Question

上面的代码很好，但是第二部分试图创建一个新的txt文件，其中包含有关在第一部分中创建的文件的信息，对于每个文件，例如，将写入该txt文件：INPUT FILE1 SIZE IS 42，OUTPUT FILE1 SIZE IS 324，比第二个文件：INPUT FILE2 SIZE IS 62，OUTPUT FILE1 SIZE IS 543 ...等等等

import pandas as pd
import glob
import os

files = glob.glob('*.csv')
for file in files:
    df = pd.read_csv(file, header= None)
    df1 = df.iloc[:, :4].agg(['sum','max','std'])
    df1.columns = range(1, len(df1.columns) + 1)
    s = df1.stack()
    L = ['{} of the {}. column is {}'.format(a, b, c) for (a, b), c in s.items()]
    output_file_name = "output_" + file
    pd.Series(L).to_csv(output_file_name ,index=False) 

#this part is good


for file in files:
    with open(file + "stats.txt", 'a+') as f:
        f.write(' input file size is {}'.format(os.path.getsize(file)))
        f.write('output file size is {}'.format(os.path.getsize(output_file_name)))
    f.close()

Answer 1

使用os.path.splitext删除原始文件的扩展名，也不需要f.close()，因为with会自动关闭文件：

import glob, os
import pandas as pd

files = glob.glob('*.csv')

#loop by all files
for file in files:
    if not file.startswith(('output_','file_size_')):
        #for write to parameter w
        with open(os.path.splitext(file)[0] + "stats.txt", 'w') as f:
            output_file_name = "output_" + file
            #add both format
            infile = 'SIZE OF INPUT FILE {} IS {}, '.format(file, os.path.getsize(file))
            outfile = 'SIZE OF INPUT FILE {} IS {}'.format(output_file_name, 
                                                           os.path.getsize(output_file_name))

            f.write(infile)
            f.write(outfile)

编辑：

解决方案需要sum的输入和输出文件到变量：

import glob, os
import pandas as pd

files = glob.glob('*.csv')

input_all, output_all = 0, 0
#loop by all files
for file in files:
    if not (file.startswith('output_') or file.endswith('stats.txt')):
        with open(os.path.splitext(file)[0] + "stats.txt", 'w') as f:
            output_file_name = "output_" + file
            #add both format
            i = os.path.getsize(file)
            o = os.path.getsize(output_file_name)
            input_all += i
            output_all += o
            infile = 'SIZE OF INPUT FILE {} IS {}, '.format(file, i)
            outfile = 'SIZE OF INPUT FILE {} IS {}'.format(output_file_name, o)

            f.write(infile)
            f.write(outfile)


with open("final_stats.txt", 'w') as f:
    instring = 'SIZE OF ALL INPUT FILES IS {}, '.format(input_all)
    outstring = 'SIZE OF ALL OUTPUT FILES IS {}, '.format(output_all)
    both = 'SIZE OF ALL  FILES IS {}'.format(input_all + output_all)
    f.write(instring)
    f.write(outstring)
    f.write(both)

Answer 2

更好的方法是将输出文件与输入文件放在不同的目录中，以免造成混淆。

data/
- input
- output
- stats

您还需要1次循环，而不是循环两次文件。

使用pathlib.Path和f字符串（python 3.6及更高版本）将变为：

from pathlib import Path

DATA_DIR = Path("<data>") # fill in the correct path
INPUT_DIR = DATA_DIR / "input"
OUTPUT_DIR = DATA_DIR / "output"
STATS_DIR = DATA_DIR / "stats"

for file in INPUT_DIR.glob("*.csv"):
    df = pd.read_csv(file, header= None)
    df1 = df.iloc[:, :4].agg(['sum','max','std'])
    df1.columns = range(1, len(df1.columns) + 1)
    s = df1.stack()
    L = [f'{a} of the {b}. column is {c}' for (a, b), c in s.items()]

    output_file = OUTPUT_DIR / ("output_" + file.name)
    pd.Series(L).to_csv(output_file ,index=False) 

    size_input = file.stat().st_size
    size_output = output_file.stat().st_size

    stats_file = STATS_DIR / file.with_suffix("stats.txt").name

    message = f"""input file size is {size_input}
    output file size is {size_output}"""

    stats_file.write_text(message)

使用每个文件的输出和输入文件的大小信息分别创建新的txt文件

2 个答案: