Support sklearn pipeline interface. Continuing #932.

[tmylk]

Pipeline interface is not supported in the sklearn wrapper added in #932 .

[rodrigocesar]

I tried to create a simple pipeline using the sklearn wrapper and got a an error.

The code is:

from sklearn.pipeline import Pipeline text_lda = Pipeline([('vec', CountVectorizer(min_df=10, stop_words='english')), ('clf', SklearnWrapperLdaModel(id2word=id2word,num_topics=5,passes=20)), ]) text_lda = text_clf.fit(data.data)

The error i got was:

---

TypeError Traceback (most recent call last)
in ()
----> 1 text_lda = text_clf.fit(data.data)

C:\Users\posgr\Anaconda3\lib\site-packages\sklearn\pipeline.py in fit(self, X, y, **fit_params)
163 """
164 Xt, fit_params = self._pre_transform(X, y, **fit_params)
--> 165 self.steps[-1][-1].fit(Xt, y, **fit_params)
166 return self
167

TypeError: fit() takes 2 positional arguments but 3 were given

[tmylk]

CC @AadityaJ

[menshikh-iv]

Resolved in #1462, #1473, #1437 and another PRs from @chinmayapancholi13.