if __name__ == '__main__':
## for LJ2M word vector model
w2vmodel = Word2Vec.load('/corpus/LJ2M/exp/model/lj2mStanfordparser_300features_50minwords_10context')
index2word_set = set(w2vmodel.index2word)
# # for 42B word vector model
# w2vmodel = txt_to_wordvecmodel(filepath='glove.42B.300d.txt')
# index2word_set = set(w2vmodel.keys())
use_unicode = False
if type(list(index2word_set)[0]) == unicode:
use_unicode = True
model = {}
data = pickle.load(open('/corpus/LJ40K/data/features/tfidf/GlobalInfo.pkl'))
LJ40K_axis = build_axis(LJ40K)
for i,word in enumerate(data):
if i % 1000 == 0: print i
if use_unicode:
word = word.decode('utf-8')
if word in index2word_set:
# case1:
model[word] = map_word_on_axis(word, Feeling_Wheel, model=w2vmodel)
# case2:
# model[word] = map_word_on_axis(word, LJ40K_axis, model=w2vmodel)
print 'dump..'
pickle.dump(model,open('model_wordvec_semantic_similarity_lemma_63768_LJ2M_Feeling_Wheel.pkl', 'wb'))
))
words_set = pickle.load(open('../data/wordset/wordsetlemma_35304.pkl'))
## two pole
# path_graph = pickle.load(open('../data/graph/calculate_path/ss_for_path_wv_lemma_42b_50172.pkl'))
# score_graph = pickle.load(open('../data/graph/calculate_score/pos_wv_lemma_42b_50172.pkl'))
# words_set = pickle.load(open('../data/wordset/wordsetlemma_35304.pkl'))
model = {}
for i, word in enumerate(words_set):
print i
## one pole
##case1
model[word] = map_word_on_axis(word,
LJ40K,
score_graph=score_graph,
path_graph=path_graph)
##case2
# model[word] = map_word_on_axis(word, LJ40K, score_graph=score_graph, path_graph=path_graph, threshold=0.6)
##case3
# model[word] = map_word_on_axis(word, Emotion_wheel, score_graph=score_graph, path_graph=path_graph)
## two pole
# model[word] = map_word_on_axis(word, Feeling_Wheel, score_graph=score_graph, path_graph=path_graph)
print 'dump..'
pickle.dump(
model,
open(
only for using graph to build the model
'''
## one pole
path_graph = pickle.load(open('../data/graph/calculate_path/ss_ant_for_path_wv_LJ40k_enhance_lemma_42b_50785.pkl'))
score_graph = pickle.load(open('../data/graph/calculate_score/pos_neg_wv_LJ40k_enhance_lemma_42b_50785.pkl'))
words_set = pickle.load(open('../data/wordset/wordsetlemma_35304.pkl'))
## two pole
# path_graph = pickle.load(open('../data/graph/calculate_path/ss_for_path_wv_lemma_42b_50172.pkl'))
# score_graph = pickle.load(open('../data/graph/calculate_score/pos_wv_lemma_42b_50172.pkl'))
# words_set = pickle.load(open('../data/wordset/wordsetlemma_35304.pkl'))
model = {}
for i,word in enumerate(words_set):
print i
## one pole
##case1
model[word] = map_word_on_axis(word, LJ40K, score_graph=score_graph, path_graph=path_graph)
##case2
# model[word] = map_word_on_axis(word, LJ40K, score_graph=score_graph, path_graph=path_graph, threshold=0.6)
##case3
# model[word] = map_word_on_axis(word, Emotion_wheel, score_graph=score_graph, path_graph=path_graph)
## two pole
# model[word] = map_word_on_axis(word, Feeling_Wheel, score_graph=score_graph, path_graph=path_graph)
print 'dump..'
pickle.dump(model,open('model_one_minusone_semantic_similarity_lj40k_enhance_lemma_50785_42b.pkl', 'wb'))
