def build_graph(self):
"""Build the graph for the full model."""
opts = self._options
# The training data. A text file.
(words, counts, words_per_epoch, self._epoch, self._words, examples,
labels) = word2vec.skipgram(filename=opts.train_data,
batch_size=opts.batch_size,
window_size=opts.window_size,
min_count=opts.min_count,
subsample=opts.subsample)
(opts.vocab_words, opts.vocab_counts,
opts.words_per_epoch) = self._session.run([words, counts, words_per_epoch])
opts.vocab_size = len(opts.vocab_words)
print("Data file: ", opts.train_data)
print("Vocab size: ", opts.vocab_size - 1, " + UNK")
print("Words per epoch: ", opts.words_per_epoch)
self._examples = examples
self._labels = labels
self._id2word = opts.vocab_words
for i, w in enumerate(self._id2word):
self._word2id[w] = i
true_logits, sampled_logits = self.forward(examples, labels)
loss = self.nce_loss(true_logits, sampled_logits)
tf.scalar_summary("NCE loss", loss)
self._loss = loss
self.optimize(loss)
# Properly initialize all variables.
tf.initialize_all_variables().run()
self.saver = tf.train.Saver()
def build_graph(self):
"""Build the graph for the full model."""
opts = self._options
# The training data. A text file.
(words, counts, words_per_epoch, self._epoch, self._words, examples,
labels) = word2vec.skipgram(filename=opts.train_data,
batch_size=opts.batch_size,
window_size=opts.window_size,
min_count=opts.min_count,
subsample=opts.subsample)
(opts.vocab_words, opts.vocab_counts,
opts.words_per_epoch) = self._session.run(
[words, counts, words_per_epoch])
opts.vocab_size = len(opts.vocab_words)
print("Data file: ", opts.train_data)
print("Vocab size: ", opts.vocab_size - 1, " + UNK")
print("Words per epoch: ", opts.words_per_epoch)
self._examples = examples
self._labels = labels
self._id2word = opts.vocab_words
for i, w in enumerate(self._id2word):
self._word2id[w] = i
true_logits, sampled_logits = self.forward(examples, labels)
loss = self.nce_loss(true_logits, sampled_logits)
tf.scalar_summary("NCE loss", loss)
self._loss = loss
self.optimize(loss)
# Properly initialize all variables.
tf.initialize_all_variables().run()
self.saver = tf.train.Saver()
def build_graph(self):
#get the training data
(words, counts, words_per_epoch, current_epoch, total_words_processed,
examples, labels) = word2vec.skipgram(filename=word_config.train_data_path,
batch_size=word_config.batch_size,
window_size=word_config.window_size,
min_count=word_config.min_count,
subsample=word_config.subsample)
# vocab_words, vocab_counts, words_per_epoch = self._sess.run([words, counts, words_per_epoch])
if tf.gfile.Exists(os.path.join(word_config.output_dir, 'vocab.txt')):
vocab_words, vocab_counts = self.load_vocab()
else:
vocab_words, vocab_counts = self._sess.run([words, counts])
vocab_size = len(vocab_words)
print("Data file: ", word_config.train_data_path)
print("Vocab size: ", vocab_size - 1, " + UNK")
# print("Words per epoch: ", words_per_epoch)
self._id2word = vocab_words
for id, word in enumerate(self._id2word):
self._word2id[word] = id
w_embed_in = tf.Variable(tf.random_uniform([vocab_size, word_config.embed_size],
-0.5 / word_config.embed_size, 0.5 / word_config.embed_size),
name="w_embed_in")
w_embed_out = tf.Variable(tf.zeros([vocab_size, word_config.embed_size]), name="w_embed_out")
self.param_summary(w_embed_in)
self.param_summary(w_embed_out)
# learning_rate = tf.Variable(word_config.learning_rate, trainable=False, name="learning_rate")
global_step = tf.Variable(0, trainable=False, name="global_step")
total_words = words_per_epoch * word_config.max_steps
learning_rate = word_config.learning_rate * tf.maximum(0.0001, tf.cast(1 - total_words_processed / total_words, tf.float32))
inc = global_step.assign_add(1)
with tf.control_dependencies([inc]):
train = word2vec.neg_train(w_embed_in, w_embed_out, examples, labels, learning_rate, vocab_counts.tolist(),
word_config.nr_neg_samples)
self._vocab_words = vocab_words
self._vocab_counts = vocab_counts
self._vocab_size = vocab_size
self._w_embed_in = w_embed_in
self._w_embed_out = w_embed_out
self._train = train
self._examples = examples
self._labels = labels
self._global_step = global_step
self._current_epoch = current_epoch
self._total_words_processed = total_words_processed
self._learning_rate = learning_rate
print("end of build graph")
def build_graph(self):
"""Build the model graph."""
