def test_remove_long_seq(self): a = [[[1, 1]], [[2, 1], [2, 2]], [[3, 1], [3, 2], [3, 3]]] new_seq, new_label = preprocessing_sequence._remove_long_seq( maxlen=3, seq=a, label=['a', 'b', ['c', 'd']]) self.assertEqual(new_seq, [[[1, 1]], [[2, 1], [2, 2]]]) self.assertEqual(new_label, ['a', 'b'])
def test_remove_long_seq(): maxlen = 5 seq = [ [1, 2, 3], [1, 2, 3, 4, 5, 6], ] label = ['a', 'b'] new_seq, new_label = _remove_long_seq(maxlen, seq, label) assert new_seq == [[1, 2, 3]] assert new_label == ['a']
def test_remove_long_seq(self): maxlen = 5 seq = [ [1, 2, 3], [1, 2, 3, 4, 5, 6], ] label = ['a', 'b'] new_seq, new_label = sequence._remove_long_seq(maxlen, seq, label) self.assertEqual(new_seq, [[1, 2, 3]]) self.assertEqual(new_label, ['a'])
def vectorize_words_file(path, num_words=None, skip_top=0, maxlen=None, seed=113, start_char=1, oov_char=2, index_from=3): with np.load(path) as f: x_train, labels_train = f['x_train'], f['y_train'] x_test, labels_test = f['x_test'], f['y_test'] np.random.seed(seed) indices = np.arange(len(x_train)) np.random.shuffle(indices) x_train = x_train[indices] labels_train = labels_train[indices] indices = np.arange(len(x_test)) np.random.shuffle(indices) x_test = x_test[indices] labels_test = labels_test[indices] xs = np.concatenate([x_train, x_test]) labels = np.concatenate([labels_train, labels_test]) if start_char is not None: xs = [[start_char] + [w + index_from for w in x] for x in xs] elif index_from: xs = [[w + index_from for w in x] for x in xs] if maxlen: xs, labels = _remove_long_seq(maxlen, xs, labels) if not xs: raise ValueError( 'After filtering for sequences shorter than maxlen=' + str(maxlen) + ', no sequence was kept. ' 'Increase maxlen.') if not num_words: num_words = max([max(x) for x in xs]) # by convention, use 2 as OOV word # reserve 'index_from' (=3 by default) characters: # 0 (padding), 1 (start), 2 (OOV) if oov_char is not None: xs = [[w if (skip_top <= w < num_words) else oov_char for w in x] for x in xs] else: xs = [[w for w in x if skip_top <= w < num_words] for x in xs] idx = len(x_train) x_train, y_train = np.array(xs[:idx]), np.array(labels[:idx]) x_test, y_test = np.array(xs[idx:]), np.array(labels[idx:]) return (x_train, y_train), (x_test, y_test)
def load_data(path='/home/jchourio/.keras/datasets/imdb.npz', num_words=None, skip_top=0, maxlen=None, seed=113, start_char=1, oov_char=2, index_from=3, **kwargs): if 'nb_words' in kwargs: warnings.warn('The nb_words argument in load_data has been renamed to num_words') kwargs.pop('nb_words') if kwargs: raise TypeError('Unrecognized keyword argument: {}'.format(kwargs)) with np.load(path, allow_pickle=True) as f: x_train, labels_train = f['x_train'], f['y_train'] x_test, labels_test = f['x_test'], f['y_test'] np.random.seed(seed) indices = np.arange(len(x_train)) np.random.shuffle(indices) x_train = x_train[indices] labels_train = labels_train[indices] indices = np.arange(x_test.shape[0]) np.random.shuffle(indices) x_test = x_test[indices] labels_test = labels_test[indices] xs = np.concatenate([x_train, x_test]) labels = np.concatenate([labels_train, labels_test]) if start_char is not None: xs = [[start_char] + [w + index_from for w in x] for x in xs] elif index_from: xs = [[w + index_from for w in x] for x in xs] if maxlen: xs, labels = _remove_long_seq(maxlen, xs, labels) if not xs: raise ValueError('After filtering for sequences shorter than maxlen') if not num_words: num_words = max([max(x) for x in xs]) if oov_char is not None: xs = [[w if (skip_top <= w < num_words) else oov_char for w in x] for x in xs] else: xs = [[w for w in x if skip_top <= w <= num_words] for x in xs] idx = len(x_train) x_train, y_train = np.array(xs[: idx]), np.array(labels[: idx]) x_test, y_test = np.array(xs[idx: ]), np.array(labels[idx: ]) return (x_train, y_train), (x_test, y_test)
