'''
data:数据集
test_ratio:测试机占比
如果data为numpy.numpy.ndarray直接使用此代码
如果data为pandas.DatFrame类型则
  return data[train_indices],data[test_indices]
修改为
  return data.iloc[train_indices],data.iloc[test_indices]
'''
def split_train(data,test_ratio):
  shuffled_indices=np.random.permutation(len(data))
  test_set_size=int(len(data)*test_ratio)
  test_indices =shuffled_indices[:test_set_size]
  train_indices=shuffled_indices[test_set_size:]
  return data[train_indices],data[test_indices]

import numpy as np
import pandas as pd
data=np.random.randint(100,size=[25,4])
print(data)

def split_train(data,test_ratio):
  np.random.seed(43)
  shuffled_indices=np.random.permutation(len(data))
  test_set_size=int(len(data)*test_ratio)
  test_indices =shuffled_indices[:test_set_size]
  train_indices=shuffled_indices[test_set_size:]
  return data[train_indices],data[test_indices]