順序切分

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.4, random_state=0)

ShuffleSplit

from sklearn.model_selection import ShuffleSplit

sample = pd.DataFrame()

rs = ShuffleSplit(n_splits=5, test_size=0.2, random_state=0)

for train_indices, test_indices in rs.split(sample):

#共循環5次

#每次循環拿到打亂順序的訓練集和驗證集的索引值，訓練集數量為80%，測試集數量為20%

這種數據切分方式經常與CV結合使用

from sklearn.model_selection import cross_val_score

from sklearn.model_selection import ShuffleSplit

cv = ShuffleSplit(n_splits=3, test_size=0.3, random_state=0)

cross_val_score(clf, iris.data, iris.target, cv=cv)

GroupShuffleSplit

from sklearn.model_selection import GroupShuffleSplit

sample = pd.DataFrame()

rs = GroupShuffleSplit(n_splits=4, test_size=0.25, random_state=0)

#獲取組標記

_, driver_indices = np.unique(np.array(driver_ids), return_inverse=True)

driver_indices = [0 0 1 1 1 2 2 2 2 3]

#這裏是按照groups所給列的類別進行數據集的劃分

for train_indices, test_indices in rs.split(x_train_names_all, y_train_labels_all, groups=driver_indices):

#共循環4次

#假設groups列中有4個類別，每次循環，從中選擇75%的類別數，屬於這75%的類別數的所有數據集作為訓練集，其余

#為驗證集。

模型評估：數據切分