23 lines
827 B
Python
23 lines
827 B
Python
import pandas as pd
|
|
from sklearn.model_selection import train_test_split
|
|
|
|
# 读取CSV文件
|
|
data = pd.read_csv('data.csv')
|
|
|
|
# 假设'rent_price'是我们要预测的目标变量
|
|
X = data.drop('rent_price', axis=1) # 所有的特征列,除了目标变量
|
|
y = data['rent_price'] # 目标变量
|
|
|
|
# 使用train_test_split函数进行数据集拆分
|
|
# test_size参数表示测试集所占的比例,这里设置为20%
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
|
|
|
|
# 将训练集和测试集重新组合为DataFrame
|
|
train_data = pd.concat([X_train, y_train], axis=1)
|
|
test_data = pd.concat([X_test, y_test], axis=1)
|
|
|
|
# 保存到新的CSV文件
|
|
train_data.to_csv('train.csv', index=False)
|
|
test_data.to_csv('test.csv', index=False)
|
|
|
|
print("数据已成功拆分为train.csv和test.csv") |