def GensimClient(texts):
gsDir = os.getcwd()
logger.debug(u"GSDir %s" % gsDir)
gss = gsDir + os.sep + u"gensim_server" + os.sep
logger.debug(u"%s" % gss)
server = SessionServer(gss)
logger.info(u"%s" % server.status())
corpus = [{u"id": u"url_%i" % n, u"tokens": utils.simple_preprocess(text)} for n, text in enumerate(texts)]
# send 1k docs at a time
utils.upload_chunked(server, corpus, chunksize=1000)
server.train(corpus, method=u"lsi")
# index the same documents that we trained on...
server.index(corpus)
# supply a list of document ids to be removed from the index
# server.delete(["doc_5", "doc_8"])
# overall index size unchanged (just 3 docs overwritten)
server.index(corpus[:3])
# Option Ons
for n in range(0, len(corpus)):
doc = u"doc_%d" % n
logger.info(u"------------------------------------------------------")
logger.info(u"Find similar N doc_%d to %s" % (n, corpus[n][u"tokens"]))
logger.info(u"------------------------------------------------------")
for sim in server.find_similar(doc):
m = int(sim[0][-1:])
if m != n:
logger.info(u"\t%s \t %3.2f : M %s" % (sim[0], float(sim[1]), corpus[m][u"tokens"]))
d = [unicode(x) for x in corpus[n][u"tokens"]]
e = [unicode(y) for y in corpus[m][u"tokens"]]
s1 = set(e)
s2 = set(d)
common = s1 & s2
lc = [x for x in common]
logger.info(u"\t\tCommon Topics : %s" % (lc))
if False:
# Option two
doc = {u"tokens": utils.simple_preprocess(str("Graph and minors and humans and trees."))}
logger.info(u"%s" % server.find_similar(doc, min_score=0.4, max_results=50))
def findSimilarities(self, texts):
gsDir = os.getcwd()
logger.debug(u"GSDir %s" % gsDir)
gss = gsDir + os.sep + u"gensim_server" + os.sep
logger.debug(u"%s" % gss)
server = SessionServer(gss)
corpus = [{u"id": u"doc_%i" % num, u"tokens": utils.simple_preprocess(text)} for num, text in enumerate(texts)]
# send 1k docs at a time
# utils.upload_chunked(server, corpus, chunksize=1000)
# server.train(corpus, method=u"lsi")
# index the same documents that we trained on...
# server.index(corpus)
# overall index size unchanged (just 3 docs overwritten)
# server.index(corpus[:3])
# Option Ons
if True:
for n in range(0, len(texts)):
doc = u"doc_%d" % n
self.output += u"Find similar doc_%d to %s%s" % (n, corpus[n][u"tokens"], os.linesep)
logger.info(self.output[:-1])
for sim in server.find_similar(doc):
m = int(sim[0][-1:])
if m != n:
self.output += u"\t%s \t %3.2f : %s%s" % (sim[0], float(sim[1]), corpus[m][u"tokens"], os.linesep)
logger.info(self.output[:-1])
d = [unicode(x) for x in corpus[n][u"tokens"]]
e = [unicode(y) for y in corpus[m][u"tokens"]]
s1 = set(e)
s2 = set(d)
common = s1 & s2
lc = [x for x in common]
self.output += u"\tCommon Topics : %s%s" % (lc, os.linesep)
logger.info(self.output[:-1])
else:
# Option two
doc = {u"tokens": utils.simple_preprocess(u"Graph and minors and humans and trees.")}
logger.info(u"%s" % server.find_similar(doc, min_score=0.4, max_results=50))
return self.output
class Indexer(object):
def __init__(self):
self.server = SessionServer("./tmp")
def _create_corpus(self, texts):
corpus = []
for id, text in texts:
corpus.append({
'id': id,
'tokens': utils.simple_preprocess(text)
})
return corpus
def index(self, texts):
corpus = self._create_corpus(texts)
utils.upload_chunked(self.server, corpus, chunksize=1000)
self.server.train(corpus, method='lsi')
self.server.index(corpus)
def add_documents(self, texts):
self.index(texts)
def recommend(self, id, max_results=10):
print "Id is: ", id
return self.server.find_similar(id, max_results=max_results)
def gensimsimserverII ():
reloadData = True
useremoteserver = False
if (useremoteserver):
server = Pyro4.Proxy(Pyro4.locateNS().lookup('gensim.testserver'))
else:
server = SessionServer('/tmp/testserver') #SessionServer('myserver')
if (reloadData):
client = Elasticsearch([Util.config['eshost']])
# response = client.search(
# index="blogs",
# body={
# "size": "5000",
# "query": {
# "match": {
# "country": country
# }
# }
# }
# )
response = client.search(
index="blogs",
body={
"size": "5000",
"query": {"match_all": {}}
}
)
stops = [unicode(word) for word in stopwords.words('english')] + [u':-).', u'–', u'-', u'…', '!!!', '!!', 'x', 'got', 'get', 'went', 'us', u'i\'m', '&','it\'s', 'i\'ve' ]
corpus = []
for hit in response['hits']['hits']:
try:
body = hit["_source"]["body"]
id = hit["_source"]["url"]
title = hit["_source"]["title"]
newBody = [word for word in body.lower().split() if word not in stops]
corpus.append({
'id': id,
'tokens':newBody,
'title':title
})
server.stable.payload[id] = title
except Exception:
logger.exception("Couldn't parse blog id: {0}".format(hit["_id"]))
server.train(corpus, method='lsi')
server.index(corpus)
print "********************************************"
