def test_conversion(self):
problem_doc_path = os.path.join(os.path.dirname(__file__), 'data',
'problems', 'iris_problem_1',
'problemDoc.json')
problem_uri = 'file://{problem_doc_path}'.format(
problem_doc_path=problem_doc_path)
problem_description = problem.Problem.load(problem_uri)
self.assertEqual(
problem_description.to_simple_structure(),
problem.Problem.from_json_structure(
problem_description.to_json_structure(),
strict_digest=True).to_simple_structure())
# Legacy.
self.assertEqual(
utils.to_json_structure(problem_description.to_simple_structure()),
problem.Problem.from_json_structure(
utils.to_json_structure(
problem_description.to_simple_structure()),
strict_digest=True).to_simple_structure())
self.assertIs(
problem.Problem.from_json_structure(
problem_description.to_json_structure(),
strict_digest=True)['problem']['task_keywords'][0],
problem.TaskKeyword.CLASSIFICATION)
def test_dataframe_with_objects(self):
df = pandas.DataFrame({str(i): [str(j) for j in range(10)] for i in range(5)}, columns=[str(i) for i in range(5)])
df = container.DataFrame(df, generate_metadata=False)
compact_metadata = df.metadata.generate(df, compact=True)
noncompact_metadata = df.metadata.generate(df, compact=False)
basic_metadata = [
{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 10,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 5,
},
},
},
]
column_names = [{'selector': ['__ALL_ELEMENTS__', i], 'metadata': {'name': str(i)}} for i in range(5)]
self.assertEqual(utils.to_json_structure(compact_metadata.to_internal_simple_structure()), basic_metadata + [
{
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'str',
},
}
] + column_names)
column_names = [{'selector': ['__ALL_ELEMENTS__', i], 'metadata': {'name': str(i), 'structural_type': 'str'}} for i in range(5)]
self.assertEqual(utils.to_json_structure(noncompact_metadata.to_internal_simple_structure()), basic_metadata + column_names)
def test_list_with_objects(self):
l = container.List([container.List([str(j) for i in range(5)]) for j in range(10)], generate_metadata=True)
self.assertEqual(utils.to_json_structure(l.metadata.to_internal_simple_structure()), [
{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.list.List',
'dimension': {
'length': 10,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'd3m.container.list.List',
'dimension': {
'length': 5,
},
}
},
{
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'str',
},
},
])
def test_basic(self):
main = container.DataFrame({'timestamp': [1, 2, 3,4], 'value': [0.32,0.32,0.31,0.33],}, {
'top_level': 'main',
}, generate_metadata=True)
self.assertEqual(utils.to_json_structure(main.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'top_level': 'main',
'schema': metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 4,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 2,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {'structural_type': 'numpy.int64', 'name': 'timestamp'},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {'structural_type': 'numpy.float64', 'name': 'value'},
}])
hyperparams_class = HoltWintersExponentialSmoothing.HoltWintersExponentialSmoothing.metadata.get_hyperparams()
primitive = HoltWintersExponentialSmoothing.HoltWintersExponentialSmoothing(hyperparams=hyperparams_class.defaults())
# primitive.set_training_data(inputs=main)
# primitive.fit()
output_main = primitive.produce(inputs=main).value
output_main = round(output_main,2)
# new_main_drop = new_main.iloc[2:]
# new_main_drop = new_main_drop.reset_index(drop = True)
print ( "output", output_main)
expected_result = container.DataFrame(data = { 'timestamp' : [1,2,3,4], 'value': [0.32,0.32,0.31,0.32]})
print ("expected_result", expected_result)
# output_main.reset_index()
self.assertEqual(output_main[['timestamp','value_holt_winters_smoothing']].values.tolist(), expected_result[['timestamp','value']].values.tolist())
params = primitive.get_params()
primitive.set_params(params=params)
def test_problem(self):
problem_description = problem_module.parse_problem_description(os.path.join(TEST_PROBLEMS_DIR, 'iris_problem_1', 'problemDoc.json'))
# TA2-TA3 API does not encode outputs.
del problem_description['outputs']
problem_description['digest'] = d3m_utils.compute_digest(d3m_utils.to_json_structure(problem_description))
problem_message = utils.encode_problem_description(problem_description)
self.assertEqual(utils.decode_problem_description(problem_message, strict_digest=True), problem_description)
def test_metadata(self):
# print(self.prediction_labels.metadata.to_internal_simple_structure())
self.assertEqual(
utils.to_json_structure(self.prediction_labels.metadata.
to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
10,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
1,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name':
'LSTMODetector0_0',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.int64',
},
}
])
def test_dataframe_tabular_semantic_types(self):
# A DataFrame with explicit WRONG metadata.
df = container.DataFrame({'A': [1, 2, 3], 'B': ['a', 'b', 'c']}, {
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
},
})
df.A = df.A.astype(numpy.int64)
df.metadata = df.metadata.generate(df)
self.assertEqual(utils.to_json_structure(df.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
