def build_model_glove(args):
from glove import Glove, Corpus
if not os.path.exists(args.corpus_model) or \
max(map(os.path.getmtime, args.input)) >= os.path.getmtime(args.corpus_model):
# Build the corpus dictionary and the cooccurrence matrix.
logging.info('Pre-processing corpus')
corpus_model = Corpus()
corpus_model.fit(get_sentences(args), window=CONFIG['glove']['window'])
corpus_model.save(args.corpus_model)
logging.info('Dict size: %s' % len(corpus_model.dictionary))
logging.info('Collocations: %s' % corpus_model.matrix.nnz)
else:
# Try to load a corpus from disk.
logging.info('Reading corpus statistics')
corpus_model = Corpus.load(args.corpus_model)
logging.info('Dict size: %s' % len(corpus_model.dictionary))
logging.info('Collocations: %s' % corpus_model.matrix.nnz)
# Train the GloVe model and save it to disk.
logging.info('Training the GloVe model')
glove = Glove(no_components=CONFIG['glove']['size'], learning_rate=CONFIG['glove']['learning_rate'])
glove.fit(corpus_model.matrix, epochs=CONFIG['glove']['epochs'],
no_threads=args.workers, verbose=args.verbose)
glove.add_dictionary(corpus_model.dictionary)
return glove
def train_glove(target_group, glove_para, src_file, save_model_name):
"""
example: train_glove(target_group='words', glove_para=glove_para_word)
after save the mode, u can use it by : glove_ana = Glove.load('glove_words.model')
:param target_group: 'words' or 'chars'
:param glove_para: glove_para_word = {'window_size':4, 'no_components':300, 'learning_rate':0.05, 'no_epochs':2, 'parallelism':4}
:return:
"""
corpus_model = Corpus()
corpus_model.fit(read_corpus(src_file=src_file,
words_or_chars=target_group),
window=glove_para['window_size']
) #avg word size is 6 for each sentence
corpus_model.save('corpus_model_{}.model'.format(target_group))
print target_group
print('Dict size: %s' % len(corpus_model.dictionary))
print('Collocations: %s' % corpus_model.matrix.nnz)
print('Training the GloVe model')
glove = Glove(no_components=glove_para['no_components'],
learning_rate=glove_para['learning_rate'])
glove.fit(corpus_model.matrix,
epochs=glove_para['no_epochs'],
no_threads=glove_para['parallelism'],
verbose=True)
glove.add_dictionary(corpus_model.dictionary)
glove.save(save_model_name)
def train_glove(corpus, params, exp_id, save_dir, save_dict=False):
dictionary = load_glove_dictionary(exp_id, save_dir)
# Build the corpus dictionary and the cooccurrence matrix.
print('Pre-processing corpus')
dict_path = os.path.join(save_dir, 'glove_dict_{}.model'.format(exp_id))
if os.path.exists(dict_path):
corpus_model = Corpus.load(dict_path)
else:
corpus_model = Corpus(dictionary)
corpus_model.fit(corpus,
window=params['window'] * 2,
ignore_missing=True)
if save_dict:
corpus_model.save(dict_path)
print('Dict size: %s' % len(corpus_model.dictionary))
print('Collocations: %s' % corpus_model.matrix.nnz)
glove = Glove(no_components=100, learning_rate=params['alpha'])
glove.fit(corpus_model.matrix,
epochs=50,
no_threads=params['workers'],
verbose=True)
glove.add_dictionary(corpus_model.dictionary)
return glove
class GloVeFilter(object):
def __init__(self):
# Corpus model
vocab = dict(torch.load("../data/dialogue.vocab.pt", "text"))
self.corpus_model = Corpus(dictionary=vocab['tgt'].stoi)
# Model
self.glove = Glove(no_components=args.no_components,
learning_rate=args.learning_rate)
def load_corpus_from_txt(self):
print('Reading corpus statistics...')
#texts = [self.pp.preprocessing(l.strip().decode("utf8", "ignore")) for l in open(args.data_path)]
texts = [
l.strip().decode("utf8", "ignore").split(" ")
for l in open(args.data_path)
]
self.corpus_model.fit(texts, window=args.window, ignore_missing=True)
self.corpus_model.save(args.corpus_model_path)
print('Dict size: %s' % len(self.corpus_model.dictionary))
print('Collocations: %s' % self.corpus_model.matrix.nnz)
def load_corpus_from_model(self):
print('Reading corpus statistics...')
self.corpus_model = Corpus.load(args.corpus_model_path)
print('Dict size: %s' % len(self.corpus_model.dictionary))
print('Collocations: %s' % self.corpus_model.matrix.nnz)
def train(self):
print('Training the GloVe model...')
self.glove.fit(self.corpus_model.matrix,
epochs=args.epochs,
verbose=True)
self.glove.add_dictionary(self.corpus_model.dictionary)
self.glove.save(args.model_path)
print('Training finished')
def train_glove_fashionrec(dimensionality, context, epochs):
""" Train with Glove on IG corpora"""
total_count, vocab_size = corpus_stats("data/clean2_corpus.txt")
print("total word count: {}, vocabulary size: {}".format(
total_count, vocab_size))
fileName = "results/training/glove_fashion_epochs" + str(
epochs) + "_d" + str(dimensionality) + "_c" + str(
context) + "_" + ".txt"
corpus = readCorpus()
lines = corpus.split("\n")
linessplit = map(lambda x: x.split(" "), lines)
corpus_model = Corpus()
start_time = datetime.now()
corpus_model.fit(linessplit, window=context)
corpusModelFile = "trained/glove_fashion_epochs" + str(
epochs) + "_d" + str(dimensionality) + "_c" + str(
context) + "_corpus" + ".model"
corpus_model.save(corpusModelFile)
glove = Glove(no_components=dimensionality, learning_rate=0.05)
glove.fit(corpus_model.matrix,
epochs=int(epochs),
no_threads=8,
verbose=True)
glove.add_dictionary(corpus_model.dictionary)
time_elapsed = datetime.now() - start_time
gloveModelFile = "trained/glove_fashion_epochs" + str(epochs) + "_d" + str(
dimensionality) + "_c" + str(context) + "_vecs" + ".model"
glove.save(gloveModelFile)
notes = "Glove Fashion Data," + str(dimensionality) + " dim, " + str(
context) + " context, " + str(
epochs) + " epochs \n" + "Training time: " + str(time_elapsed)
save_to_file(fileName, notes)
gloveVecFile = "trained/glove_fashion_epochs" + str(epochs) + "_d" + str(
dimensionality) + "_c" + str(context) + "_vecs" + ".vec"
save_glove_bin_to_vec(glove, gloveVecFile)
def build_model_glove(args):
if not os.path.exists(args.corpus_model) or \
max(map(os.path.getmtime, args.input)) >= os.path.getmtime(args.corpus_model):
# Build the corpus dictionary and the cooccurrence matrix.
logging.info('Pre-processing corpus')
corpus_model = Corpus()
corpus_model.fit(get_sentences(args), window=CONFIG['glove']['window'])
corpus_model.save(args.corpus_model)
logging.info('Dict size: %s' % len(corpus_model.dictionary))
logging.info('Collocations: %s' % corpus_model.matrix.nnz)
else:
# Try to load a corpus from disk.
logging.info('Reading corpus statistics')
corpus_model = Corpus.load(args.corpus_model)
logging.info('Dict size: %s' % len(corpus_model.dictionary))
logging.info('Collocations: %s' % corpus_model.matrix.nnz)
