Can't pickle : it's not the same object as sklearn.linear_model.logistic.LogisticRegression

Asked Jul 05 '19 at 06:21

Active Jul 05 '19 at 07:47

Viewed 225 times

I am getting the following error message:

Can't pickle <class 'sklearn.linear_model.logistic.LogisticRegression'>: it's not the same object as sklearn.linear_model.logistic.LogisticRegression

Here is the code:

logR_pipeline_ngram = Pipeline([('LogR_tfidf',FeatureSelection.tfidf_ngram),
    ('LogR_clf',LogisticRegression(penalty="l2",C=1))])

logR_pipeline_ngram.fit(DataPrep.train_news['Statement'],DataPrep.train_news['label'])

model_file = 'final_model.sav'
pickle.dump(logR_pipeline_ngram,open(model_file,'wb'))

What is causing this?

edited Jul 05 '19 at 07:47

Martin Evans

45,791
17
81
97

asked Jul 05 '19 at 06:21

Mriganka Bora

trying to save this model but it returns the error mentioned in the title – Mriganka Bora Jul 05 '19 at 06:22
Your question is hard to understand. On the [ask] page you find some help to upgrade your question. – Stef Geysels Jul 05 '19 at 07:22
what would you like to save as a pickle? – Matteo Peluso Jul 05 '19 at 09:26
the logRngram model – Mriganka Bora Jul 05 '19 at 12:27
Does this answer your question? [Save classifier to disk in scikit-learn](https://stackoverflow.com/questions/10592605/save-classifier-to-disk-in-scikit-learn) – Capybara May 31 '22 at 19:49

Can't pickle : it's not the same object as sklearn.linear_model.logistic.LogisticRegression

0 Answers0