scikit_classifier.py 文件源码

def train(labeled_featuresets, C=1e5):
        """
        :param labeled_featuresets: A list of classified featuresets,
            i.e., a list of tuples ``(featureset, label)``.
        """
        feat = [featureset for featureset, label in labeled_featuresets]
        feature_vectorizer = MVectorizer.DictsVectorizer()
        X = feature_vectorizer.fit_transform(feat)
        X = Normalizer().fit_transform(X)
        label_set = set( [label for featureset, label in labeled_featuresets] )
        label_vectorizer = dict( [(label,num) for num,label in enumerate(label_set)] )
        y = numpy.array([label_vectorizer[label] for featureset, label in labeled_featuresets])
        # print "Training on %d examples with %d features..."%(X.shape[0],X.shape[1]),
        classifier = OneVsRestClassifier(LinearSVC(loss='squared_hinge', penalty='l2', dual=True, tol=1e-5, C=C))
        classifier.fit(X,y)
        # print "done"

        return scikit_classifier(feature_vectorizer,label_vectorizer,classifier)