Sklearn中的数据划分方法（划分训练集与测试集）
Sklearn中的数据划分方法（划分训练集与测试集）
1. K折交叉验证：
代码实现
KFold(n_splits=2)
#KFold
import numpy as np
from sklearn.model_selection import KFold
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,3,4,5,6])
kf=KFold(n_splits=2) # 定义分成几个组
# kf.get_n_splits(X) # 查询分成几个组
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]
#print(X_train,X_test,y_train,y_test)
GroupKFold(n_splits=2)
# GroupKFold
import numpy as np
from sklearn.model_selection import GroupKFold
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,3,4,5,6])
groups=np.array([1,2,3,4,5,6])
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]
#print(X_train,X_test,y_train,y_test)
#GroupKFold(n_splits=2)
#Train Index: [0 2 4] ,Test Index: [1 3 5]
#Train Index: [1 3 5] ,Test Index: [0 2 4]
StratifiedKFold(n_splits=3)
# stratifiedKFold：保证训练集中每一类的比例是相同的（尽量）
import numpy as np
from sklearn.model_selection import StratifiedKFold
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,1,1,2,2,2])
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]
#print(X_train,X_test,y_train,y_test)
#StratifiedKFold(n_splits=3, random_state=None, shuffle=False)
#Train Index: [1 2 4 5] ,Test Index: [0 3]
#Train Index: [0 2 3 5] ,Test Index: [1 4]
2.留一法：
代码实现
LeaveOneOut()
# leaveOneOut：测试集就留下一个
import numpy as np
from sklearn.model_selection import LeaveOneOut
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,3,4,5,6])
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]
#print(X_train,X_test,y_train,y_test)
#LeaveOneOut()
#Train Index: [1 2 3 4 5] ,Test Index: [0]
#Train Index: [0 2 3 4 5] ,Test Index: [1]
#Train Index: [0 1 3 4 5] ,Test Index: [2]
#Train Index: [0 1 2 4 5] ,Test Index: [3]
#Train Index: [0 1 2 3 5] ,Test Index: [4]
#Train Index: [0 1 2 3 4] ,Test Index: [5]
LeavePOut(p=3)
LeavePOut：测试集留下P个
import numpy as np
from sklearn.model_selection import LeavePOut
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,3,4,5,6])
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]
#print(X_train,X_test,y_train,y_test)
#LeavePOut(p=3)
#Train Index: [3 4 5] ,Test Index: [0 1 2]
#Train Index: [2 4 5] ,Test Index: [0 1 3]
#Train Index: [2 3 5] ,Test Index: [0 1 4]
#Train Index: [2 3 4] ,Test Index: [0 1 5]
#Train Index: [1 4 5] ,Test Index: [0 2 3]
#Train Index: [1 3 5] ,Test Index: [0 2 4]
#Train Index: [1 3 4] ,Test Index: [0 2 5]
#Train Index: [1 2 5] ,Test Index: [0 3 4]
#Train Index: [1 2 4] ,Test Index: [0 3 5]
#Train Index: [1 2 3] ,Test Index: [0 4 5]
#Train Index: [0 4 5] ,Test Index: [1 2 3]
#Train Index: [0 3 5] ,Test Index: [1 2 4]
#Train Index: [0 3 4] ,Test Index: [1 2 5]
#Train Index: [0 2 5] ,Test Index: [1 3 4]
#Train Index: [0 2 4] ,Test Index: [1 3 5]
#Train Index: [0 2 3] ,Test Index: [1 4 5]
#Train Index: [0 1 5] ,Test Index: [2 3 4]
#Train Index: [0 1 4] ,Test Index: [2 3 5]
#Train Index: [0 1 3] ,Test Index: [2 4 5]
#Train Index: [0 1 2] ,Test Index: [3 4 5]
3.随机划分法：
ShuffleSplit(n_splits=3,test_size=.25,random_state=0)
# ShuffleSplit 把数据集打乱顺序，然后划分测试集和训练集，训练集额和测试集的比例随机选定，
# 训练集和测试集的比例的和可以小于1
import numpy as np
from sklearn.model_selection import ShuffleSplit
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,3,4,5,6])
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]
#print(X_train,X_test,y_train,y_test)
print("==============================")
rs=ShuffleSplit(n_splits=3,train_size=.5,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)
#ShuffleSplit(n_splits=3, random_state=0, test_size=0.25, train_size=None)
#Train Index: [1 3 0 4] ,Test Index: [5 2]
#Train Index: [4 0 2 5] ,Test Index: [1 3]
#Train Index: [1 2 4 0] ,Test Index: [3 5]
#==============================
#ShuffleSplit(n_splits=3, random_state=0, test_size=0.25, train_size=0.5)
#Train Index: [1 3 0] ,Test Index: [5 2]
#Train Index: [4 0 2] ,Test Index: [1 3]
#Train Index: [1 2 4] ,Test Index: [3 5]
StratifiedShuffleSplit(n_splits=3,test_size=.5,random_state=0)
可以保证train、test的数据集里正负样本的样本比例保持一致
import numpy as np
from sklearn.model_selection import StratifiedShuffleSplit
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,1,2,1,2])
sss=StratifiedShuffleSplit(n_splits=3,test_size=.5,random_state=0) #分成3组，测试集比例是0.random_state表示是否要将样本随机打乱。
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]
#print(X_train,X_test,y_train,y_test)
#StratifiedShuffleSplit(n_splits=3, random_state=0, test_size=0.5,train_size=None)
#Train Index: [5 4 1] ,Test Index: [3 2 0]
#Train Index: [5 2 3] ,Test Index: [0 4 1]
#Train Index: [5 0 4] ,Test Index: [3 1 2]