Method to convert docs using sklearn to pyLDAVis

from_sklearn.py

def from_sklearn(docs,vect,lda,**kwargs):
    
    """Create Prepared Data from sklearn's vectorizer and Latent Dirichlet
    Application
    
    Parameters
    ----------
    docs : Pandas Series.
        Documents to be passed as an input.
    vect : Scikit-Learn Vectorizer (CountVectorizer,TfIdfVectorizer).
        vectorizer to convert documents into matrix sparser
    lda  : sklearn.decomposition.LatentDirichletAllocation.
        Latent Dirichlet Allocation
    
    **kwargs: Keyword argument to be passed to pyLDAvis.prepare()
    
    
    Returns
    -------
    prepared_data : PreparedData
    vect : sklearn's Vectorizer.
    lda : sklearn's Latent Dirichlet Allocation.
    """
    
    norm = lambda data: pd.DataFrame(data).div(data.sum(1),axis=0).values
    
    vected = vect.fit_transform(docs)
    doc_topic_dists = norm(lda.fit_transform(vected))
    
    prepared = prepare(
                        doc_lengths = docs.str.len(),
                        vocab = vect.get_feature_names(),
                        term_frequency = vected.sum(axis=0).tolist()[0],
                        topic_term_dists = norm(lda.components_),
                        doc_topic_dists = doc_topic_dists,
                        **kwargs)

    return prepared,lda,vect

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.decomposition import LatentDirichletAllocation
from pyLDAVis import prepare


vect = CountVectorizer()
lda = LatentDirichletAllocation()

prepared = from_sklearn(docs,vect,lda)

#Using LDA module from https://github.com/ariddell/lda

import lda

lda = lda.LDA()
prepared = from_sklearn(docs,vect,lda)