categorize.py 文件源码

def train_sgdc(training_list):
    footnotes=[]
    cate=[]
    for i in training_list:
        footnotes.append(i[0])
        cate.append(i[1])  
    text_clf=Pipeline([('vect',CountVectorizer()),('tfidf',TfidfTransformer()),('clf',SGDClassifier(loss='hinge', penalty='l2',alpha=1e-3,n_iter=5, random_state=42)),])
    _ = text_clf.fit(footnotes,cate)
    return text_clf