如何在 sklearn 上拆分平衡训练集和测试集的数据

Question

我正在使用sklearn进行多分类任务。我需要将所有数据拆分为train_set和test_set。我想从每个班级中随机抽取相同的样本数。实际上，我很有趣这个功能

X_train, X_test, y_train, y_test = cross_validation.train_test_split(Data, Target, test_size=0.3, random_state=0)

但它给出了不平衡的数据集！任何建议。

Answer 1

尽管克里斯蒂安的建议是正确的，但从技术上讲，train_test_split应该通过使用stratify参数来为您提供分层结果。

所以你可以做：

X_train, X_test, y_train, y_test = cross_validation.train_test_split(Data, Target, test_size=0.3, random_state=0, stratify=Target)

这里的诀窍是它从 sklearn 中的版本 0.17 开始。

来自有关参数的文档 stratify ：

分层：类似数组或无（默认值为无） 如果不是 None，则以分层方式拆分数据，将其用作标签数组。 版本 0.17 中的新功能：分层拆分

Answer 2

您可以使用 StratifiedShuffleSplit 创建具有与原始类别相同百分比的数据集：

import numpy as np
from sklearn.model_selection import StratifiedShuffleSplit
X = np.array([[1, 3], [3, 7], [2, 4], [4, 8]])
y = np.array([0, 1, 0, 1])
stratSplit = StratifiedShuffleSplit(y, n_iter=1, test_size=0.5, random_state=42)
for train_idx, test_idx in stratSplit:
    X_train=X[train_idx]
    y_train=y[train_idx]
print(X_train)
# [[3 7]
#  [2 4]]
print(y_train)
# [1 0]

Answer 3

如果类不平衡，但您希望拆分平衡，那么分层将无济于事。似乎没有一种方法可以在 sklearn 中进行平衡采样，但使用基本的 numpy 很容易，例如这样的函数可能会帮助你：

def split_balanced(data, target, test_size=0.2):
    classes = np.unique(target)
    # can give test_size as fraction of input data size of number of samples
    if test_size<1:
        n_test = np.round(len(target)*test_size)
    else:
        n_test = test_size
    n_train = max(0,len(target)-n_test)
    n_train_per_class = max(1,int(np.floor(n_train/len(classes))))
    n_test_per_class = max(1,int(np.floor(n_test/len(classes))))
    ixs = []
    for cl in classes:
        if (n_train_per_class+n_test_per_class) > np.sum(target==cl):
            # if data has too few samples for this class, do upsampling
            # split the data to training and testing before sampling so data points won't be
            #  shared among training and test data
            splitix = int(np.ceil(n_train_per_class/(n_train_per_class+n_test_per_class)*np.sum(target==cl)))
            ixs.append(np.r_[np.random.choice(np.nonzero(target==cl)[0][:splitix], n_train_per_class),
                np.random.choice(np.nonzero(target==cl)[0][splitix:], n_test_per_class)])
        else:
            ixs.append(np.random.choice(np.nonzero(target==cl)[0], n_train_per_class+n_test_per_class,
                replace=False))
    # take same num of samples from all classes
    ix_train = np.concatenate([x[:n_train_per_class] for x in ixs])
    ix_test = np.concatenate([x[n_train_per_class:(n_train_per_class+n_test_per_class)] for x in ixs])
    X_train = data[ix_train,:]
    X_test = data[ix_test,:]
    y_train = target[ix_train]
    y_test = target[ix_test]
    return X_train, X_test, y_train, y_test

请注意，如果您使用它并且每个类的采样点多于输入数据中的点，则将对这些点进行上采样（带有替换的采样）。因此，某些数据点将多次出现，这可能会对准确性测量等产生影响。如果某个类只有一个数据点，就会出现错误。您可以轻松检查每个班级的分数，例如使用np.unique(target, return_counts=True)

Answer 4

另一种方法是从分层测试/训练拆分中过度或不足采样。不平衡学习库非常方便，如果您正在进行在线学习并希望保证管道中的平衡训练数据，则特别有用。

from imblearn.pipeline import Pipeline as ImbalancePipeline
model = ImbalancePipeline(steps=[
  ('data_balancer', RandomOverSampler()),
  ('classifier', SVC()),
])

Answer 5

这是我

用来获取训练/测试数据索引的实现

def get_safe_balanced_split(target, trainSize=0.8, getTestIndexes=True, shuffle=False, seed=None):
    classes, counts = np.unique(target, return_counts=True)
    nPerClass = float(len(target))*float(trainSize)/float(len(classes))
    if nPerClass > np.min(counts):
        print("Insufficient data to produce a balanced training data split.")
        print("Classes found %s"%classes)
        print("Classes count %s"%counts)
        ts = float(trainSize*np.min(counts)*len(classes)) / float(len(target))
        print("trainSize is reset from %s to %s"%(trainSize, ts))
        trainSize = ts
        nPerClass = float(len(target))*float(trainSize)/float(len(classes))
    # get number of classes
    nPerClass = int(nPerClass)
    print("Data splitting on %i classes and returning %i per class"%(len(classes),nPerClass ))
    # get indexes
    trainIndexes = []
    for c in classes:
        if seed is not None:
            np.random.seed(seed)
        cIdxs = np.where(target==c)[0]
        cIdxs = np.random.choice(cIdxs, nPerClass, replace=False)
        trainIndexes.extend(cIdxs)
    # get test indexes
    testIndexes = None
    if getTestIndexes:
        testIndexes = list(set(range(len(target))) - set(trainIndexes))
    # shuffle
    if shuffle:
        trainIndexes = random.shuffle(trainIndexes)
        if testIndexes is not None:
            testIndexes = random.shuffle(testIndexes)
    # return indexes
    return trainIndexes, testIndexes

Answer 6

这是我

正在使用的功能。您可以对其进行调整和优化。

# Returns a Test dataset that contains an equal amounts of each class
# y should contain only two classes 0 and 1
def TrainSplitEqualBinary(X, y, samples_n): #samples_n per class
    
    indicesClass1 = []
    indicesClass2 = []
    
    for i in range(0, len(y)):
        if y[i] == 0 and len(indicesClass1) < samples_n:
            indicesClass1.append(i)
        elif y[i] == 1 and len(indicesClass2) < samples_n:
            indicesClass2.append(i)
            
        if len(indicesClass1) == samples_n and len(indicesClass2) == samples_n:
            break
    
    X_test_class1 = X[indicesClass1]
    X_test_class2 = X[indicesClass2]
    
    X_test = np.concatenate((X_test_class1,X_test_class2), axis=0)
    
    #remove x_test from X
    X_train = np.delete(X, indicesClass1 + indicesClass2, axis=0)
    
    Y_test_class1 = y[indicesClass1]
    Y_test_class2 = y[indicesClass2]
    
    y_test = np.concatenate((Y_test_class1,Y_test_class2), axis=0)
    
    #remove y_test from y
    y_train = np.delete(y, indicesClass1 + indicesClass2, axis=0)
    
    if (X_test.shape[0] != 2 * samples_n or y_test.shape[0] != 2 * samples_n):
        raise Exception("Problem with split 1!")
        
    if (X_train.shape[0] + X_test.shape[0] != X.shape[0] or y_train.shape[0] + y_test.shape[0] != y.shape[0]):
        raise Exception("Problem with split 2!")
    
    return X_train, X_test, y_train, y_test