def search(url: str,
query: dict,
data: pd.DataFrame or str or d3m_ds.Dataset=None,
send_data=True,
max_return_docs: int=20,
return_named_entity: bool=False) -> typing.List[Dataset]:
"""
Follow the API defined by https://datadrivendiscovery.org/wiki/display/work/Python+API
Args:
url: str - the datamart server(for ISI's datamart it is meaningless, just a flag)
query: JSON object describing the query(https://datadrivendiscovery.org/wiki/display/work/Query+results+schema)
data: the data you are trying to augment. It can be provided as one of:
- a pandas.DataFrame object
- a D3M Dataset object
- the path to a D3M datasetDoc.json file
- the path to a CSV file
send_data: (for ISI's datamart it is meaningless)
Returns: a list of datamart.Dataset objects
"""
if not url.startswith(SEARCH_URL):
return []
loaded_data = DataLoader.load_data(data)
augmenter = Augment(es_index=PRODUCTION_ES_INDEX)
es_results = []
if (query and ('required_variables' in query)) or (loaded_data is None):
# if ("required_variables" exists or no data):
es_results = augmenter.query_by_json(query, loaded_data,
size=max_return_docs,
return_named_entity=return_named_entity) or []
else:
# if there is no "required_variables" in the query JSON, but the dataset exists,
# try each named entity column as "required_variables" and concat the results:
query = query or {}
exist = set()
for col in loaded_data:
if Utils.is_column_able_to_query(loaded_data[col]):
query['required_variables'] = [{
"type": "dataframe_columns",
"names": [col]
}]
cur_results = augmenter.query_by_json(query, loaded_data,
size=max_return_docs,
return_named_entity=return_named_entity)
if not cur_results:
continue
for res in cur_results:
if res['_id'] not in exist:
# TODO: how about the score ??
exist.add(res['_id'])
es_results.append(res)
return [Dataset(es_result, original_data=loaded_data, query_json=query) for es_result in es_results]
def search(
query: dict,
data: pd.DataFrame or str
or d3m_ds.Dataset = None) -> typing.List[Dataset]:
"""
Follow the API defined by https://datadrivendiscovery.org/wiki/display/work/Python+API
Args:
query: JSON object describing the query(https://datadrivendiscovery.org/wiki/display/work/Query+results+schema)
data: the data you are trying to augment. It can be provided as one of:
- a pandas.DataFrame object
- a D3M Dataset object
- the path to a D3M datasetDoc.json file
- the path to a CSV file
Returns: a list of datamart.Dataset objects.
"""
loaded_data = DataLoader.load_data(data)
augmenter = Augment(es_index=DEFAULT_ES)
if not (query and
('required_variables' in query)) and (loaded_data is not None):
query = query or {}
query['required_variables'] = []
for col in loaded_data:
if Utils.is_column_able_to_query(loaded_data[col]):
query['required_variables'].append({
"type": "dataframe_columns",
"names": [col]
})
es_results = augmenter.query_by_json(query, loaded_data)
if es_results:
return [
Dataset(es_result, original_data=loaded_data, query_json=query)
for es_result in es_results
]
return []