有人可以指出我的正确方向来理解在pandas.read_csv期间定义dtype的(似乎)不一致之处吗?
dtype = int#->如果值为空,则会产生错误
dtype = int32,int64和Int64#->未定义
dtype ='Int64'#->正确读取csv文件为int并带有空白值
import pandas as pd; print(pd.__version__)
pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)
MY_DTYPES = {
'date_string': str,
'description': str,
# 'ValueError_Integer_column_has_NA_values': int,
# 'int32_is_not_defined': int32,
# 'int64_is_not_defined': int64,
# 'Int_64_is_not_defined': Int64,
'Int64_with_quote_and_NaN': 'Int64', # !! THIS WORKS !!
'quantity': float,
'total': float}
f = 'dataset.csv'
df = pd.read_csv(f, dtype = MY_DTYPES)
df.head(15)
date_string description Int64_with_quote_and_NaN quantity total
0 201202 "Lorem ips 513 186.0 4.0
1 200909 um dolor 601 502.0 13.0
2 201701 sit NaN 462.0 20.0
3 201401 amet, 513 934.0 206.0
4 201202 consectetur 513 NaN 194.0
5 200710 adipiscing 602 570.0 930.0
6 200501 elit, 513 160.0 NaN
7 200808 sed NaN 508.0 461.0
8 201906 do 513 316.0 3.0
9 201009 eiusmod NaN 994.0 1.0
10 NaN NaN 513 709.0 0.0
11 201905 incididunt 513 318.0 6.0
12 201612 ut 513 NaN 1.0
13 201506 labore 513 901.0 74.0
14 201002 NaN 625 33.0 739.0