83 lines
3.1 KiB
Python
83 lines
3.1 KiB
Python
|
# -*- coding: UTF-8 -*-
|
|||
|
|
"""
|
|||
|
|
@Project -> File ：IoD_data_analysis_tool -> pd_util
|
|||
|
|
@IDE ：PyCharm
|
|||
|
|
@Author ：rengengchen
|
|||
|
|
@Date ：2022/7/13 11:00
|
|||
|
|
@Desc ：
|
|||
|
|
"""
|
|||
|
|
from __future__ import annotations
|
|||
|
|
|
|||
|
|
import os
|
|||
|
|
from functools import partial
|
|||
|
|
from multiprocessing import Pool
|
|||
|
|
from typing import Hashable, Callable
|
|||
|
|
|
|||
|
|
import pandas as pd
|
|||
|
|
from pandas._typing import CompressionOptions, FilePath, StorageOptions, WriteBuffer
|
|||
|
|
from pandas.core.generic import bool_t
|
|||
|
|
|
|||
|
|
|
|||
|
|
class to_same_csv:
|
|||
|
|
|
|||
|
|
def __init__(self,
|
|||
|
|
path_or_buf: FilePath | WriteBuffer[bytes] | WriteBuffer[str] | None = None,
|
|||
|
|
sep: str = ",",
|
|||
|
|
na_rep: str = "",
|
|||
|
|
float_format: str | None = None,
|
|||
|
|
columns: pd.Sequence[Hashable] | None = None,
|
|||
|
|
header: bool_t | list[str] = True,
|
|||
|
|
index: bool_t = False,
|
|||
|
|
index_label: pd.IndexLabel | None = None,
|
|||
|
|
mode: str = "w",
|
|||
|
|
encoding: str = 'utf8',
|
|||
|
|
compression: CompressionOptions = "infer",
|
|||
|
|
quoting: int | None = None,
|
|||
|
|
quotechar: str = '"',
|
|||
|
|
line_terminator: str | None = None,
|
|||
|
|
chunksize: int | None = None,
|
|||
|
|
date_format: str | None = None,
|
|||
|
|
doublequote: bool_t = True,
|
|||
|
|
escapechar: str | None = None,
|
|||
|
|
decimal: str = ".",
|
|||
|
|
errors: str = "strict",
|
|||
|
|
storage_options: StorageOptions = None,
|
|||
|
|
prepare: Callable = None):
|
|||
|
|
self.not_first = False
|
|||
|
|
self.mode = mode
|
|||
|
|
if self.mode == 'a' and isinstance(path_or_buf, str) and os.path.exists(path_or_buf):
|
|||
|
|
header = False
|
|||
|
|
self.header = header
|
|||
|
|
self.prepare = prepare
|
|||
|
|
self.kwargs = {'path_or_buf': path_or_buf,
|
|||
|
|
'sep': sep,
|
|||
|
|
'na_rep': na_rep,
|
|||
|
|
'float_format': float_format,
|
|||
|
|
'columns': columns,
|
|||
|
|
'index': index,
|
|||
|
|
'index_label': index_label,
|
|||
|
|
'encoding': encoding,
|
|||
|
|
'compression': compression,
|
|||
|
|
'quoting': quoting,
|
|||
|
|
'quotechar': quotechar,
|
|||
|
|
'line_terminator': line_terminator,
|
|||
|
|
'chunksize': chunksize,
|
|||
|
|
'date_format': date_format,
|
|||
|
|
'doublequote': doublequote,
|
|||
|
|
'escapechar': escapechar,
|
|||
|
|
'decimal': decimal,
|
|||
|
|
'errors': errors,
|
|||
|
|
'storage_options': storage_options}
|
|||
|
|
|
|||
|
|
def __call__(self, df_or_series: pd.Series | pd.DataFrame):
|
|||
|
|
if self.not_first:
|
|||
|
|
df_or_series.to_csv(mode=self.mode, header=self.header, **self.kwargs)
|
|||
|
|
else:
|
|||
|
|
if self.prepare:
|
|||
|
|
result = self.prepare(df_or_series)
|
|||
|
|
if result:
|
|||
|
|
df_or_series = result
|
|||
|
|
df_or_series.to_csv(mode=self.mode, header=self.header, **self.kwargs)
|
|||
|
|
self.mode = 'a'
|
|||
|
|
self.header = False
|