def load_data(path='reuters.npz', num_words=None, skip_top=0, maxlen=None, test_split=0.2, seed=113, start_char=1, oov_char=2, index_from=3, **kwargs): """Loads the Reuters newswire classification dataset. This is a dataset of 11,228 newswires from Reuters, labeled over 46 topics. This was originally generated by parsing and preprocessing the classic Reuters-21578 dataset, but the preprocessing code is no longer packaged with Keras. See this [github discussion](https://github.com/keras-team/keras/issues/12072) for more info. Each newswire is encoded as a list of word indexes (integers). For convenience, words are indexed by overall frequency in the dataset, so that for instance the integer "3" encodes the 3rd most frequent word in the data. This allows for quick filtering operations such as: "only consider the top 10,000 most common words, but eliminate the top 20 most common words". As a convention, "0" does not stand for a specific word, but instead is used to encode any unknown word. Args: path: where to cache the data (relative to `~/.keras/dataset`). num_words: integer or None. Words are ranked by how often they occur (in the training set) and only the `num_words` most frequent words are kept. Any less frequent word will appear as `oov_char` value in the sequence data. If None, all words are kept. Defaults to None, so all words are kept. skip_top: skip the top N most frequently occurring words (which may not be informative). These words will appear as `oov_char` value in the dataset. Defaults to 0, so no words are skipped. maxlen: int or None. Maximum sequence length. Any longer sequence will be truncated. Defaults to None, which means no truncation. test_split: Float between 0 and 1. Fraction of the dataset to be used as test data. Defaults to 0.2, meaning 20% of the dataset is used as test data. seed: int. Seed for reproducible data shuffling. start_char: int. The start of a sequence will be marked with this character. Defaults to 1 because 0 is usually the padding character. oov_char: int. The out-of-vocabulary character. Words that were cut out because of the `num_words` or `skip_top` limits will be replaced with this character. index_from: int. Index actual words with this index and higher. **kwargs: Used for backwards compatibility. Returns: Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`. **x_train, x_test**: lists of sequences, which are lists of indexes (integers). If the num_words argument was specific, the maximum possible index value is `num_words - 1`. If the `maxlen` argument was specified, the largest possible sequence length is `maxlen`. **y_train, y_test**: lists of integer labels (1 or 0). Note: The 'out of vocabulary' character is only used for words that were present in the training set but are not included because they're not making the `num_words` cut here. Words that were not seen in the training set but are in the test set have simply been skipped. """ # Legacy support if 'nb_words' in kwargs: logging.warning('The `nb_words` argument in `load_data` ' 'has been renamed `num_words`.') num_words = kwargs.pop('nb_words') if kwargs: raise TypeError('Unrecognized keyword arguments: ' + str(kwargs)) origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/' path = get_file( path, origin=origin_folder + 'reuters.npz', file_hash= 'd6586e694ee56d7a4e65172e12b3e987c03096cb01eab99753921ef915959916') with np.load(path, allow_pickle=True) as f: xs, labels = f['x'], f['y'] rng = np.random.RandomState(seed) indices = np.arange(len(xs)) rng.shuffle(indices) xs = xs[indices] labels = labels[indices] if start_char is not None: xs = [[start_char] + [w + index_from for w in x] for x in xs] elif index_from: xs = [[w + index_from for w in x] for x in xs] if maxlen: xs, labels = _remove_long_seq(maxlen, xs, labels) if not num_words: num_words = max(max(x) for x in xs) # by convention, use 2 as OOV word # reserve 'index_from' (=3 by default) characters: # 0 (padding), 1 (start), 2 (OOV) if oov_char is not None: xs = [[w if skip_top <= w < num_words else oov_char for w in x] for x in xs] else: xs = [[w for w in x if skip_top <= w < num_words] for x in xs] idx = int(len(xs) * (1 - test_split)) x_train, y_train = np.array(xs[:idx]), np.array(labels[:idx]) x_test, y_test = np.array(xs[idx:]), np.array(labels[idx:]) return (x_train, y_train), (x_test, y_test)
