def train_val_test_split(X, y, train_size, val_size, test_size):
    X_train_val, X_test, y_train_val, y_test = train_test_split(X, y, test_size = test_size)
    relative_train_size = train_size / (val_size + train_size)
    X_train, X_val, y_train, y_val = train_test_split(X_train_val, y_train_val,
                                                      train_size = relative_train_size, test_size = 1-relative_train_size)
    return X_train, X_val, X_test, y_train, y_val, y_test

在这里，我们使用sklearn的train_test_split将数据分割2次

将数据集分割为训练集和测试集，如在其他答案中一样，使用

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

然后，如果您适合您的模型，您可以添加validation_split作为参数。这样就不需要提前创建验证集。例如:

from tensorflow.keras import Model

model = Model(input_layer, out)

[...]

history = model.fit(x=X_train, y=y_train, [...], validation_split = 0.3)

验证集旨在作为训练集训练期间的代表运行测试集，完全来自训练集，无论是通过k-fold交叉验证(推荐)还是通过validation_split;然后，您不需要单独创建一个验证集，仍然可以将数据集分为您所要求的三个集。

使用train_test_split非常方便，不需要在划分到几个集后执行重新索引，也不需要编写一些额外的代码。上面的最佳答案没有提到使用train_test_split分隔两次而不改变分区大小将不会给出最初预期的分区:

x_train, x_remain = train_test_split(x, test_size=(val_size + test_size))

那么x_remain中的验证集和测试集的部分就会发生变化，可以算作

new_test_size = np.around(test_size / (val_size + test_size), 2)
# To preserve (new_test_size + new_val_size) = 1.0 
new_val_size = 1.0 - new_test_size

x_val, x_test = train_test_split(x_remain, test_size=new_test_size)

在这种情况下，将保存所有初始分区。

下面是一个Python函数，它将Pandas数据帧划分为分层抽样的训练、验证和测试数据帧。它通过两次调用scikit-learn的函数train_test_split()来执行这种分割。

import pandas as pd
from sklearn.model_selection import train_test_split

def split_stratified_into_train_val_test(df_input, stratify_colname='y',
                                         frac_train=0.6, frac_val=0.15, frac_test=0.25,
                                         random_state=None):
    '''
    Splits a Pandas dataframe into three subsets (train, val, and test)
    following fractional ratios provided by the user, where each subset is
    stratified by the values in a specific column (that is, each subset has
    the same relative frequency of the values in the column). It performs this
    splitting by running train_test_split() twice.

    Parameters
    ----------
    df_input : Pandas dataframe
        Input dataframe to be split.
    stratify_colname : str
        The name of the column that will be used for stratification. Usually
        this column would be for the label.
    frac_train : float
    frac_val   : float
    frac_test  : float
        The ratios with which the dataframe will be split into train, val, and
        test data. The values should be expressed as float fractions and should
        sum to 1.0.
    random_state : int, None, or RandomStateInstance
        Value to be passed to train_test_split().

    Returns
    -------
    df_train, df_val, df_test :
        Dataframes containing the three splits.
    '''

    if frac_train + frac_val + frac_test != 1.0:
        raise ValueError('fractions %f, %f, %f do not add up to 1.0' % \
                         (frac_train, frac_val, frac_test))

    if stratify_colname not in df_input.columns:
        raise ValueError('%s is not a column in the dataframe' % (stratify_colname))

    X = df_input # Contains all columns.
    y = df_input[[stratify_colname]] # Dataframe of just the column on which to stratify.

    # Split original dataframe into train and temp dataframes.
    df_train, df_temp, y_train, y_temp = train_test_split(X,
                                                          y,
                                                          stratify=y,
                                                          test_size=(1.0 - frac_train),
                                                          random_state=random_state)

    # Split the temp dataframe into val and test dataframes.
    relative_frac_test = frac_test / (frac_val + frac_test)
    df_val, df_test, y_val, y_test = train_test_split(df_temp,
                                                      y_temp,
                                                      stratify=y_temp,
                                                      test_size=relative_frac_test,
                                                      random_state=random_state)

    assert len(df_input) == len(df_train) + len(df_val) + len(df_test)

    return df_train, df_val, df_test

下面是一个完整的工作示例。

考虑一个数据集，该数据集具有一个标签，您希望在其上执行分层。这个标签在原始数据集中有自己的分布，比如75% foo, 15% bar和10% baz。现在，让我们使用60/20/20的比例将数据集分割为训练、验证和测试子集，其中每个分割保留相同的标签分布。如下图所示:

下面是示例数据集:

df = pd.DataFrame( { 'A': list(range(0, 100)),
                     'B': list(range(100, 0, -1)),
                     'label': ['foo'] * 75 + ['bar'] * 15 + ['baz'] * 10 } )

df.head()
#    A    B label
# 0  0  100   foo
# 1  1   99   foo
# 2  2   98   foo
# 3  3   97   foo
# 4  4   96   foo

df.shape
# (100, 3)

df.label.value_counts()
# foo    75
# bar    15
# baz    10
# Name: label, dtype: int64

现在，让我们从上面调用split_stratified_into_train_val_test()函数，按照60/20/20的比例获取训练、验证和测试数据帧。

df_train, df_val, df_test = \
    split_stratified_into_train_val_test(df, stratify_colname='label', frac_train=0.60, frac_val=0.20, frac_test=0.20)

三个数据帧df_train、df_val和df_test包含所有原始行，但它们的大小将遵循上面的比例。

df_train.shape
#(60, 3)

df_val.shape
#(20, 3)

df_test.shape
#(20, 3)

此外，三次分割中的每一次都将具有相同的标签分布，即75% foo, 15% bar和10% baz。

df_train.label.value_counts()
# foo    45
# bar     9
# baz     6
# Name: label, dtype: int64

df_val.label.value_counts()
# foo    15
# bar     3
# baz     2
# Name: label, dtype: int64

df_test.label.value_counts()
# foo    15
# bar     3
# baz     2
# Name: label, dtype: int64

在监督学习的情况下，你可能想拆分X和y(其中X是你的输入，y是基本真理输出)。 你只需要注意在分割之前以同样的方式洗牌X和y。

在这里，X和y在同一个数据帧中，所以我们对它们进行洗牌，将它们分开，并对每个数据帧应用拆分(就像在选择的答案中一样)，或者X和y在两个不同的数据帧中，所以我们洗牌X，将y按洗牌X的方式重新排序，并对每个数据帧应用拆分。

# 1st case: df contains X and y (where y is the "target" column of df)
df_shuffled = df.sample(frac=1)
X_shuffled = df_shuffled.drop("target", axis = 1)
y_shuffled = df_shuffled["target"]

# 2nd case: X and y are two separated dataframes
X_shuffled = X.sample(frac=1)
y_shuffled = y[X_shuffled.index]

# We do the split as in the chosen answer
X_train, X_validation, X_test = np.split(X_shuffled, [int(0.6*len(X)),int(0.8*len(X))])
y_train, y_validation, y_test = np.split(y_shuffled, [int(0.6*len(X)),int(0.8*len(X))])

注意:

函数被编写来处理随机集创建的播种。你不应该依赖集分割，它不会随机化集合。

import numpy as np
import pandas as pd

def train_validate_test_split(df, train_percent=.6, validate_percent=.2, seed=None):
    np.random.seed(seed)
    perm = np.random.permutation(df.index)
    m = len(df.index)
    train_end = int(train_percent * m)
    validate_end = int(validate_percent * m) + train_end
    train = df.iloc[perm[:train_end]]
    validate = df.iloc[perm[train_end:validate_end]]
    test = df.iloc[perm[validate_end:]]
    return train, validate, test

示范

np.random.seed([3,1415])
df = pd.DataFrame(np.random.rand(10, 5), columns=list('ABCDE'))
df

train, validate, test = train_validate_test_split(df)

train

validate

test