学习笔记TF019:序列分类、IMDB影评分类

    import tarfile
    import re

    from helpers import download


    class ImdbMovieReviews:

        DEFAULT_URL =         ‘http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz‘
        TOKEN_REGEX = re.compile(r‘[A-Za-z]+|[!?.:,()]‘)

    def __init__(self, cache_dir, url=None):
        self._cache_dir = cache_dir
        self._url = url or type(self).DEFAULT_URL

        def __iter__(self):
            filepath = download(self._url, self._cache_dir)
            with tarfile.open(filepath) as archive:
                for filename in archive.getnames():
                    if filename.startswith(‘aclImdb/train/pos/‘):
                        yield self._read(archive, filename), True
                    elif filename.startswith(‘aclImdb/train/neg/‘):
                        yield self._read(archive, filename), False

        def _read(self, archive, filename):
            with archive.extractfile(filename) as file_:
                data = file_.read().decode(‘utf-8‘)
                data = type(self).TOKEN_REGEX.findall(data)
                data = [x.lower() for x in data]
                return data

    import bz2
    import numpy as np


    class Embedding:

        def __init__(self, vocabulary_path, embedding_path, length):
            self._embedding = np.load(embedding_path)
            with bz2.open(vocabulary_path, ‘rt‘) as file_:
                self._vocabulary = {k.strip(): i for i, k in enumerate(file_)}
            self._length = length

        def __call__(self, sequence):
            data = np.zeros((self._length, self._embedding.shape[1]))
            indices = [self._vocabulary.get(x, 0) for x in sequence]
            embedded = self._embedding[indices]
            data[:len(sequence)] = embedded
            return data

        @property
        def dimensions(self):
            return self._embedding.shape[1]

    import tensorflow as tf

    from helpers import lazy_property


    class SequenceClassificationModel:

        def __init__(self, data, target, params):
            self.data = data
            self.target = target
            self.params = params
            self.prediction
            self.cost
            self.error
            self.optimize

        @lazy_property
        def length(self):
            used = tf.sign(tf.reduce_max(tf.abs(self.data), reduction_indices=2))
            length = tf.reduce_sum(used, reduction_indices=1)
            length = tf.cast(length, tf.int32)
            return length

        @lazy_property
        def prediction(self):
            # Recurrent network.
            output, _ = tf.nn.dynamic_rnn(
                self.params.rnn_cell(self.params.rnn_hidden),
                self.data,
                dtype=tf.float32,
                sequence_length=self.length,
            )
            last = self._last_relevant(output, self.length)
            # Softmax layer.
            num_classes = int(self.target.get_shape()[1])
            weight = tf.Variable(tf.truncated_normal(
                [self.params.rnn_hidden, num_classes], stddev=0.01))
            bias = tf.Variable(tf.constant(0.1, shape=[num_classes]))
            prediction = tf.nn.softmax(tf.matmul(last, weight) + bias)
            return prediction

        @lazy_property
        def cost(self):
            cross_entropy = -tf.reduce_sum(self.target * tf.log(self.prediction))
            return cross_entropy

        @lazy_property
        def error(self):
            mistakes = tf.not_equal(
                tf.argmax(self.target, 1), tf.argmax(self.prediction, 1))
            return tf.reduce_mean(tf.cast(mistakes, tf.float32))

        @lazy_property
        def optimize(self):
            gradient = self.params.optimizer.compute_gradients(self.cost)
            try:
                limit = self.params.gradient_clipping
                gradient = [
                    (tf.clip_by_value(g, -limit, limit), v)
                    if g is not None else (None, v)
                    for g, v in gradient]
            except AttributeError:
                print(‘No gradient clipping parameter specified.‘)
            optimize = self.params.optimizer.apply_gradients(gradient)
            return optimize

        @staticmethod
        def _last_relevant(output, length):
            batch_size = tf.shape(output)[0]
            max_length = int(output.get_shape()[1])
            output_size = int(output.get_shape()[2])
            index = tf.range(0, batch_size) * max_length + (length - 1)
            flat = tf.reshape(output, [-1, output_size])
            relevant = tf.gather(flat, index)
            return relevant

    import tensorflow as tf

    from helpers import AttrDict

    from Embedding import Embedding
    from ImdbMovieReviews import ImdbMovieReviews
    from preprocess_batched import preprocess_batched
    from SequenceClassificationModel import SequenceClassificationModel

    IMDB_DOWNLOAD_DIR = ‘./imdb‘
    WIKI_VOCAB_DIR = ‘../01_wikipedia/wikipedia‘
    WIKI_EMBED_DIR = ‘../01_wikipedia/wikipedia‘


    params = AttrDict(
        rnn_cell=tf.contrib.rnn.GRUCell,
        rnn_hidden=300,
        optimizer=tf.train.RMSPropOptimizer(0.002),
        batch_size=20,
    )

    reviews = ImdbMovieReviews(IMDB_DOWNLOAD_DIR)
    length = max(len(x[0]) for x in reviews)

    embedding = Embedding(
        WIKI_VOCAB_DIR + ‘/vocabulary.bz2‘,
        WIKI_EMBED_DIR + ‘/embeddings.npy‘, length)
    batches = preprocess_batched(reviews, length, embedding, params.batch_size)

    data = tf.placeholder(tf.float32, [None, length, embedding.dimensions])
    target = tf.placeholder(tf.float32, [None, 2])
    model = SequenceClassificationModel(data, target, params)

    sess = tf.Session()
    sess.run(tf.initialize_all_variables())
    for index, batch in enumerate(batches):
        feed = {data: batch[0], target: batch[1]}
        error, _ = sess.run([model.error, model.optimize], feed)
        print(‘{}: {:3.1f}%‘.format(index + 1, 100 * error))