def match_jobsr(self, resumeModel, jobColl):
jobscore = {}
for jobModelDict in jobColl.find():
jid = str(jobModelDict["_id"])
# print "jid=", jid
jobModel = JobModel(jid)
jobModel.deserialize(jobModelDict)
score = random.randint(1, 90)
# print jid , "--->" ,score
jobscore[jid] = score
jobscore = sorted(jobscore.items(), key=operator.itemgetter(1), reverse= True)
return jobscore
def match_jobsr(self, resumeModel, jobColl):
jobscore = {}
for jobModelDict in jobColl.find():
jid = str(jobModelDict["_id"])
# print "jid=", jid
jobModel = JobModel(jid)
jobModel.deserialize(jobModelDict)
score = random.randint(1, 90)
# print jid , "--->" ,score
jobscore[jid] = score
jobscore = sorted(jobscore.items(),
key=operator.itemgetter(1),
reverse=True)
return jobscore
def match_jobModels(self, resumeModel, jobModels):
jobscore = {}
for jobModelDict in jobModels:
jid = str(jobModelDict["_id"])
# print "jid=", jid
jobModel = JobModel(jid)
jobModel.deserialize(jobModelDict)
score = int (self.getSimilarity( resumeModel, jobModel )*100)
# print jid , "--->" ,score
if score > 0 :
jobscore[jid] = score
jobscore = sorted(jobscore.items(), key=operator.itemgetter(1), reverse= True)
return jobscore
def match_jobModels(self, resumeModel, jobModels):
jobscore = {}
for jobModelDict in jobModels:
jid = str(jobModelDict["_id"])
# print "jid=", jid
jobModel = JobModel(jid)
jobModel.deserialize(jobModelDict)
score = int(self.getSimilarity(resumeModel, jobModel) * 100)
# print jid , "--->" ,score
if score > 0:
jobscore[jid] = score
jobscore = sorted(jobscore.items(),
key=operator.itemgetter(1),
reverse=True)
return jobscore
def processjobs(dbname, collname):
srcBbClient = DbClient('localhost', 27017, dbname)
jobCollName = collname
jobmodelCollName = jobCollName+"_model"
collection = srcBbClient.getCollection(jobCollName)
modelColl = srcBbClient.getCollection(jobmodelCollName)
# newCol = srcBbClient.getCollection("daily_job_info_2014-06-16")
removeHtml(collection)
copyTitle(collection)
for job in collection.find():
sents = preprocess(job)
jobModel = JobModel(job["_id"])
processSents(jobModel, sents )
titleModel = processTitle(job)
jobModel.titleModel = titleModel
jobclassifier.classifyJob(jobModel)
modelColl.save(jobModel.serialize())
import os, sys
sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", ".."))
import modelsimilarity
from jobaly.db.dbclient import DbClient
from model.jobmodel import JobModel
from model.resumemodel import ResumeModel
from modelsimilarity import ModelSimilarity
resumeModel1 = ResumeModel("r001")
resumeModel1.addDegrees(["BS_LEVEL"])
resumeModel1.addMajors(["MAJOR_INFO"])
resumeModel1.addSkills([ "CSS", "J2EE"])
jobModel1 = JobModel("j001")
jobModel1.addDegrees(["BS_LEVEL", "MS_LEVEL" ])
jobModel1.addMajors(["MAJOR_CE", "MAJOR_RELATED"])
jobModel1.addSkills([ "HTML", "Java"])
def test_tranferDegree():
degrees = set(["AS_LEVEL", "BS_LEVEL", "MS_LEVEL", "GRAD_LEVEL"])
degreeNum = modelsimilarity.tranferDegree(degrees)
for num in degreeNum:
print num
def test_similarity():
similarity = ModelSimilarity()
result = similarity.getSimilarity(resumeModel1 , jobModel1 )
print "result=", result
def markByTitle(self, resumeModel, jobColl):
titleModel = resumeModel.titleModels[0]
jobmodels = []
pro_lang = None
domain = None
level = None
role = None
if titleModel.has_key("pro_lang"):
pro_lang = titleModel["pro_lang"]
if titleModel.has_key("domain"):
domain = titleModel["domain"]
if titleModel.has_key("level"):
level = titleModel["level"]
if titleModel.has_key("role"):
role = titleModel["role"]
for jobModelDict in jobColl.find():
jid = str(jobModelDict["_id"])
# print "jid=", jid
jobModel = JobModel(jid)
jobModel.deserialize(jobModelDict)
jobSummary = jobModel.summary
jobmodels.append(jobModel)
if pro_lang is not None and \
jobSummary.has_key("pro_lang") and \
jobSummary["pro_lang"] == pro_lang :
jobModel.same_pro_lang = True
else:
jobModel.same_pro_lang = False
if level is not None and \
jobSummary.has_key("level") and \
jobSummary["level"] == pro_lang :
jobModel.same_level = True
else:
jobModel.same_level = False
if domain is not None and \
jobSummary.has_key("domain") and \
jobSummary["domain"] == domain :
jobModel.same_domain = True
else:
jobModel.same_domain = False
if role is not None and \
jobSummary.has_key("role") and \
jobSummary["role"] == role :
jobModel.same_role = True
else:
jobModel.same_role = False
return jobmodels
def markByTitle(self, resumeModel, jobColl):
titleModel = resumeModel.titleModels[0]
jobmodels = []
pro_lang = None
domain = None
level = None
role = None
if titleModel.has_key("pro_lang") :
pro_lang = titleModel["pro_lang"]
if titleModel.has_key("domain") :
domain = titleModel["domain"]
if titleModel.has_key("level") :
level = titleModel["level"]
if titleModel.has_key("role") :
role = titleModel["role"]
for jobModelDict in jobColl.find():
jid = str(jobModelDict["_id"])
# print "jid=", jid
jobModel = JobModel(jid)
jobModel.deserialize(jobModelDict)
jobSummary = jobModel.summary
jobmodels.append(jobModel)
if pro_lang is not None and \
jobSummary.has_key("pro_lang") and \
jobSummary["pro_lang"] == pro_lang :
jobModel.same_pro_lang = True
else :
jobModel.same_pro_lang = False
if level is not None and \
jobSummary.has_key("level") and \
jobSummary["level"] == pro_lang :
jobModel.same_level = True
else :
jobModel.same_level = False
if domain is not None and \
jobSummary.has_key("domain") and \
jobSummary["domain"] == domain :
jobModel.same_domain = True
else :
jobModel.same_domain = False
if role is not None and \
jobSummary.has_key("role") and \
jobSummary["role"] == role :
jobModel.same_role = True
else :
jobModel.same_role = False
return jobmodels