# We respect the name, but we override the semantic types.
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 2,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'A',
'structural_type': 'numpy.int64',
}
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'B',
'structural_type': 'str',
},
}])
def test_ndarray(self):
array = container.ndarray(numpy.array([1, 2, 3], dtype=numpy.int64), generate_metadata=True)
self.assertEqual(utils.to_json_structure(array.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.numpy.ndarray',
'dimension': {
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.int64',
},
}])
def test_ndarray_with_objects(self):
array = numpy.array([[[str(k) for k in range(5)] for i in range(10)] for j in range(10)], dtype=object)
array = container.ndarray(array, generate_metadata=True)
self.assertEqual(utils.to_json_structure(array.metadata.to_internal_simple_structure()), [
{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.numpy.ndarray',
'dimension': {
'length': 10,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'length': 10,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'length': 5,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'str',
},
},
])
def test_basic(self):
self.maxDiff = None
main = container.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6]
},
columns=['A', 'B'],
generate_metadata=True)
self.assertEqual(
utils.to_json_structure(
main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
2,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'structural_type': 'numpy.int64',
'name': 'A',
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'structural_type': 'numpy.int64',
'name': 'B',
},
}
])
a = np.array([[1, 0, 1, 0, 1], [1, 0, 1, 0, 1], [1, 0, 1, 0, 1]])
b = np.array([[1, 0], [1, 0], [1, 0], [1, 0], [1, 0]])
hyperparams_class = NonNegativeMatrixFactorization.NonNegativeMatrixFactorization.metadata.get_hyperparams(
)
hp = hyperparams_class.defaults().replace({
'use_semantic_types': True,
'use_columns': (
0,
1,
),
'return_result': 'append',
'rank': 5,
'seed': 'fixed',
'W': a,
'H': b,
})
primitive = NonNegativeMatrixFactorization.NonNegativeMatrixFactorization(
hyperparams=hp)
new_main = primitive.produce(inputs=main).value
print("new_main", new_main)
c = pd.DataFrame({
"A": [1, 2, 3, np.nan, np.nan],
"B": [4, 5, 6, np.nan, np.nan],
'row_latent_vector_0':
[0.816725, 1.078965, 1.341205, np.nan, np.nan],
'row_latent_vector_1':
[3.514284e-16, 2.383547e-16, 2.227207e-16, np.nan, np.nan],
'row_latent_vector_2':
[0.816725, 1.078965, 1.341205, np.nan, np.nan],
'row_latent_vector_3':
[3.514284e-16, 2.383547e-16, 2.227207e-16, np.nan, np.nan],
'row_latent_vector_4':
[0.816725, 1.078965, 1.341205, np.nan, np.nan],
'column_latent_vector_0':
[0.642626, 0.542312, 0.642626, 0.542312, 0.642626],
'column_latent_vector_1':
[1.534324, 1.848782, 1.534324, 1.848782, 1.534324],
})
pd.testing.assert_frame_equal(new_main, c)
params = primitive.get_params()
primitive.set_params(params=params)
# print(utils.to_json_structure(new_main.metadata.to_internal_simple_structure()))
self.assertEqual(
utils.to_json_structure(
new_main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
9,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'A',
'structural_type': 'numpy.int64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'B',
'structural_type': 'numpy.int64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name':
'row_latent_vector_0',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'name':
'row_latent_vector_1',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 4],
'metadata': {
'name':
'row_latent_vector_2',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 5],
'metadata': {
'name':
'row_latent_vector_3',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 6],
'metadata': {
'name':
'row_latent_vector_4',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 7],
'metadata': {
'name':
'column_latent_vector_0',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 8],
'metadata': {
'name':
'column_latent_vector_1',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
}
])
params = primitive.get_params()
primitive.set_params(params=params)
def test_basic(self):
self.maxDiff=None
main = container.DataFrame({'timestamp': [1, 3, 2, 5], 'values': [1.0, 2.0, 3.0, 4.0], 'b': [1.0, 4.0, 5.0, 6.0]},
columns=['timestamp', 'values', 'b'],
generate_metadata=True)
self.assertEqual(utils.to_json_structure(main.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema': metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 4,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {'structural_type': 'numpy.int64', 'name': 'timestamp'},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {'structural_type': 'numpy.float64', 'name': 'values'},
}, {
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {'structural_type': 'numpy.float64', 'name': 'b'},
}])
hyperparams_class = StatisticalMaximum.StatisticalMaximumPrimitive.metadata.get_hyperparams()
hp = hyperparams_class.defaults().replace({
'use_columns': [1,2],
'use_semantic_types' : True,
'window_size':2
})
primitive = StatisticalMaximum.StatisticalMaximumPrimitive(hyperparams=hp)
output_main = primitive.produce(inputs=main).value
print(output_main)
expected_output = container.DataFrame(
{'timestamp': [1, 3, 2, 5], 'values': [1.0, 2.0, 3.0, 4.0], 'b': [1.0, 4.0, 5.0, 6.0],
'values_maximum': [2.0,2.0, 3.0, 4.0], 'b_maximum': [4.0,4.0, 5.0, 6.0]},
columns=['timestamp', 'values', 'b', 'values_maximum', 'b_maximum'])
self.assertEqual(output_main[['timestamp', 'values', 'b', 'values_maximum',
'b_maximum']].values.tolist(), expected_output[
['timestamp', 'values', 'b', 'values_maximum', 'b_maximum'
]].values.tolist())
self.assertEqual(utils.to_json_structure(output_main.metadata.to_internal_simple_structure()),
[{'metadata': {'dimension': {'length': 4,
'name': 'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow']},
'schema': 'https://metadata.datadrivendiscovery.org/schemas/v0/container.json',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'structural_type': 'd3m.container.pandas.DataFrame'},
'selector': []},
{'metadata': {'dimension': {'length': 5,
'name': 'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn']}},
'selector': ['__ALL_ELEMENTS__']},
{'metadata': {'name': 'timestamp', 'structural_type': 'numpy.int64'},
'selector': ['__ALL_ELEMENTS__', 0]},
{'metadata': {'name': 'values', 'structural_type': 'numpy.float64'},
'selector': ['__ALL_ELEMENTS__', 1]},
{'metadata': {'name': 'b', 'structural_type': 'numpy.float64'},
'selector': ['__ALL_ELEMENTS__', 2]},
{'metadata': {'name': 'values_maximum',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Attribute'],
'structural_type': 'numpy.float64'},
'selector': ['__ALL_ELEMENTS__', 3]},
{'metadata': {'name': 'b_maximum',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Attribute'],
'structural_type': 'numpy.float64'},
'selector': ['__ALL_ELEMENTS__', 4]},
])
params = primitive.get_params()
primitive.set_params(params=params)
def _test_metadata(self, metadata):
self.assertEqual(
utils.to_json_structure(metadata.to_internal_simple_structure()),
[
{
'metadata': {
'dimension': {
'length':
5,
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
},
'schema':
'https://metadata.datadrivendiscovery.org/schemas/v0/container.json',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table',
'https://metadata.datadrivendiscovery.org/types/FilesCollection',
],
'structural_type':
'd3m.container.pandas.DataFrame',
},
'selector': [],
},
{
'metadata': {
'dimension': {
'length':
1,
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
}
},
'selector': ['__ALL_ELEMENTS__'],
},
{
'metadata': {
'structural_type': 'd3m.container.numpy.ndarray'
},
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__']
},
{
'metadata': {
'structural_type': 'str'
},
'selector': [
'__ALL_ELEMENTS__', '__ALL_ELEMENTS__',
'__ALL_ELEMENTS__', '__ALL_ELEMENTS__'
],
},
{
'metadata': {
'dimension': {
'length':
1,
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
},
'location_base_uris':
'__NO_VALUE__',
'media_types':
'__NO_VALUE__',
'name':
'filename',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/PrimaryKey',
'http://schema.org/ImageObject',
'https://metadata.datadrivendiscovery.org/types/Table',
]
},
'selector': ['__ALL_ELEMENTS__', 0],
},
{
'metadata': {
'dimension': {
'length':
1,
