NLP-词向量（Vector Representations of Words）

Tensorflow官网词向量 解释和实现公式
为何文本信息要是用Word2Vec呢？ 是由于文本信息没有像音频和图片那么多的信息包含，因此词才具有特殊性，为了克服离散的词需要大量数据的支撑，因此采用词向量方式。

---

实现逻辑

这里我们进行分布的介绍：主要策略为 DataSet–>转化2维数据–>SkipParam和CBOW–>添加数据至图中–>获取图信息–>TensorBorad中查看。

当然如果你感兴趣Skipgram模型是如何工作的Skip-gram的原理中查看。

• 第一步
  首先我们需要加载我们的训练数据集。此实例中定义了一个maybe_download方法，进行查询是否已经下载，未下载则检查文件大小是否对应则开始下载。

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


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


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

• 第二步
  此步进行讲下载后的text8.zip讲文件对象内的内容转化为字符串，并去掉空格转化为list数组。

# 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


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

• 第三部
  此步骤进行构建我们的字典数据，并且使用字符串UNK进行替换稀疏的单词。

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

# @param words 传入单词数组
# @param vocabulary_size 要拿到的单词大小
def build_dataset(words, vocabulary_size):

    count = [['UNK', -1]]
    # 罗列每个单词出现的次数
    count.extend(collections.Counter(words).most_common(vocabulary_size - 1))
    # 建立一个空的Map对象 用来存放我们的单词的字典
    dictionary = dict()
    for word, _ in count:
        dictionary[word] = len(dictionary)
    data = list()
    unk_count = 0
    for word in words:
        if word in dictionary:
            index = dictionary[word]
        else:
            index = 0  # dictionary['UNK']
            unk_count += 1
        data.append(index)
    count[0][1] = unk_count
    reverse_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
    return data, count, dictionary, reverse_dictionary


data, count, dictionary, reverse_dictionary = build_dataset(words, vocabulary_size)
del words  # 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

• 第四部
  我们开始进行设置的模型,使用了Skip-gram模型。

if __name__ == "__main__":
    # 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.

    # 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.
    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)
    num_sampled = 64  # Number of negative examples to sample.

    # 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.
    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()

---

以下为全部代码：

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import collections
import math
import os
import random
import zipfile

import numpy as np
from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin
import tensorflow as tf
from tensorflow.contrib.tensorboard.plugins import projector

from pandas import DataFrame

# Step 1: Download the data.
url = 'http://mattmahoney.net/dc/'


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


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


# 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


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

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


def build_dataset(words, vocabulary_size):
    count = [['UNK', -1]]
    count.extend(collections.Counter(words).most_common(vocabulary_size - 1))
    dictionary = dict()
    for word, _ in count:
        dictionary[word] = len(dictionary)
    data = list()
    unk_count = 0
    for word in words:
        if word in dictionary:
            index = dictionary[word]
        else:
            index = 0  # dictionary['UNK']
            unk_count += 1
        data.append(index)
    count[0][1] = unk_count
    reverse_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
    return data, count, dictionary, reverse_dictionary


data, count, dictionary, reverse_dictionary = build_dataset(words, vocabulary_size)
del words  # 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


# 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)
    for _ in range(span):
        buffer.append(data[data_index])
        data_index = (data_index + 1) % len(data)
    for i in range(batch_size // num_skips):
        target = skip_window  # target label at the center of the buffer
        targets_to_avoid = [skip_window]
        for j in range(num_skips):
            while target in targets_to_avoid:
                target = random.randint(0, span - 1)
            targets_to_avoid.append(target)
            batch[i * num_skips + j] = buffer[skip_window]
            labels[i * num_skips + j, 0] = buffer[target]
        buffer.append(data[data_index])
        data_index = (data_index + 1) % len(data)
    # 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]])

if __name__ == "__main__":
    # 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.

    # 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.
    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)
    num_sampled = 64  # Number of negative examples to sample.

    # 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.
    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()

# Step 5: Begin training.
num_steps = 100001
LOG_DIR = 'D:/Project_coding/Tensorflow/Season2/Word2Vec/log/'

with tf.Session() 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

    """
    Use TensorBoard to visualize our model. 
    This is not included in the TensorFlow website tutorial.
    """
    words_to_visualize = 3000
    final_embeddings = normalized_embeddings.eval()[:words_to_visualize]
    embedding_var = tf.Variable(final_embeddings)
    session.run(embedding_var.initializer)
    saver = tf.train.Saver([embedding_var])
    saver.save(session, os.path.join(LOG_DIR, "model.ckpt"), 0)

    # Format: tensorflow/contrib/tensorboard/plugins/projector/projector_config.proto
    config = projector.ProjectorConfig()

    # You can add multiple embeddings. Here we add only one.
    embedding = config.embeddings.add()
    embedding.tensor_name = embedding_var.name
    # Link this tensor to its metadata file (e.g. labels).
    embedding.metadata_path = os.path.join(LOG_DIR, 'metadata.tsv')

    # Use the same LOG_DIR where you stored your checkpoint.
    summary_writer = tf.summary.FileWriter(LOG_DIR, session.graph)
    # summary_writer.add_graph()

    # The next line writes a projector_config.pbtxt in the LOG_DIR. TensorBoard will
    # read this file during startup.
    projector.visualize_embeddings(summary_writer, config)

    labels = [(reverse_dictionary[i], i) for i in range(words_to_visualize)]
    DataFrame(labels, columns=['word', 'freq_rank']).to_csv('log/metadata.tsv', index=False, sep='\t')

---