def test_create_dataset_list(self):
data = [
['a', 'sunny', 85.0, 85.0, 'FALSE', 'no'],
['b', 'sunny', 80.0, 90.0, 'TRUE', 'no'],
['c', 'overcast', 83.0, 86.0, 'FALSE', 'yes'],
['d', 'rainy', 70.0, 96.0, 'FALSE', 'yes'],
['e', 'rainy', 68.0, 80.0, 'FALSE', 'yes'],
['f', 'rainy', 65.0, 70.0, 'TRUE', 'no'],
['g', 'overcast', 64.0, 65.0, 'TRUE', 'yes'],
['h', 'sunny', 72.0, 95.0, 'FALSE', 'no'],
['i', 'sunny', 69.0, 70.0, 'FALSE', 'yes'],
['j', 'rainy', 75.0, 80.0, 'FALSE', 'yes'],
['k', 'sunny', 75.0, 70.0, 'TRUE', 'yes'],
['l', 'overcast', 72.0, 90.0, 'TRUE', 'yes'],
['m', 'overcast', 81.0, 75.0, 'FALSE', 'yes'],
['n', 'rainy', 71.0, 91.0, 'TRUE', 'no'],
]
attributes = [
('rnd_str', 'STRING'),
('outlook', ['sunny', 'overcast', 'rainy']),
('temperature', 'REAL'),
('humidity', 'REAL'),
('windy', ['TRUE', 'FALSE']),
('play', ['yes', 'no']),
]
dataset = create_dataset(
name="%s-ModifiedWeather" % self._get_sentinel(),
description=(
'Testing dataset upload when the data is a list of lists'
),
creator='OpenML test',
contributor=None,
collection_date='21-09-2018',
language='English',
licence='MIT',
default_target_attribute='play',
row_id_attribute=None,
ignore_attribute=None,
citation='None',
attributes=attributes,
data=data,
version_label='test',
original_data_url='http://openml.github.io/openml-python',
paper_url='http://openml.github.io/openml-python'
)
upload_did = dataset.publish()
self.assertEqual(
_get_online_dataset_arff(upload_did),
dataset._dataset,
"Uploaded ARFF does not match original one"
)
self.assertEqual(
_get_online_dataset_format(upload_did),
'arff',
"Wrong format for dataset"
)
def test_create_dataset_numpy(self):
data = np.array([[1, 2, 3], [1.2, 2.5, 3.8], [2, 5, 8], [0, 1, 0]]).T
attributes = [('col_{}'.format(i), 'REAL')
for i in range(data.shape[1])]
dataset = create_dataset(
name='%s-NumPy_testing_dataset' % self._get_sentinel(),
description='Synthetic dataset created from a NumPy array',
creator='OpenML tester',
contributor=None,
collection_date='01-01-2018',
language='English',
licence='MIT',
default_target_attribute='col_{}'.format(data.shape[1] - 1),
row_id_attribute=None,
ignore_attribute=None,
citation='None',
attributes=attributes,
data=data,
version_label='test',
original_data_url='http://openml.github.io/openml-python',
paper_url='http://openml.github.io/openml-python')
upload_did = dataset.publish()
self.assertEqual(_get_online_dataset_arff(upload_did),
dataset._dataset,
"Uploaded arff does not match original one")
self.assertEqual(_get_online_dataset_format(upload_did), 'arff',
"Wrong format for dataset")
def test_create_dataset_row_id_attribute_inference(self):
# meta-information
name = '%s-pandas_testing_dataset' % self._get_sentinel()
description = 'Synthetic dataset created from a Pandas DataFrame'
creator = 'OpenML tester'
collection_date = '01-01-2018'
language = 'English'
licence = 'MIT'
default_target_attribute = 'target'
citation = 'None'
original_data_url = 'http://openml.github.io/openml-python'
paper_url = 'http://openml.github.io/openml-python'