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
}
},
'selector': ['__ALL_ELEMENTS__', 0, '__ALL_ELEMENTS__'],
},
{
'metadata': {
'image_reader_metadata': {
'foobar': 42
},
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/PrimaryKey',
'http://schema.org/ImageObject',
'https://metadata.datadrivendiscovery.org/types/Table',
],
},
'selector': [0, 0],
},
{
'metadata': {
'image_reader_metadata': {
'foobar': 42
},
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/PrimaryKey',
'http://schema.org/ImageObject',
'https://metadata.datadrivendiscovery.org/types/Table',
],
},
'selector': [1, 0],
},
{
'metadata': {
'image_reader_metadata': {
'foobar': 42
},
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/PrimaryKey',
'http://schema.org/ImageObject',
'https://metadata.datadrivendiscovery.org/types/Table',
],
},
'selector': [2, 0],
},
{
'metadata': {
'image_reader_metadata': {
'foobar': 42
},
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/PrimaryKey',
'http://schema.org/ImageObject',
'https://metadata.datadrivendiscovery.org/types/Table',
],
},
'selector': [3, 0],
},
{
'metadata': {
'image_reader_metadata': {
'foobar': 42
},
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/PrimaryKey',
'http://schema.org/ImageObject',
'https://metadata.datadrivendiscovery.org/types/Table',
],
},
'selector': [4, 0],
},
],
)
def test_basic(self):
main = container.DataFrame(
{
'd3mIndex': [0, 1, 2],
'timestamp': [1., 2., 4.],
'a': [1., 2., 3.],
'b': [2., 3., 4.],
'ground_truth': [0, 0, 0],
},
columns=['d3mIndex', 'timestamp', 'a', 'b', 'ground_truth'],
generate_metadata=True)
# print(main)
self.assertEqual(
utils.to_json_structure(
main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
5,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'structural_type': 'numpy.int64',
'name': 'd3mIndex'
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'timestamp'
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'a'
}
},
{
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'b'
}
},
{
'selector': ['__ALL_ELEMENTS__', 4],
'metadata': {
'structural_type': 'numpy.int64',
'name': 'ground_truth'
}
}
])
self.assertIsInstance(main, container.DataFrame)
hyperparams_class = ContinuityValidation.ContinuityValidation.metadata.get_hyperparams(
)
primitive = ContinuityValidation.ContinuityValidation(
hyperparams=hyperparams_class.defaults())
new_main = primitive.produce(inputs=main).value
# print(new_main)
expected_output = container.DataFrame({
'd3mIndex': [0, 1, 2, 3],
'timestamp': [1., 2., 3., 4.],
'a': [1., 2., 2.5, 3.],
'b': [2., 3., 3.5, 4.],
'ground_truth': [0, 0, 0, 0]
})
self.assertEqual(new_main.values.tolist(),
expected_output.values.tolist())
self.assertEqual(
utils.to_json_structure(
new_main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
4,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
5,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'd3mIndex',
'structural_type': 'numpy.int64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'timestamp',
'structural_type': 'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name': 'a',
'structural_type': 'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'name': 'b',
'structural_type': 'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 4],
'metadata': {
'name': 'ground_truth',
'structural_type': 'numpy.int64',
},
}
])
self._test_continuity(new_main)
def test_list(self):
lst = container.List(['a', 'b', 'c'], generate_metadata=True)
self.assertEqual(utils.to_json_structure(lst.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.list.List',
'dimension': {
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'str',
},
}])
lst = container.List([1, 'a', 2.0], generate_metadata=True)
self.assertEqual(utils.to_json_structure(lst.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.list.List',
'dimension': {
'length': 3,
},
},
}, {
'selector': [0],
'metadata': {
'structural_type': 'int',
},
}, {
'selector': [1],
'metadata': {
'structural_type': 'str',
},
}, {
'selector': [2],
'metadata': {
'structural_type': 'float',
},
}])
dataframe = container.DataFrame({'A': [1, 2, 3], 'B': ['a', 'b', 'c']})
dataframe.A = dataframe.A.astype(numpy.int64)
lst = container.List([dataframe], generate_metadata=True)
self.assertEqual(utils.to_json_structure(lst.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.list.List',
'dimension': {
'length': 1,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 2,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'A',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'B',
'structural_type': 'str',
},
}])
def test_basic(self):
self.maxDiff = None
dataset_fname = os.path.join(
this_path,
'../../datasets/anomaly/kpi/TRAIN/dataset_TRAIN/tables/learningData.csv'
)
dataset = pd.read_csv(dataset_fname)
# dataset = np.random.rand(1000)
main = d3m_dataframe(dataset, generate_metadata=True)
# print(main)
hyperparams_class = SKPowerTransformer.SKPowerTransformer.metadata.get_hyperparams(
)
primitive = SKPowerTransformer.SKPowerTransformer(
hyperparams=hyperparams_class.defaults())
primitive.set_training_data(inputs=main)
primitive.fit()
new_main = primitive.produce(inputs=main).value
test_data = new_main.values[:, 2]
# hist_data = new_main.values
std_normal_samples = np.random.randn(test_data.__len__())
# Plot the distribution
# import matplotlib.pyplot as plt
# plt.hist(test_data, bins=100, alpha=0.6)
# plt.hist(std_normal_samples, bins=100, alpha=0.6)
# plt.legend(labels=['PowerTransformer', 'Standard Gaussian'], loc='best')
# plt.savefig('./fig/test_SKPowerTransformer.png')
# plt.close()
# plt.show()
# centerization check
new_mean, new_std = test_data.mean(), test_data.std()
mean_mse = new_mean**2
std_mse = (new_std - 1)**2
# print(mean_mse, std_mse)
self.assertAlmostEqual(mean_mse.__float__(), 0., delta=1e-5)
self.assertAlmostEqual(std_mse.__float__(), 0., delta=1e-5)
#
# print(main.metadata.to_internal_simple_structure())
# print(new_main.metadata.to_internal_simple_structure())
self.assertEqual(
utils.to_json_structure(
new_main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
7027,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
4,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name':
'd3mIndex',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name':
'timestamp',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name':
'value',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'name':
'ground_truth',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
}
])
params = primitive.get_params()
primitive.set_params(params=params)
def test_basic(self):
self.maxDiff = None
main = container.DataFrame(
{
'a': [1., 2., 3., 4., 5, 6, 7, 8, 9],
'b': [2., 3., 4., 5., 6, 7, 8, 9, 10],
'c': [3., 4., 5., 6., 7, 8, 9, 10, 11]
},
columns=['a', 'b', 'c'],
generate_metadata=True)
print(main)
self.assertEqual(
utils.to_json_structure(
main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
9,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'a'
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'b'
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'c'
}
}
])
self.assertIsInstance(main, container.DataFrame)
hyperparams_class = TelemanomPrimitive.metadata.get_hyperparams()
hyperparams = hyperparams_class.defaults()
hyperparams = hyperparams.replace({
'l_s': 2,
'n_predictions': 1,
'return_result': 'new',
'return_subseq_inds': True,
'use_columns': (0, 1, 2)
})
# print("hyperparams",hyperparams)
primitive = TelemanomPrimitive(hyperparams=hyperparams)
primitive.set_training_data(inputs=main)
primitive.fit()
new_main = primitive.produce_score(inputs=main).value
print("new main", new_main)
# print(utils.to_json_structure(new_main.metadata.to_internal_simple_structure()))
self.assertEqual(
utils.to_json_structure(
new_main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
6,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name':
'Telemanom0_0',
'structural_type':
'numpy.float64',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'structural_type':
'numpy.float64',
'name':
'Telemanom0_1',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'structural_type':
'numpy.float64',
'name':
'Telemanom0_2',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
}
}
])
def test_basic(self):
self.maxDiff = None
main = container.DataFrame(
{
'a1': [1., 2., 3.],
'b1': [2., 3., 4.],
'a2': [3., 4., 5.],
'c1': [4., 5., 6.],
'a3': [5., 6., 7.],
'a1a': [6., 7., 8.]
