python包sklearn中数据集的划分

学习预测函数的参数并在相同的数据上进行测试是一个方法上的错误。因此，机器学习需要划分数据集，在训练集中进行参数的选择和模型的训练，在测试集中进行模型的评价。

数据集的划分方法：

train_test_split，KFold，GroupKFold，StratifiedKFold，LeaveOneGroupOut，LeavePGroupsOut，LeaveOneOut，LeavePOut，ShuffleSplit，GroupShuffleSplit，StratifiedShuffleSplit等

#######数据集的划分############
### 演示数据
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12],[13,14],[15,16],[17,18],[19,20]])
y=np.array([1,2,1,2,1,2,1,1,2,2])
groups=np.array([1,1,1,1,1,2,2,2,2,2])
### 1. 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=0.4, random_state=0)
print(X_train)
print(X_test)
print(y_train)
print(y_test)
### 2. KFold
from sklearn.model_selection import KFold
kf=KFold(n_splits=2)
kf.get_n_splits(X)
print(kf)
for train_index,test_index in kf.split(X):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]

### 3.GroupKFold
from sklearn.model_selection import GroupKFold
group_kfold=GroupKFold(n_splits=2)
group_kfold.get_n_splits(X,y,groups)
print(group_kfold)
for train_index,test_index in group_kfold.split(X,y,groups):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]

### 4.RepeatedKFold
from sklearn.model_selection import RepeatedKFold

rkf = RepeatedKFold(n_splits=2, n_repeats=2, random_state=0)
print(skf)
for train_index,test_index in rkf.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]

### 5.StratifiedKFold
from sklearn.model_selection import StratifiedKFold
skf=StratifiedKFold(n_splits=3)
skf.get_n_splits(X,y)
print(skf)
for train_index,test_index in skf.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]
    
### 6.LeaveOneOut
from sklearn.model_selection import LeaveOneOut
loo=LeaveOneOut()
loo.get_n_splits(X)
print(loo)
for train_index,test_index in loo.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]

### 7.LeavePOut
from sklearn.model_selection import LeavePOut
lpo=LeavePOut(p=3)
lpo.get_n_splits(X)
print(lpo)
for train_index,test_index in lpo.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]
    
### 8.ShuffleSplit
from sklearn.model_selection import ShuffleSplit
rs=ShuffleSplit(n_splits=3,test_size=.25,random_state=0)
rs.get_n_splits(X)
print(rs)
for train_index,test_index in rs.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]
    
### 9. StratifiedShuffleSplit
from sklearn.model_selection import StratifiedShuffleSplit
sss=StratifiedShuffleSplit(n_splits=3,test_size=.5,random_state=0)
sss.get_n_splits(X,y)
print(sss)
for train_index,test_index in sss.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]