Using the probabilities of the topics, you can try to set some threshold and use it as a clustering baseline, but i am sure there are better ways to do clustering than this ‘hacky’ method.
from gensim import corpora, models, similarities
from itertools import chain
""" DEMO """
documents = ["Human machine interface for lab abc computer applications",
"A survey of user opinion of computer system response time",
"The EPS user interface management system",
"System and human system engineering testing of EPS",
"Relation of user perceived response time to error measurement",
"The generation of random binary unordered trees",
"The intersection graph of paths in trees",
"Graph minors IV Widths of trees and well quasi ordering",
"Graph minors A survey"]
# remove common words and tokenize
stoplist = set('for a of the and to in'.split())
texts = [[word for word in document.lower().split() if word not in stoplist]
for document in documents]
# remove words that appear only once
all_tokens = sum(texts, [])
tokens_once = set(word for word in set(all_tokens) if all_tokens.count(word) == 1)
texts = [[word for word in text if word not in tokens_once] for text in texts]
# Create Dictionary.
id2word = corpora.Dictionary(texts)
# Creates the Bag of Word corpus.
mm = [id2word.doc2bow(text) for text in texts]
# Trains the LDA models.
lda = models.ldamodel.LdaModel(corpus=mm, id2word=id2word, num_topics=3, \
update_every=1, chunksize=10000, passes=1)
# Prints the topics.
for top in lda.print_topics():
print top
print
# Assigns the topics to the documents in corpus
lda_corpus = lda[mm]
# Find the threshold, let's set the threshold to be 1/#clusters,
# To prove that the threshold is sane, we average the sum of all probabilities:
scores = list(chain(*[[score for topic_id,score in topic] \
for topic in [doc for doc in lda_corpus]]))
threshold = sum(scores)/len(scores)
print threshold
print
cluster1 = [j for i,j in zip(lda_corpus,documents) if i[0][1] > threshold]
cluster2 = [j for i,j in zip(lda_corpus,documents) if i[1][1] > threshold]
cluster3 = [j for i,j in zip(lda_corpus,documents) if i[2][1] > threshold]
print cluster1
print cluster2
print cluster3
[out]:
0.131*trees + 0.121*graph + 0.119*system + 0.115*user + 0.098*survey + 0.082*interface + 0.080*eps + 0.064*minors + 0.056*response + 0.056*computer
0.171*time + 0.171*user + 0.170*response + 0.082*survey + 0.080*computer + 0.079*system + 0.050*trees + 0.042*graph + 0.040*minors + 0.040*human
0.155*system + 0.150*human + 0.110*graph + 0.107*minors + 0.094*trees + 0.090*eps + 0.088*computer + 0.087*interface + 0.040*survey + 0.028*user
0.333333333333
['The EPS user interface management system', 'The generation of random binary unordered trees', 'The intersection graph of paths in trees', 'Graph minors A survey']
['A survey of user opinion of computer system response time', 'Relation of user perceived response time to error measurement']
['Human machine interface for lab abc computer applications', 'System and human system engineering testing of EPS', 'Graph minors IV Widths of trees and well quasi ordering']
Just to make it clearer:
# Find the threshold, let's set the threshold to be 1/#clusters,
# To prove that the threshold is sane, we average the sum of all probabilities:
scores = []
for doc in lda_corpus
for topic in doc:
for topic_id, score in topic:
scores.append(score)
threshold = sum(scores)/len(scores)
The above code is sum the score of all words and in all topics for all documents.
Then normalize the sum by the number of scores.