1
2
3
4
5
6

import csv

with open('data.csv', mode='r', encoding='utf-8') as file:
    reader = csv.reader(file)
    for row in reader:
        print(row)  # 每行是一个列表 ٩(◕‿◕｡)۶

1
2
3
4

import pandas as pd

df = pd.read_csv('data.csv')
print(df.head())  # 显示前5行数据 ฅ^•ﻌ•^ฅ

1
2
3
4
5
6
7

import csv

data = [['Name', 'Age'], ['Alice', 25], ['Bob', 30]]

with open('output.csv', 'w', newline='') as file:
    writer = csv.writer(file)
    writer.writerows(data)  # 写入多行数据 (•̀ᴗ•́)و

1

df.to_csv('output.csv', index=False)  # index=False 避免写入索引列 (ง •̀_•́)ง

1
2
3
4
5

# 选择特定列
ages = df['Age']

# 条件筛选
young_people = df[df['Age'] < 30]  # 筛选年龄小于30岁的人 ╰(*°▽°*)╯

1
2
3
4
5

# 添加列
df['Senior'] = df['Age'] > 60

# 删除列
df = df.drop(columns=['Unnecessary'])  # 拜拜不需要的列 (╯‵□′)╯︵┻━┻

1
2
3
4
5

# 删除包含缺失值的行
df = df.dropna()

# 填充缺失值
df = df.fillna(0)  # 用0填充 ✨

1
2
3
4
5
6
7
8

df1 = pd.read_csv('data1.csv')
df2 = pd.read_csv('data2.csv')

# 垂直合并 (行数增加)
merged = pd.concat([df1, df2])

# 水平合并 (列数增加)
merged = pd.merge(df1, df2, on='ID')  # 根据ID列合并 (ﾉ◕ヮ◕)ﾉ*:･ﾟ✧

1
2

# 按城市分组计算平均年龄
city_stats = df.groupby('City')['Age'].mean()  # 统计学的快乐 ┬─┬ ノ( ゜-゜ノ)

1
2

df['Date'] = pd.to_datetime(df['Date'])
df['Year'] = df['Date'].dt.year  # 提取年份部分 ٩(｡•ω•｡)و