def load_data( path="imdb.npz", num_words=None, skip_top=0, maxlen=None, seed=113, start_char=1, oov_char=2, index_from=3, **kwargs, ): """Loads the [IMDB dataset](https://ai.stanford.edu/~amaas/data/sentiment/). This is a dataset of 25,000 movies reviews from IMDB, labeled by sentiment (positive/negative). Reviews have been preprocessed, and each review is encoded as a list of word indexes (integers). For convenience, words are indexed by overall frequency in the dataset, so that for instance the integer "3" encodes the 3rd most frequent word in the data. This allows for quick filtering operations such as: "only consider the top 10,000 most common words, but eliminate the top 20 most common words". As a convention, "0" does not stand for a specific word, but instead is used to encode any unknown word. Args: path: where to cache the data (relative to `~/.keras/dataset`). num_words: integer or None. Words are ranked by how often they occur (in the training set) and only the `num_words` most frequent words are kept. Any less frequent word will appear as `oov_char` value in the sequence data. If None, all words are kept. Defaults to None, so all words are kept. skip_top: skip the top N most frequently occurring words (which may not be informative). These words will appear as `oov_char` value in the dataset. Defaults to 0, so no words are skipped. maxlen: int or None. Maximum sequence length. Any longer sequence will be truncated. Defaults to None, which means no truncation. seed: int. Seed for reproducible data shuffling. start_char: int. The start of a sequence will be marked with this character. Defaults to 1 because 0 is usually the padding character. oov_char: int. The out-of-vocabulary character. Words that were cut out because of the `num_words` or `skip_top` limits will be replaced with this character. index_from: int. Index actual words with this index and higher. **kwargs: Used for backwards compatibility. Returns: Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`. **x_train, x_test**: lists of sequences, which are lists of indexes (integers). If the num_words argument was specific, the maximum possible index value is `num_words - 1`. If the `maxlen` argument was specified, the largest possible sequence length is `maxlen`. **y_train, y_test**: lists of integer labels (1 or 0). Raises: ValueError: in case `maxlen` is so low that no input sequence could be kept. Note that the 'out of vocabulary' character is only used for words that were present in the training set but are not included because they're not making the `num_words` cut here. Words that were not seen in the training set but are in the test set have simply been skipped. """ # Legacy support if "nb_words" in kwargs: logging.warning( "The `nb_words` argument in `load_data` " "has been renamed `num_words`." ) num_words = kwargs.pop("nb_words") if kwargs: raise TypeError(f"Unrecognized keyword arguments: {str(kwargs)}.") origin_folder = ( "https://storage.googleapis.com/tensorflow/tf-keras-datasets/" ) path = get_file( path, origin=origin_folder + "imdb.npz", file_hash="69664113be75683a8fe16e3ed0ab59fda8886cb3cd7ada244f7d9544e4676b9f", ) with np.load( path, allow_pickle=True ) as f: # pylint: disable=unexpected-keyword-arg