Gensim sparse corpus fix (#82)

* updated gensim prepare logic to allow csc_corpus as an input
* patched gensim.prepare to properly accept corpuses in csc_matrix format

pyLDAvis/gensim.py

@@ -16,9 +16,11 @@ def _extract_data(topic_model, corpus, dictionary, doc_topic_dists=None):
    import gensim
 
    if not gensim.matutils.ismatrix(corpus):
-      corpus_csc = gensim.matutils.corpus2csc(corpus)
+      corpus_csc = gensim.matutils.corpus2csc(corpus, num_terms=len(dictionary))
    else:
       corpus_csc = corpus
+      # Need corpus to be a streaming gensim list corpus for len and inference functions below:
+      corpus = gensim.matutils.Sparse2Corpus(corpus_csc)
 
    vocab = list(dictionary.token2id.keys())
    # TODO: add the hyperparam to smooth it out? no beta in online LDA impl.. hmm..