更新：命令行错误：ValueError：无效的文件路径或缓冲区对象类型：<class 'pandas.core.frame.DataFrame'>

Question

我现在的函数工作如下：即使它执行了正确的解决方案，我的 CMD 行中也出现了一个巨大的错误 https://i.stack.imgur.com/PBTwz.png（ValueError：无效的文件路径或缓冲区对象类型：）。有谁知道为什么我得到这个错误，即使输出执行正确？

import pandas as pd
import numpy as np
import argparse

target_col = "CountryRefs"

sep = ","

input_file = 'Test_set'

def arg_parse():
    parser = argparse.ArgumentParser()
    parser.add_argument("-f", "--input_file", required = True)
    parser.add_argument("-s", "--sep", required=True,)
    parser.add_argument("-t", "--target_col", required=True)
    args=parser.parse_args()
    return vars(args)

def splitter(input_file, target_col, sep, new_col = None, *argv):
    df = pd.read_csv(input_file)
    df[target_col] = df[target_col].str.split(sep)
    exploded = df.explode(target_col)
    exploded[target_col].replace(r'^\s*$', np.nan, regex=True, inplace = True)
    exploded.dropna(subset=[target_col], inplace=True)
    if new_col == None:
        return(pd.DataFrame(exploded[[target_col,*argv]]))
    else:
        exploded[new_col] = exploded[target_col]
        return(pd.DataFrame(exploded[[new_col,*argv]]))

if __name__ == '__main__':
    args = arg_parse()
    print(splitter(**args))

Answer 1

你想要这样的东西

import pandas as pd
import numpy as np
import argparse


target_col = "CountryRefs"

sep = ","

data = {'CountryRefs':['Italy, Germany', 'Japan , France', '', 'Alaska'],
    'Authors':['Dom', 'Xavier', 'Kathleen', 'Joe'], 'Friends':['Amy Pete', 'Joe', None, 'Franklin'],
    'Colors':['red.blue', ' ', 'yellow', 'black.blue']}
df = pd.DataFrame(data, columns = ['CountryRefs', 'Authors', 'Friends', 'Colors'])

def arg_parse():
    parser = argparse.ArgumentParser()
    parser.add_argument('argv', type=str, nargs='*', default=[])
    parser.add_argument("-s", "--sep", dest="sep", required=True, default=',')
    parser.add_argument("-t", "--target_col", dest="target_col", required=True, default='1')

    args=parser.parse_args()
    return vars(args)

def splitter(df, target_col, sep, new_col = None, argv=[]):

    df[target_col] = df[target_col].str.split(sep)
    exploded = df.explode(target_col)
    exploded[target_col].replace(r'^\s*$', np.nan, regex=True, inplace = True)
    exploded.dropna(subset=[target_col], inplace=True)
    if new_col == None:
        return(pd.DataFrame(exploded[[target_col,*argv]]))
    else:
        exploded[new_col] = exploded[target_col]
        return(pd.DataFrame(exploded[[new_col,*argv]]))

if __name__ == '__main__':
    args = arg_parse()
    print(splitter(df, **args))

然后你通过调用 this 来执行这段代码

python sep.py -t CountryRefs -s ','

或者像这样

python sep.py -t CountryRefs -s ',' Friends Colors