Function load_data

code/imdb.py:82–175

Loads the dataset :type path: String :param path: The path to the dataset (here IMDB) :type n_words: int :param n_words: The number of word to keep in the vocabulary. All extra words are set to unknow (1). :type valid_portion: float :param valid_portion: The proporti

(path="imdb.pkl", n_words=100000, valid_portion=0.1, maxlen=None,
              sort_by_len=True)

def load_data(path="imdb.pkl", n_words=100000, valid_portion=0.1, maxlen=None,
              sort_by_len=True):
    '''Loads the dataset

    :type path: String
    :param path: The path to the dataset (here IMDB)
    :type n_words: int
    :param n_words: The number of word to keep in the vocabulary.
        All extra words are set to unknow (1).
    :type valid_portion: float
    :param valid_portion: The proportion of the full train set used for
        the validation set.
    :type maxlen: None or positive int
    :param maxlen: the max sequence length we use in the train/valid set.
    :type sort_by_len: bool
    :name sort_by_len: Sort by the sequence lenght for the train,
        valid and test set. This allow faster execution as it cause
        less padding per minibatch. Another mechanism must be used to
        shuffle the train set at each epoch.

    '''

    #############
    # LOAD DATA #
    #############

    # Load the dataset
    path = get_dataset_file(
        path, "imdb.pkl",
        "http://www.iro.umontreal.ca/~lisa/deep/data/imdb.pkl")

    if path.endswith(".gz"):
        f = gzip.open(path, 'rb')
    else:
        f = open(path, 'rb')

    train_set = pickle.load(f)
    test_set = pickle.load(f)
    f.close()
    if maxlen:
        new_train_set_x = []
        new_train_set_y = []
        for x, y in zip(train_set[0], train_set[1]):
            if len(x) < maxlen:
                new_train_set_x.append(x)
                new_train_set_y.append(y)
        train_set = (new_train_set_x, new_train_set_y)
        del new_train_set_x, new_train_set_y

    # split training set into validation set
    train_set_x, train_set_y = train_set
    n_samples = len(train_set_x)
    sidx = numpy.random.permutation(n_samples)
    n_train = int(numpy.round(n_samples * (1. - valid_portion)))
    valid_set_x = [train_set_x[s] for s in sidx[n_train:]]
    valid_set_y = [train_set_y[s] for s in sidx[n_train:]]
    train_set_x = [train_set_x[s] for s in sidx[:n_train]]
    train_set_y = [train_set_y[s] for s in sidx[:n_train]]