将一个文件的代码应用于多个文件python（新手问题）

Question

我编写了以下代码，它从 csv 文件中获取一列，然后将其转换为整数并将它们全部相加。我只为一个文件做了这个，我有大约 80 个文件可以应用相同的代码。

import csv
from collections import defaultdict
columns = defaultdict(list)
with open('Team11BoM.csv') as f:
    reader = csv.DictReader(f)
    for row in reader:
        for (k,v) in row.items():
            if k not in columns:
                columns[k] = list()
            columns[k].append(v)

import pandas as pd
df = pd.read_csv("Team11BoM.csv")

b = list(df['Reported Price'])
a = list(df['Actual Price'])

for i in range(0, len(a)):
    a[i] = int(float(a[i]))

v = sum(a)
print("the total actual cost(s) for team 11 is:", v)

for i in range(0, len(b)):
    b[i] = int(float(b[i]))

h = sum(b)
print("the total reported price for team 11 is:", h)

它打印出以下内容：

the total actual cost(s) for team 11 is: 945
the total reported price for team 11 is: 707

我希望它打印出来：

the total actual cost(s) for *filename* is: *Total cost of that team*
the total reported price for *filename* is: *Total reported price of that team*

有什么简单的方法吗？

谢谢， 伊尔凡 S.

Answer 1

import os
import csv
import pandas as pd
from collections import defaultdict

files_dir = 'csv'

csv_files = os.listdir(files_dir)
print(csv_files)

def convert_to_int(file_name):
    file_name = f'{files_dir}/{file_name}'
    columns = defaultdict(list)
    with open(file_name) as f:
        reader = csv.DictReader(f)
        for row in reader:
            for (k,v) in row.items():
                if k not in columns:
                    columns[k] = list()
                columns[k].append(v)

    df = pd.read_csv(file_name)

    b = list(df['Reported Price'])
    a = list(df['Actual Price'])

    for i in range(0, len(a)):
        a[i] = int(float(a[i]))

    v = sum(a)
    print("the total actual cost(s) for team 11 is:", v)

    for i in range(0, len(b)):
        b[i] = int(float(b[i]))

    h = sum(b)
    print("the total reported price for team 11 is:", h)

for file in csv_files:
    convert_to_int(file)

Answer 2

首先，您应该定义一个可重复使用的函数以避免代码重复。

import csv
from collections import defaultdict

def process_file(file_name):
    columns = defaultdict(list)
    with open(file_namename) as f:
        reader = csv.DictReader(f)
        for row in reader:
            for (k,v) in row.items():
                if k not in columns:
                    columns[k] = list()
                columns[k].append(v)

    import pandas as pd
    df = pd.read_csv(file_name)

    b = list(df['Reported Price'])
    a = list(df['Actual Price'])

    for i in range(0, len(a)):
        a[i] = int(float(a[i]))

    v = sum(a)
    print(f"the total actual cost(s) for {file_name} 11 is:", v)

    for i in range(0, len(b)):
        b[i] = int(float(b[i]))

    h = sum(b)
    print(f"the total reported price for {file_name} 11 is:", h)

其次，调用这个函数并遍历文件列表：

# assuming all of this files are in the current directory

list_of_files = [f for f in os.listdir('.') if os.path.isfile(f)]
for file_name in list_of_files:
    process_file(file_name)

Answer 3

如何将 csvs 放在一个目录中并像这样执行循环：

import pandas as pd
def summer(f):
    name = f.split('.')[0]
    df = pd.read_csv(f)

    b = list(df['Reported Price'])
    a = list(df['Actual Price'])

    for i in range(0, len(a)):
        a[i] = int(float(a[i]))

    v = sum(a)
    print(f"the total actual cost(s) for {name} is:", v)

    for i in range(0, len(b)):
        b[i] = int(float(b[i]))

    h = sum(b)
    print("the total reported price for {name} is:", h)

path = 'path/to/csv-files/directory/'

import os
for fil in os.listdir(path):
    summer(fil)

Answer 4

您可以使用 for 循环并遍历 cwd 中的每个文件并对所有文件执行相同操作，确保所有文件位于同一目录中

import csv
from collections import defaultdict
import pandas as pd
import os

def valueSum(filename):
    columns = defaultdict(list)
    with open(filename) as f:
        reader = csv.DictReader(f)
        for row in reader:
            for (k,v) in row.items():
                if k not in columns:
                    columns[k] = list()
                columns[k].append(v)

    df = pd.read_csv(filename)

    b = list(df['Reported Price'])
    a = list(df['Actual Price'])

    for i in range(0, len(a)):
        a[i] = int(float(a[i]))

    v = sum(a)

    for i in range(0, len(b)):
        b[i] = int(float(b[i]))

    h = sum(b)

    print("the total actual cost(s) for team 11 is:", v)
    print("the total reported price for team 11 is:", h)

for filename in os.listdir("."):
    if filename.endswith(".csv"): #count only csv files
        valueSum(filename)