# Train the GloVe model and save it to disk.
logging.info('Training the GloVe model')
glove = Glove(no_components=CONFIG['glove']['size'], learning_rate=CONFIG['glove']['learning_rate'])
glove.fit(corpus_model.matrix, epochs=CONFIG['glove']['epochs'],
no_threads=args.workers, verbose=args.verbose)
glove.add_dictionary(corpus_model.dictionary)
return glove
def generate_glove_corpus():
global article_info_path, output_path
write_log('GloVe Load article info : Start')
with open(article_info_path, 'r') as f_art:
article_info = json.load(f_art)
write_log('GloVe Load article info : End')
write_log('GloVe Generate sentences : Start')
sentences = []
for url, dict_info in article_info.items():
sentence_header = dict_info.get('sentence_header', None)
sentence_body = dict_info.get('sentence_body', None)
if (sentence_header == None) or (sentence_body == None):
continue
words = []
#for sentence in sentence_header + sentence_body:
for sentence in sentence_header:
for word in sentence.split(' '):
words.append(word)
sentences.append(words)
write_log('GloVe Generate sentences : End')
write_log('GloVe Generate corpus : Start')
corpus = Corpus()
corpus.fit(sentences, window=10)
write_log('GloVe Generate corpus : End')
corpus.save(output_path)
def glove_single(domain_name):
corpus_model = Corpus()
corpus_model.fit(labeled_reviews(domain_name), window=10)
corpus_model.save('../work/%s/corpus.model'% domain_name)
print('Dict size: %s' % len(corpus_model.dictionary))
print('Collocations: %s' % corpus_model.matrix.nnz)
print('Training the GloVe model')
model = Glove(no_components=300, learning_rate=0.05)
model.fit(corpus_model.matrix, epochs=int(10),
no_threads=6, verbose=True)
model.add_dictionary(corpus_model.dictionary)
model.save('../work/%s/glove.model' % domain_name)
return
def train_glove(sequence_file_path, output_folder, no_components, epochs):
corpus_model = Corpus()
corpus_model.fit(read_corpus(sequence_file_path), window=10)
corpus_model.save(get_corpus_model_path(output_folder))
print('Dict size: %s' % len(corpus_model.dictionary))
print('Collocations: %s' % corpus_model.matrix.nnz)
glove = Glove(no_components=int(no_components), learning_rate=0.05)
glove.fit(corpus_model.matrix,
epochs=int(epochs),
no_threads=50,
verbose=True)
glove.add_dictionary(corpus_model.dictionary)
glove.save(get_glove_model_path(output_folder))
def create_glove_corpus():
corpus_path = '%s/Embedding/glove/glove.corpus'%(folder)
if not os.path.exists(corpus_path):
corpus = Corpus() # 建立glove corpus物件，並設定matrix scan window大小
corpus.fit(embedding_corpus, window=10)
corpus.fit(embedding_corpus, window=10)
print('Dict size: %s' % len(corpus.dictionary))
print('Collocations: %s' % corpus.matrix.nnz)
corpus.save('%s/Embedding/glove/glove.corpus'%(folder)) # 存字典
else:
corpus = Corpus.load('%s/Embedding/glove/glove.corpus'%(folder))
print('Already get glove corpus')
return corpus
def get_glove_corpus_model(setting):
if not force_gen and os.path.isfile("models/" + setting_string(**setting) + "__glove_corpus_model"):
return Corpus.load("models/" + setting_string(**setting) + "__glove_corpus_model")
else:
token2index_map = json.load(open("derived_data/" + setting_string(**setting) + "__processed_token2index_map.json"))
if setting['granularity'] == 'documents':
item_generator = get_all_documents_as_token_list(setting['token_method'], setting['data_basis'])
elif setting['granularity'] == 'paragraphs':
item_generator = get_all_docs_paragrahps_as_token_list(setting['token_method'], setting['data_basis'])
else:
raise
corpus = (filter(lambda token: token in token2index_map, doc[1]) for doc in item_generator)
corpus_model = Corpus(dictionary=token2index_map)
corpus_model.fit(corpus)
corpus_model.save("models/" + setting_string(**setting) + "__glove_corpus_model")
return corpus_model
def prepare_corpus(args):
logging.info('Preparing corpus')
word_counts = Counter()
for tokens in map(str.split, open(args.data_path)):
word_counts.update(tokens)