},
# {'top_level': 'main', },
columns=['a1', 'b1', 'a2', 'c1', 'a3', 'a1a'],
generate_metadata=True)
main.metadata = main.metadata.update_column(0, {'name': 'aaa111'})
main.metadata = main.metadata.update_column(1, {'name': 'bbb111'})
main.metadata = main.metadata.update_column(2, {'name': 'aaa222'})
main.metadata = main.metadata.update_column(3, {'name': 'ccc111'})
main.metadata = main.metadata.update_column(4, {'name': 'aaa333'})
main.metadata = main.metadata.update_column(5, {'name': 'aaa111'})
# print(main)
self.assertEqual(
utils.to_json_structure(
main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
6,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'aaa111'
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'bbb111'
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'aaa222'
},
},
{
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'ccc111'
},
},
{
'selector': ['__ALL_ELEMENTS__', 4],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'aaa333'
},
},
{
'selector': ['__ALL_ELEMENTS__', 5],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'aaa111'
},
}
])
hyperparams_class = SKStandardScaler.SKStandardScaler.metadata.get_hyperparams(
)
primitive = SKStandardScaler.SKStandardScaler(
hyperparams=hyperparams_class.defaults())
primitive.set_training_data(inputs=main)
primitive.fit()
new_main = primitive.produce(inputs=main).value
new_mean, new_std = new_main.values.mean(0), new_main.values.std(0)
mean_mse = np.matmul(new_mean.T, new_mean)
std_mse = np.matmul((new_std - np.ones_like(new_std)).T,
(new_std - np.ones_like(new_std)))
# print(new_main)
# print(mean_mse, std_mse)
self.assertAlmostEqual(mean_mse.__float__(), 0., delta=1e-8)
self.assertAlmostEqual(std_mse.__float__(), 0., delta=1e-8)
# print(main.metadata.to_internal_simple_structure())
# print(new_main.metadata.to_internal_simple_structure())
self.assertEqual(
utils.to_json_structure(
new_main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
6,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name':
'aaa111',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name':
'bbb111',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name':
'aaa222',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'name':
'ccc111',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 4],
'metadata': {
'name':
'aaa333',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 5],
'metadata': {
'name':
'aaa111',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
}
])
params = primitive.get_params()
primitive.set_params(params=params)
def test_combine_columns_new_with_index_noncompact_metadata(self):
main = container.DataFrame(
{
'd3mIndex': [1, 2, 3],
'b1': [4, 5, 6],
'c1': [7, 8, 9]
},
columns=['d3mIndex', 'b1', 'c1'],
generate_metadata=False)
main.metadata = main.metadata.generate(main, compact=False)
main.metadata = main.metadata.update_column(
0, {
'name':
'd3mIndex',
'semantic_types': [
'http://schema.org/Integer',
'https://metadata.datadrivendiscovery.org/types/PrimaryKey'
]
})
main.metadata = main.metadata.update_column(
1, {
'name':
'b1',
'semantic_types':
['https://metadata.datadrivendiscovery.org/types/Attribute']
})
main.metadata = main.metadata.update_column(
2, {
'name':
'c1',
'semantic_types':
['https://metadata.datadrivendiscovery.org/types/Attribute']
})
columns = container.DataFrame({
'd3mIndex': [1, 2, 3],
'b2': [4, 5, 6]
},
columns=['d3mIndex', 'b2'],
generate_metadata=False)
columns.metadata = columns.metadata.generate(columns, compact=False)
columns.metadata = columns.metadata.update_column(
0, {
'name':
'd3mIndex',
'semantic_types': [
'http://schema.org/Integer',
'https://metadata.datadrivendiscovery.org/types/PrimaryKey'
]
})
columns.metadata = columns.metadata.update_column(
1, {
'name':
'b2',
'semantic_types':
['https://metadata.datadrivendiscovery.org/types/Attribute']
})
result = utils.combine_columns(main, [], [columns],
return_result='new',
add_index_columns=True)
self.assertEqual(result.values.tolist(), [
[1, 4],
[2, 5],
[3, 6],
])
self.assertEqual(
d3m_utils.to_json_structure(
result.metadata.to_internal_simple_structure()),
[{
'selector': [],
'metadata': {
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types':
['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
2,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name':
'd3mIndex',
'semantic_types': [
'http://schema.org/Integer',
'https://metadata.datadrivendiscovery.org/types/PrimaryKey'
],
'structural_type':
'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name':
'b2',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.int64',
},
}])
def test_update_with_generated_metadata(self):
metadata = base.DataMetadata({
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': container.ndarray,
})
cells_metadata = collections.OrderedDict()
cells_metadata[('a',)] = {'other': 1}
cells_metadata[('b',)] = {'other': 2}
cells_metadata[('c',)] = {'other': 3}
cells_metadata[(base.ALL_ELEMENTS,)] = {'foo': 'bar'}
cells_metadata[('other', 'a')] = {'other': 4}
cells_metadata[('other', 'b')] = {'other': 5}
cells_metadata[('other', 'c')] = {'other': 6}
cells_metadata[('other', base.ALL_ELEMENTS)] = {'foo': 'bar2'}
metadata._update_with_generated_metadata(cells_metadata)
self.assertEqual(utils.to_json_structure(metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.numpy.ndarray',
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {'foo': 'bar'},
}, {
'selector': ['a'],
'metadata': {'other': 1},
}, {
'selector': ['b'],
'metadata': {'other': 2},
}, {
'selector': ['c'],
'metadata': {'other': 3},
}, {
'selector': ['other', '__ALL_ELEMENTS__'],
'metadata': {'foo': 'bar2'},
}, {
'selector': ['other', 'a'],
'metadata': {'other': 4},
}, {
'selector': ['other', 'b'],
'metadata': {'other': 5},
}, {
'selector': ['other', 'c'],
'metadata': {'other': 6},
}])
metadata = base.DataMetadata({
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': container.ndarray,
'semantic_types': ['http://example.com/Type1'],
'dimension': {
'length': 0,
'foobar': 42,
'semantic_types': ['http://example.com/Type2'],
}
})
metadata = metadata.update(('a',), {
'semantic_types': ['http://example.com/Type3'],
'dimension': {
'length': 0,
'foobar': 45,
'semantic_types': ['http://example.com/Type4'],
}
})
cells_metadata = collections.OrderedDict()
cells_metadata[()] = {
'other': 1,
'structural_type': container.ndarray,
'semantic_types': ['http://example.com/Type1a'],
'dimension': {
'length': 100,
'name': 'test1',
'semantic_types': ['http://example.com/Type2a'],
}
}
cells_metadata[('a',)] = {
'semantic_types': ['http://example.com/Type3', 'http://example.com/Type3a'],
'dimension': {
'length': 200,
'name': 'test2',
'semantic_types': ['http://example.com/Type4', 'http://example.com/Type4a'],
