def read_dataset():
dataset = sets.Ocr()
dataset = sets.OneHot(dataset.target, depth=2)(dataset, columns=['target'])
dataset['data'] = dataset.data.reshape(dataset.data.shape[:-2] +
(-1, )).astype(float)
train, test = sets.Split(0.66)(dataset)
return train, test
def get_dataset():
"""Read dataset and flatten images."""
dataset = sets.Ocr()
dataset = sets.OneHot(dataset.target, depth=2)(dataset, columns=['target'])
dataset['data'] = dataset.data.reshape(dataset.data.shape[:-2] +
(-1, )).astype(float)
train, test = sets.Split(0.66)(dataset)
return train, test
def test_embedding_found():
data = list('ceabb')
target = list('abddd')
vocabulary = list('abc')
dataset = sets.Dataset(data=data, target=target)
dataset, found = sets.OneHot(vocabulary)(
dataset, columns=['data', 'target'], return_found=True)
assert found == 6 / 10
def test_semeval():
dataset = sets.SemEvalRelation()
dataset = sets.Tokenize()(dataset)
dataset = sets.OneHot(dataset.target)(dataset, columns=['target'])
dataset = sets.WordDistance('<e1>', '<e2>', depth=2)(
dataset, column='data')
dataset = sets.Glove(100, depth=2)(dataset, columns=['data'])
dataset = sets.Concat(2, 'data')(
dataset, columns=('data', 'word_distance'))
def test_onehot(dataset):
result = sets.OneHot(dataset.target)(dataset, columns=['target'])
assert result.target.shape[1] == len(np.unique(dataset.target))
assert (result.target.sum(axis=1)).all()
assert (result.target.max(axis=1)).all()
def test_ocr():
dataset = sets.Ocr()
dataset = sets.OneHot(dataset.target, depth=2)(dataset, columns=['target'])