opts = self._options
# The training data. A text file.
(words, counts, words_per_epoch, current_epoch, total_words_processed,
examples, labels) = word2vec.skipgram(filename=opts.train_data,
batch_size=opts.batch_size,
window_size=opts.window_size,
min_count=opts.min_count,
subsample=opts.subsample)
(opts.vocab_words, opts.vocab_counts, opts.words_per_epoch) = self._session.run([words, counts, words_per_epoch])
opts.vocab_size = len(opts.vocab_words)
print("Data file: ", opts.train_data)
print("Vocab size: ", opts.vocab_size - 1, " + UNK")
print("Words per epoch: ", opts.words_per_epoch)
self._id2word = opts.vocab_words
for i, w in enumerate(self._id2word):
self._word2id[w] = i
# Declare all variables we need.
# Input words embedding: [vocab_size, emb_dim]
w_in = tf.Variable(
tf.random_uniform([opts.vocab_size,opts.emb_dim], -0.5 / opts.emb_dim, 0.5 / opts.emb_dim), name="w_in")
# Global step: scalar, i.e., shape [].
w_out = tf.Variable(tf.zeros([opts.vocab_size, opts.emb_dim]), name="w_out")
# Global step: []
global_step = tf.Variable(0, name="global_step")
# Linear learning rate decay.
words_to_train = float(opts.words_per_epoch * opts.epochs_to_train)
lr = opts.learning_rate * tf.maximum(0.0001, 1.0 - tf.cast(total_words_processed, tf.float32) / words_to_train)
# Training nodes.
inc = global_step.assign_add(1)
with tf.control_dependencies([inc]):
train = word2vec.neg_train(w_in,
w_out,
examples,
labels,
lr,
vocab_count=opts.vocab_counts.tolist(),
num_negative_samples=opts.num_samples)
self._w_in = w_in
self._examples = examples
self._labels = labels
self._lr = lr
self._train = train
self.step = global_step
self._epoch = current_epoch
self._words = total_words_processed
def build_graph(self):
"""Build the graph for the full model."""
opts = self._options
# The training data. A text file.
(words, counts, words_per_epoch, self._epoch, self._words, examples,
labels) = word2vec.skipgram(filename=opts.train_data,
batch_size=opts.batch_size,
window_size=opts.window_size,
min_count=opts.min_count,
subsample=opts.subsample)
(opts.vocab_words, opts.vocab_counts,
opts.words_per_epoch) = self._session.run(
[words, counts, words_per_epoch])
opts.vocab_size = len(opts.vocab_words)
print("Data file: ", opts.train_data)
print("Vocab size: ", opts.vocab_size - 1, " + UNK")
print("Words per epoch: ", opts.words_per_epoch)
self._examples = examples
self._labels = labels
self._id2word = opts.vocab_words
for i, w in enumerate(self._id2word):
self._word2id[w] = i
loss = self.calculate_loss(examples, labels)
self._loss = loss
if opts.normclip:
self._clip_ops = self.clip_ops_graph(self._examples, self._labels,
self._neg_idxs)
if opts.adagrad:
print("Using Adagrad as an optimizer!")