}
}
cells_metadata[('b',)] = {'other': 2}
metadata._update_with_generated_metadata(cells_metadata)
self.assertEqual(utils.to_json_structure(metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.numpy.ndarray',
'other': 1,
'semantic_types': ['http://example.com/Type1', 'http://example.com/Type1a'],
'dimension': {
'length': 100,
'name': 'test1',
'foobar': 42,
'semantic_types': ['http://example.com/Type2', 'http://example.com/Type2a'],
},
},
}, {
'selector': ['a'],
'metadata': {
'semantic_types': ['http://example.com/Type3', 'http://example.com/Type3a'],
'dimension': {
'length': 200,
'name': 'test2',
'foobar': 45,
'semantic_types': ['http://example.com/Type4', 'http://example.com/Type4a'],
},
},
}, {
'selector': ['b'],
'metadata': {'other': 2},
}])
self.assertEqual(metadata.to_json_structure(), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.numpy.ndarray',
'other': 1,
'semantic_types': ['http://example.com/Type1', 'http://example.com/Type1a'],
'dimension': {
'length': 100,
'name': 'test1',
'foobar': 42,
'semantic_types': ['http://example.com/Type2', 'http://example.com/Type2a'],
},
},
}, {
'selector': ['a'],
'metadata': {
'semantic_types': ['http://example.com/Type3', 'http://example.com/Type3a'],
'dimension': {
'length': 200,
'name': 'test2',
'foobar': 45,
'semantic_types': ['http://example.com/Type4', 'http://example.com/Type4a'],
},
},
}, {
'selector': ['b'],
'metadata': {'other': 2},
}])
def test_unset_structural_type(self):
dataframe = container.DataFrame({'a': ['a', 'b', 'c'], 'b': ['a', 'b', 'c']}, generate_metadata=False)
compact_metadata = dataframe.metadata.generate(dataframe, compact=True)
all_elements_metadata = compact_metadata.query((base.ALL_ELEMENTS, base.ALL_ELEMENTS))
compact_metadata = compact_metadata.remove((base.ALL_ELEMENTS, base.ALL_ELEMENTS), strict_all_elements=True)
compact_metadata = compact_metadata.update((base.ALL_ELEMENTS, 0), all_elements_metadata)
compact_metadata = compact_metadata.update((base.ALL_ELEMENTS, 1), all_elements_metadata)
compact_metadata = compact_metadata.generate(dataframe, compact=True)
self.assertEqual(utils.to_json_structure(compact_metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 2,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'str',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'a',
},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'b',
},
}])
compact_metadata = dataframe.metadata.generate(dataframe, compact=False)
all_elements_metadata = compact_metadata.query((base.ALL_ELEMENTS, base.ALL_ELEMENTS))
compact_metadata = compact_metadata.remove((base.ALL_ELEMENTS, base.ALL_ELEMENTS), strict_all_elements=True)
compact_metadata = compact_metadata.update((base.ALL_ELEMENTS, 0), all_elements_metadata)
compact_metadata = compact_metadata.update((base.ALL_ELEMENTS, 1), all_elements_metadata)
compact_metadata = compact_metadata.generate(dataframe, compact=False)
self.assertEqual(utils.to_json_structure(compact_metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 2,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'a',
'structural_type': 'str',
},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'b',
'structural_type': 'str',
},
}])
def test_dataset(self):
dataframe = container.DataFrame({'A': [1, 2, 3], 'B': ['a', 'b', 'c']})
dataframe.A = dataframe.A.astype(numpy.int64, copy=False)
dataset = container.Dataset({'0': dataframe}, generate_metadata=False)
compact_metadata = dataset.metadata.generate(dataset, compact=True)
noncompact_metadata = dataset.metadata.generate(dataset, compact=False)
self.assertEqual(utils.to_json_structure(compact_metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.dataset.Dataset',
'dimension': {
'name': 'resources',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/DatasetResource'],
'length': 1,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 2,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'A',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'B',
'structural_type': 'str',
},
}])
self.assertEqual(utils.to_json_structure(noncompact_metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.dataset.Dataset',
'dimension': {
'name': 'resources',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/DatasetResource'],
'length': 1,
},
},
}, {
'selector': ['0'],
'metadata': {
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 3,
},
},
}, {
'selector': ['0', '__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 2,
},
},
}, {
'selector': ['0', '__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'A',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['0', '__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'B',
'structural_type': 'str',
},
}])
def test_complex_value(self):
self.maxDiff = None
dataset = container.Dataset({
'0': container.DataFrame({
'A': [
container.ndarray(numpy.array(['a', 'b', 'c'])),
container.ndarray(numpy.array([1, 2, 3], dtype=numpy.int64)),
container.ndarray(numpy.array([1.0, 2.0, 3.0])),
],
'B': [
container.List(['a', 'b', 'c']),
container.List([1, 2, 3]),
container.List([1.0, 2.0, 3.0]),
],
}),
}, generate_metadata=False)
dataset_metadata = dataset.metadata.generate(dataset, compact=True)
self.assertEqual(utils.to_json_structure(dataset_metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.dataset.Dataset',
'dimension': {
'name': 'resources',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/DatasetResource'],
'length': 1,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 2,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'length': 3
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__', 0],
'metadata': {
'structural_type': 'd3m.container.numpy.ndarray',
'name': 'A',
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__', 1],
'metadata': {
'structural_type': 'd3m.container.list.List',
'name': 'B',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0, 0, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.str_',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0, 1, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'str',
},
}, {
'selector': ['__ALL_ELEMENTS__', 1, 0, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 1, 1, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'int',
},
}, {
'selector': ['__ALL_ELEMENTS__', 2, 0, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.float64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 2, 1, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'float',
}
}])
dataset_metadata = dataset.metadata.generate(dataset, compact=False)
self.assertEqual(utils.to_json_structure(dataset_metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'dimension': {
'length': 1,
'name': 'resources',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/DatasetResource'],
