def __init__(self, lexicon_name='', *args, **kwargs): super().__init__(*args, **kwargs) self.lexicon_name = lexicon_name model0 = emb.get_custom0() self.embedding = emb.get_custom3(initial_model=model0, lexicon_name=self.lexicon_name, suffix='model0_' + self.lexicon_name)
def main(): parser = argparse.ArgumentParser( description='Build inequalities.', formatter_class=argparse.ArgumentDefaultsHelpFormatter) parser.add_argument('output', help='Output file') args = parser.parse_args() model = emb.get_custom0() lexicon = read_bing_liu(res.bing_liu_lexicon_path) print('Save inequalities to %s', args.output) feat.find_ineq(model, lexicon, args.output)
def load_resources(self): super().load_resources() self.word2vec = emb.get_custom0(word2vec_param=self.word2vec_param)
# anew_french = reader.read_anew(res.anew_french_lexicon_path) # lexicons = [('lidilem_adjectifs', lidilem_adjectifs_lexicon), # ('lidilem_noms', lidilem_noms_lexicon), # ('lidilem_verbes', lidilem_verbes_lexicon), # ('blogoscopie', blogoscopie_lexicon)] lexicons = [('lidilem', lidilem_lexicon), ('blogoscopie', blogoscopie_lexicon)] for (lex_name, lex) in lexicons: utils.remove_multi_words_in_lexicon(lex) model_name = 'model0' logger.info('Processing %s', model_name) model = emb.get_custom0(train_path=train_path) for (lex_test_name, lex_test) in lexicons: logger.info('Compare %s on %s', model_name, lex_test_name) emb.compare_model_with_lexicon(model, lex_test) emb.compare_model_with_lexicon_class(model, lex_test) model_name = 'model1' logger.info('Processing %s', model_name) for lex_train_name, lex_train in lexicons: logger.info('Training %s with %s', model_name, lex_train_name) model = emb.get_custom1(train_path=train_path, lexicon=lex_train, suffix=lex_train_name) for lex_test_name, lex_test in lexicons: # Skip test lexicon if it's the same as the training lexicon if lex_test_name == lex_train_name: continue logger.info('Compare %s on %s', model_name, lex_test_name)
def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) self.embedding = emb.get_custom0()
# -*- coding: utf-8 -*- import logging import numpy as np import embeddings as emb import resources as res import reader import utils logger = logging.getLogger(__name__) models = [] models.append(('model0', emb.get_custom0())) models.append(('model1', emb.get_custom1())) models.append(('modelGnews', emb.get_gnews())) model0 = emb.get_custom0() # model1 = emb.get_custom1() modelGnews = emb.get_gnews() topn = 1000 sample_size = 5000 bing_liu_lexicon = reader.read_bing_liu(res.bing_liu_lexicon_path) nrc_emotion_lexicon = reader.read_nrc_emotion(res.nrc_emotion_lexicon_path) nrc_emotions_lexicon = reader.read_nrc_emotions(res.nrc_emotion_lexicon_path) lexicons = [('bing_liu_lexicon', bing_liu_lexicon), ('nrc_emotion_lexicon', nrc_emotion_lexicon),