x_train, labels_train = f["x_train"], f["y_train"] x_test, labels_test = f["x_test"], f["y_test"] rng = np.random.RandomState(seed) indices = np.arange(len(x_train)) rng.shuffle(indices) x_train = x_train[indices] labels_train = labels_train[indices] indices = np.arange(len(x_test)) rng.shuffle(indices) x_test = x_test[indices] labels_test = labels_test[indices] if start_char is not None: x_train = [[start_char] + [w + index_from for w in x] for x in x_train] x_test = [[start_char] + [w + index_from for w in x] for x in x_test] elif index_from: x_train = [[w + index_from for w in x] for x in x_train] x_test = [[w + index_from for w in x] for x in x_test] if maxlen: x_train, labels_train = _remove_long_seq(maxlen, x_train, labels_train) x_test, labels_test = _remove_long_seq(maxlen, x_test, labels_test) if not x_train or not x_test: raise ValueError( "After filtering for sequences shorter than maxlen=" f"{str(maxlen)}, no sequence was kept. Increase maxlen." ) xs = x_train + x_test labels = np.concatenate([labels_train, labels_test]) if not num_words: num_words = max(max(x) for x in xs) # by convention, use 2 as OOV word # reserve 'index_from' (=3 by default) characters: # 0 (padding), 1 (start), 2 (OOV) if oov_char is not None: xs = [ [w if (skip_top <= w < num_words) else oov_char for w in x] for x in xs ] else: xs = [[w for w in x if skip_top <= w < num_words] for x in xs] idx = len(x_train) x_train, y_train = np.array(xs[:idx], dtype="object"), labels[:idx] x_test, y_test = np.array(xs[idx:], dtype="object"), labels[idx:] return (x_train, y_train), (x_test, y_test)
def load_data(word_index=None, path='imdb', num_words=None, skip_top=0, maxlen=None, seed=113, start_char=1, oov_char=2, index_from=3, **kwargs): # """Loads the IMDB dataset. # # # Arguments # path: where to cache the data (relative to `~/.keras/dataset`). # num_words: max number of words to include. Words are ranked # by how often they occur (in the training set) and only # the most frequent words are kept # skip_top: skip the top N most frequently occurring words # (which may not be informative). # maxlen: sequences longer than this will be filtered out. # seed: random seed for sample shuffling. # start_char: The start of a sequence will be marked with this character. # Set to 1 because 0 is usually the padding character. # oov_char: words that were cut out because of the `num_words` # or `skip_top` limit will be replaced with this character. # index_from: index actual words with this index and higher. # # # Returns # Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`. # # # Raises # ValueError: in case `maxlen` is so low # that no input sequence could be kept. # # Note that the 'out of vocabulary' character is only used for # words that were present in the training set but are not included # because they're not making the `num_words` cut here. # Words that were not seen in the training set but are in the test set # have simply been skipped. # """ # # Legacy support if 'nb_words' in kwargs: warnings.warn('The `nb_words` argument in `load_data` ' 'has been renamed `num_words`.') num_words = kwargs.pop('nb_words') if kwargs: raise TypeError('Unrecognized keyword arguments: ' + str(kwargs)) if path == 'imdb': if os.path.exists(os.path.join(os.getcwd(), 'dataset/imdb.npz')): path = os.path.join(os.getcwd(), 'dataset/imdb.npz') if os.path.exists(os.path.join(os.getcwd(), '../dataset/imdb.npz')): path = os.path.join(os.getcwd(), '../dataset/imdb.npz') if os.path.exists(os.path.join(os.getcwd(), 'IMDB_sentiment_Analysis/dataset/imdb.npz')): path = os.path.join(os.getcwd(), 'IMDB_sentiment_Analysis/dataset/imdb.npz') if path == 'filtered_imdb': if os.path.exists(os.path.join(os.getcwd(), 'dataset/filtered_imdb.npz')): path = os.path.join(os.getcwd(), 'dataset/filtered_imdb.npz') if