Created
July 21, 2018 14:44
-
-
Save Honga1/25e1bb8f73b912e7be79adb493ca6f4a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python | |
# -*- coding: utf-8 -*- | |
import json | |
import csv | |
from nltk.stem.lancaster import LancasterStemmer | |
stemmer = LancasterStemmer() | |
f = open('mscoco.json') | |
data = json.load(f) | |
f.close() | |
corpus = [] | |
for image_desc in data['val']: | |
tot_phrase = [] | |
for image_sentence in image_desc[1]: | |
sentence = [] | |
for word in image_sentence: | |
word = stemmer.stem(word) | |
sentence.append(word) | |
sentence_str = ' '.join(sentence) | |
tot_phrase.append(sentence_str) | |
tot_para = ''.join(tot_phrase) | |
corpus.append(tot_para) | |
from sklearn.feature_extraction.text import TfidfVectorizer | |
tf = TfidfVectorizer(analyzer='word', ngram_range=(1, 3), min_df=0, | |
stop_words='english') | |
corpus = corpus[0:4000] | |
tfidf_matrix = tf.fit_transform(corpus) | |
feature_names = tf.get_feature_names() | |
print len(feature_names) | |
print feature_names[50:70] | |
print tfidf_matrix | |
dense = tfidf_matrix.todense() | |
image = dense[0].tolist()[0] | |
phrase_scores = [pair for pair in zip(range(0, len(image)), image) | |
if pair[1] > 0] | |
print len(phrase_scores) | |
print sorted(phrase_scores, key=lambda t: t[1] * -1)[:5] | |
sorted_phrase_scores = sorted(phrase_scores, key=lambda t: t[1] * -1) | |
for (phrase, score) in [(feature_names[word_id], score) for (word_id, | |
score) in sorted_phrase_scores][:20]: | |
print '{0: <20} {1}'.format(phrase, score) | |
with open('out.csv', 'w') as file: | |
writer = csv.writer(file, delimiter=',') | |
writer.writerow(['Image', 'Phrase', 'Score']) | |
doc_id = 0 | |
for doc in tfidf_matrix.todense(): | |
print 'Document %d' % doc_id | |
word_id = 0 | |
for score in doc.tolist()[0]: | |
if score > 0: | |
word = feature_names[word_id] | |
writer.writerow([doc_id + 1, word.encode('utf-8'), | |
score]) | |
word_id += 1 | |
doc_id += 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment