def _update_metadata(metadata: DataMetadata,
resource_id: SelectorSegment) -> DataMetadata:
resource_metadata = dict(metadata.query((resource_id, )))
if 'structural_type' not in resource_metadata or not issubclass(
resource_metadata['structural_type'], container.DataFrame):
raise TypeError(
"The Dataset resource is not a DataFrame, but \"{type}\".".format(
type=resource_metadata.get('structural_type', None), ))
resource_metadata.update({
'schema': CONTAINER_SCHEMA_VERSION,
}, )
new_metadata = DataMetadata(resource_metadata)
new_metadata = metadata.copy_to(new_metadata, (resource_id, ))
# Resource is not anymore an entry point.
new_metadata = new_metadata.remove_semantic_type(
(), 'https://metadata.datadrivendiscovery.org/types/DatasetEntryPoint')
return new_metadata
jsonCall = json.load(inputFile)
inputFile.close()
# Load the problem description schema
with open( path.join(jsonCall['train_data'], 'problem_TRAIN', 'problemDoc.json' ) , 'r') as inputFile:
problemSchema = json.load(inputFile)
inputFile.close()
# Load the json dataset description file
with open( path.join(jsonCall['train_data'], 'dataset_TRAIN', 'datasetDoc.json' ) , 'r') as inputFile:
datasetSchema = json.load(inputFile)
inputFile.close()
# Load dataset
ds_uri = 'file://' + path.join(jsonCall['train_data'], 'dataset_TRAIN', 'datasetDoc.json')
ds = container.Dataset(resources=dict(), metadata=DataMetadata())
ds = ds.load(ds_uri)
# Profile dataset
param = Hyperparams.sample()
prof = Profiler(hyperparams=param)
ds2 = prof.produce(inputs=ds)
# Get resource Ids, return ['0'] for this dataset
print(ds.metadata.get_elements( () ))
# Get available columns, returns [0, 1, 2, ..., 30] for 38_sick dataset
print(ds.metadata.get_elements(('0', ALL_ELEMENTS)))
# Metadata for column 1
column_one_metadata = ds.metadata.query(('0', ALL_ELEMENTS, 1))