def test(args):
corpus = load_corpus(args.input)
vocab, docs = corpus['vocab'], corpus['docs']
n_vocab = len(vocab)
doc_keys = docs.keys()
X_docs = []
for k in doc_keys:
X_docs.append(vecnorm(doc2vec(docs[k], n_vocab), 'logmax1', 0))
del docs[k]
X_docs = np.r_[X_docs]
ae = load_ae_model(args.load_model)
doc_codes = ae.predict(X_docs)
dump_json(dict(zip(doc_keys, doc_codes.tolist())), args.output)
print 'Saved doc codes file to %s' % args.output
if args.save_topics:
topics_strength = get_topics_strength(ae, revdict(vocab), topn=50)
print_topics(topics_strength)
# save_topics_strength(topics_strength, args.save_topics)
save_chinese_topics_strength(topics_strength, args.save_topics)
# topics = get_topics(ae, revdict(vocab), topn=10)
# write_file(topics, args.save_topics)
print 'Saved topics file to %s' % args.save_topics
if args.word_clouds:
queries = ['interest', 'trust', 'cash', 'payment', 'rate', 'price', 'stock', 'share', 'award', 'risk', 'security', 'bank', 'company',
'service', 'grant', 'agreement', 'proxy', 'loan', 'capital', 'asset', 'bonus', 'shareholder', 'income', 'financial', 'net', 'purchase',
'position', 'management', 'loss', 'salary', 'stockholder', 'due', 'business', 'transaction', 'govern', 'trading',
'tax', 'march', 'april', 'june', 'july']
weights = ae.get_weights()[0]
weights = unitmatrix(weights) # normalize
word_cloud(weights, vocab, queries, save_file=args.word_clouds)
print 'Saved word clouds file to %s' % args.word_clouds
if args.sample_words:
revocab = revdict(vocab)
queries = ['weapon', 'christian', 'compani', 'israel', 'law', 'hockey', 'comput', 'space']
words = []
for each in queries:
if each in vocab:
words.append(get_similar_words(ae, vocab[each], revocab, topn=11))
write_file(words, args.sample_words)
print 'Saved sample words file to %s' % args.sample_words
if args.translate_words:
revocab = revdict(vocab)
queries = [['father', 'man', 'woman'], ['mother', 'woman', 'man']]
for each in queries:
print each
print translate_words(ae, each, vocab, revocab, topn=10)
if args.calc_distinct:
# mean, std = calc_pairwise_cosine(ae)
# print 'Average pairwise angle (pi): %s (%s)' % (mean / math.pi, std / math.pi)
sd = calc_pairwise_dev(ae)
print 'Average squared deviation from 0 (90 degree): %s' % sd
def test(args):
corpus = load_corpus(args.input)
vocab, docs = corpus['vocab'], corpus['docs']
n_vocab = len(vocab)
doc_keys = docs.keys()
X_docs = []
for k in doc_keys:
X_docs.append(vecnorm(doc2vec(docs[k], n_vocab), 'logmax1', 0))
del docs[k]
X_docs = np.r_[X_docs]
model = AutoEncoder
# model = DeepAutoEncoder
ae = load_model(model, args.load_arch, args.load_weights)
doc_codes = ae.encoder.predict(X_docs)
dump_json(dict(zip(doc_keys, doc_codes.tolist())), args.output)
print('Saved doc codes file to %s' % args.output)
if args.save_topics:
topics_strength = get_topics_strength(ae, revdict(vocab), topn=10)
save_topics_strength(topics_strength, args.save_topics)
# topics = get_topics(ae, revdict(vocab), topn=10)
# write_file(topics, args.save_topics)
print('Saved topics file to %s' % args.save_topics)
if args.sample_words:
revocab = revdict(vocab)
queries = [
'weapon', 'christian', 'compani', 'israel', 'law', 'hockey',
'comput', 'space'
]
words = []
for each in queries:
words.append(get_similar_words(ae, vocab[each], revocab, topn=11))
write_file(words, args.sample_words)
print('Saved sample words file to %s' % args.sample_words)
if args.translate_words:
revocab = revdict(vocab)
queries = [['father', 'man', 'woman'], ['mother', 'woman', 'man']]
for each in queries:
print(each)
print(translate_words(ae, each, vocab, revocab, topn=10))
if args.calc_distinct:
# mean, std = calc_pairwise_cosine(ae)
# print('Average pairwise angle (pi): %s (%s)' % (mean / math.pi, std / math.pi))
sd = calc_pairwise_dev(ae)
