def download_data():
load_config = ct_load_config.get_load_config()
source_files_directory = load_config.source_files_directory()
csv_downloader = CSVDownloader(source_files_directory)
for ct_table in CT_TABLES:
csv_downloader.download(ct_table)
def verify():
load_config = ct_load_config.get_load_config()
for data_source in DATA_SOURCES:
# print 'Verifying', data_source
stats = load_stats(load_config, data_source)
total_ids = 0
if 'total_ids' in stats:
total_ids = stats['total_ids']
url = load_config.server + '/' + load_config.index + '/' + load_config.type + '/_search?size=0'
data = {
"query":{
"exists":{
"field":data_source
}
}
}
response = requests.post(url, json=data)
# print response
if response.status_code == 200:
response_data = json.loads(response.text)
if 'hits' in response_data:
hits = response_data['hits']
if 'total' in hits:
total = hits['total']
complete = ''
if total != total_ids:
complete = 'Incomplete'
print data_source, 'es_count:', total, 'stats_count:', total_ids, '[', complete, ']'
else:
print response.text
def process_relationships(data_source_name):
print 'processing', data_source_name
load_config = ct_load_config.get_load_config()
load_config.data_source_name = data_source_name
# Relationships
load_config.append_relations = False
load_config.source = data_source_name
source_files_directory = load_config.source_files_directory()
data_source_file_path = source_files_directory + '/' + data_source_name + '.csv'
data_processor = CTRelationshipProcessor(load_config, CSVDataSource(data_source_file_path))
# data_processor.mode = DataProcessor.MODE_RETRY_FAILED_DOCS
data_processor.run()
def process_file(data_source_name):
print 'processing', data_source_name
load_config = ct_load_config.get_load_config()
load_config.data_source_name = data_source_name
source_files_directory = load_config.source_files_directory()
data_source_file_path = source_files_directory + '/' + data_source_name + '.csv'
print 'Processing file', data_source_file_path
# data_processor = DataProcessor(load_config, CSVDataSource(data_source_file_path))
# data_processor.mode = DataProcessor.MODE_RETRY_FAILED_DOCS
# data_processor.process_rows()
data_processor = DataSourceProcessor(load_config, CSVDataSource(data_source_file_path))
data_processor.run()
def run():
server = SERVER
load_config = ct_load_config.get_load_config()
other_files_directory = load_config.other_files_directory()
ct_v2_ids = export_doc_ids.get_doc_ids(SERVER, 'clinical_trials_v2',
'study', other_files_directory,
'ct_v2_ids.json')
ct_v1_ids = export_doc_ids.get_doc_ids(SERVER, 'clinical_trials', 'study',
other_files_directory,
'ct_v1_ids.json')
common_ids = {}
for _id in ct_v2_ids:
if _id in ct_v1_ids:
common_ids[_id] = 0
print 'ct_v1_ids', len(ct_v1_ids)
print 'ct_v2_ids', len(ct_v2_ids)
print 'common_ids', len(common_ids)
def run():
load_config = ct_load_config.get_load_config()
generated_files_dir = load_config.generated_files_directory()
for data_source in data_sources:
unique_ids = 0
try:
data_source_dir = generated_files_dir + '/' + data_source
stats_file = data_source + '_stats.json'
stats = file_utils.load_file(data_source_dir, stats_file)
unique_ids = stats['unique_ids']
except Exception as e:
pass
# print 'verifing', data_source
url = 'http://localhost:9200/clinical_trials/study/_search?size=0'
data = {
"query": {
"exists": {
"field": data_source
}
}
}
response = requests.post(url, json=data)
if response.status_code == 200 or response.status_code == 201:
response_obj = json.loads(response.text)
total = response_obj['hits']['total']
percent_completion = 0
if unique_ids > 0:
percent_completion = (total / float(unique_ids)) * 100
print data_source, '- [', total, '/', unique_ids, '] -', percent_completion, '%'
print '----------------------------------------------------------------------------------'
else:
print response.text
def save_processed_data_sources(processed_data_sources):
load_config = ct_load_config.get_load_config()
other_files_directory = load_config.other_files_directory()
file_utils.save_file(other_files_directory, 'processed_data_sources.json', processed_data_sources)
def get_processed_data_sources():
load_config = ct_load_config.get_load_config()
other_files_directory = load_config.other_files_directory()
processed_data_sources = file_utils.load_file(other_files_directory, 'processed_data_sources.json')
return processed_data_sources
