python - 如何在Python中仅提取CSV文件的特定列

Question

我们必须计算 Excel 工作表中第 5 行的平均值，并保存为 csv 文件。文件的第一行包含使它们成为字符串的列的名称。我似乎无法获得一种循环所有行 [4] 并将其计算为一个变量“总和”的代码。这是我的代码。另外，

import csv
import os
sum = x_length = 0
with open('2.5_week.csv', newline='') as f:
    rows = csv.reader(f)
    for row in rows:
        if row[4] is int:
            sum = sum + float(row[4])
            x_length = x_length + 1
x_average = sum/len(x_length)
print(x_average)

我使用的是 python 3.4.x

Answer 1

这个示例应该可以帮助您实现您试图通过程序解决的目标:

import csv
import random
import statistics


def main():
    make_csv()
    read_csv_1()
    read_csv_2()


def make_csv():
    with open('2.5_week.csv', 'w', newline='') as file:
        writer = csv.writer(file)
        for index in range(1000):
            row = (random.random() * index,
                   random.randint(index, index * 2),
                   random.randrange(1 + index * 3),
                   random.random() + index,
                   random.randint(index, index + 10),
                   random.randrange(1 + index ** 2))
            writer.writerow(row)


def read_csv_1():
    with open('2.5_week.csv', 'r', newline='') as file:
        table = pivot_table(csv.reader(file))
    print(statistics.mean(map(float, table[4])))


def pivot_table(table):
    iterator = iter(table)
    pivot = tuple([cell] for cell in next(iterator))
    for row in iterator:
        for column, cell in zip(pivot, row):
            column.append(cell)
    return pivot


def read_csv_2():
    with open('2.5_week.csv', 'r', newline='') as file:
        print(statistics.mean(float(row[4]) for row in csv.reader(file)))

if __name__ == '__main__':
    main()