sklearn.model_selection.train_test_split

from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(iris.data,iris.target,shuffle=False)
# shuffle=False : 섞지 않겠다
# 기본 75% / 25%
np.bincount(y_test)

array([ 0,  0, 38], dtype=int64)

 

 

from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(iris.data,iris.target,shuffle=True)
# shuffle=True : 섞겠다
# 기본 75% / 25%
np.bincount(y_test)

array([11, 12, 15], dtype=int64)

 

X_train,X_test,y_train,y_test=train_test_split(iris.data,iris.target,shuffle=True,random_state=1)
# random_state=1 : 씨드값
np.bincount(y_test)

array([13, 16,  9], dtype=int64)

 

X_train,X_test,y_train,y_test=train_test_split(iris.data,iris.target,test_size=0.2,shuffle=True)
# test_size=20 : 테스트 데이터의 갯수를 20개로!
# test_size=0.2 : 테스트 데이터의 비율을 20%로!
np.bincount(y_test)

array([6, 6, 8], dtype=int64)