print('Average squared deviation from 0 (90 degree): %s' % sd)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--corpus',
required=True,
type=str,
help='path to the corpus file')
parser.add_argument('-mf',
'--mod_file',
required=True,
type=str,
help='path to the word2vec mod file')
parser.add_argument('-sw',
'--sample_words',
type=str,
help='path to the output sample words file')
parser.add_argument('-o',
'--output',
type=str,
help='path to the output doc codes file')
args = parser.parse_args()
corpus = load_corpus(args.corpus)
docs, vocab_dict = corpus['docs'], corpus['vocab']
w2v = load_w2v(args.mod_file)
# doc_codes = doc_word2vec(w2v, docs, revdict(vocab_dict), args.output, avg=True)
if args.sample_words:
queries = [
'weapon', 'christian', 'compani', 'israel', 'law', 'hockey',
'comput', 'space'
]
words = []
for each in queries:
words.append(get_similar_words(w2v, each, topn=5))
write_file(words, args.sample_words)
print('Saved sample words file to %s' % args.sample_words)
import pdb
pdb.set_trace()
def test(args):
corpus = load_corpus(args.input)
vocab, docs = corpus['vocab'], corpus['docs']
n_vocab = len(vocab)
doc_keys = list(docs.keys())
X_docs = []
for k in doc_keys:
X_docs.append(vecnorm(doc2vec(docs[k], n_vocab), 'logmax1', 0))
del docs[k]
X_docs = np.r_[X_docs]
ae = load_ae_model(args.load_model)
doc_codes = ae.predict(X_docs)
dump_json(dict(zip(doc_keys, doc_codes.tolist())), args.output)
print('Saved doc codes file to %s' % args.output)
if args.save_topics:
topics_strength = get_topics_strength(ae, revdict(vocab), topn=10)
save_topics_strength(topics_strength, args.save_topics)
# topics = get_topics(ae, revdict(vocab), topn=10)
# write_file(topics, args.save_topics)
print('Saved topics file to %s' % args.save_topics)
if args.word_clouds:
queries = [
'interest', 'trust', 'cash', 'payment', 'rate', 'price', 'stock',
'share', 'award', 'risk', 'security', 'bank', 'company', 'service',
'grant', 'agreement', 'proxy', 'loan', 'capital', 'asset', 'bonus',
'shareholder', 'income', 'financial', 'net', 'purchase',
'position', 'management', 'loss', 'salary', 'stockholder', 'due',
'business', 'transaction', 'govern', 'trading', 'tax', 'march',
'april', 'june', 'july'
]
weights = ae.get_weights()[0]
weights = unitmatrix(weights) # normalize
word_cloud(weights, vocab, queries, save_file=args.word_clouds)
print('Saved word clouds file to %s' % args.word_clouds)
if args.sample_words:
revocab = revdict(vocab)
while True:
print("----------------------------\n? ", end='')
sys.stdout.flush()
query = sys.stdin.readline()
query = re.sub(r'[^\w\s-]', ' ',
query) # remove punctuations except hyphen
query_words = []
for word in query.lower().split(): # convert to lowercase
if word not in stopwords.words('english'): # remove stop words
query_words.append(word)
# ===== make the query length to be (32) = times_steps size
"""long_enough = False
while not long_enough:
for word in query_words:
query_vectors.append(word2vec_map[word])
if len(query_vectors) == 32:
long_enough = True
break"""
words = []
for each in query_words:
words.append(
get_similar_words(ae, vocab[each], revocab, topn=11))
write_file(words, args.sample_words)
print('Saved sample words file to %s' % args.sample_words)
if args.translate_words:
revocab = revdict(vocab)
queries = [['father', 'man', 'woman'], ['mother', 'woman', 'man']]
for each in queries:
print(each)
print(translate_words(ae, each, vocab, revocab, topn=10))
if args.calc_distinct:
# mean, std = calc_pairwise_cosine(ae)
# print 'Average pairwise angle (pi): %s (%s)' % (mean / math.pi, std / math.pi)
sd = calc_pairwise_dev(ae)
print('Average squared deviation from 0 (90 degree): %s' % sd)