logging.info('Counted {} unique words.'.format(len(word_counts)))
logging.info('Truncating vocabulary at min_count {}, max_tokens {}'.format(
args.min_count, args.max_tokens))
tokens = {
token
for token, count in word_counts.most_common(args.max_tokens)
if count >= args.min_count
}
dictionary = {token: i for i, token in enumerate(tokens)}
logging.info('Using vocabulary of size {}'.format(len(dictionary)))
corpus = Corpus(dictionary)
logging.info('Counting co-occurrences. Window size {}'.format(args.window))
corpus.fit(map(str.split, open(args.data_path)),
window=args.window,
ignore_missing=True)
corpus.save(args.co_path)
return corpus
len_train = train.shape[0]
qs = []
ts = []
ds = []
sentences = []
for q, t in zip(data_all['question1'].values.tolist(),
data_all['question2'].values.tolist()):
sentences.append(q.split(' '))
sentences.append(t.split(' '))
qs.append(q.split(' '))
ts.append(t.split(' '))
corpus_model = Corpus()
corpus_model.fit(sentences, window=10)
corpus_model.save(path + 'corpus.mdl')
corpus_model = Corpus.load(path + 'corpus.mdl')
glove = Glove(no_components=200, learning_rate=0.05)
glove.fit(corpus_model.matrix, epochs=10, no_threads=7, verbose=True)
glove.add_dictionary(corpus_model.dictionary)
glove.save(path + 'glove.glv')
glove = Glove.load(path + 'glove.glv')
print glove
qt_sims_dists = []
qt_diff = []
def calc_cosine_dist(text_a, text_b, metric='euclidean'):
def train_glove(inst, meta_data={}):
start_total = datetime.now()
meta_data["glove_params"] = settings.GLOVE_PARAMS
glove_paramgrid = ParameterGrid(settings.GLOVE_PARAMS)
for params in glove_paramgrid:
start = datetime.now()
# MAKE CORPUS
# set corpus filepath
corpus_fp = os.path.join(settings.WVEC_OPT_DIRP, '{}_window{}.glovecorpus'.format(
settings.DATASET,
params["window"]))
# load if corpus exists
if os.path.isfile(corpus_fp):
logging.info("Loading existing corpus {}.".format(corpus_fp))
corpus_model = Corpus.load(corpus_fp)
logging.info("Successfully loaded existing corpus {}.".format(corpus_fp))
# make a new coocurrence corpus if it does not exist
else:
logging.info("Creating new corpus at {}.".format(corpus_fp))
corpus_model = Corpus()
corpus_model.fit(inst, window=params["window"])
os.makedirs(settings.WVEC_OPT_DIRP, exist_ok=True)
corpus_model.save(corpus_fp)
logging.info("Dict size: {}.".format(len(corpus_model.dictionary)))
logging.info("Collocations: {}.".format(corpus_model.matrix.nnz))
# GLOVE VECTOR TRAINING
glove = Glove(no_components=params["dims"], learning_rate=params["lr"])
logging.info("Start fitting GloVe with parameters: {}.".format(params))
glove.fit(corpus_model.matrix, epochs=params["epochs"],
no_threads=params["njobs"], verbose=False)
glove.add_dictionary(corpus_model.dictionary)
os.makedirs(settings.WVEC_OPT_DIRP, exist_ok=True)
model_name = 'glove.{}_w{}_lr{}_ep{}.{}d.glovemodel'.format(settings.DATASET,
params["window"],
params["lr"],
params["epochs"],
params["dims"])
glove.save(os.path.join(settings.WVEC_OPT_DIRP, model_name))
duration = (datetime.now() - start).total_seconds()
meta_data["models"][model_name] = params
meta_data["models"][model_name]["duration_training"] = duration
logging.info("Finished fitting GloVe {} in {}s with parameters: {}.".format(
model_name,
duration,
params))
# SIMILARITY TEST
for test_word in settings.TESTSIM_WORDS:
if test_word not in meta_data["most_similar"]:
meta_data["most_similar"][test_word] = {}
logging.info("Querying model {} for {} most similar to \'{}\':".format(
model_name,
settings.N_TESTSIM,
test_word))
sim = glove.most_similar(test_word, number=settings.N_TESTSIM)
meta_data["most_similar"][test_word][model_name] = sim
logging.info(pprint.pformat(sim))
total_duration = (datetime.now() - start_total).total_seconds()
meta_data["glove_duration_training"] = total_duration
return meta_data
def main():
corpus_model = Corpus()
corpus_model.fit(itertexts(), window=10, max_map_size=1000000)
corpus_model.save('bioc-corpus-AZ2.model')
args = parser.parse_args()
if args.create:
# Build the corpus dictionary and the cooccurrence matrix.
print('Pre-processing corpus')
if args.wiki:
print('Using wikipedia corpus')
get_data = read_wikipedia_corpus
else:
get_data = read_corpus
corpus_cooc = Corpus()
corpus_cooc.fit(get_data(args.create), window=10)
corpus_cooc.save('corpus.model')
print('Dict size: %s' % len(corpus_cooc.dictionary))
print('Collocations: %s' % corpus_cooc.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_cooc = Corpus.load('corpus.model')
print('Dict size: %s' % len(corpus_cooc.dictionary))
print('Collocations: %s' % corpus_cooc.matrix.nnz)
'''
from glove import Glove
from glove import Corpus
from gensim import corpora
import time
dic_file=r'/home/dannl/tmp/newstech/glove/news.dic'
corpus_file='/home/dannl/tmp/newstech/news.txt'
cooc_file='/home/dannl/tmp/newstech/glove/word.cooc'
def read_corpus(filename):
with open(filename, 'r') as datafile:
for line in datafile:
yield line.split()[1:]
# get a cooccurrence matrix
oldtime=time.time()
dictionary = corpora.Dictionary.load(dic_file)
# corpus_cooc = Corpus()
# corpus_cooc.fit(read_corpus(corpus_file), window=10)
corpus_cooc = Corpus(dictionary=dictionary.token2id)
corpus_cooc.fit(read_corpus(corpus_file), window=10,ignore_missing=True)
corpus_cooc.save(cooc_file)
print('Dict size: %s' % len(corpus_cooc.dictionary))
print('Collocations: %s' % corpus_cooc.matrix.nnz)
print 'time cost:%.2f'%(time.time()-oldtime,)
action='store',
type=int,
default=10,
help=
'The length of the (symmetric) context window used for co-occurrence.')
parser.add_argument('--max_count',
'-m',
action='store',
type=int,
default=100,
help='The max co-occurrence count.')
args = parser.parse_args()
print('Pre-processing corpus')
corpus_model = Corpus()
corpus_model.fit(read_corpus(args.corpus), window=args.window)
corpus_model.save('%s.corpus.model' % args.out)
print('Dict size: %s' % len(corpus_model.dictionary))
print('Collocations: %s' % corpus_model.matrix.nnz)
print('Training the GloVe model')
glove = Glove(no_components=args.components,
learning_rate=args.learning_rate,
max_count=args.max_count)
glove.fit(corpus_model.matrix,
epochs=int(args.train),
no_threads=args.parallelism,
verbose=True)
glove.add_dictionary(corpus_model.dictionary)
glove.save('%s.glove.model' % args.out)
args = parser.parse_args()
if args.create:
# Build the corpus dictionary and the cooccurrence matrix.
print('Pre-processing corpus')
if args.wiki:
print('Using wikipedia corpus')
get_data = read_wikipedia_corpus
else:
get_data = read_corpus
corpus_model = Corpus()
corpus_model.fit(get_data(args.create), window=10)
corpus_model.save('corpus.model')
print('Dict size: %s' % len(corpus_model.dictionary))
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)
texts.append(clean(row[3]).split())
classes.append(row[0])
# Calculate distribution, to account for 95th percentile of messages.
max_sentence_length = int(np.mean([len(x) for x in texts]) + (norm.ppf(0.95) * np.std([len(x) for x in texts])))
print("Max sentence length: {}, put that in settings.json.".format(max_sentence_length))
corpus = Corpus()
try:
print("Loading pretrained corpus...")