},
'schema': 'https://metadata.datadrivendiscovery.org/schemas/v0/container.json',
'structural_type': 'd3m.container.dataset.Dataset',
},
}, {
'selector': ['0'],
'metadata': {
'dimension': {
'length': 3,
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
},
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'structural_type': 'd3m.container.pandas.DataFrame',
},
},
{
'selector': ['0', '__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'length': 2,
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
},
},
},
{
'selector': ['0', '__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'A',
},
},
{
'selector': ['0', '__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'B',
},
},
{
'selector': ['0', 0, 0],
'metadata': {
'dimension': {
'length': 3,
},
'structural_type': 'd3m.container.numpy.ndarray',
},
},
{
'selector': ['0', 0, 0, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.str_'
},
},
{
'selector': ['0', 0, 1],
'metadata': {
'dimension': {
'length': 3,
},
'structural_type': 'd3m.container.list.List',
},
}, {
'selector': ['0', 0, 1, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'str',
},
}, {
'selector': ['0', 1, 0],
'metadata': {
'dimension': {
'length': 3,
},
'structural_type': 'd3m.container.numpy.ndarray',
},
}, {
'selector': ['0', 1, 0, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.int64',
},
}, {
'selector': ['0', 1, 1],
'metadata': {
'dimension': {
'length': 3,
},
'structural_type': 'd3m.container.list.List',
},
}, {
'selector': ['0', 1, 1, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'int',
},
}, {
'selector': ['0', 2, 0],
'metadata': {
'dimension': {
'length': 3,
},
'structural_type': 'd3m.container.numpy.ndarray',
},
}, {
'selector': ['0', 2, 0, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.float64',
},
},
{
'selector': ['0', 2, 1],
'metadata': {
'dimension': {
'length': 3,
},
'structural_type': 'd3m.container.list.List',
},
}, {
'selector': ['0', 2, 1, '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'float',
},
}])
def time_to_simple_structure_with_json(self, dataset_files):
utils.to_json_structure(
self.dataset_metadata.to_internal_simple_structure())
def test_basic(self):
self.maxDiff = None
curr_path = os.path.dirname(__file__)
dataset_fname = os.path.join(
curr_path,
'../../datasets/anomaly/kpi/TRAIN/dataset_TRAIN/tables/learningData.csv'
)
dataset = pd.read_csv(dataset_fname)
# print(dataset.columns)
value = dataset['value']
main = d3m_dataframe(value, generate_metadata=True)
################## Test Wavelet transform ##################
hyperparams_default = WaveletTransformer.metadata.get_hyperparams(
).defaults()
hyperparams = hyperparams_default.replace({
'wavelet': 'db8',
'level': 2,
'inverse': 0,
'return_result': 'new'
})
primitive = WaveletTransformer(hyperparams=hyperparams)
new_main = primitive.produce(inputs=main).value
# print(new_main)
# print(mean_mse, std_mse)
# self.assertAlmostEqual(mean_mse.__float__(), 0., delta=1e-8)
# self.assertAlmostEquael(std_mse.__float__(), 0., delta=1e-8)
# print(main.metadata.to_internal_simple_structure())
# print(new_main.metadata.to_internal_simple_structure())
self.assertEqual(
utils.to_json_structure(
new_main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3521,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name':
'value',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name':
'output_1',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name':
'output_2',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
}
])
################## Test inverse transform ##################
hyperparams = hyperparams_default.replace({'inverse': 1})
primitive = WaveletTransformer(hyperparams=hyperparams)
main_recover = primitive.produce(inputs=main).value
self.assertAlmostEqual(main_recover.values.tolist(),
main.values.tolist(),
delta=1e-6)
# print(main.metadata.to_internal_simple_structure())
# print(main_recover.metadata.to_internal_simple_structure())
self.assertEqual(
utils.to_json_structure(
main_recover.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
7027,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
1,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name':
'value',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'numpy.float64',
},
}
])
params = primitive.get_params()
primitive.set_params(params=params)
def test_basic(self):
self.maxDiff = None
main = container.DataFrame(
{
'a': [1., 2., 3.],
'b': [2., 3., 4.],
'c': [3., 4., 5.],
},
columns=['a', 'b', 'c'],
generate_metadata=True)
print(main)
self.assertEqual(
utils.to_json_structure(
main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'a'
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'b'
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'c'
}
}
])
self.assertIsInstance(main, container.DataFrame)
hyperparams_class = ABODPrimitive.metadata.get_hyperparams()
hyperparams = hyperparams_class.defaults()
hyperparams = hyperparams.replace({
'return_result': 'new',
'method': 'default',
})
primitive = ABODPrimitive(hyperparams=hyperparams)
primitive.set_training_data(inputs=main)
primitive.fit()
new_main = primitive.produce(inputs=main).value
new_main_score = primitive.produce_score(inputs=main).value
print(new_main)
print(new_main_score)
self.assertEqual(
utils.to_json_structure(
new_main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
1,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name':
'Angle-base Outlier Detection Primitive0_0',
'structural_type':
'numpy.int64',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
]
},
}
])
self.assertEqual(
utils.to_json_structure(
new_main_score.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
1,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name':
'Angle-base Outlier Detection Primitive0_0',
'structural_type':
'numpy.float64',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
]
},
}
])
def test_basic(self):
self.maxDiff = None
main = container.DataFrame({
'A': [1, 2],
'B': ['a', 'b']
},
columns=['A', 'B'],
generate_metadata=True)
self.assertEqual(
utils.to_json_structure(
main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
2,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
2,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'structural_type': 'numpy.int64',
'name': 'A',
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'structural_type': 'str',
'name': 'B',
},
}
])
self.assertIsInstance(main, container.DataFrame)
hyperparams_class = CategoricalToBinary.CategoricalToBinary.metadata.get_hyperparams(
)
hp = hyperparams_class.defaults().replace({
'use_semantic_types': True,
'use_columns': (0, ),
'return_result': 'append',
})
primitive = CategoricalToBinary.CategoricalToBinary(hyperparams=hp)
