tensorflow37《TensorFlow实战》笔记-07-01 TensorFlow实现Word2Vec code

# 《TensorFlow实战》07 TensorFlow实现循环神经网络及Word2Vec# win10 Tensorflow1.0.1 python3.5.3# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1# filename:sz07.01.py # TensorFlow实现Word2Vec# https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/tutorials/word2vec/word2vec_basic.py# tensorflow\tensorflow\examples\tutorials\word2vec\word2vec_basic.pyimport collectionsimport mathimport osimport randomimport zipfileimport numpy as npfrom six.moves import urllibimport tensorflow as tf# 如果下载失败，就手动下载http://mattmahoney.net/dc/text8.zip到sz07.01.py同目录下# http://mattmahoney.net/dc/text8.zipurl = 'http://mattmahoney.net/dc/'def maybe_download(filename, expected_bytes):    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 filenamefilename = maybe_download('text8.zip', 31344016)def read_data(filename):    with zipfile.ZipFile(filename) as f:        data = tf.compat.as_str(f.read(f.namelist()[0])).split()    return datawords = read_data(filename)print('Data size', len(words))vocabulary_size = 50000def 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_dictionarydata, count, dictionary, reverse_dictionary = build_dataset(words)del wordsprint('Most common words (+UNK)', count[:5])print('Sample data', data[:10], [reverse_dictionary[i] for i in data[:10]])data_index = 0def 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, labelsbatch, 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]])batch_size = 128embedding_size = 128skip_window = 1num_skips = 2valid_size = 16valid_window = 100valid_examples = np.random.choice(valid_window, valid_size, replace=False)num_sampled = 64graph = 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('/cpu: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()num_steps = 100001with 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_word = reverse_dictionary[nearest[k]]                    log_str = "%s %s," % (log_str, close_word)                print(log_str)    final_embeddings = normalized_embeddings.eval()from sklearn.manifold import TSNEimport matplotlib.pyplot as pltdef 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),                     xytext=(5,2),                     textcoords='offset points',                     ha='right',                     va='bottom')    plt.savefig(filename)tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)plot_only = 100low_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)'''Found and verified text8.zipData size 17005207Most common words (+UNK) [['UNK', 418391], ('the', 1061396), ('of', 593677), ('and', 416629), ('one', 411764)]Sample data [5242, 3084, 12, 6, 195, 2, 3137, 46, 59, 156] ['anarchism', 'originated', 'as', 'a', 'term', 'of', 'abuse', 'first', 'used', 'against']3084 originated -> 12 as3084 originated -> 5242 anarchism12 as -> 3084 originated12 as -> 6 a6 a -> 195 term6 a -> 12 as195 term -> 2 of195 term -> 6 aInitializedAverage loss at step  0 :  242.824676514Nearest to this: beatrix, territorial, odo, eileen, bicameral, animists, baptize, malm,...Nearest to world: crb, alexander, diphthongs, adventist, persons, alabama, leftist, idol,Nearest to would: will, may, can, could, might, must, should, to,Average loss at step  92000 :  4.71387670171Average loss at step  94000 :  4.62264616895Average loss at step  96000 :  4.71346354306Average loss at step  98000 :  4.62557934207Average loss at step  100000 :  4.66860903692Nearest to this: which, it, the, that, mico, spokesperson, one, dwell,Nearest to however: but, although, that, dasyprocta, ssbn, and, opencyc, microsite,Nearest to was: is, had, has, were, became, been, when, by,Nearest to d: b, lomond, raions, gh, t, deemed, aon, microsite,Nearest to use: thaler, histone, agouti, crb, primigenius, potomac, callithrix, upanija,Nearest to other: many, agouti, including, these, some, bends, callithrix, clodius,Nearest to over: about, lw, off, coolidge, absent, six, mileva, four,Nearest to after: before, when, during, in, persisted, following, was, gave,Nearest to called: UNK, used, subatomic, clo, aorta, and, emblems, implied,Nearest to often: sometimes, usually, generally, still, commonly, now, frequently, also,Nearest to of: nine, in, dasyprocta, and, including, callithrix, amo, thaler,Nearest to have: had, has, are, were, be, include, aral, elevate,Nearest to can: may, would, will, could, must, should, might, to,Nearest to three: four, five, two, six, seven, eight, one, nine,Nearest to world: alexander, diphthongs, crb, leftist, adventist, guerrilla, vortigern, appointment,Nearest to would: will, may, can, could, might, must, should, to,'''