self.optimize_adagrad(loss)
else:
# Using Standard SGD
self.optimize(loss)
tf.scalar_summary('learning rate', self._lr)
# Properly initialize all variables.
self.check_op = tf.add_check_numerics_ops()
tf.initialize_all_variables().run()
try:
print('Try using saver version v2')
self.saver = tf.train.Saver(write_version=tf.train.SaverDef.V2,
max_to_keep=opts.max_to_keep)
except:
print('Default to saver version v1')
self.saver = tf.train.Saver(max_to_keep=opts.max_to_keep)
def build_graph(self):
opts = self._options
(words, counts, words_per_epoch, self._epoch, self._words, examples,
labels) = word2vec.skipgram(filename="text8",
batch_size=opt.batch_size,
window_size=opt.window_size,
min_count=opt.min_count,
subsample=0)
(opts.vocab_words, opts.vocab_counts,
opts.words_per_epoch) = self._session.run([words, counts, words_per_epoch])
opts.vocab_size = len(opts.vocab_words)
print("Data file: ", opts.train_data)
print("Vocab size: ", opts.vocab_size - 1, " + UNK")
print("Words per epoch: ", opts.words_per_epoch)
self._examples = examples
self._labels = labels
self._id2word = opts.vocab_words
for i, w in enumerate(self._id2word):
self._word2id[w] = i
true_logits, sampled_logits = self.forward(examples, labels)
loss = self.nce_loss(true_logits, sampled_logits)
tf.scalar_summary("NCE loss", loss)
self._loss = loss
self.optimize(loss)
def build_graph(self):
"""Build the model graph."""
opts = self._options
# The training data. A text file.
(words, counts, words_per_epoch, current_epoch, total_words_processed,
examples, labels) = word2vec.skipgram(filename=opts.train_data,
batch_size=opts.batch_size,
window_size=opts.window_size,
min_count=opts.min_count,
subsample=opts.subsample)
(opts.vocab_words, opts.vocab_counts,
opts.words_per_epoch) = self._session.run([words, counts, words_per_epoch])
opts.vocab_size = len(opts.vocab_words)
print("Data file: ", opts.train_data)
print("Vocab size: ", opts.vocab_size - 1, " + UNK")
print("Words per epoch: ", opts.words_per_epoch)
self._id2word = opts.vocab_words
for i, w in enumerate(self._id2word):
self._word2id[w] = i
# Declare all variables we need.
# Input words embedding: [vocab_size, emb_dim]
w_in = tf.Variable(
tf.random_uniform(
[opts.vocab_size,
opts.emb_dim], -0.5 / opts.emb_dim, 0.5 / opts.emb_dim),
name="w_in")
# Global step: scalar, i.e., shape [].
w_out = tf.Variable(tf.zeros([opts.vocab_size, opts.emb_dim]), name="w_out")
# Global step: []
global_step = tf.Variable(0, name="global_step")
# Linear learning rate decay.
words_to_train = float(opts.words_per_epoch * opts.epochs_to_train)
lr = opts.learning_rate * tf.maximum(
0.0001,
1.0 - tf.cast(total_words_processed, tf.float32) / words_to_train)
# Training nodes.
inc = global_step.assign_add(1)
with tf.control_dependencies([inc]):
train = word2vec.neg_train(w_in,
w_out,
examples,
labels,
lr,
vocab_count=opts.vocab_counts.tolist(),
num_negative_samples=opts.num_samples)
self._w_in = w_in
self._examples = examples
self._labels = labels
self._lr = lr
self._train = train
self.step = global_step
self._epoch = current_epoch
self._words = total_words_processed
def build_graph(self):
"""Build the model graph."""
