proba(term | topic) = beta[topic][term]
We shall for each topic find the top 20 words that contribute
to a document being classified as said topic
"""
top_20_per_topic = np.argsort(self.beta * (-1), axis=1)
for i in range(self.nb_topics):
for j in range(self.nb_terms):
if top_20_per_topic[i][j] < 20:
print(self.index[j], end=" ")
print()
if __name__ == "__main__":
"""
Example of application using newsgroups
"""
from sklearn.datasets import fetch_20newsgroups
train = fetch_20newsgroups(subset='train',
remove=('headers', 'footers', 'quotes'))
pp = Preprocessing()
index, bow = pp.build_bow(pp.corpus_preproc(train["data"]))
lda = LDA(5, bow, index, alpha=0.1, set_alpha=True)
lda.estimation(max_iter_em=100, max_iter_var=10)
lda.display_word_topic_association()
