def q04_topic_modelling(path, n_top_words=20):
v1, v2 = q02_count_vectorizer_for_LDA(path)
v3 = q03_LDA(path)
message = []
for topic_idx, topic in enumerate(v3):
message = [v2[i] for i in topic.argsort()[:-n_top_words:-1]]
return message
def q03_LDA(path):
matrix, feature_names = q02_count_vectorizer_for_LDA(path)
# vocab = feature_names
model =LatentDirichletAllocation(n_topics=20, random_state=1,learning_method='batch',max_iter=500)
model.fit(matrix)
topic_word = model.components_
return topic_word
def q04_topic_modelling(path, n_top_words=20):
v1, v2 = q02_count_vectorizer_for_LDA(path)
v3 = q03_LDA(path)
message = list()
for topic_idx, topic in enumerate(v3):
topic = 'Topic ' + str(topic_idx) + ': ' + ' '.join(
[v2[i] for i in topic.argsort()[:-n_top_words:-1]])
message.append(topic)
return message
def q04_topic_modelling(path, n_top_words=20):
topic_word = q03_LDA(path)
topics = []
for i, topic_dist in enumerate(topic_word):
matrix, feature_names = q02_count_vectorizer_for_LDA(path)
topic_words = np.array(feature_names)[np.argsort(
topic_dist)][:-n_top_words:-1]
func = ('Topic {}: {}'.format(i, ' '.join(topic_words)))
topics.append(func)
return topics
def q03_LDA(path):
tf,v2=q02_count_vectorizer_for_LDA(path)
lda = LatentDirichletAllocation(n_components=20, max_iter=500,learning_method='batch',random_state=1)
lda.fit(tf)
return lda.components_