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)
help='Get closes words to this word.')
args = parser.parse_args()
if args.create:
# Build the corpus dictionary and the cooccurrence matrix.
print('Pre-processing corpus')
if args.wiki:
print('Using wikipedia corpus')
get_data = read_wikipedia_corpus
else:
get_data = read_corpus
corpus_model = Corpus()
corpus_model.fit(get_data(args.create), window=10)
corpus_model.save('corpus.model', 'corpus.pmi')
print('Dict size: %s' % len(corpus_model.dictionary))
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)
# import pdb; pdb.set_trace()
#importing the glove library
from glove import Corpus, Glove
import pandas as pd
from tqdm import tqdm
pruned_tagset = pd.read_csv("termstr_all.csv", index_col=0)
pruned_tagset = pruned_tagset[pruned_tagset['termstr'].notnull()]
tqdm.pandas(desc="split tagset string")
pruned_tagset = list(
pruned_tagset['termstr'].progress_apply(lambda x: x.split(';')))
#creating a corpus object
corpus = Corpus()
#training the corpus to generate the co occurence matrix which is used in GloVe
#
corpus.fit(pruned_tagset, window=3)
corpus.save('corpus.model')
#creating a Glove object which will use the matrix created in the above lines to create embeddings
#We can set the learning rate as it uses Gradient Descent and number of components
glove = Glove(no_components=150, learning_rate=0.05)
glove.fit(corpus.matrix, epochs=30, no_threads=4, verbose=True)
glove.add_dictionary(corpus.dictionary)
glove.save('glove.model')
#print(glove.dictionary)
termvec = glove.word_vectors
termdic = glove.dictionary
temp1 = glove.most_similar('rock', number=10)
print(temp1)
import pickle
def main():
corpus_model = Corpus()
corpus_model.fit(itertexts(), window=10, max_map_size=1000000)
corpus_model.save('bioc-corpus-AZ2.model')
if not os.path.exists("Embedding/main_cat/glove/glove.model"):
corpus_model = Corpus()
corpus_model.fit(sentences, window=10)
#corpus_model.save('corpus.model')
print('Dict size: %s' % len(corpus_model.dictionary))
print('Collocations: %s' % corpus_model.matrix.nnz)
glove = Glove(no_components=300, learning_rate=0.05)
glove.fit(corpus_model.matrix, epochs=100,
no_threads=10, verbose=True)
glove.add_dictionary(corpus_model.dictionary)
glove.save('Embedding/main_cat/glove/glove.model') # 存模型
corpus_model.save('Embedding/main_cat/glove/corpus.model') # 存字典
glove = Glove.load('Embedding/main_cat/glove/glove.model')
corpus_model = Corpus.load('Embedding/main_cat/glove/corpus.model')
# In[ ]:
vocab_file = "Embedding/main_cat/glove/word.vocab"
if not os.path.exists(vocab_file):
# vocab_count = len(glove.dictionary)
vocab_count = 0
print("Writing vocab file...")
"""
Created on Fri Sep 14 12:45:30 2018
@author: charlie
"""
import itertools
from gensim.models.word2vec import Text8Corpus
from glove import Corpus, Glove
import os
cur_dir = os.getcwd()
glove_fname = '/glove.model'
corpus_fname = "/corpus.model"
if os.path.exists(cur_dir + glove_fname):
glove = Glove.load(cur_dir+glove_fname)
# corpus = Corpus.load(cur_dir+corpus_fname)
else:
sentences = list(itertools.islice(Text8Corpus('text/text8'), None))
corpus = Corpus()
corpus.fit(sentences, window = 10)
glove = Glove(no_components=100, learning_rate = 0.05)
glove.fit(corpus.matrix, epochs=30, no_threads=4, verbose=True)
glove.add_dictionary(corpus.dictionary)
glove.save(cur_dir + glove_fname)
corpus.save(cur_dir+corpus_fname)
glove.most_similar('men') # Parameters are hashable string not list
glove.word_vectors[glove.dictionary['perfect']]
print('Could not find existing corpus. Creating new one.')
class Iterable:
def __init__(self, df, col='text'):
self.df = df
self.col = col
def __iter__(self):
for article in self.df[self.col].values:
yield preprocess(article)
corpus = Corpus()
start = time.time()
corpus.fit(Iterable(pd.read_csv(DATA)))
print(f'finished co_occur in {int(time.time() - start)} seconds.')
corpus.save(CORPUS_PATH)
def train_dim(size):
"""
Trains and saves a SIZE-dimensional glove embedding.