# Check that the index name is well inferred.
data = [['a', 1, 0],
['b', 2, 1],
['c', 3, 0],
['d', 4, 1],
['e', 5, 0]]
column_names = ['rnd_str', 'integer', 'target']
df = pd.DataFrame(data, columns=column_names)
row_id_attr = [None, 'integer']
df_index_name = [None, 'index_name']
expected_row_id = [None, 'index_name', 'integer', 'integer']
for output_row_id, (row_id, index_name) in zip(expected_row_id,
product(row_id_attr,
df_index_name)):
df.index.name = index_name
dataset = openml.datasets.functions.create_dataset(
name=name,
description=description,
creator=creator,
contributor=None,
collection_date=collection_date,
language=language,
licence=licence,
default_target_attribute=default_target_attribute,
ignore_attribute=None,
citation=citation,
attributes='auto',
data=df,
row_id_attribute=row_id,
version_label='test',
original_data_url=original_data_url,
paper_url=paper_url
)
self.assertEqual(dataset.row_id_attribute, output_row_id)
upload_did = dataset.publish()
arff_dataset = arff.loads(_get_online_dataset_arff(upload_did))
arff_data = np.array(arff_dataset['data'], dtype=object)
# if we set the name of the index then the index will be added to
# the data
expected_shape = (5, 3) if index_name is None else (5, 4)
self.assertEqual(arff_data.shape, expected_shape)
def test_get_online_dataset_arff(self):
dataset_id = 100 # Australian
# lazy loading not used as arff file is checked.
dataset = openml.datasets.get_dataset(dataset_id)
decoder = arff.ArffDecoder()
# check if the arff from the dataset is
# the same as the arff from _get_arff function
d_format = (dataset.format).lower()
self.assertEqual(
dataset._get_arff(d_format),
decoder.decode(
_get_online_dataset_arff(dataset_id),
encode_nominal=True,
return_type=arff.DENSE if d_format == 'arff' else arff.COO),
"ARFF files are not equal")
def test_create_dataset_numpy(self):
data = np.array(
[
[1, 2, 3],
[1.2, 2.5, 3.8],
[2, 5, 8],
[0, 1, 0]
]
).T
attributes = [('col_{}'.format(i), 'REAL')
for i in range(data.shape[1])]
dataset = create_dataset(
name='%s-NumPy_testing_dataset' % self._get_sentinel(),
description='Synthetic dataset created from a NumPy array',
creator='OpenML tester',
contributor=None,
collection_date='01-01-2018',
language='English',
licence='MIT',
default_target_attribute='col_{}'.format(data.shape[1] - 1),
row_id_attribute=None,
ignore_attribute=None,
citation='None',
attributes=attributes,
data=data,
version_label='test',
original_data_url='http://openml.github.io/openml-python',
paper_url='http://openml.github.io/openml-python'
)
upload_did = dataset.publish()
self.assertEqual(
_get_online_dataset_arff(upload_did),
dataset._dataset,
"Uploaded arff does not match original one"
)
self.assertEqual(
_get_online_dataset_format(upload_did),
'arff',
"Wrong format for dataset"
)
def test_get_online_dataset_arff(self):
# Australian dataset
dataset_id = 100
dataset = openml.datasets.get_dataset(dataset_id)
decoder = arff.ArffDecoder()
# check if the arff from the dataset is
# the same as the arff from _get_arff function
d_format = (dataset.format).lower()
self.assertEqual(
dataset._get_arff(d_format),
decoder.decode(
_get_online_dataset_arff(dataset_id),
encode_nominal=True,
return_type=arff.DENSE
if d_format == 'arff' else arff.COO
),
"ARFF files are not equal"
)
def test_create_dataset_pandas(self):
data = [
['a', 'sunny', 85.0, 85.0, 'FALSE', 'no'],
['b', 'sunny', 80.0, 90.0, 'TRUE', 'no'],
['c', 'overcast', 83.0, 86.0, 'FALSE', 'yes'],
['d', 'rainy', 70.0, 96.0, 'FALSE', 'yes'],
['e', 'rainy', 68.0, 80.0, 'FALSE', 'yes']
]
column_names = ['rnd_str', 'outlook', 'temperature', 'humidity',
'windy', 'play']
df = pd.DataFrame(data, columns=column_names)
# enforce the type of each column
df['outlook'] = df['outlook'].astype('category')
df['windy'] = df['windy'].astype('bool')
df['play'] = df['play'].astype('category')
# meta-information
name = '%s-pandas_testing_dataset' % self._get_sentinel()
description = 'Synthetic dataset created from a Pandas DataFrame'
creator = 'OpenML tester'
collection_date = '01-01-2018'
language = 'English'
licence = 'MIT'
default_target_attribute = 'play'
citation = 'None'
original_data_url = 'http://openml.github.io/openml-python'
paper_url = 'http://openml.github.io/openml-python'
