TensorFlow实战11：实现Word2Vec

1.Word2Vec简介

Word2Vec也称Word Embeddings，中文比较常见的叫法是“词向量”或者是“词嵌入”。通俗的来说就是把单词进行编码，变成数字的形式让计算机知道那个单词的代号。哈哈， 感觉就像以前的间谍通过莫尔斯电码进行信息传递，只不过那个是通过声音的长短进行编码，我们如果使用one-hot的编码方式，比如I是第一个单词，那么在维度为10的单词向量中，编码就是[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]。通过这种方式我们进行编码，可以发现如果把一片文章进行编码，那么肯定是非常稀疏的，因为一个单词对应的向量只有一个有效的位置。而且还会存在一个问题，通常我们对单词的编码都是随机的，那么如果以“江苏”和“南京”为例，那么那样的编码关系不会存在地理联系，即江苏的省会城市是南京，这种包含关系是没办法体现的。
使用向量表达就可以有效地解决这个问题。它可以从原始语料中学习字词空间向量的预测模型。主要分为CBOW（Continuous Bag of Words）和Skip-Gram两种模式。在本篇博客中，我们主要使用的是Skip-Gram的模式。

2.Word2Vec的代码实现

#coding:utf-8
#因为要下载数据，所以导入的依赖库比较多
import collections
import math 
import os
import random
import zipfile
import numpy as np
import sys
import tensorflow as tf
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt



#这边是python版本的一个检查，不同版本对应函数调用的接口是不一样的
if sys.version_info[0] >= 3:
    from urllib.request import urlretrieve
else:
    from urllib import urlretrieve

#从网址下载数据并检查数据的准确性
url = 'http://mattmahoney.net/dc/'

def maybe_download(filename, excepted_bytes):
    if not os.path.exists(filename):
        filename, _ = urlretrieve(url + filename, filename)
    statinfo = os.stat(filename)
    if statinfo.st_size == excepted_bytes:
        print("Found and verified", filename)

    else:
        print(statinfo.st_size)
        raise Exception(
            "Failed to verfy" + filename + "Can you get to it with browser?")
    return filename
filename = maybe_download('text8.zip', 31344016)

#定义读取数据的函数，并把数据转成列表
def read_data(filename):
    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))

#创建词汇表，选取前50000频数的单词，其余单词认定为Unknown,编号为0
vocabulary_size = 50000

def build_dataset(words):
    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
            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)

#为了节约内存删除原始单词列表，打印出最高频出现的词汇及其数量
del words
print ('Most common words (+UNK)', count[:5])
print('Sample data', data[:10], [reverse_dictionary[i] for i in data[:10]])

#生成训练样本，assert断言：申明其布尔值必须为真的判定，如果发生异常，就表示为假
data_index = 0

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
    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
        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) 
    return batch, labels

#调用generate_batch函数简单测试一下功能
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]])

#定义训练是的参数
batch_size = 128
embedding_size = 128
skip_window = 1
num_skips = 2

valid_size = 16
valid_window = 100
valid_examples = np.random.choice(valid_window, valid_size, replace = False)
num_sampled = 64

#定义Skip-Gram Word2Vec模型的网络结构
graph = tf.Graph()
with graph.as_default():

    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)

    with tf.device('/gpu:0'):
        embeddings = tf.Variable(
            tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
        embed = tf.nn.embedding_lookup(embeddings, train_inputs)

        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]))

    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))

    optimizer = tf.train.GradientDescentOptimizer(1.0).minimize(loss)

    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)

    init = tf.global_variables_initializer()


#定义最大迭代次数，创建并设置默认的session
num_steps = 100001

with tf.Session(graph = graph) as session:
    init.run()
    print("Initialized")

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

        _, loss_val = session.run([optimizer, loss], feed_dict = feed_dict)
        average_loss += loss_val

        if step % 2000 == 0:
            if step > 0:
                average_loss /= 2000
            print("Average loss at step ", step, ":", average_loss)
            average_loss = 0

        if step % 10000 == 0:
            sim = similarity.eval()
            for i in range(valid_size):
                valid_word = reverse_dictionary[valid_examples[i]]
                top_k = 8
                nearest = (-sim[i, :]).argsort()[1: top_k+1]
                log_str = "Nearest to %s:" % valid_word
                for k in range(top_k):
                    close_woreverse_dictionary[nearest[k]]
                    log_str = "%s  %s," %(log_str, close_word)
                print(log_str)
    final_embeddings = normalized_embeddings.eval()

#定义可视化Word2Vec效果的函数
def plot_with_labels(low_dim_embs, labels, filename = 'tsne.png'):
    assert low_dim_embs.shape[0] >= len(labels), "More labels than embeddings"
    plt.figure(figsize= (18, 18))
    for i, label in enumerate(labels):
        x, y = low_dim_embs[i, :]
        plt.scatter(x, y)
        plt.annotate(label, xy = (x, y), xy= (5, 2), textcoords = 'offset points', ha = 'right', va = 'bottom')
    plt.savefig(filename) 

tsne = TSNE(perplexity = 30, n_components = 2, init = 'pca', n_iter = 5000)
plo





t_only = 100
low_dim_embs = tsne.fit_transform(final_embeddings[:plot_only, :])
labels = [reverse_dictionary[i] for i in range(plot_only)]
plot_with_labels(low_dim_embs, labels)

LZ其实对自然语言处理也不是很懂，所以NLP的部分也就只能浅尝辄止啦O(∩_∩)O