opts = self._options
# The training data for text skipgram. A text file.
(words, w_counts, words_per_epoch, w_current_epoch, total_words_processed, w_examples, w_labels) = word2vec.skipgram(filename=opts.text_data, batch_size=opts.batch_size, window_size=opts.window_size, min_count=opts.min_count, subsample=opts.subsample)
# the training data for entity skipgram
(entities, e_counts, entities_per_epoch, e_current_epoch, total_entities_processed,
e_examples, e_labels) = kg_skipgram(filename=opts.kg_data,
batch_size=opts.batch_size,
min_count=opts.min_count)
(opts.vocab_words, vocab_word_counts,
opts.words_per_epoch, opts.vocab_entities, vocab_entity_counts, opts.entities_per_epoch) = self._session.run([words, w_counts, words_per_epoch, entities, e_counts, entities_per_epoch])
# the training data for align anchor skipgram
(anchors_per_epoch, a_current_epoch, total_anchors_processed,
a_examples, a_labels) = align_model(filename=opts.anchor_data,
batch_size=opts.batch_size,
window_size=opts.window_size,
subsample=opts.subsample,vocab_word=opts.vocab_words.tolist(),vocab_word_freq=vocab_word_counts.tolist(),vocab_entity=opts.vocab_entities.tolist())
opts.vocab_word_size = len(opts.vocab_words)
opts.vocab_entity_size = len(opts.vocab_entities)
opts.vocab_size = opts.vocab_word_size+opts.vocab_entity_size
opts.anchors_per_epoch = self._session.run(anchors_per_epoch)
# for neg sample, [vocab_word_counts, 0...0] and [0...0, vocab_entity_counts]
opts.vocab_word_counts = tf.concat(0,[vocab_word_counts,tf.zeros([opts.vocab_entity_size])]).eval()
opts.vocab_entity_counts = tf.concat(0,[tf.zeros([opts.vocab_word_size]), vocab_entity_counts]).eval()
print("Text data file: ", opts.text_data)
print("Word vocab size: ", opts.vocab_word_size - 1, " + UNK")
print("Words per epoch: ", opts.words_per_epoch)
print("Entity data file: ", opts.kg_data)
print("Entity vocab size: ", opts.vocab_entity_size)
print("Entities per epoch: ", opts.entities_per_epoch)
print("Anchor data file: ", opts.anchor_data)
print("Anchors per epoch: ", opts.anchors_per_epoch)
# for i< opts.vocab_word_size is a word, others is entity
self._id2item = np.concatenate((opts.vocab_words, opts.vocab_entities), 0)
for i, w in enumerate(self._id2item):
self._item2id[w] = i
# Declare all variables we need.
# Input embedding including both words and entities: [vocab_size, emb_dim]
# shard variable if larger than 2g, because saver's limit
self._is_shard = False
vocab_size_limit = 511000000/opts.emb_dim
# 2048/4-1 mb
if opts.vocab_size > vocab_size_limit:
self._is_shard = True
remain_size = opts.vocab_size
for i in xrange(opts.vocab_size/vocab_size_limit):
self._v_in.append(tf.Variable(tf.random_uniform([vocab_size_limit,opts.emb_dim], -0.5 / opts.emb_dim, 0.5 / opts.emb_dim),name="v_in"+i))
self._v_out.append(tf.Variable(tf.zeros([vocab_size_limit,opts.emb_dim]),name="v_out"+i))
remain_size -= vocab_size_limit
if remain_size!=0:
tmp_cap = len(self._v_in)
self._v_in.append(tf.Variable(tf.random_uniform([remain_size,opts.emb_dim], -0.5 / opts.emb_dim, 0.5 / opts.emb_dim),name="v_in"+tmp_cap))
self._v_out.append(tf.Variable(tf.zeros([remain_size,opts.emb_dim]),name="v_out"+tmp_cap))
else:
self._v_in.append(tf.Variable(tf.random_uniform([opts.vocab_size,opts.emb_dim], -0.5 / opts.emb_dim, 0.5 / opts.emb_dim),name="v_in"))
self._v_out.append(tf.Variable(tf.zeros([opts.vocab_size,opts.emb_dim]),name="v_out"))
# Global step: []
global_step = tf.Variable(0, name="global_step")
# Linear learning rate decay.
words_to_train = float(opts.words_per_epoch * opts.epochs_to_train)
lr = opts.learning_rate * tf.maximum(
0.0001,
1.0 - tf.cast(total_words_processed, tf.float32) / words_to_train)