"""
glove = Glove(no_components=size, random_state=random.seed(SEED))
start = time.time()
glove.fit(corpus.matrix, epochs=epochs, no_threads=12, verbose=True)
print(
f'finished {size}d vectors in {(time.time() - start)/60:.2f} minutes.')
with open(f'{PATH}/custom.{size}d.txt', 'w') as f:
for word, i in corpus.dictionary.items():
word += ' '
def build_model():
# Set up command line parameters.
parser = argparse.ArgumentParser(description='Fit a GloVe model.')
parser.add_argument('--create',
'-c',
action='store',
default=None,
help=('The filename of the corpus to pre-process. '
'The pre-processed corpus will be saved '
'and will be ready for training.'))
parser.add_argument(
'--train',
'-t',
action='store',
default=0,
help=('Train the GloVe model with this number of epochs.'
'If not supplied, '
'We\'ll attempt to load a trained model'))
parser.add_argument(
'--parallelism',
'-p',
action='store',
default=1,
help=('Number of parallel threads to use for training'))
parser.add_argument('--query',
'-q',
action='store',
default='',
help='Get closes words to this word.')
args = parser.parse_args()
if args.create:
# Build the corpus dictionary and the cooccurrence matrix.
print('Pre-processing corpus')
data = read_data(args.create)
corpus_model = Corpus()
corpus_model.fit(data, window=10)
corpus_model.save('corpus.model')
print('Dict size: %s' % len(corpus_model.dictionary))
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=50, 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))
if not os.path.exists('%s/Embedding/glove' % (folder)):
os.makedirs('%s/Embedding/glove' % (folder))
if not os.path.exists("%s/Embedding/glove/glove.model" % (folder)):
corpus_model = Corpus()
corpus_model.fit(embedding_corpus, window=10)
#corpus_model.save('corpus.model')
print('Dict size: %s' % len(corpus_model.dictionary))
print('Collocations: %s' % corpus_model.matrix.nnz)
glove = Glove(no_components=300, learning_rate=0.05)
glove.fit(corpus_model.matrix, epochs=100, no_threads=10, verbose=True)
glove.add_dictionary(corpus_model.dictionary)
glove.save('%s/Embedding/glove/glove.model' % (folder)) # 存模型
corpus_model.save('%s/Embedding/glove/corpus.model' % (folder)) # 存字典
#透過gensim以text_data建立字典
dictionary = corpora.Dictionary(embedding_corpus)
dictionary.save('%s/Embedding/glove/dictionary.gensim' % (folder))
glove = Glove.load('%s/Embedding/glove/glove.model' % (folder))
corpus_model = Corpus.load('%s/Embedding/glove/corpus.model' % (folder))
dictionary = gensim.corpora.Dictionary.load(
'%s/Embedding/glove/dictionary.gensim' % (folder))
# write vocab to file
vocab_file = "%s/Embedding/glove/word.vocab" % (folder)
if not os.path.exists(vocab_file):
# vocab_count = len(glove.dictionary)
vocab_count = 0
# In[55]:
if not os.path.exists("Embedding/category/glove/glove.model"):
corpus_model = Corpus()
corpus_model.fit(sentences, window=10)
#corpus_model.save('corpus.model')
print('Dict size: %s' % len(corpus_model.dictionary))
print('Collocations: %s' % corpus_model.matrix.nnz)
glove = Glove(no_components=300, learning_rate=0.05)
glove.fit(corpus_model.matrix, epochs=100, no_threads=10, verbose=True)
glove.add_dictionary(corpus_model.dictionary)
glove.save('Embedding/category/glove/glove.model') # 存模型
corpus_model.save('Embedding/category/glove/corpus.model') # 存字典
glove = Glove.load('Embedding/category/glove/glove.model')
corpus_model = Corpus.load('Embedding/category/glove/corpus.model')
# In[56]:
vocab_file = "Embedding/category/glove/word.vocab"
if not os.path.exists(vocab_file):
# vocab_count = len(glove.dictionary)
vocab_count = 0
print("Writing vocab file...")
