def test_load_line_corpus():
docs = data.load_line_corpus(CURDIR + '/../datasets/nips-2008.dat',
tokenize=True)
assert_equal(len(docs), 250)
assert_true(isinstance(docs[0], list))
docs = data.load_line_corpus(CURDIR + '/../datasets/nips-2008.dat',
tokenize=False)
assert_equal(len(docs), 250)
assert_true(isinstance(docs[0], basestring))
def get_topic_labels(corpus_path, n_topics,
n_top_words,
preprocessing_steps,
n_cand_labels, label_min_df,
label_tags, n_labels,
lda_random_state,
lda_n_iter):
"""
Refer the arguments to `create_parser`
"""
print("Loading docs...")
docs = load_line_corpus(corpus_path)
if 'wordlen' in preprocessing_steps:
print("Word length filtering...")
wl_filter = CorpusWordLengthFilter(minlen=3)
docs = wl_filter.transform(docs)
if 'stem' in preprocessing_steps:
print("Stemming...")
stemmer = CorpusStemmer()
docs = stemmer.transform(docs)
if 'tag' in preprocessing_steps:
print("POS tagging...")
tagger = CorpusPOSTagger()
tagged_docs = tagger.transform(docs)
tag_constraints = []
if label_tags != ['None']:
for tags in label_tags:
tag_constraints.append(tuple(map(lambda t: t.strip(),
tags.split(','))))
if len(tag_constraints) == 0:
tag_constraints = None
print("Tag constraints: {}".format(tag_constraints))
print("Generate candidate bigram labels(with POS filtering)...")
finder = BigramLabelFinder('pmi', min_freq=label_min_df,
pos=tag_constraints)
if tag_constraints:
assert 'tag' in preprocessing_steps, \
'If tag constraint is applied, pos tagging(tag) should be performed'
cand_labels = finder.find(tagged_docs, top_n=n_cand_labels)
else: # if no constraint, then use untagged docs
cand_labels = finder.find(docs, top_n=n_cand_labels)
print("Collected {} candidate labels".format(len(cand_labels)))
print("Calculate the PMI scores...")
pmi_cal = PMICalculator(
doc2word_vectorizer=WordCountVectorizer(
min_df=5,
stop_words=load_lemur_stopwords()),
doc2label_vectorizer=LabelCountVectorizer())
pmi_w2l = pmi_cal.from_texts(docs, cand_labels)
print("Topic modeling using LDA...")
model = lda.LDA(n_topics=n_topics, n_iter=lda_n_iter,
random_state=lda_random_state)
model.fit(pmi_cal.d2w_)
print("\nTopical words:")
print("-" * 20)
for i, topic_dist in enumerate(model.topic_word_):
top_word_ids = np.argsort(topic_dist)[:-n_top_words:-1]
topic_words = [pmi_cal.index2word_[id_]
for id_ in top_word_ids]
print('Topic {}: {}'.format(i, ' '.join(topic_words)))
ranker = LabelRanker(apply_intra_topic_coverage=False)
return ranker.top_k_labels(topic_models=model.topic_word_,
pmi_w2l=pmi_w2l,
index2label=pmi_cal.index2label_,
label_models=None,
k=n_labels)
def get_topic_labels(
corpus_path,
n_topics,
n_top_words,
preprocessing_steps,
n_cand_labels,
label_min_df,
label_tags,
n_labels,
lda_random_state,
lda_n_iter,
):
"""
Refer the arguments to `create_parser`
"""
print("Loading docs...")
docs = load_line_corpus(corpus_path)
if "wordlen" in preprocessing_steps:
print("Word length filtering...")
wl_filter = CorpusWordLengthFilter(minlen=3)
docs = wl_filter.transform(docs)
if "stem" in preprocessing_steps:
print("Stemming...")
stemmer = CorpusStemmer()
docs = stemmer.transform(docs)
if "tag" in preprocessing_steps:
print("POS tagging...")
tagger = CorpusPOSTagger()
tagged_docs = tagger.transform(docs)
tag_constraints = []
if label_tags != ["None"]:
for tags in label_tags:
tag_constraints.append(tuple(map(lambda t: t.strip(), tags.split(","))))
if len(tag_constraints) == 0:
tag_constraints = None
print("Tag constraints: {}".format(tag_constraints))
print("Generate candidate bigram labels(with POS filtering)...")
finder = BigramLabelFinder("pmi", min_freq=label_min_df, pos=tag_constraints)
if tag_constraints:
assert "tag" in preprocessing_steps, "If tag constraint is applied, pos tagging(tag) should be performed"
cand_labels = finder.find(tagged_docs, top_n=n_cand_labels)
else: # if no constraint, then use untagged docs
cand_labels = finder.find(docs, top_n=n_cand_labels)
print("Collected {} candidate labels".format(len(cand_labels)))
print("Calculate the PMI scores...")
pmi_cal = PMICalculator(
doc2word_vectorizer=WordCountVectorizer(min_df=5, stop_words=load_lemur_stopwords()),
doc2label_vectorizer=LabelCountVectorizer(),
)
pmi_w2l = pmi_cal.from_texts(docs, cand_labels)
print("Topic modeling using LDA...")
model = lda.LDA(n_topics=n_topics, n_iter=lda_n_iter, random_state=lda_random_state)
model.fit(pmi_cal.d2w_)
print("\nTopical words:")
print("-" * 20)
for i, topic_dist in enumerate(model.topic_word_):
top_word_ids = np.argsort(topic_dist)[:-n_top_words:-1]
topic_words = [pmi_cal.index2word_[id_] for id_ in top_word_ids]
print("Topic {}: {}".format(i, " ".join(topic_words)))
ranker = LabelRanker(apply_intra_topic_coverage=False)
return ranker.top_k_labels(
topic_models=model.topic_word_, pmi_w2l=pmi_w2l, index2label=pmi_cal.index2label_, label_models=None, k=n_labels
)