os.path.exists(os.path.join(os.getcwd(), '../dataset/filtered_imdb.npz')): path = os.path.join(os.getcwd(), '../dataset/filtered_imdb.npz') if os.path.exists(os.path.join(os.getcwd(), 'IMDB_sentiment_Analysis/dataset/filtered_imdb.npz')): path = os.path.join(os.getcwd(), 'IMDB_sentiment_Analysis/dataset/filtered_imdb.npz') with np.load(path, allow_pickle=True) as f: x_train, labels_train = f['x_train'], f['y_train'] x_test, labels_test = f['x_test'], f['y_test'] # Filtering dataset with vocabulary list if word_index is not None: word_list = list(word_index.values()) for train in tqdm(x_train): for word in train: if word not in word_list: train.remove(word) for test in tqdm(x_test): for test_word in test: if test_word not in word_list: test.remove(test_word) # Randomize Data rng = np.random.RandomState(seed) indices = np.arange(len(x_train)) rng.shuffle(indices) x_train = x_train[indices] labels_train = labels_train[indices] indices = np.arange(len(x_test)) rng.shuffle(indices) x_test = x_test[indices] labels_test = labels_test[indices] xs = np.concatenate([x_train, x_test]) labels = np.concatenate([labels_train, labels_test]) if start_char is not None: xs = [[start_char] + [w + index_from for w in x] for x in xs] elif index_from: xs = [[w + index_from for w in x] for x in xs] if maxlen: xs, labels = _remove_long_seq(maxlen, xs, labels) if not xs: raise ValueError('After filtering for sequences shorter than maxlen=' + str(maxlen) + ', no sequence was kept. ' 'Increase maxlen.') if not num_words: num_words = max([max(x) for x in xs]) # by convention, use 2 as OOV word # reserve 'index_from' (=3 by default) characters: # 0 (padding), 1 (start), 2 (OOV) if oov_char is not None: xs = [[w if (skip_top <= w < num_words) else oov_char for w in x] for x in xs] else: xs = [[w for w in x if skip_top <= w < num_words] for x in xs] idx = len(x_train) x_train, y_train = np.array(xs[:idx]), np.array(labels[:idx]) x_test, y_test = np.array(xs[idx:]), np.array(labels[idx:]) return (x_train, y_train), (x_test, y_test)
def load_imdb_data(path = r'D:/projects/dataset/imdb.npz', num_words=None, skip_top=0, maxlen=None, seed=113, start_char=1, oov_char=2, index_from=3, **kwargs): """Loads the IMDB dataset. # Arguments path: imdb.npz 的路径. num_words: max number of words to include. skip_top: skip the top N most frequently occurring words (which may not be informative). maxlen: sequences longer than this will be filtered out. seed: random seed for sample shuffling. start_char: The start of a sequence will be marked with this character. Set to 1 because 0 is usually the padding character. oov_char: words that were cut out because of the `num_words` or `skip_top` limit will be replaced with this character. index_from: index actual words with this index and higher. # Returns Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`. # Raises ValueError: in case `maxlen` is so low that no input sequence could be kept. """ # Legacy support if 'nb_words' in kwargs: warnings.warn('The `nb_words` argument in `load_data` ' 'has been renamed `num_words`.') num_words = kwargs.pop('nb_words') if kwargs: raise TypeError('Unrecognized keyword arguments: ' + str(kwargs)) with np.load(path,allow_pickle=True) as f: x_train, labels_train = f['x_train'], f['y_train'] x_test, labels_test = f['x_test'], f['y_test'] np.random.seed(seed) indices = np.arange(len(x_train)) np.random.shuffle(indices) x_train = x_train[indices] labels_train = labels_train[indices] indices = np.arange(len(x_test)) np.random.shuffle(indices) x_test = x_test[indices] labels_test = labels_test[indices] xs = np.concatenate([x_train, x_test]) labels = np.concatenate([labels_train, labels_test]) if start_char is not None: xs = [[start_char] + [w + index_from for w in x] for x in xs] elif index_from: xs = [[w + index_from