笔记——Train_test_split

1. train_test_split 1

# train_test_split

##将x训练集中的元素进行乱序处理，返回索引
shuffle_indexes=np.random.permutation(len(x))
## 划分训练数据集、测试数据集

test_ratio=0.2
test_size=int(len(x)*test_ratio)

test_indexes=shuffle_indexes[:test_size]
train_indexes=shuffle_indexes[test_size:]

x_train=x[train_indexes]
y_train=y[train_indexes]
x_test=x[test_indexes]
y_test=y[test_indexes]

print(x_train.shape)
print(y_train.shape)

print(x_test.shape)
print(y_test.shape)

2. train_test_split2

#提取出每种类别的鸢尾花数据
t0=data[data["Name"]==0]
t1=data[data["Name"]==1]
t2=data[data["Name"]==2]
#打乱顺序(随机抽取样本)
t0=t0.sample(len(t0),random_state=666)
t1=t1.sample(len(t1),random_state=666)
t2=t2.sample(len(t2),random_state=666)
#进行切分,构建训练集与测试机
train_X=pd.concat([t0.iloc[:40,:-1],t1.iloc[:40,:-1],t2.iloc[:40,:-1]],axis=0)
train_y=pd.concat([t0.iloc[:40,-1],t1.iloc[:40,-1],t2.iloc[:40,-1]],axis=0)
test_X=pd.concat([t0.iloc[40:,:-1],t1.iloc[40:,:-1],t2.iloc[40:,:-1]],axis=0)
test_y=pd.concat([t0.iloc[40:,-1],t1.iloc[40:,-1],t2.iloc[40:,-1]],axis=0)

3. sklearn中的train_test_split

from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)