print(str(candidatetotal))
#print(candidateIdList)
log_file = open("resumeParser.log", "a")
etl_job_log = {}
temp = []
charcteristics_list = getCharacteristicMap()
for i in range(0,candidatetotal):
candidateResumeSkills = list(db.candidate_resume_text.find({"candidate_id":candidateIdList[i]}))
print(str(candidateIdList[i]))
#print(str(candidateResumeSkills))
print("Parsing")
temp = candResumeParser(candidateResumeSkills)
print("Classifier")
candidate_classifier_incre(candidateIdList[i],charcteristics_list)
print("Scoring")
rzindex_candidate(candidateIdList[i])
#print("---Total Time: %s seconds ---" % (time.time() - start_time))
etl_job_log["job_name"] = JOB_NAME
etl_job_log["start_datetime"] = beginTime
etl_job_log["end_datetime"] = datetime.utcnow()
etl_job_log["elapsed_time_in_seconds"] = time.time() - start_time
etl_job_log["total_records_processed"] = candidatetotal
db.etl_job_log.insert_one(etl_job_log)
log_file.write(str(etl_job_log))
except Exception as e:
DebugException(e)
log_file.write("Exception during resume parsing: [" + str(e) + "]")
log_file.close()
def main():
print("GO")
start_time = time.time()
document_map = {}
category_map = db["category_candidate_map"]
try:
cand_table = db["candidate"]
characteristic_list = getCharacteristicMap()
print("[candidateClassifierJob] ---query Time: %s seconds ---" % (time.time() - start_time))
skip_amount = 0
cand_count = 0
total_cand = cand_table.find(
{"$or": [{"loaded_date": {"$gt": lastRunDate}}, {"update_date": {"$gt": lastRunDate}}]}).count()
# print("[candidateClassifierJob] [TotalCandidates] %s" % total_cand)
start_delta = 0
query_dict = {
"$and": [
{"job_skill_names.0": {"$exists": True}},
{"$or": [
{"loaded_date": {"$gt": lastRunDate}},
{"update_date": {"$gt": lastRunDate}}
]},
]
}
proj_dict = {"candidate_id": 1, "job_skill_names": 1}
# candidate_list = list(
# cand_table.find(query_dict, proj_dict).skip(start_delta + skip_amount).limit(fetch_limit))
candidate_list = cand_table.find(query_dict, proj_dict) # .distinct("candidate_id")
candlist = []
for candidate in candidate_list:
candlist.append(candidate["candidate_id"])
match_count = 0
if len(candidate["job_skill_names"]) > 0:
cand_count += 1
cand_job_skill_name_list = []
for can_job_skill in candidate["job_skill_names"]:
cand_job_skill_name_list.append(can_job_skill["job_skill_name"].lower())
for job_cat_id, skill in characteristic_list.items():
# print("main : Running candidate [" + str(candidate["candidate_id"]) + "] reqSkillCount[" +
# str(len(skill["Skills"])) + "] vs candSkillsCount [" + str(len(cand_job_skill_name_list)) +"]")
if matchSkills(cand_job_skill_name_list, skill["Skills"], .40):
# print("main : <<<MACTHED>> IdealCharac Section JobCatId[{0}] candidate_id [{1}".format(
# str(job_cat_id), str(candidate["candidate_id"])))
match_count += 1
if document_map.get(job_cat_id) is None:
document_map[job_cat_id] = []
if candidate["candidate_id"] not in document_map[job_cat_id]:
document_map[job_cat_id].append(candidate["candidate_id"])
# print("main : job_cat_id [" + str(job_cat_id) + "] candidate_id [" + str(
# candidate["candidate_id"]) + "]")
# print("Candidate_id [" + str(candidate["candidate_id"]) + " matched catids [" + str(match_count) + "]")
# print("%s" % json.dumps(document_map, default=obj_dict))
# Execute the update
for cat_id, val in document_map.items():
category_map.update({"global_job_category_id": cat_id}, {"$push": {"candidates": {"$each": val}}})
print(candlist)
for cand in candlist:
print(cand)
rzindex_candidate(cand)
# print("---Parse Time: %s seconds ---" % (time.time() - start_time))
etl_job_log["job_name"] = JOB_NAME
etl_job_log["start_datetime"] = beginTime
etl_job_log["end_datetime"] = datetime.now()
etl_job_log["elapsed_time_in_seconds"] = time.time() - start_time
etl_job_log["total_records_processed"] = cand_count
db.etl_job_log.insert_one(etl_job_log)
# log_file.write(str(etl_job_log))
timeNow = datetime.utcnow().isoformat()
print("[" + timeNow + "] [candidateClassifierJob] ---Run Time: [" + str(
time.time() - start_time) + "] seconds ---")
except Exception as e:
DebugException(e)
print("[candidateClassifierJob] ---Run Time: %s seconds ---" % (time.time() - start_time))
print("Job : [candidate_classifier] failed due to error [" + str(e) + "]")
