Python keras.datasets.reuters.load_data() Examples

The following are 30 code examples of keras.datasets.reuters.load_data(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module keras.datasets.reuters , or try the search function .
Example #1
Source File: datasets.py    From DEC-keras with MIT License 6 votes vote down vote up 
def load_imdb():
    from keras.preprocessing.text import Tokenizer
    from keras.datasets import imdb
    max_words = 1000

    print('Loading data...')
    (x1, y1), (x2, y2) = imdb.load_data(num_words=max_words)
    x = np.concatenate((x1, x2))
    y = np.concatenate((y1, y2))
    print(len(x), 'train sequences')

    num_classes = np.max(y) + 1
    print(num_classes, 'classes')

    print('Vectorizing sequence data...')
    tokenizer = Tokenizer(num_words=max_words)
    x = tokenizer.sequences_to_matrix(x, mode='binary')
    print('x_train shape:', x.shape)

    return x.astype(float), y
Example #2
Source File: test_datasets.py    From CAPTCHA-breaking with MIT License 6 votes vote down vote up 
def test_imdb(self):
        print('imdb')
        (X_train, y_train), (X_test, y_test) = imdb.load_data()
Example #3
Source File: datasets.py    From DEC-keras with MIT License 6 votes vote down vote up 
def load_retures_keras():
    from keras.preprocessing.text import Tokenizer
    from keras.datasets import reuters
    max_words = 1000

    print('Loading data...')
    (x, y), (_, _) = reuters.load_data(num_words=max_words, test_split=0.)
    print(len(x), 'train sequences')

    num_classes = np.max(y) + 1
    print(num_classes, 'classes')

    print('Vectorizing sequence data...')
    tokenizer = Tokenizer(num_words=max_words)
    x = tokenizer.sequences_to_matrix(x, mode='binary')
    print('x_train shape:', x.shape)

    return x.astype(float), y
Example #4
Source File: test_datasets.py    From CAPTCHA-breaking with MIT License 6 votes vote down vote up 
def test_cifar(self):
        print('cifar10')
        (X_train, y_train), (X_test, y_test) = cifar10.load_data()
        print(X_train.shape)
        print(X_test.shape)
        print(y_train.shape)
        print(y_test.shape)

        print('cifar100 fine')
        (X_train, y_train), (X_test, y_test) = cifar100.load_data('fine')
        print(X_train.shape)
        print(X_test.shape)
        print(y_train.shape)
        print(y_test.shape)