with open(vocab_file, 'w', encoding='utf-8') as writer:
for word, idx in glove.dictionary.items():
if word in vocab._word_to_id.keys():
GLOVE_MODEL_FILE = args.glove
if not os.path.exists(RESULT_DIR):
os.mkdir(RESULT_DIR)
# MAIN
if os.path.exists(CORPUS_FILE):
print('[{}] Reading corpus from file...'.format(chalk.yellow(CORPUS_FILE)))
corpus = Corpus.load(CORPUS_FILE)
else:
nx_G = util.get_nx_graph()
walks = util.get_node2vec_walks(nx_G)
corpus = Corpus()
corpus.fit(walks, window=WINDOW_SIZE)
print('[{}] Writing corpus file...'.format(chalk.green(CORPUS_FILE)))
corpus.save(CORPUS_FILE)
if os.path.exists(GLOVE_MODEL_FILE) and not args.train:
print('[{}] Reading glove model from file...'.format(
chalk.yellow(GLOVE_MODEL_FILE)))
glove = Glove.load(GLOVE_MODEL_FILE)
else:
glove = Glove(no_components=VECTOR_DIMENSION, learning_rate=0.05)
glove.fit(corpus.matrix,
epochs=GLOVE_EPOCHS,
no_threads=PARALLEL_WORKER_COUNT,
verbose=True)
glove.add_dictionary(corpus.dictionary)
print('[{}] Writing glove file...'.format(chalk.green(GLOVE_MODEL_FILE)))
glove.save(GLOVE_MODEL_FILE)
if args.query:
return sents_token
if __name__ == '__main__':
# Set up parameters.
train = 1
parallelism = 1
query = 'brave'
# Build the corpus dictionary and the cooccurrence matrix.
print('Pre-processing corpus')
corpus_model = Corpus()
corpus_model.fit(read_corpus(), window=10)
corpus_model.save('corpus.model')
print('Dict size: %s' % len(corpus_model.dictionary))
print('Collocations: %s' % corpus_model.matrix.nnz)
# Train the GloVe model and save it to disk.
print('Training the GloVe model')
glove = Glove(no_components=100, learning_rate=0.05)
glove.fit(corpus_model.matrix,
epochs=train,
no_threads=parallelism,
verbose=True)
glove.add_dictionary(corpus_model.dictionary)
glove.save('glove.model')
text = text.replace('Trump', 'Trump_Pre_Election')
elif date and date >= ELECTION_DATE:
text = text.replace('Trump', 'Trump_Post_Election')
text = text.replace("\xa0", " ").replace('“',
'"').replace('”', '"')
sents = sent_tokenize(text)
for sent in sents:
yield self.tokenizer.tokenize(sent)
dirname = os.path.expanduser('./output/articles')
sentences = SentencesIterator(dirname)
print('Building Corpus...')
corpus_model = Corpus()
corpus_model.fit(sentences, window=10)
corpus_model.save(OUTPUT_DIR + 'corpus.model')
print('Build and saved!')
print('Dict size: %s' % len(corpus_model.dictionary))
print('Collocations: %s' % corpus_model.matrix.nnz)
print('Training the GloVe model')
glove = Glove(no_components=300, learning_rate=0.05)
glove.fit(corpus_model.matrix, epochs=25, no_threads=10, verbose=True)
glove.add_dictionary(corpus_model.dictionary)
glove.save(OUTPUT_DIR + 'glove.model')
# model = gensim.models.Word2Vec(sentences, size=300, min_count=5, iter=10, workers=10, sg=1)
# model.save('./vectors/trump_preprocess_skipgram/w2v_foxnews')