dataset = openml.datasets.functions.create_dataset(
name=name,
description=description,
creator=creator,
contributor=None,
collection_date=collection_date,
language=language,
licence=licence,
default_target_attribute=default_target_attribute,
row_id_attribute=None,
ignore_attribute=None,
citation=citation,
attributes='auto',
data=df,
version_label='test',
original_data_url=original_data_url,
paper_url=paper_url
)
upload_did = dataset.publish()
self.assertEqual(
_get_online_dataset_arff(upload_did),
dataset._dataset,
"Uploaded ARFF does not match original one"
)
# Check that SparseDataFrame are supported properly
sparse_data = scipy.sparse.coo_matrix((
[0.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0],
([0, 1, 1, 2, 2, 3, 3], [0, 1, 2, 0, 2, 0, 1])
))
column_names = ['input1', 'input2', 'y']
df = pd.SparseDataFrame(sparse_data, columns=column_names)
# meta-information
description = 'Synthetic dataset created from a Pandas SparseDataFrame'
dataset = openml.datasets.functions.create_dataset(
name=name,
description=description,
creator=creator,
contributor=None,
collection_date=collection_date,
language=language,
licence=licence,
default_target_attribute=default_target_attribute,
row_id_attribute=None,
ignore_attribute=None,
citation=citation,
attributes='auto',
data=df,
version_label='test',
original_data_url=original_data_url,
paper_url=paper_url
)
upload_did = dataset.publish()
self.assertEqual(
_get_online_dataset_arff(upload_did),
dataset._dataset,
"Uploaded ARFF does not match original one"
)
self.assertEqual(
_get_online_dataset_format(upload_did),
'sparse_arff',
"Wrong format for dataset"
)
# Check that we can overwrite the attributes
data = [['a'], ['b'], ['c'], ['d'], ['e']]
column_names = ['rnd_str']
df = pd.DataFrame(data, columns=column_names)
df['rnd_str'] = df['rnd_str'].astype('category')
attributes = {'rnd_str': ['a', 'b', 'c', 'd', 'e', 'f', 'g']}
dataset = openml.datasets.functions.create_dataset(
name=name,
description=description,
creator=creator,
contributor=None,
collection_date=collection_date,
language=language,
licence=licence,
default_target_attribute=default_target_attribute,
row_id_attribute=None,
ignore_attribute=None,
citation=citation,
attributes=attributes,
data=df,
version_label='test',
original_data_url=original_data_url,
paper_url=paper_url
)
upload_did = dataset.publish()
downloaded_data = _get_online_dataset_arff(upload_did)
self.assertEqual(
downloaded_data,
dataset._dataset,
"Uploaded ARFF does not match original one"
)
self.assertTrue(
'@ATTRIBUTE rnd_str {a, b, c, d, e, f, g}' in downloaded_data)
def test_create_dataset_sparse(self):
# test the scipy.sparse.coo_matrix
sparse_data = scipy.sparse.coo_matrix((
[0.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0],
([0, 1, 1, 2, 2, 3, 3], [0, 1, 2, 0, 2, 0, 1])
))
column_names = [
('input1', 'REAL'),
('input2', 'REAL'),
('y', 'REAL'),
]
xor_dataset = create_dataset(
name="%s-XOR" % self._get_sentinel(),
description='Dataset representing the XOR operation',
creator=None,
contributor=None,
collection_date=None,
language='English',
licence=None,
default_target_attribute='y',
row_id_attribute=None,
ignore_attribute=None,
citation=None,
attributes=column_names,
data=sparse_data,
version_label='test',
)
upload_did = xor_dataset.publish()
self.assertEqual(
_get_online_dataset_arff(upload_did),
xor_dataset._dataset,
"Uploaded ARFF does not match original one"
)
self.assertEqual(
_get_online_dataset_format(upload_did),
'sparse_arff',
"Wrong format for dataset"
)
# test the list of dicts sparse representation
sparse_data = [
{0: 0.0},
{1: 1.0, 2: 1.0},
{0: 1.0, 2: 1.0},
{0: 1.0, 1: 1.0}
]
xor_dataset = create_dataset(
name="%s-XOR" % self._get_sentinel(),
description='Dataset representing the XOR operation',
creator=None,
contributor=None,
collection_date=None,
language='English',
licence=None,
default_target_attribute='y',
row_id_attribute=None,
ignore_attribute=None,
citation=None,
attributes=column_names,
data=sparse_data,
version_label='test',
)
upload_did = xor_dataset.publish()
self.assertEqual(
_get_online_dataset_arff(upload_did),
xor_dataset._dataset,
"Uploaded ARFF does not match original one"
)
self.assertEqual(
_get_online_dataset_format(upload_did),
'sparse_arff',
"Wrong format for dataset"
)