Word2vec-Tensorflow实战

Word2vec:Tensorflow实战

本文代码可视化过程：传送门

引言

前面我曾系统分析过Word2vec的理论及工具包的使用，那么在深度学习框架tensorflow中如何实现Word2Vec呢？接下来，我们将介绍tensorflow中word2vec简化版实现方法。

Minimalistic Implementation

Step1 下载数据

这里我们直接从这个网站上下载文本数据集：http://mattmahoney.net/dc/，代码如下：

url = 'http://mattmahoney.net/dc/'

# pylint: disable=redefined-outer-name
def maybe_download(filename, expected_bytes):
"""Download a file if not present, and make sure it's the right size."""
local_filename = os.path.join(gettempdir(), filename)
if not os.path.exists(local_filename):
local_filename, _ = urllib.request.urlretrieve(url + filename,
local_filename)
statinfo = os.stat(local_filename)
if statinfo.st_size == expected_bytes:
print('Found and verified', filename)
else:
print(statinfo.st_size)
raise Exception('Failed to verify ' + local_filename +
'. Can you get to it with a browser?')
return local_filename

filename = maybe_download('text8.zip', 31344016)

数据集大约30M左右，默认下载位置为/tmp/

下载完数据后，将文本转换成字符串：

# Read the data into a list of strings.
def read_data(filename):
"""Extract the first file enclosed in a zip file as a list of words."""
with zipfile.ZipFile(filename) as f:
data = tf.compat.as_str(f.read(f.namelist()[0])).split()
return data

vocabulary = read_data(filename)
print('Data size', len(vocabulary))

Step2 构建词汇表，并将常见词汇用’UNK’代替

# Step 2: Build the dictionary and replace rare words with UNK token.
vocabulary_size = 50000

def build_dataset(words, n_words):
"""Process raw inputs into a dataset."""
count = [['UNK', -1]]
count.extend(collections.Counter(words).most_common(n_words - 1))
dictionary = dict()
for word, _ in count:
dictionary[word] = len(dictionary)
data = list()
unk_count = 0
for word in words:
index = dictionary.get(word, 0)
if index == 0:  # dictionary['UNK']
unk_count += 1
data.append(index)
count[0][1] = unk_count
reversed_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
return data, count, dictionary, reversed_dictionary

# Filling 4 global variables:
# data - list of codes (integers from 0 to vocabulary_size-1).
#   This is the original text but words are replaced by their codes
# count - map of words(strings) to count of occurrences
# dictionary - map of words(strings) to their codes(integers)
# reverse_dictionary - maps codes(integers) to words(strings)
data, count, dictionary, reverse_dictionary = build_dataset(vocabulary,
vocabulary_size)
del vocabulary  # Hint to reduce memory.
print('Most common words (+UNK)', count[:5])
print('Sample data', data[:10], [reverse_dictionary[i] for i in data[:10]])

data_index = 0

这里的常见单词主要有’the’,’of’,’and’,’one’

Most common words (+UNK) [[‘UNK’, 418391], (‘the’, 1061396), (‘of’, 593677), (‘and’, 416629), (‘one’, 411764)]

Step3 为skip-gram模型生成一个training batch

# Step 3: Function to generate a training batch for the skip-gram model.
def generate_batch(batch_size, num_skips, skip_window):
global data_index
assert batch_size % num_skips == 0
assert num_skips <= 2 * skip_window
batch = np.ndarray(shape=(batch_size), dtype=np.int32)
labels = np.ndarray(shape=(batch_size, 1), dtype=np.int32)
span = 2 * skip_window + 1  # [ skip_window target skip_window ]
buffer = collections.deque(maxlen=span)
if data_index + span > len(data):
data_index = 0
buffer.extend(data[data_index:data_index + span])
data_index += span
for i in range(batch_size // num_skips):
context_words = [w for w in range(span) if w != skip_window]
words_to_use = random.sample(context_words, num_skips)
for j, context_word in enumerate(words_to_use):
batch[i * num_skips + j] = buffer[skip_window]
labels[i * num_skips + j, 0] = buffer[context_word]
4000
if data_index == len(data):
buffer[:] = data[:span]
data_index = span
else:
buffer.append(data[data_index])
data_index += 1
# Backtrack a little bit to avoid skipping words in the end of a batch
data_index = (data_index + len(data) - span) % len(data)
return batch, labels

batch, labels = generate_batch(batch_size=8, num_skips=2, skip_window=1)
for i in range(8):
print(batch[i], reverse_dictionary[batch[i]],
'->', labels[i, 0], reverse_dictionary[labels[i, 0]])

Step4 构建并训练skip-gram模型

# Step 4: Build and train a skip-gram model.

batch_size = 128
embedding_size = 128  # Dimension of the embedding vector.
skip_window = 1       # How many words to consider left and right.
num_skips = 2         # How many times to reuse an input to generate a label.
num_sampled = 64      # Number of negative examples to sample.