new_main = primitive.produce(inputs=main).value
c = pd.DataFrame({
"A": [1, 2],
"B": ['a', 'b'],
"A_1": ["1", "0"],
"A_2": ["0", "1"]
})
pd.testing.assert_frame_equal(new_main, c)
# print("new_main\n",new_main)
# print(utils.to_json_structure(new_main.metadata.to_internal_simple_structure()))
self.assertEqual(
utils.to_json_structure(
new_main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
2,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
4,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'A',
'structural_type': 'numpy.int64',
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'B',
'structural_type': 'str',
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name':
'A_1',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'str',
},
},
{
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'name':
'A_2',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Attribute'
],
'structural_type':
'str',
},
}
])
# print(new_main)
# print(test_utils.convert_through_json(new_main.metadata.query(())))
# print(test_utils.convert_through_json(new_main.metadata.query((metadata_base.ALL_ELEMENTS,))))
# print(mean_mse, std_mse)
# print("after testing")
# self.assertAlmostEqual(mean_mse.__float__(), 0., delta=1e-8)
# self.assertAlmostEqual(std_mse.__float__(), 0., delta=1e-8)
# print(main.metadata.to_internal_simple_structure())
# print(new_main.metadata.to_internal_simple_structure())
params = primitive.get_params()
primitive.set_params(params=params)
def test_basic(self):
self.maxDiff = None
main = container.DataFrame(
{
'a': [1., 2., 3., 4., 5., 6., 7., 8., 9.],
'b': [2., 3., 4., 5., 6., 7., 8., 9., 10.],
'c': [3., 4., 5., 6., 7., 8., 9., 10., 11.]
},
columns=['a', 'b', 'c'],
generate_metadata=True)
print(main)
self.assertEqual(
utils.to_json_structure(
main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
9,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'a'
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'b'
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'c'
}
}
])
self.assertIsInstance(main, container.DataFrame)
hyperparams_class = MatrixProfile.metadata.get_hyperparams()
hyperparams = hyperparams_class.defaults()
hyperparams = hyperparams.replace({'window_size': 3})
primitive = MatrixProfile(hyperparams=hyperparams)
#primitive.set_training_data(inputs=main)
#primitive.fit()
new_main = primitive.produce(inputs=main).value
print(new_main)
self.assertEqual(
utils.to_json_structure(
main.metadata.to_internal_simple_structure()),
[
{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/Table'
],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
9,
},
},
},
{
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
3,
},
},
},
{
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'a'
},
},
{
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'b'
},
},
{
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'structural_type': 'numpy.float64',
'name': 'c'
}
}
])
def test_dataframe_with_names_kept(self):
df = container.DataFrame({'A': [1, 2, 3], 'B': ['a', 'b', 'c']})
df.A = df.A.astype(numpy.int64)
df.metadata = df.metadata.generate(df)
df.metadata = df.metadata.update((base.ALL_ELEMENTS, 0), {
'name': 'first_column',
})
df.metadata = df.metadata.update((base.ALL_ELEMENTS, 1), {
'name': 'second_column',
})
self.assertEqual(utils.to_json_structure(df.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 2,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'first_column',
'structural_type': 'numpy.int64',
}
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'second_column',
'structural_type': 'str',
},
}])
df2 = container.DataFrame({'A': [1, 2, 3, 4], 'B': ['a', 'b', 'c', 'd']})
df2.metadata = df.metadata.generate(df2)
self.assertEqual(utils.to_json_structure(df2.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 4,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 2,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'first_column',
'structural_type': 'numpy.int64',
}
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'second_column',
'structural_type': 'str',
},
}])
def test_combine_columns_compact_metadata(self):
main = container.DataFrame(
{
'a1': [1, 2, 3],
'b1': [4, 5, 6],
'c1': [7, 8, 9],
'd1': [10, 11, 12],
'e1': [13, 14, 15]
}, {
'top_level': 'main',
},
generate_metadata=False)
main.metadata = main.metadata.generate(main, compact=True)
main.metadata = main.metadata.update_column(0, {'name': 'aaa111'})
main.metadata = main.metadata.update_column(1, {
'name': 'bbb111',
'extra': 'b_column'
})
main.metadata = main.metadata.update_column(2, {'name': 'ccc111'})
columns2 = container.DataFrame({
'a2': [21, 22, 23],
'b2': [24, 25, 26]
}, {
'top_level': 'columns2',
},
generate_metadata=False)
columns2.metadata = columns2.metadata.generate(columns2, compact=True)
columns2.metadata = columns2.metadata.update_column(
0, {'name': 'aaa222'})
columns2.metadata = columns2.metadata.update_column(
1, {'name': 'bbb222'})
columns3 = container.DataFrame({
'a3': [31, 32, 33],
'b3': [34, 35, 36]
}, {
'top_level': 'columns3',
},
generate_metadata=False)
columns3.metadata = columns3.metadata.generate(columns3, compact=True)
columns3.metadata = columns3.metadata.update_column(
0, {'name': 'aaa333'})
columns3.metadata = columns3.metadata.update_column(
1, {'name': 'bbb333'})
result = utils.combine_columns(main, [1, 2], [columns2, columns3],
return_result='append',
add_index_columns=False)
self.assertEqual(result.values.tolist(), [
[1, 4, 7, 10, 13, 21, 24, 31, 34],
[2, 5, 8, 11, 14, 22, 25, 32, 35],
[3, 6, 9, 12, 15, 23, 26, 33, 36],
])
self.assertEqual(
d3m_utils.to_json_structure(
result.metadata.to_internal_simple_structure()),
[{
'selector': [],
'metadata': {
'top_level':
'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types':
['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
9,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'aaa111',
},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'bbb111',
'extra': 'b_column',
},
}, {
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name': 'ccc111',
},
}, {
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'name': 'd1',
},
}, {
'selector': ['__ALL_ELEMENTS__', 4],
'metadata': {
'name': 'e1',
},
}, {
'selector': ['__ALL_ELEMENTS__', 5],
'metadata': {
'name': 'aaa222',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 6],
'metadata': {
'name': 'bbb222',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 7],
'metadata': {
'name': 'aaa333',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 8],
'metadata': {
'name': 'bbb333',
'structural_type': 'numpy.int64',
},
}])
result = utils.combine_columns(main, [1, 2], [columns2, columns3],
return_result='new',
add_index_columns=False)
self.assertEqual(result.values.tolist(), [
