Python Glove.save方法代码示例

# 需要导入模块: from glove import Glove [as 别名]
# 或者: from glove.Glove import save [as 别名]
def main():
    corpus_model = Corpus()
    corpus_model = Corpus.load('bioc-corpus-AZ2.model')
    glove = Glove(no_components=100, learning_rate=0.05)
    glove.fit(corpus_model.matrix, epochs=10, no_threads=16, verbose=True)
    glove.add_dictionary(corpus_model.dictionary)
    glove.save('bioc-glove-AZ2.model')

# 需要导入模块: from glove import Glove [as 别名]
# 或者: from glove.Glove import save [as 别名]
 def pretrain(self,data_src):
     if not os.path.isfile("glove.model"):
         data_src = DataClean([
                             ["[^a-z]"," "],  # only letters
                             [" [ ]+", " "],  # remove extra spaces
                             ],html_clean=True,split_words=True).fit(data_src).transform(data_src)
         corpus_model = Corpus()
         corpus_model.fit(data_src,window=self.window)
         glove = Glove(no_components=self.num_features,learning_rate=self.learning_rate)
         glove.fit(corpus_model.matrix,epochs=self.epochs,verbose=True)
         glove.add_dictionary(corpus_model.dictionary)
         glove.save("glove.model")

# 需要导入模块: from glove import Glove [as 别名]
# 或者: from glove.Glove import save [as 别名]
        print('Collocations: %s' % corpus_model.matrix.nnz)

    if args.train:
        # Train the GloVe model and save it to disk.

        if not args.create:
            # Try to load a corpus from disk.
            print('Reading corpus statistics')
            corpus_model = Corpus.load('corpus.model')

            print('Dict size: %s' % len(corpus_model.dictionary))
            print('Collocations: %s' % corpus_model.matrix.nnz)

        print('Training the GloVe model')

        glove = Glove(no_components=100, learning_rate=0.05)
        glove.fit(corpus_model.matrix, epochs=int(args.train),
                  no_threads=args.parallelism, verbose=True)
        glove.add_dictionary(corpus_model.dictionary)

        glove.save('glove.model')

    if args.query:
        # Finally, query the model for most similar words.
        if not args.train:
            print('Loading pre-trained GloVe model')
            glove = Glove.load('glove.model')

        print('Querying for %s' % args.query)
        pprint.pprint(glove.most_similar(args.query, number=10))

# 需要导入模块: from glove import Glove [as 别名]
# 或者: from glove.Glove import save [as 别名]
@author: dannl
'''
from glove import Glove
from glove import Corpus
import time

cooc_file='/home/dannl/tmp/newstech/glove/word.cooc'
model_file='/home/dannl/tmp/newstech/glove/glove.model'

oldtime=time.time()
# get a cooccurrence matrix
corpus_cooc = Corpus.load(cooc_file)

# get a model
glove = Glove(no_components=100, learning_rate=0.05)
glove.fit(corpus_cooc.matrix, epochs=5,no_threads=4, verbose=True)
glove.add_dictionary(corpus_cooc.dictionary)
glove.save(model_file)

# count=0
# for word,wid in corpus_cooc.dictionary.items():
#     count+=1
#     if count>100:
#         break
#     print word,wid
    
print('Dict size: %s' % len(corpus_cooc.dictionary))
print('Collocations: %s' % corpus_cooc.matrix.nnz)

print 'time cost:%.2f'%(time.time()-oldtime)

# 需要导入模块: from glove import Glove [as 别名]
# 或者: from glove.Glove import save [as 别名]
    corpus = Corpus.load("cache/corpus.p")
except:
    print("Training corpus...")
    corpus.fit(texts, window=max_sentence_length)
    corpus.save("cache/corpus.p")

glove = Glove(no_components=number_components, learning_rate=0.05)
try:
    print("Loading pretrained GloVe vectors...")
    glove = Glove.load("cache/glove.p")
except:
    print("Training GloVe vectors...")
    # More epochs seems to make it worse
    glove.fit(corpus.matrix, epochs=30, no_threads=4, verbose=True)
    glove.add_dictionary(corpus.dictionary)
    glove.save("cache/glove.p")

# Convert input text
print("Vectorizing input sentences...")
X = vectify(texts, previous_message, glove.dictionary, max_sentence_length, contextual)
y = np.array([x == u'1' for x in classes]).astype(np.int32)

X, y, texts = X[:207458], y[:207458], texts[:207458]

def print_accurate_forwards(net, history):
    X_train, X_valid, y_train, y_valid = net.train_split(X, y, net)
    y_classified = net.predict(X_valid)
    acc_fwd = np.mean([x == y_ and y_ == 1 for x, y_ in zip(y_valid, y_classified)])/np.mean(y_valid)
    fls_pos = np.mean([x != y_ and y_ == 0 for x, y_ in zip(y_classified, y_valid)])/(np.mean(y_valid))
    print('Accurately forwarded: {:.4f}'.format(acc_fwd) + ', False Positives: {:.4f}'.format(fls_pos) + ', Valid forwards: {:.4f}'.format((acc_fwd / (acc_fwd + fls_pos))) )