为不同的拟合模型重用逻辑回归对象

Question

我有一个 Pipeline 对象，我想将其适应训练和测试标签的不同组合，因此使用 fit 对象创建不同的预测。但我相信 fit 使用相同的分类器对象会摆脱以前的 fit 个对象。

我的代码示例是：

text_clf = Pipeline([('vect', CountVectorizer(analyzer="word",tokenizer=None,preprocessor=None,stop_words=None,max_features=5000)),
                          ('tfidf', TfidfTransformer(use_idf=True,norm='l2',sublinear_tf=True)),
                          ('clf',LogisticRegression(solver='newton-cg',class_weight='balanced', multi_class='multinomial',fit_intercept=True),
                          )])

    print "Fitting the open multinomial BoW logistic regression model for probability models...\n"
    open_multi_logit_words = text_clf.fit(train_wordlist, train_property_labels)

    print "Fitting the open multinomial BoW logistic regression model w/ ",threshold," MAPE threshold...\n"
    open_multi_logit_threshold_words = (text_clf.copy.deepcopy()).fit(train_wordlist, train_property_labels_threshold)

但是，分类器对象没有 deepcopy() 方法。我怎样才能实现我所需要的而不必定义：

text_clf_open_multi_logit = Pipeline([('vect', CountVectorizer(analyzer="word",tokenizer=None,preprocessor=None,stop_words=None,max_features=5000)),
                              ('tfidf', TfidfTransformer(use_idf=True,norm='l2',sublinear_tf=True)),
                              ('clf',LogisticRegression(solver='newton-cg',class_weight='balanced', multi_class='multinomial',fit_intercept=True),
                              )])

对于我所有的 16 个分类器组合？

Answer 1

我会试试

text_clf0=copy.deepcopy(text_clf)
open_multi_logit_threshold_words = text_clf0.fit(train_wordlist, train_property_labels_threshold)

编辑：您可以使用列表

text_clf_list=[copy.deepcopy(text_clf) for _ in range(16)]

或直接

copy.deepcopy(text_c‌lf).fit(train_wordlis‌t, train_property_label‌s_threshold)

为不同的拟合模型重用逻辑回归对象

Reuse a logistic regression object for different fitted models

python

scikit-learn

text-classification

logistic-regression