pandas 分组 抽样

import pandas as pd

data = pd.read_csv("data.csv")
grouped_data = data.groupby("Group")

sampled_data = grouped_data.apply(pd.DataFrame.sample, n=200, random_state=42)

#拆分训练集和测试集
delete_index = [i[1] for i in sampled_data.index]

train = data[~data.index.isin(delete_index)]
train

train[['MD','label']].sample(frac=1).to_csv('train.csv',index=False)

test = sampled_data
test[['MD']].sample(frac=1).to_csv('test.csv',index=False)