# Training nodes.
inc = global_step.assign_add(1)
with tf.control_dependencies([inc]):
w_train = word2vec.neg_train(tf.concat(0,self._v_in) if self._is_shard else self._v_in[0],
tf.concat(0,self._v_out) if self._is_shard else self._v_out[0],
w_examples,
w_labels,
lr,
vocab_count=opts.vocab_word_counts.tolist(),
num_negative_samples=opts.num_samples)
e_train = neg_train(tf.concat(0,self._v_in) if self._is_shard else self._v_in[0],
tf.concat(0,self._v_out) if self._is_shard else self._v_out[0],
e_examples+opts.vocab_word_size,
e_labels+opts.vocab_word_size,
lr,
vocab_count=opts.vocab_entity_counts.tolist(),
num_negative_samples=opts.num_samples)
a_train = word2vec.neg_train(tf.concat(0,self._v_in) if self._is_shard else self._v_in[0], tf.concat(0,self._v_out) if self._is_shard else self._v_out[0], a_examples+opts.vocab_word_size, a_labels, lr, vocab_count=opts.vocab_word_counts.tolist(), num_negative_samples=opts.num_samples)
self._lr = lr
self._train_text = w_train
self._train_kg = e_train
self._train_align = a_train
self.step = global_step
self._epoch_text = w_current_epoch
self._epoch_kg = e_current_epoch
self._epoch_align = a_current_epoch
self._words = total_words_processed
self._entities = total_entities_processed
self._anchors = total_anchors_processed
def build_graph(self):
"""Build the model graph."""
opts = self._options
# The training data. A text file.
(words, counts, words_per_epoch, current_epoch, total_words_processed,
examples, labels) = word2vec.skipgram(filename=opts.train_data,
batch_size=opts.batch_size,
window_size=opts.window_size,
min_count=opts.min_count,
subsample=opts.subsample)
(opts.vocab_words, opts.vocab_counts,
opts.words_per_epoch) = self._session.run(
[words, counts, words_per_epoch])
opts.vocab_size = len(opts.vocab_words)
print("Data file: ", opts.train_data)
print("Vocab size: ", opts.vocab_size - 1, " + UNK")
print("Words per epoch: ", opts.words_per_epoch)
self._id2word = opts.vocab_words
for i, w in enumerate(self._id2word):
self._word2id[w] = i
#let me interrupt and get pos/neg words in vocab
SOCIAL = False
SOL = True
num_words = 100
LOVEHATE = False
FIN = False
BULLBEAR = False
if (SOCIAL): #use one of the social polar lexicons
fileNames = [
"./data/train_lexicons/10_social_employment_opportunities.txt",
"./data/train_lexicons/10_social_freedom_from_discrimination.txt",
"./data/train_lexicons/10_social_good_education.txt",
"./data/train_lexicons/10_social_honest_and_responsive_government.txt",
"./data/train_lexicons/10_social_political_freedom.txt"
]
social_issue_to_use = 0
polarity_dict = pd.read_csv(fileNames[social_issue_to_use],
header=None,
names=["pos", "neg"])
neg_terms = polarity_dict["neg"]
pos_terms = polarity_dict["pos"]
elif (SOL): #use the stock opinion lexicon
neg_terms = pd.read_csv("./data/train_lexicons/sol_train_neg.csv",
header=0)
pos_terms = pd.read_csv("./data/train_lexicons/sol_train_pos.csv",
header=0)
ordered = True
if (ordered):
neg_terms = neg_terms.sort_values(
["v1"], axis=0, ascending=True)["w1"].iloc[:num_words]
pos_terms = pos_terms.sort_values(
["v1"], axis=0, ascending=False)["w1"].iloc[:num_words]
else:
neg_terms = neg_terms.sample(n=num_words)["w1"]
pos_terms = pos_terms.sample(n=num_words)["w1"]
elif (LOVEHATE): #use the love-hate lexicon
justlovehate = True
neg_terms = pd.read_csv("./data/train_lexicons/hate.txt",
names=["neg"])
pos_terms = pd.read_csv("./data/train_lexicons/love.txt",
names=["pos"])
if (justlovehate):
neg_terms = neg_terms["neg"].iloc[-1]
pos_terms = pos_terms["pos"].iloc[-1]
else:
neg_terms = neg_terms["neg"].iloc[15:]
pos_terms = pos_terms["pos"].iloc[15:]
elif (FIN): #use FIN lexicon
neg_terms = pd.read_csv("./data/train_lexicons/fin_negatives.csv",
header=0,
index_col=0)["negs"]
pos_terms = pd.read_csv("./data/train_lexicons/fin_positives.csv",
header=0,
index_col=0)["poss"]
elif (BULLBEAR):
neg_terms = ["bearish"]
pos_terms = ["bullish"]
self.neg_terms_in_vocab = []
self.neg_ids = []
self.pos_terms_in_vocab = []
self.pos_ids = []
opts = self._options
for neg_term in neg_terms:
neg_term = neg_term.encode()
if neg_term in opts.vocab_words:
self.neg_terms_in_vocab.append(neg_term)
self.neg_ids.append(self._word2id.get(neg_term, 0))
self.neg_ids = tf.constant(self.neg_ids)
for pos_term in pos_terms:
pos_term = pos_term.encode()
if pos_term in opts.vocab_words:
self.pos_terms_in_vocab.append(pos_term)
self.pos_ids.append(self._word2id.get(pos_term, 0))
self.pos_ids = tf.constant(self.pos_ids)
if (LOVEHATE):
#evaluation only works for the love-hate lexicon ...
