def _infer_restriction(project_id, _, module_params):
'''
Runs the training data and infers possible restrictions that can be made
on the referential.
ARGUMENTS (GET):
project_id: ID for "link" project
ARGUMENTS (POST):
- data_params: none
- module_params: {#TODO: fill with params from restrict}
'''
if module_params is None:
module_params = dict()
proj = ESLinker(project_id=project_id)
training = proj.read_config_data('dedupe_linker', 'training.json')
if not training:
raise Exception('No training file was found in this project')
module_params['training'] = training
result = proj.infer('infer_restriction', module_params)
# Write log
proj._write_log_buffer(False)
return result
def _link_results_analyzer(project_id, data_params, module_params):
'''
Runs the link results analyzer module
wrapper around ESNormalizer.infer ?
ARGUMENTS (GET):
project_id: ID for "normalize" project
ARGUMENTS (POST):
- data_params: {
"module_name": module to fetch from
"file_name": file to fetch
}
- (module_params): {
"col_matches": dict like {"source": col_source, "ref": col_ref}
A pair of columns that can be used a joining key:
"lower": bool (defaults to False)
Whether or not the values of the joining should be lowercased
before joining
}
'''
if module_params is None:
module_params = dict()
proj = ESLinker(project_id=project_id)
proj.load_data(data_params['module_name'], data_params['file_name'])
result = proj.analyze_results(module_params)
# Write log
proj._write_log_buffer(False)
return result
def _link_results_analyzer(project_id, data_params, *argv):
'''
Runs the link results analyzer module
wrapper around ESNormalizer.infer ?
ARGUMENTS (GET):
project_id: ID for "normalize" project
ARGUMENTS (POST):
- data_params: {
"module_name": module to fetch from
"file_name": file to fetch
}
'''
proj = ESLinker(project_id=project_id)
proj.load_data(data_params['module_name'], data_params['file_name'])
result = proj.infer('link_results_analyzer', {})
# Write log
proj._write_log_buffer(False)
return result