TensorFlow使用案例

一、TensorFlow-word2vec

连续词袋模型（CBOW）：根据词的上下文词汇来预测目标词汇，例如上下文词汇是“今天早餐吃__”，要预测的目标词汇可能
是“面包“；

Skip-Gram模型：Skip-Gram模型刚好和CBOW相反，它是通过目标词汇来预测上下文词汇。例如目标词汇是“早餐”
，上下文词汇可能是“今天”和“吃面包”：

Word2vec模型
训练Word2vec模型我们通常可以选择使用噪声对比估计（Noise Contrastive Estimation）：NCE使用的方法是把上下文h对应地正确的目标词汇标记为正样本（D=1），然后再抽取一些错误的词汇作为负样本（D=0）。然后最大化目标函数的值：

当真实的目标单词被分配到较高的概率，同时噪声单词的概率很低时，目标函数也就达到最大值了。计算这个函数时，只需要计算挑选出来的k个噪声单词，而不是整个语料库。所以训练速度会很快。
Word2Vec图形化:

案例代码：

# encoding=utf8  
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

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

# 下载数据集
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)
    # 获取文件相关属性
    statinfo = os.stat(filename)
    # 比对文件的大小是否正确
    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

# 单词表
words = read_data(filename)

# Data size
print('Data size', len(words))

# Step 2: Build the dictionary and replace rare words with UNK token.
# 只留50000个单词，其他的词都归为UNK
vocabulary_size = 50000

def build_dataset(words, vocabulary_size):
    count = [['UNK', -1]]
    # extend追加一个列表
    # Counter用来统计每个词出现的次数
    # most_common返回一个TopN列表，只留50000个单词包括UNK  
    # c = Counter('abracadabra')
    # c.most_common()
    # [('a', 5), ('r', 2), ('b', 2), ('c', 1), ('d', 1)]
    # c.most_common(3)
    # [('a', 5), ('r', 2), ('b', 2)]
    # 前50000个出现次数最多的词
    count.extend(collections.Counter(words).most_common(vocabulary_size - 1))
    # 生成 dictionary，词对应编号, word:id(0-49999)
    # 词频越高编号越小
    dictionary = dict()
    for word, _ in count:
        dictionary[word] = len(dictionary)
    # data把数据集的词都编号
    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)
    # 记录UNK词的数量
    count[0][1] = unk_count
    # 编号对应词的字典
    reverse_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
    return data, count, dictionary, reverse_dictionary

# data 数据集，编号形式
# count 前50000个出现次数最多的词
# dictionary 词对应编号
# reverse_dictionary 编号对应词
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)
    # [ skip_window target skip_window ]
            # [ skip_window target skip_window ]
                    # [ skip_window target skip_window ]
            
#     [0 1 2 3 4 5 6 7 8 9 ...]
#            t     i  
    # 循环3次
    for _ in range(span):
        buffer.append(data[data_index])
        data_index = (data_index + 1) % len(data)
    # 获取batch和labels
    for i in range