self.eval_neg_id = [self._word2id.get("hate", 0)]
self.eval_neg_id = tf.constant(self.eval_neg_id)
self.eval_pos_id = [self._word2id.get("love", 0)]
self.eval_pos_id = tf.constant(self.eval_pos_id)
#eval neg_ids and pos_ids (all train words)
neg_terms = pd.read_csv("./data/train_lexicons/hate.txt",
names=["neg"])
pos_terms = pd.read_csv("./data/train_lexicons/love.txt",
names=["pos"])
neg_terms = neg_terms["neg"].iloc[15:]
pos_terms = pos_terms["pos"].iloc[15:]
self.eval_neg_ids = []
self.eval_pos_ids = []
opts = self._options
for neg_term in neg_terms:
neg_term = neg_term.encode()
if neg_term in opts.vocab_words:
self.eval_neg_ids.append(self._word2id.get(neg_term, 0))
self.eval_neg_ids = tf.constant(self.eval_neg_ids)
for pos_term in pos_terms:
pos_term = pos_term.encode()
if pos_term in opts.vocab_words:
self.eval_pos_ids.append(self._word2id.get(pos_term, 0))
self.eval_pos_ids = tf.constant(self.eval_pos_ids)
else:
neg_terms = pd.read_csv("./data/train_lexicons/sol_train_neg.csv",
names=["neg"])
pos_terms = pd.read_csv("./data/train_lexicons/sol_train_pos.csv",
names=["pos"])
neg_terms = neg_terms["neg"].iloc[num_words:]
pos_terms = pos_terms["pos"].iloc[num_words:]
self.eval_neg_ids = []
self.eval_pos_ids = []
opts = self._options
for neg_term in neg_terms:
neg_term = neg_term.encode()
if neg_term in opts.vocab_words:
self.eval_neg_ids.append(self._word2id.get(neg_term, 0))
self.eval_neg_ids = tf.constant(self.eval_neg_ids)
for pos_term in pos_terms:
pos_term = pos_term.encode()
if pos_term in opts.vocab_words:
self.eval_pos_ids.append(self._word2id.get(pos_term, 0))
self.eval_pos_ids = tf.constant(self.eval_pos_ids)
#continue where it left off
# Declare all variables we need.
# Input words embedding: [vocab_size, emb_dim]
w_in = tf.Variable(tf.random_uniform([opts.vocab_size, opts.emb_dim],
-0.5 / opts.emb_dim,
0.5 / opts.emb_dim),
name="w_in")
# Global step: scalar, i.e., shape [].
w_out = tf.Variable(tf.zeros([opts.vocab_size, opts.emb_dim]),
name="w_out")
# Global step: []
global_step = tf.Variable(0, name="global_step")
# Linear learning rate decay.
words_to_train = float(opts.words_per_epoch * opts.epochs_to_train)
lr = opts.learning_rate * tf.maximum(
0.0001,
1.0 - tf.cast(total_words_processed, tf.float32) / words_to_train)
# Training nodes.
inc = global_step.assign_add(1)
with tf.control_dependencies([inc]):
train = word2vec.neg_train(w_in,
w_out,
examples,
labels,
lr,
vocab_count=opts.vocab_counts.tolist(),
num_negative_samples=opts.num_samples)
self._w_in = w_in
self._examples = examples
self._labels = labels
self._lr = lr
self._train = train
self.step = global_step
self._epoch = current_epoch
self._words = total_words_processed
#Train nodes with antonyms
loss2 = self.antonym_loss_and_optimize()
self._loss2 = loss2
def build_graph(self):
"""Build the graph for the full model."""