for w in x] for x in xs] if maxlen: xs, labels = _remove_long_seq(maxlen, xs, labels) if not xs: raise ValueError('After filtering for sequences shorter than maxlen=' + str(maxlen) + ', no sequence was kept. ' 'Increase maxlen.') if not num_words: num_words = max([max(x) for x in xs]) # by convention, use 2 as OOV word # reserve 'index_from' (=3 by default) characters: # 0 (padding), 1 (start), 2 (OOV) if oov_char is not None: xs = [[w if (skip_top <= w < num_words) else oov_char for w in x] for x in xs] else: xs = [[w for w in x if skip_top <= w < num_words] for x in xs] idx = len(x_train) x_train, y_train = np.array(xs[:idx]), np.array(labels[:idx]) x_test, y_test = np.array(xs[idx:]), np.array(labels[idx:]) return (x_train, y_train), (x_test, y_test)
def load_data(path='imdb.npz', num_words=None, skip_top=0, maxlen=None, seed=113, start_char=1, oov_char=2, index_from=3, **kwargs): """Loads the IMDB dataset. # Arguments path: where to cache the data (relative to `~/.keras/dataset`). num_words: max number of words to include. Words are ranked by how often they occur (in the training set) and only the most frequent words are kept skip_top: skip the top N most frequently occurring words (which may not be informative). maxlen: sequences longer than this will be filtered out. seed: random seed for sample shuffling. start_char: The start of a sequence will be marked with this character. Set to 1 because 0 is usually the padding character. oov_char: words that were cut out because of the `num_words` or `skip_top` limit will be replaced with this character. index_from: index actual words with this index and higher. # Returns Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`. # Raises ValueError: in case `maxlen` is so low that no input sequence could be kept. Note that the 'out of vocabulary' character is only used for words that were present in the training set but are not included because they're not making the `num_words` cut here. Words that were not seen in the training set but are in the test set have simply been skipped. """ # Legacy support if 'nb_words' in kwargs: warnings.warn('The `nb_words` argument in `load_data` ' 'has been renamed `num_words`.') num_words = kwargs.pop('nb_words') if kwargs: raise TypeError('Unrecognized keyword arguments: ' + str(kwargs)) # path = get_file(path, # origin='https://s3.amazonaws.com/text-datasets/imdb.npz', # file_hash='599dadb1135973df5b59232a0e9a887c') with np.load(path) as f: x_train, labels_train = f['x_train'], f['y_train'] x_test, labels_test = f['x_test'], f['y_test'] np.random.seed(seed) indices = np.arange(len(x_train)) np.random.shuffle(indices) x_train = x_train[indices] labels_train = labels_train[indices] indices = np.arange(len(x_test)) np.random.shuffle(indices) x_test = x_test[indices] labels_test = labels_test[indices] xs = np.concatenate([x_train, x_test]) labels = np.concatenate([labels_train, labels_test]) if start_char is not None: xs = [[start_char] + [w + index_from for w in x] for x in xs] elif index_from: xs = [[w + index_from for w in x] for x in xs] if maxlen: xs, labels = _remove_long_seq(maxlen, xs, labels) if not xs: raise ValueError( 'After filtering for sequences shorter than maxlen=' + str(maxlen) + ', no sequence was kept. ' 'Increase maxlen.') if not num_words: num_words = max([max(x) for x in xs]) # by convention, use 2 as OOV word # reserve 'index_from' (=3 by default) characters: # 0 (padding), 1 (start), 2 (OOV) if oov_char is not None: xs = [[w if (skip_top <= w < num_words) else oov_char for w in x] for x in xs] else: xs = [[w for w in x if skip_top <= w < num_words] for x in xs] idx = len(x_train) x_train, y_train = np.array(xs[:idx]), np.array(labels[:idx]) x_test, y_test = np.array(xs[idx:]), np.array(labels[idx:]) return (x_train, y_train), (x_test, y_test)