def __init__(self, DocPath=None, text=None): if text is None: self.DocPath = DocPath self.DocText = DocReader.Reader(self.DocPath) tfres = WordCount.get_term_one_list(WordCount.map(self.DocText)) self.DocTermList = tfres self.ParseResume() else: self.DocText = text self.DocTermList = WordCount.get_term_one_list(WordCount.map(self.DocText)) print(self.DocTermList) self.ParseText() self.ParseResume()
def __init__(self, DocPath=None, text=None):
if text is None:
self.DocPath = DocPath
self.DocText = DocReader.Reader(self.DocPath)
tfres = WordCount.get_term_one_list(WordCount.map(self.DocText))
self.DocTermList = tfres
self.ParseResume()
else:
self.DocText = text
self.DocTermList = WordCount.get_term_one_list(
WordCount.map(self.DocText))
print(self.DocTermList)
self.ParseText()
self.ParseResume()
def getSpecializationUserListByText(self): #сопоставляет специализацию и ЛЮБОЙ ТЕКСТ i = 0 self.specializationIdList = [] specdict = self.ProceedSpecList(self.SpecializationDict) tfrestmp = WordCount.get_term_one_list(WordCount.map(self.tmptext))[0] # langs = self.documents.DocProgLangs self.progLangs = self.documents.DocProgLangs for val in tfrestmp: #self.progLangs |= Document.GetProgLangsFromText(val[0]) res = self.getSpecialization(specdict, val[0]) if res is not None: i += 1 self.specializationIdList.append(res) if i > 100: break self.GetImportantSpecializations(self.specializationIdList)
def user(request, _id):
template = loader.get_template('suggesting_system/user.html')
FindedUser = User.objects.get(id = _id)
t1 = time.time()
hhapi = hhAPI(FindedUser)
info = hhapi.CreateQuery(GitHubAPI.GetLanguages(FindedUser.gitHub))
textList = []
doctitleList = []
for vac in info:
textList.append(vac.description)
doctitleList.append(vac.vacancy_Id)
# print(vac.description + ' ' + vac.name)
allDict = hhapi.docdict
i = 0
BIGTextData = ''
for i in range(len(textList)):
BIGTextData += textList[i]
allDict.update(dict(zip([doctitleList[i]], [textList[i]])))
i += 1
# print(allDict)
vacancyTerms = WordCount.get_term_one_list(WordCount.map(BIGTextData))
print("vacancy terms = ")
print(vacancyTerms[1])
print("hhDATA = ")
print(hhapi.documents.DocTermList[1])
print("terms = ")
test = dict(list(hhapi.documents.DocTermList[1].items()) + list(vacancyTerms[1].items()))
print("test = ")
print (test)
documentWords, documentTitles, allwords = NMF.ConvertData(allDict, test)
print("doc worlds = ")
print(documentWords)
tmp = NMF.CreateMatrix(allwords, documentWords)
# print(tmp[0])
# print(tmp[1])
test = NMF.calculate(tmp[0])
print(documentTitles)
WeightMatrix = test[0]
HeightMatrix = test[1]
topp, pn, res = NMF.prepareToVis(WeightMatrix, HeightMatrix, documentTitles, tmp[1])
print("fin res" + str(res))
finalres = []
a = "ssss"
for val in res:
try:
idVac = int(val[1])
except:
idVac = 0
print("idvac = " + str(idVac))
print(val[0])
if idVac != 0 and int(val[0]) > 3:
print("appending...")
finalres.append(VacancyCache.objects.filter(vacancy_Id=idVac)[0])
info = finalres
# print(topp['kinect'])
#info = Competition("test", ["course1", "course2"], ["c", "c++"], ["soft1", "soft2", "soft3"], None)
#info = Document(FindedUser.resumeField._get_path())
#tmp = EduStandartsParser.printresult()
#parm = hhAPI.get_data_from_user_model(FindedUser)
t2 = time.time()
print("working time = " + str(t2 - t1))
descrs = []
context = RequestContext(request, {'FindedUser': FindedUser, "info": info, "descrs": descrs})
return HttpResponse(template.render(context))
def user(request, _id):
template = loader.get_template('suggesting_system/user.html')
FindedUser = User.objects.get(id=_id)
t1 = time.time()
hhapi = hhAPI(FindedUser)
info = hhapi.CreateQuery(GitHubAPI.GetLanguages(FindedUser.gitHub))
textList = []
doctitleList = []
for vac in info:
textList.append(vac.description)
doctitleList.append(vac.vacancy_Id)
# print(vac.description + ' ' + vac.name)
allDict = hhapi.docdict
i = 0
BIGTextData = ''
for i in range(len(textList)):
BIGTextData += textList[i]
allDict.update(dict(zip([doctitleList[i]], [textList[i]])))
i += 1
# print(allDict)
vacancyTerms = WordCount.get_term_one_list(WordCount.map(BIGTextData))
print("vacancy terms = ")
print(vacancyTerms[1])
print("hhDATA = ")
print(hhapi.documents.DocTermList[1])
print("terms = ")
test = dict(
list(hhapi.documents.DocTermList[1].items()) +
list(vacancyTerms[1].items()))
print("test = ")
print(test)
documentWords, documentTitles, allwords = NMF.ConvertData(allDict, test)
print("doc worlds = ")
print(documentWords)
tmp = NMF.CreateMatrix(allwords, documentWords)
# print(tmp[0])
# print(tmp[1])
test = NMF.calculate(tmp[0])
print(documentTitles)
WeightMatrix = test[0]
HeightMatrix = test[1]
topp, pn, res = NMF.prepareToVis(WeightMatrix, HeightMatrix,
documentTitles, tmp[1])
print("fin res" + str(res))
finalres = []
a = "ssss"
for val in res:
try:
idVac = int(val[1])
except:
idVac = 0
print("idvac = " + str(idVac))
print(val[0])
if idVac != 0 and int(val[0]) > 3:
print("appending...")
finalres.append(VacancyCache.objects.filter(vacancy_Id=idVac)[0])
info = finalres
# print(topp['kinect'])
#info = Competition("test", ["course1", "course2"], ["c", "c++"], ["soft1", "soft2", "soft3"], None)
#info = Document(FindedUser.resumeField._get_path())
#tmp = EduStandartsParser.printresult()
#parm = hhAPI.get_data_from_user_model(FindedUser)
t2 = time.time()
print("working time = " + str(t2 - t1))
descrs = []
context = RequestContext(request, {
'FindedUser': FindedUser,
"info": info,
"descrs": descrs
})
return HttpResponse(template.render(context))