[21, 24, 31, 34],
[22, 25, 32, 35],
[23, 26, 33, 36],
])
self.assertEqual(
d3m_utils.to_json_structure(
result.metadata.to_internal_simple_structure()),
[{
'selector': [],
'metadata': {
'top_level':
'columns2',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types':
['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
4,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'aaa222',
},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'bbb222',
},
}, {
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name': 'aaa333',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'name': 'bbb333',
'structural_type': 'numpy.int64',
},
}])
result = utils.combine_columns(main, [1, 2], [columns2, columns3],
return_result='replace',
add_index_columns=False)
self.assertEqual(result.values.tolist(), [
[1, 21, 24, 31, 34, 10, 13],
[2, 22, 25, 32, 35, 11, 14],
[3, 23, 26, 33, 36, 12, 15],
])
self.assertEqual(
d3m_utils.to_json_structure(
result.metadata.to_internal_simple_structure()),
[{
'selector': [],
'metadata': {
'top_level':
'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types':
['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
7,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'aaa111',
},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'aaa222',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name': 'bbb222',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'name': 'aaa333',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 4],
'metadata': {
'name': 'bbb333',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 5],
'metadata': {
'name': 'd1',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 6],
'metadata': {
'name': 'e1',
'structural_type': 'numpy.int64',
},
}])
result = utils.combine_columns(main, [0, 1, 2, 3, 4],
[columns2, columns3],
return_result='replace',
add_index_columns=False)
self.assertEqual(result.values.tolist(), [
[21, 24, 31, 34],
[22, 25, 32, 35],
[23, 26, 33, 36],
])
self.assertEqual(
d3m_utils.to_json_structure(
result.metadata.to_internal_simple_structure()),
[{
'selector': [],
'metadata': {
'top_level':
'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types':
['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
4,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'aaa222',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'bbb222',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name': 'aaa333',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'name': 'bbb333',
'structural_type': 'numpy.int64',
},
}])
result = utils.combine_columns(main, [4], [columns2, columns3],
return_result='replace',
add_index_columns=False)
self.assertEqual(result.values.tolist(), [
[1, 4, 7, 10, 21, 24, 31, 34],
[2, 5, 8, 11, 22, 25, 32, 35],
[3, 6, 9, 12, 23, 26, 33, 36],
])
self.assertEqual(
d3m_utils.to_json_structure(
result.metadata.to_internal_simple_structure()),
[{
'selector': [],
'metadata': {
'top_level':
'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types':
['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
8,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'aaa111',
},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'bbb111',
'extra': 'b_column',
},
}, {
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name': 'ccc111',
},
}, {
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'name': 'd1',
},
}, {
'selector': ['__ALL_ELEMENTS__', 4],
'metadata': {
'structural_type': 'numpy.int64',
'name': 'aaa222',
},
}, {
'selector': ['__ALL_ELEMENTS__', 5],
'metadata': {
'structural_type': 'numpy.int64',
'name': 'bbb222',
},
}, {
'selector': ['__ALL_ELEMENTS__', 6],
'metadata': {
'structural_type': 'numpy.int64',
'name': 'aaa333',
},
}, {
'selector': ['__ALL_ELEMENTS__', 7],
'metadata': {
'structural_type': 'numpy.int64',
'name': 'bbb333',
},
}])
result = utils.combine_columns(main, [0, 2, 4], [columns2, columns3],
return_result='replace',
add_index_columns=False)
self.assertEqual(result.values.tolist(), [
[21, 4, 24, 10, 31, 34],
[22, 5, 25, 11, 32, 35],
[23, 6, 26, 12, 33, 36],
])
self.assertEqual(
d3m_utils.to_json_structure(
result.metadata.to_internal_simple_structure()),
[{
'selector': [],
'metadata': {
'top_level':
'main',
'schema':
metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type':
'd3m.container.pandas.DataFrame',
'semantic_types':
['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name':
'rows',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularRow'
],
'length':
3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name':
'columns',
'semantic_types': [
'https://metadata.datadrivendiscovery.org/types/TabularColumn'
],
'length':
6,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'aaa222',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {
'name': 'bbb111',
'extra': 'b_column',
},
}, {
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {
'name': 'bbb222',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {
'name': 'd1',
},
}, {
'selector': ['__ALL_ELEMENTS__', 4],
'metadata': {
'name': 'aaa333',
'structural_type': 'numpy.int64',
},
}, {
'selector': ['__ALL_ELEMENTS__', 5],
'metadata': {
'name': 'bbb333',
'structural_type': 'numpy.int64',
},
}])
def test_custom_column_name_with_compacting(self):
dataframe = container.DataFrame({'a': ['1.0', '2.0', '3.0']}, generate_metadata=False)
dataframe.metadata = dataframe.metadata.generate(dataframe, compact=True)
dataframe.metadata = dataframe.metadata.update((base.ALL_ELEMENTS, 0), {
'name': 'test',
'foo': 'bar',
})
self.assertEqual(utils.to_json_structure(dataframe.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 1,
}
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'str',
'name': 'a',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'test',
'foo': 'bar',
},
}])
dataframe.metadata = dataframe.metadata.generate(dataframe, compact=True)
self.assertEqual(utils.to_json_structure(dataframe.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 1,
}
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'str',
'name': 'a',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': 'test',
'foo': 'bar',
},
}])
dataframe.metadata = dataframe.metadata.update((base.ALL_ELEMENTS, 0), {
'name': base.NO_VALUE,
})
dataframe.metadata = dataframe.metadata.generate(dataframe, compact=True)
self.assertEqual(utils.to_json_structure(dataframe.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
'schema': base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 3,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 1,
}
},
}, {
'selector': ['__ALL_ELEMENTS__', '__ALL_ELEMENTS__'],
'metadata': {
'structural_type': 'str',
'name': 'a',
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {
'name': '__NO_VALUE__',
'foo': 'bar',
},
}])
