machine learning - Why is Multi-label classification (Binary relevance) is acting up? -

i'm new multi-label classification using binary relevance , having issues explaining result:

the result is: [[ 0. 0.] [ 2. 2.]]

does mean first case classified [0,0] , 2nd [2,2]? not @ all. or missing else?

after gentelmen answers i'm getting following error because of y_train label [2**,0,**3,4] because of zero

traceback (most recent call last): file "driver.py", line 22, in <module> clf_dict[i] = clf.fit(x_train, y_tmp) file "c:\users\baderex\anaconda22\lib\site-packages\sklearn\linear_model\logistic.py", line 1154, in fit self.max_iter, self.tol, self.random_state) file "c:\users\baderex\anaconda22\lib\site-packages\sklearn\svm\base.py", line 885, in _fit_liblinear " class: %r" % classes_[0]) valueerror: solver needs samples of @ least 2 classes in data, data contains 1 class: 1 

updated code:

import numpy np sklearn.linear_model import logisticregression sklearn.metrics import *  numer_classes = 5  x_train = np.array([[1,2,3,4],[0,1,2,1],[1,2,0,3]]) y_train = [[0],[1,0,3],[2,0,3,4]]  x_test = np.array([[1,2,3,4],[0,1,2,1],[1,2,0,3]]) y_test = [[0],[1,0,3],[2,0,3,4]]  clf_dict = {} in range(numer_classes):     y_tmp = []     j in range(len(y_train)):         if in y_train[j]:             y_tmp.append(1)         else:             y_tmp.append(0)     clf = logisticregression()     clf_dict[i] = clf.fit(x_train, y_tmp)  prediction_matrix = np.zeros((len(x_test),numer_classes)) in range(numer_classes):     prediction = clf_dict[i].predict(x_test)     prediction_matrix[:,i] = prediction      print('predicted') print(prediction_matrix) 

thanks

i think made mistake in implementation. binary relevance, need separate classifier each of labels. there 3 labels, there should 3 classifiers. each classifier tell weather instance belongs class or not. example, classifier corresponds class 1 (clf[1]) tell weather instance belongs class 1 or not.

thus, if want manually implement binary relevance, in loop creates classifiers, label should binarized:

for in range(numer_classes):     y_tmp = []     j in range(len(y_train)):         if in y_train[j]:             y_tmp.append(1)         else:             y_tmp.append(0)     clf = logisticregression()     clf_dict[i] = clf.fit(x_train, y_tmp) 

however, if use sklearn, things more convenient:

from sklearn.multiclass import onevsrestclassifier sklearn.preprocessing import multilabelbinarizer  binarizer = multilabelbinarizer() y_train_binarized = binarizer.fit_transform(y_train) y_test_binarized = binarizer.fit_transform(y_test) cls = onevsrestclassifier(estimator=logisticregression()) cls.fit(x_train,y_train_binarized) y_predict = cls.predict(x_test) 

the results like: [[1 0 1] [0 1 1]] means first case predicted as: [0,2] , second case predicted [1,2]