我在一个有 5 个类的数据集上测试不同的分类器，每个实例可以属于这些类中的一个或多个，所以我使用 scikit-learn 的多标签分类器，特别是sklearn.multiclass.OneVsRestClassifier. 现在我想使用sklearn.cross_validation.StratifiedKFold. 这会产生以下错误：

Traceback (most recent call last):
  File "mlfromcsv.py", line 93, in <module>
    main()
  File "mlfromcsv.py", line 77, in main
    test_classifier_multilabel(svm.LinearSVC(), X, Y, 'Linear Support Vector Machine')
  File "mlfromcsv.py", line 44, in test_classifier_multilabel
    scores = cross_validation.cross_val_score(clf_ml, X, Y_list, cv=cv, score_func=metrics.precision_recall_fscore_support, n_jobs=jobs)
  File "/usr/lib/pymodules/python2.7/sklearn/cross_validation.py", line 1046, in cross_val_score
    X, y = check_arrays(X, y, sparse_format='csr')
  File "/usr/lib/pymodules/python2.7/sklearn/utils/validation.py", line 144, in check_arrays
    size, n_samples))
ValueError: Found array with dim 5. Expected 98816

请注意，训练多标签分类器不会崩溃，但交叉验证会崩溃。我必须如何对这个多标签分类器执行交叉验证？

我还编写了第二个版本，将问题分解为训练和交叉验证 5 个单独的分类器。这工作得很好。

这是我的代码。功能test_classifier_multilabel是给问题的一个。 test_classifier是我的另一个尝试（将问题分解为 5 个分类器和 5 个交叉验证）。

import numpy as np
from sklearn import *
from sklearn.multiclass import OneVsRestClassifier
from sklearn.neighbors import KNeighborsClassifier
import time

def test_classifier(clf, X, Y, description, jobs=1):
    print '=== Testing classifier {0} ==='.format(description)
    for class_idx in xrange(Y.shape[1]):
        print ' > Cross-validating for class {:d}'.format(class_idx)
        n_samples = X.shape[0]
        cv = cross_validation.StratifiedKFold(Y[:,class_idx], 3)
        t_start = time.clock()
        scores = cross_validation.cross_val_score(clf, X, Y[:,class_idx], cv=cv, score_func=metrics.precision_recall_fscore_support, n_jobs=jobs)
        t_end = time.clock();
        print 'Cross validation time: {:0.3f}s.'.format(t_end-t_start)
        str_tbl_fmt = '{:>15s}{:>15s}{:>15s}{:>15s}{:>15s}'
        str_tbl_entry_fmt = '{:0.2f} +/- {:0.2f}'
        print str_tbl_fmt.format('', 'Precision', 'Recall', 'F1 score', 'Support')
        for (score_class, lbl) in [(0, 'Negative'), (1, 'Positive')]:
            mean_precision = scores[:,0,score_class].mean()
            std_precision = scores[:,0,score_class].std()
            mean_recall = scores[:,1,score_class].mean()
            std_recall = scores[:,1,score_class].std()
            mean_f1_score = scores[:,2,score_class].mean()
            std_f1_score = scores[:,2,score_class].std()
            support = scores[:,3,score_class].mean()
            print str_tbl_fmt.format(
                lbl,
                str_tbl_entry_fmt.format(mean_precision, std_precision),
                str_tbl_entry_fmt.format(mean_recall, std_recall),
                str_tbl_entry_fmt.format(mean_f1_score, std_f1_score),
                '{:0.2f}'.format(support))

def test_classifier_multilabel(clf, X, Y, description, jobs=1):
    print '=== Testing multi-label classifier {0} ==='.format(description)
    n_samples = X.shape[0]
    Y_list = [value for value in Y.T]
    print 'Y_list[0].shape:', Y_list[0].shape, 'len(Y_list):', len(Y_list)
    cv = cross_validation.StratifiedKFold(Y_list, 3)
    clf_ml = OneVsRestClassifier(clf)
    accuracy = (clf_ml.fit(X, Y).predict(X) != Y).sum()
    print 'Accuracy: {:0.2f}'.format(accuracy)
    scores = cross_validation.cross_val_score(clf_ml, X, Y_list, cv=cv, score_func=metrics.precision_recall_fscore_support, n_jobs=jobs)
    str_tbl_fmt = '{:>15s}{:>15s}{:>15s}{:>15s}{:>15s}'
    str_tbl_entry_fmt = '{:0.2f} +/- {:0.2f}'
    print str_tbl_fmt.format('', 'Precision', 'Recall', 'F1 score', 'Support')
    for (score_class, lbl) in [(0, 'Negative'), (1, 'Positive')]:
        mean_precision = scores[:,0,score_class].mean()
        std_precision = scores[:,0,score_class].std()
        mean_recall = scores[:,1,score_class].mean()
        std_recall = scores[:,1,score_class].std()
        mean_f1_score = scores[:,2,score_class].mean()
        std_f1_score = scores[:,2,score_class].std()
        support = scores[:,3,score_class].mean()
        print str_tbl_fmt.format(
            lbl,
            str_tbl_entry_fmt.format(mean_precision, std_precision),
            str_tbl_entry_fmt.format(mean_recall, std_recall),
            str_tbl_entry_fmt.format(mean_f1_score, std_f1_score),
            '{:0.2f}'.format(support))

def main():
    nfeatures = 13
    nclasses = 5
    ncolumns = nfeatures + nclasses

    data = np.loadtxt('./feature_db.csv', delimiter=',', usecols=range(ncolumns))

    print data, data.shape
    X = np.hstack((data[:,0:3], data[:,(nfeatures-1):nfeatures]))
    print 'X.shape:', X.shape
    Y = data[:,nfeatures:ncolumns]
    print 'Y.shape:', Y.shape

    test_classifier(svm.LinearSVC(), X, Y, 'Linear Support Vector Machine', jobs=-1)
    test_classifier_multilabel(svm.LinearSVC(), X, Y, 'Linear Support Vector Machine')

if  __name__ =='__main__':
    main()

我正在使用 Ubuntu 13.04 和 scikit-learn 0.12。我的数据是具有形状 (98816, 4) 和 (98816, 5) 的两个数组（X 和 Y）的形式，即每个实例有 4 个特征和 5 个类标签。标签是 1 或 0，表示该类中的成员资格。我是否使用了正确的格式，因为我没有看到太多关于它的文档？