def process(specific_info, data, *args): inputs = get_inputs(data, specific_info) tfidf_worker_id = inputs.get('tfidf_worker_id') queue = inputs.get('__read_from_queue') connection = args[0].get('connection') all_words = {} all_data = [] #for bioportal if queue: queue_values = connection.zrange(queue, 0, -1) for queue_raw_data in queue_values: queue_data = json_loads(queue_raw_data) all_data.append(queue_data) #for bioportal tfidf = select_dict_el(queue_data, 'workers_output.%s.tfidf' % tfidf_worker_id) for word, value in tfidf: if not all_words.get(word): all_words[word] = [] all_words[word].append(value) max_apperance = max([len(values) for (word, values) in all_words.iteritems()])/5 tfidf_results = [(word, 1.0*sum(values)/len(values)*0.65 + 0.35*min(len(values)/max_apperance, 1)) for (word, values) in all_words.iteritems()] tfidf_results.sort(key=lambda tup: -tup[1]) # Bioportal bioportal_worker_id = inputs.get('bioportal_worker_id') bioportal_mesh_names_url = inputs.get('bioporta_mesh_names_url') mesh_names = json_loads(requests.get(bioportal_mesh_names_url).content) bioportal_merged = {} for queue_data in all_data: bioportal_annotated = select_dict_el(queue_data, 'workers_output.%s.bioportal_annotated' % bioportal_worker_id) for mesh_data in bioportal_annotated.get('data'): ontology_id = mesh_data.get('ontology_quote_id') if not bioportal_merged.get(ontology_id): if not mesh_names.get(ontology_id): continue bioportal_merged[ontology_id] = { 'ontology_quote_id': ontology_id, 'matched_terms': [], 'total_frequency': 0, 'included_in_documents': 0, 'name': mesh_names.get(ontology_id) } bioportal_merged[ontology_id]['total_frequency'] += mesh_data.get('frequency') bioportal_merged[ontology_id]['included_in_documents'] += 1 bioportal_merged[ontology_id]['matched_terms'] = list(set(mesh_data.get('matched_terms')+bioportal_merged[ontology_id]['matched_terms'])) to_return_bioportal = sorted( bioportal_merged.values(), key=lambda k: k['included_in_documents'], reverse=True ) return [{'group_tfidf': tfidf_results, 'bioportal_merged': to_return_bioportal},]
def process(specific_info, data, *args): inputs = get_inputs(data, specific_info) mongo_connection = args[0].get('mongo_connection') data_filter = inputs.get('data_filter', {}) fields = inputs.get('fields', []) names = inputs.get('names', []) collection = inputs.get('collection', []) target_file = inputs.get('target_file') data_selector = dict([(field, 1) for field in fields]) matrix_id = inputs.get('matrix_id') if matrix_id: matrix_documents = set() matrix = mongo_connection.matrix.find_one({'_id': ObjectId(inputs.get('matrix_id'))}) matrix_documents |= set([ matrix_el.get('id') for matrix_el in select_dict_el(matrix, 'matrix_dict.matrix', []) ]) matrix_documents |= set([ matrix_el.get('id') for matrix_el in select_dict_el(matrix, 'matrix_dict.studies_order', []) ]) data_filter.update({"id": {"$in": list(matrix_documents)}}) if target_file: target_file = open(target_file, 'w') target_file.write("\t".join(names)+"\n") for episte_data in mongo_connection[collection].find(data_filter, data_selector): if target_file: text = u"\t".join([ to_unicode( select_dict_el(episte_data, field) or '' ).replace('\r\n', ' ').replace('\n', '').replace('\t', ' ') for field in fields ]).encode('utf-8') target_file.write(text+"\n") else: yield dict( [ (names[i], (select_dict_el(episte_data, field) or '')) for i, field in enumerate(fields) ] ) if target_file: yield {'episte_data_target_file': inputs.get('target_file')}