        print('cifar100 coarse')
        (X_train, y_train), (X_test, y_test) = cifar100.load_data('coarse')
        print(X_train.shape)
        print(X_test.shape)
        print(y_train.shape)
        print(y_test.shape)
Example #5
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_imdb():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = imdb.load_data()
        (x_train, y_train), (x_test, y_test) = imdb.load_data(maxlen=40)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = imdb.get_word_index()
        assert isinstance(word_index, dict)
Example #6
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_mnist():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = mnist.load_data()
        assert len(x_train) == len(y_train) == 60000
        assert len(x_test) == len(y_test) == 10000
Example #7
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_imdb():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = imdb.load_data()
        (x_train, y_train), (x_test, y_test) = imdb.load_data(maxlen=40)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = imdb.get_word_index()
        assert isinstance(word_index, dict)
Example #8
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_boston_housing():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = boston_housing.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
Example #9
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_cifar():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = cifar10.load_data()
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('fine')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('coarse')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
Example #10
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_reuters():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = reuters.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        assert len(x_train) + len(x_test) == 11228
        (x_train, y_train), (x_test, y_test) = reuters.load_data(maxlen=10)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = reuters.get_word_index()
        assert isinstance(word_index, dict)
Example #11
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_mnist():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = mnist.load_data()
        assert len(x_train) == len(y_train) == 60000
        assert len(x_test) == len(y_test) == 10000
Example #12
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_imdb():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = imdb.load_data()
        (x_train, y_train), (x_test, y_test) = imdb.load_data(maxlen=40)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = imdb.get_word_index()
        assert isinstance(word_index, dict)
Example #13
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_boston_housing():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = boston_housing.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
Example #14
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_cifar():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = cifar10.load_data()
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('fine')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('coarse')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
Example #15
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_reuters():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = reuters.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        assert len(x_train) + len(x_test) == 11228
        (x_train, y_train), (x_test, y_test) = reuters.load_data(maxlen=10)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = reuters.get_word_index()
        assert isinstance(word_index, dict)
Example #16
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_mnist():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = mnist.load_data()
        assert len(x_train) == len(y_train) == 60000
        assert len(x_test) == len(y_test) == 10000
Example #17
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_cifar():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = cifar10.load_data()
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('fine')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('coarse')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
Example #18
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_boston_housing():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = boston_housing.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
Example #19
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_cifar():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = cifar10.load_data()
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('fine')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('coarse')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
Example #20
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_reuters():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = reuters.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        assert len(x_train) + len(x_test) == 11228
        (x_train, y_train), (x_test, y_test) = reuters.load_data(maxlen=10)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = reuters.get_word_index()
        assert isinstance(word_index, dict)
Example #21
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_mnist():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = mnist.load_data()
        assert len(x_train) == len(y_train) == 60000
        assert len(x_test) == len(y_test) == 10000
Example #22
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_imdb():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = imdb.load_data()
        (x_train, y_train), (x_test, y_test) = imdb.load_data(maxlen=40)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = imdb.get_word_index()
        assert isinstance(word_index, dict)
Example #23
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_boston_housing():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = boston_housing.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
Example #24
Source File: datasets.py    From DEC-keras with MIT License 5 votes vote down vote up 
def load_mnist():
    # the data, shuffled and split between train and test sets
    from keras.datasets import mnist
    (x_train, y_train), (x_test, y_test) = mnist.load_data()
    x = np.concatenate((x_train, x_test))
    y = np.concatenate((y_train, y_test))
    x = x.reshape((x.shape[0], -1))
    x = np.divide(x, 255.)
    print('MNIST samples', x.shape)
    return x, y
Example #25
Source File: datasets.py    From DEC-keras with MIT License 5 votes vote down vote up 
def load_fashion_mnist():
    from keras.datasets import fashion_mnist  # this requires keras>=2.0.9
    (x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()
    x = np.concatenate((x_train, x_test))
    y = np.concatenate((y_train, y_test))
    x = x.reshape((x.shape[0], -1))
    x = np.divide(x, 255.)
    print('Fashion MNIST samples', x.shape)
    return x, y
Example #26
Source File: datasets.py    From DEC-keras with MIT License 5 votes vote down vote up 
def load_cifar10(data_path='./data/cifar10'):
    from keras.datasets import cifar10
    (train_x, train_y), (test_x, test_y) = cifar10.load_data()
    x = np.concatenate((train_x, test_x))
    y = np.concatenate((train_y, test_y)).reshape((60000,))

    # if features are ready, return them
    import os.path
    if os.path.exists(data_path + '/cifar10_features.npy'):
        return np.load(data_path + '/cifar10_features.npy'), y

    # extract features
    features = np.zeros((60000, 4096))
    for i in range(6):
        idx = range(i*10000, (i+1)*10000)
        print("The %dth 10000 samples" % i)
        features[idx] = extract_vgg16_features(x[idx])

    # scale to [0,1]
    from sklearn.preprocessing import MinMaxScaler
    features = MinMaxScaler().fit_transform(features)

    # save features
    np.save(data_path + '/cifar10_features.npy', features)
    print('features saved to ' + data_path + '/cifar10_features.npy')

    return features, y
Example #27
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_boston_housing():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = boston_housing.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
Example #28
Source File: test_datasets.py    From CAPTCHA-breaking with MIT License 5 votes vote down vote up 
def test_reuters(self):
        print('reuters')
        (X_train, y_train), (X_test, y_test) = reuters.load_data()
Example #29
Source File: test_datasets.py    From CAPTCHA-breaking with MIT License 5 votes vote down vote up 
def test_mnist(self):
        print('mnist')
        (X_train, y_train), (X_test, y_test) = mnist.load_data()
        print(X_train.shape)
        print(X_test.shape)
        print(y_train.shape)
        print(y_test.shape)
Example #30
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_cifar():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = cifar10.load_data()
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('fine')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('coarse')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000