import pandas as pd import os

读取原始数据

data = pd.read_csv(os.path.join("..", "input", "original_data.csv"))

划分训练集和验证集

train_data = data.sample(frac=0.8, random_state=42) val_data = data.drop(train_data.index)

将训练集和验证集保存为csv文件

train_data.to_csv(os.path.join("..", "input", "train.csv"), index=False) val_data.to_csv(os.path.join("..", "input", "val.csv"), index=False)