# We pick a random validation set to sample nearest neighbors. Here we limit the
# validation samples to the words that have a low numeric ID, which by
# construction are also the most frequent. These 3 variables are used only for
# displaying model accuracy, they don't affect calculation.
valid_size = 16     # Random set of words to evaluate similarity on.
valid_window = 100  # Only pick dev samples in the head of the distribution.
valid_examples = np.random.choice(valid_window, valid_size, replace=False)

graph = tf.Graph()

with graph.as_default():

# Input data.
train_inputs = tf.placeholder(tf.int32, shape=[batch_size])
train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])
valid_dataset = tf.constant(valid_examples, dtype=tf.int32)

# Ops and variables pinned to the CPU because of missing GPU implementation
with tf.device('/cpu:0'):
# Look up embeddings for inputs.
embeddings = tf.Variable(
tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
embed = tf.nn.embedding_lookup(embeddings, train_inputs)

# Construct the variables for the NCE loss
nce_weights = tf.Variable(
tf.truncated_normal([vocabulary_size, embedding_size],
stddev=1.0 / math.sqrt(embedding_size)))
nce_biases = tf.Variable(tf.zeros([vocabulary_size]))

# Compute the average NCE loss for the batch.
# tf.nce_loss automatically draws a new sample of the negative labels each
# time we evaluate the loss.
# Explanation of the meaning of NCE loss:
#   http://mccormickml.com/2016/04/19/word2vec-tutorial-the-skip-gram-model/ loss = tf.reduce_mean(
tf.nn.nce_loss(weights=nce_weights,
biases=nce_biases,
labels=train_labels,
inputs=embed,
num_sampled=num_sampled,
num_classes=vocabulary_size))

# Construct the SGD optimizer using a learning rate of 1.0.
optimizer = tf.train.GradientDescentOptimizer(1.0).minimize(loss)

# Compute the cosine similarity between minibatch examples and all embeddings.
norm = tf.sqrt(tf.reduce_sum(tf.square(embeddings), 1, keep_dims=True))
normalized_embeddings = embeddings / norm
valid_embeddings = tf.nn.embedding_lookup(
normalized_embeddings, valid_dataset)
similarity = tf.matmul(
valid_embeddings, normalized_embeddings, transpose_b=True)

# Add variable initializer.
init = tf.global_variables_initializer()

Step5 开始训练

# Step 5: Begin training.
num_steps = 100001

with tf.Session(graph=graph) as session:
# We must initialize all variables before we use them.
init.run()
print('Initialized')

average_loss = 0
for step in xrange(num_steps):
batch_inputs, batch_labels = generate_batch(
batch_size, num_skips, skip_window)
feed_dict = {train_inputs: batch_inputs, train_labels: batch_labels}

# We perform one update step by evaluating the optimizer op (including it
# in the list of returned values for session.run()
_, loss_val = session.run([optimizer, loss], feed_dict=feed_dict)
average_loss += loss_val

if step % 2000 == 0:
if step > 0:
average_loss /= 2000
# The average loss is an estimate of the loss over the last 2000 batches.
print('Average loss at step ', step, ': ', average_loss)
average_loss = 0

# Note that this is expensive (~20% slowdown if computed every 500 steps)
if step % 10000 == 0:
sim = similarity.eval()
for i in xrange(valid_size):
valid_word = reverse_dictionary[valid_examples[i]]
top_k = 8  # number of nearest neighbors
nearest = (-sim[i, :]).argsort()[1:top_k + 1]
log_str = 'Nearest to %s:' % valid_word
for k in xrange(top_k):
close_word = reverse_dictionary[nearest[k]]
log_str = '%s %s,' % (log_str, close_word)
print(log_str)
final_embeddings = normalized_embeddings.eval()

这里每隔10000次就打印最近的训练的得到的单词

Step6 可视化

# Step 6: Visualize the embeddings.

# pylint: disable=missing-docstring
# Function to draw visualization of distance between embeddings.
def plot_with_labels(low_dim_embs, labels, filename):
assert low_dim_embs.shape[0] >= len(labels), 'More labels than embeddings'
plt.figure(figsize=(18, 18))  # in inches
for i, label in enumerate(labels):
x, y = low_dim_embs[i, :]
plt.scatter(x, y)
plt.annotate(label,
xy=(x, y),
xytext=(5, 2),
textcoords='offset points',
ha='right',
va='bottom')

plt.savefig(filename)

try:
# pylint: disable=g-import-not-at-top
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt

tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000, method='exact')
plot_only = 500
low_dim_embs = tsne.fit_transform(final_embeddings[:plot_only, :])
labels = [reverse_dictionary[i] for i in xrange(plot_only)]
plot_with_labels(low_dim_embs, labels, os.path.join(gettempdir(), 'tsne.png'))

except ImportError as ex:
print('Please install sklearn, matplotlib, and scipy to show embeddings.')
print(ex)

可视化结果：