Python Pandas: One-Hot Encoding for CSV Data Transformation

import pandas as pd

# 读取原始csv文件
df = pd.read_csv('input.csv')

# 删除'id'和'label'列
df.drop(['id', 'label'], axis=1, inplace=True)

# 使用one-hot编码替换'proto'列
proto_encoded = pd.get_dummies(df['proto'], prefix='proto')
df.drop('proto', axis=1, inplace=True)
df = pd.concat([df, proto_encoded], axis=1)

# 使用one-hot编码替换'service'列
service_encoded = pd.get_dummies(df['service'], prefix='service')
df.drop('service', axis=1, inplace=True)
df = pd.concat([df, service_encoded], axis=1)

# 使用one-hot编码替换'state'列
state_encoded = pd.get_dummies(df['state'], prefix='state')
df.drop('state', axis=1, inplace=True)
df = pd.concat([df, state_encoded], axis=1)

# 使用one-hot编码替换'attack_cat'列
attack_cat_encoded = pd.get_dummies(df['attack_cat'], prefix='attack_cat')
df.drop('attack_cat', axis=1, inplace=True)
df = pd.concat([df, attack_cat_encoded], axis=1)

# 保存新的csv文件
df.to_csv('output.csv', index=False)