如果你希望有一个数据帧和两个数据帧(不是numpy数组)，这应该可以做到:

def split_data(df, train_perc = 0.8):

   df['train'] = np.random.rand(len(df)) < train_perc

   train = df[df.train == 1]

   test = df[df.train == 0]

   split_data ={'train': train, 'test': test}

   return split_data

shuffle = np.random.permutation(len(df))
test_size = int(len(df) * 0.2)
test_aux = shuffle[:test_size]
train_aux = shuffle[test_size:]
TRAIN_DF =df.iloc[train_aux]
TEST_DF = df.iloc[test_aux]

如果你想把它分成训练集、测试集和验证集，你可以使用这个函数:

from sklearn.model_selection import train_test_split
import pandas as pd

def train_test_val_split(df, test_size=0.15, val_size=0.45):
    temp, test = train_test_split(df, test_size=test_size)
    total_items_count = len(df.index)
    val_length = total_items_count * val_size
    new_val_propotion = val_length / len(temp.index) 
    train, val = train_test_split(temp, test_size=new_val_propotion)
    return train, test, val

像这样从df中选择range row

row_count = df.shape[0]
split_point = int(row_count*1/5)
test_data, train_data = df[:split_point], df[split_point:]

我将使用scikit-learn自己的training_test_split，并从索引生成它

from sklearn.model_selection import train_test_split


y = df.pop('output')
X = df

X_train,X_test,y_train,y_test = train_test_split(X.index,y,test_size=0.2)
X.iloc[X_train] # return dataframe train

有许多方法可以创建训练/测试甚至验证样本。

案例1:没有任何选项的经典方法train_test_split:

from sklearn.model_selection import train_test_split
train, test = train_test_split(df, test_size=0.3)

案例2:非常小的数据集(<500行):为了通过这种交叉验证获得所有行的结果。最后，您将对可用训练集的每一行都有一个预测。

from sklearn.model_selection import KFold
kf = KFold(n_splits=10, random_state=0)
y_hat_all = []
for train_index, test_index in kf.split(X, y):
    reg = RandomForestRegressor(n_estimators=50, random_state=0)
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]
    clf = reg.fit(X_train, y_train)
    y_hat = clf.predict(X_test)
    y_hat_all.append(y_hat)

案例3a:用于分类的不平衡数据集。下面是情形1的等价解:

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, test_size=0.3)

案例3b:用于分类的不平衡数据集。在情形2之后，等价解如下:

from sklearn.model_selection import StratifiedKFold
kf = StratifiedKFold(n_splits=10, random_state=0)
y_hat_all = []
for train_index, test_index in kf.split(X, y):
    reg = RandomForestRegressor(n_estimators=50, random_state=0)
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]
    clf = reg.fit(X_train, y_train)
    y_hat = clf.predict(X_test)
    y_hat_all.append(y_hat)

案例4:你需要在大数据上创建一个训练/测试/验证集来调优超参数(60%训练，20%测试和20% val)。

from sklearn.model_selection import train_test_split
X_train, X_test_val, y_train, y_test_val = train_test_split(X, y, test_size=0.6)
X_test, X_val, y_test, y_val = train_test_split(X_test_val, y_test_val, stratify=y, test_size=0.5)