python合并多个excel文件（数据超过1000万）再按指定字段拆分

Question

import pandas as pd
zx = pd.ExcelFile(r"C:\Users\W10\Desktop\aaa.xlsx")
data = zx.parse(zx.sheet_names)
data = pd.concat(data)
data.to_csv(r'C:\Users\W10\Desktop\data.csv',index=False)
import pandas as pd
data = pd.read_excel(r"C:\Users\W10\Desktop\aaa.xlsx")
data['条码分配']=pd.to_datetime(data['条码分配']).dt.date
data_excel = []
sheet_name = []
for x in data.groupby('条码分配'):
    data_excel.append(x[1])
    sheet_name.append(x[0])
for i in range(len(sheet_name)):
    data_excel[i].iloc[:,0:9].to_excel(r"C:\Users\W10\Desktop、data\\" + str(sheet_name[i]) + ".xlsx")

刚开始，to_excel无法装下，后来用to_csv,运行后还是报错，请问大神们正确的做法？

Answer 1

C:\newpy\venv\Scripts\python.exe C:/newpy/xin.py
Traceback (most recent call last):
  File "C:\newpy\venv\lib\site-packages\pandas\core\arrays\datetimes.py", line 2085, in objects_to_datetime64ns
    values, tz_parsed = conversion.datetime_to_datetime64(data)
  File "pandas\_libs\tslibs\conversion.pyx", line 350, in pandas._libs.tslibs.conversion.datetime_to_datetime64
TypeError: Unrecognized value type: <class 'str'>

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\newpy\xin.py", line 24, in <module>
    data['条码分配']=pd.to_datetime(data['条码分配']).dt.date
  File "C:\newpy\venv\lib\site-packages\pandas\core\tools\datetimes.py", line 801, in to_datetime
    cache_array = _maybe_cache(arg, format, cache, convert_listlike)
  File "C:\newpy\venv\lib\site-packages\pandas\core\tools\datetimes.py", line 178, in _maybe_cache
    cache_dates = convert_listlike(unique_dates, format)
  File "C:\newpy\venv\lib\site-packages\pandas\core\tools\datetimes.py", line 465, in _convert_listlike_datetimes
    result, tz_parsed = objects_to_datetime64ns(
  File "C:\newpy\venv\lib\site-packages\pandas\core\arrays\datetimes.py", line 2090, in objects_to_datetime64ns
    raise e
  File "C:\newpy\venv\lib\site-packages\pandas\core\arrays\datetimes.py", line 2075, in objects_to_datetime64ns
    result, tz_parsed = tslib.array_to_datetime(
  File "pandas\_libs\tslib.pyx", line 364, in pandas._libs.tslib.array_to_datetime
  File "pandas\_libs\tslib.pyx", line 591, in pandas._libs.tslib.array_to_datetime
  File "pandas\_libs\tslib.pyx", line 726, in pandas._libs.tslib.array_to_datetime_object
  File "pandas\_libs\tslib.pyx", line 717, in pandas._libs.tslib.array_to_datetime_object
  File "pandas\_libs\tslibs\parsing.pyx", line 243, in pandas._libs.tslibs.parsing.parse_datetime_string
  File "C:\newpy\venv\lib\site-packages\dateutil\parser\_parser.py", line 1374, in parse
    return DEFAULTPARSER.parse(timestr, **kwargs)
  File "C:\newpy\venv\lib\site-packages\dateutil\parser\_parser.py", line 649, in parse
    raise ParserError("Unknown string format: %s", timestr)
dateutil.parser._parser.ParserError: Unknown string format:尊享时尚生活馆（齐）