opts = self._options
# The training data. A text file.
(words, counts, words_per_epoch, self._epoch, self._words, examples,
labels) = word2vec.skipgram(filename=opts.train_data,
batch_size=opts.batch_size,
window_size=opts.window_size,
min_count=opts.min_count,
subsample=opts.subsample)
###NEW: read sampling corpus (=all files in same dir as train_data except for training data)
full_path = os.path.realpath(opts.train_data)
path, filename = os.path.split(full_path)
sampling_files = []
for file in os.listdir(path):
if file.endswith(".txt") or file.endswith(".tok") and file != filename:
sampling_files.append(path+"/"+file)
print("Files for sampling: ", ", ".join(sampling_files))
#write new file as concat of all sampling files
sample_data = opts.train_data+".sample"
sample_train_data = sample_data+".train"
o = codecs.open(sample_data, "w", "utf8")
oo = codecs.open(sample_train_data, "w", "utf8")
for sampling_file in sampling_files:
f = open(sampling_file,"r")
t = f.read()
o.write(t.decode("utf8")+" ") #concat all files
oo.write(t.decode("utf8")+" ")
f.close()
o.close()
t = codecs.open(opts.train_data, "r", "utf8")
oo.write(t.read().decode("utf8"))
t.close()
oo.close()
# The sampling data. A text file.
(words_samples, counts_samples, words_per_epoch_samples, b_epoch_samples, b_words_samples, examples_samples,
labels_samples) = word2vec.skipgram(filename=sample_data,
batch_size=opts.batch_size,
window_size=opts.window_size,
min_count=opts.min_count,
subsample=opts.subsample)
#Sampling plus training data for getting full vocabulary for embeddings
(words_samples_train, counts_samples_train, words_per_epoch_samples_train, b_epoch_samples_train, b_words_samples_train, examples_samples_train,
labels_samples_train) = word2vec.skipgram(filename=sample_train_data,
batch_size=opts.batch_size,
window_size=opts.window_size,
min_count=opts.min_count,
subsample=opts.subsample)
(opts.all_words, opts.all_counts,
all_words_per_epoch) = self._session.run([words_samples_train, counts_samples_train, words_per_epoch])
(opts.sample_words, opts.sample_counts,
sample_words_per_epoch) = self._session.run([words_samples, counts_samples, words_per_epoch])
#first add sample words
for s in opts.sample_words:
last_index = len(self._word2id)
self._word2id.setdefault(s,last_index)
(opts.vocab_words, opts.vocab_counts,
opts.words_per_epoch) = self._session.run([words, counts, words_per_epoch])
#then add training words
for v in opts.vocab_words:
last_index = len(self._word2id)
self._word2id.setdefault(v,last_index)
print("Word2id: ", self._word2id)
opts.vocab_size = len(self._word2id) #NOTE: wc20(train)+wc(sample) != wc20(train+sample) -> therefore use word2id (proper union)
print("Sample file: ", sample_data)
print("Data file: ", opts.train_data)
print("Vocab size: ", opts.vocab_size - 1, " + UNK")
print("Words per epoch: ", opts.words_per_epoch)
self._examples = examples_samples
self._labels = labels_samples
#self._id2word = opts.all_words
#for i, w in enumerate(self._id2word):
for (w,i) in self._word2id.iteritems():
self._id2word[i] = w
print("id2word: ", self._id2word)
true_logits, sampled_logits = self.forward(examples_samples, labels_samples)
loss = self.nce_loss(true_logits, sampled_logits)
tf.scalar_summary("NCE loss", loss)
self._loss = loss
self.optimize(loss)
# Properly initialize all variables.
tf.initialize_all_variables().run()
self.saver = tf.train.Saver()
