data type. + BOOL : int + Matches to boolean data type. + STRING : int + Matches to string data type (UTF-8 encoded). + DATETIME : int + Matches to datetime data type. + CATEGORICAL : int + Matches to categorical data type. + """ + + INT = 0 + UINT = 1 + FLOAT = 2 + BOOL = 20 + STRING = 21 # UTF-8 + DATETIME = 22 + CATEGORICAL = 23 + + +Dtype = Tuple[DtypeKind, int, str, str] # see Column.dtype + + +_PYARROW_KINDS = { + pa.int8(): (DtypeKind.INT, "c"), + pa.int16(): (DtypeKind.INT, "s"), + pa.int32(): (DtypeKind.INT, "i"), + pa.int64(): (DtypeKind.INT, "l"), + pa.uint8(): (DtypeKind.UINT, "C"), + pa.uint16(): (DtypeKind.UINT, "S"), + pa.uint32(): (DtypeKind.UINT, "I"), + pa.uint64(): (DtypeKind.UINT, "L"), + pa.float16(): (DtypeKind.FLOAT, "e"), + pa.float32(): (DtypeKind.FLOAT, "f"), + pa.float64(): (DtypeKind.FLOAT, "g"), + pa.bool_(): (DtypeKind.BOOL, "b"), + pa.string(): (DtypeKind.STRING, "u"), # utf-8 + pa.large_string(): (DtypeKind.STRING, "U"), Review Comment: Yes https://github.com/apache/arrow/blob/71ca596d233195105466579d138cf61df81a6a89/python/pyarrow/tests/interchange/test_extra.py#L172-L187 but I did have to change the `format_string`: https://github.com/apache/arrow/blob/71ca596d233195105466579d138cf61df81a6a89/python/pyarrow/interchange/column.py#L268-L272 What we talked about and I should note and add to the tests is that when consuming a string array from pandas it will always result in a LargeStringArray due to pandas offset being int64. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