print(server.find_similar('http://www.travelpod.com/travel-blog-entries/bvrlymm/1/1428224775/tpod.html', max_results=5))
class QueryIndex:
def __init__(self):
self.service = SessionServer('SearchServer/')
self.search_results = []
def query(self, user_query):
doc = {'tokens': utils.simple_preprocess(user_query)}
results = self.service.find_similar(doc, min_score=0.4, max_results=50)
self.search_results = results
def return_results(self):
return self.search_results
class QueryIndex:
def __init__(self):
self.service = SessionServer('SearchServer/')
self.search_results = []
def query(self, user_query):
doc = {'tokens': utils.simple_preprocess(user_query)}
results = self.service.find_similar(doc, min_score=0.4, max_results=50)
self.search_results = results
def return_results(self):
return self.search_results
def gensimsimserver ():
server = SessionServer('myserver')
texts = ["Human machine interface for lab abc computer applications",
"A survey of user opinion of computer system response time",
"The EPS user interface management system",
"System and human system engineering testing of EPS",
"Relation of user perceived response time to error measurement",
"The generation of random binary unordered trees",
"The intersection graph of paths in trees",
"Graph minors IV Widths of trees and well quasi ordering",
"Graph minors A survey"]
corpus = [{'id': 'doc_%i' % num, 'tokens': utils.simple_preprocess(text)}
for num, text in enumerate(texts)]
server.train(corpus, method='lsi')
server.index(corpus)
print "********************************************"
print(server.find_similar('doc_0'))
class gensim_news(object):
def __init__(self):
self.server = SessionServer(r'c:\temp\data_server')
print self.server
def initialise(self, docs):
corpus4server = self.create_server_corpus(docs)
self.server.train(corpus4server, method='lsi')
def create_server_corpus(self, docs):
return [{'id': '%s' % id, 'tokens': simple_preprocess(text)} for id, text in docs.iteritems()]
def gensim_similarities(self, docs_dict, new=False):
text4server = self.create_server_corpus(docs_dict)
sims = self.server.find_similar(text4server[0], min_score=0.90)
self.server.index(text4server)
return sims
class gensim_news(object):
def __init__(self):
self.server = SessionServer(r'c:\temp\data_server')
print self.server
def initialise(self, docs):
corpus4server = self.create_server_corpus(docs)
self.server.train(corpus4server, method='lsi')
def create_server_corpus(self, docs):
return [{
'id': '%s' % id,
'tokens': simple_preprocess(text)
} for id, text in docs.iteritems()]
def gensim_similarities(self, docs_dict, new=False):
text4server = self.create_server_corpus(docs_dict)
sims = self.server.find_similar(text4server[0], min_score=0.90)
self.server.index(text4server)
return sims
class Indexer(object):
def __init__(self):
self.server = SessionServer("./tmp")
def _create_corpus(self, texts):
corpus = []
for id, text in texts:
corpus.append({'id': id, 'tokens': utils.simple_preprocess(text)})
return corpus
def index(self, texts):
corpus = self._create_corpus(texts)
utils.upload_chunked(self.server, corpus, chunksize=1000)
self.server.train(corpus, method='lsi')
self.server.index(corpus)
def add_documents(self, texts):
self.index(texts)
def recommend(self, id, max_results=10):
print "Id is: ", id
return self.server.find_similar(id, max_results=max_results)
def ajax(request):
service = SessionServer('/Users/camron/Desktop/MIRCSearch/thesite/simdatabase')
data = json.loads(request.body)
print "DATA: \n"
print data
results = service.find_similar(data['identifier'], max_results=13)
print results
screen = []
temp = []
address = ""
beggining = '/static/mirc/Thumbnails/'
jpg = '.jpg'
for i in range(0, len(results)):
temp = results[i][2]
address = beggining + results[i][0] + jpg
temp['imgAdr'] = address
screen.append(temp)
a = Assemble(screen, data['width'], data['height'])
a.do_the_work()
finished = a.to_list()
print "AJAX \n"
print json.dumps(finished)
return HttpResponse(json.dumps(finished), content_type = "application/json")
def search(request):
#logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.DEBUG)
service = SessionServer('/Users/camron/Desktop/MIRCSearch/thesite/simdatabase')
form = SearchForm(request.POST)
if form.is_valid() == False:
return HttpResponse()
search = form.cleaned_data['search']
height = int(request.POST['height'])
width = int(request.POST['width'])
print height, " x ", width
if form.is_valid():
doc = {'tokens': utils.simple_preprocess(search)}
print doc
data = service.find_similar(doc, max_results=13)
test = len(data)
if test == 0:
return HttpResponseRedirect('/mirc/noresults')
#run data through the circle thingy to get the positions in there.
screen = []
temp = []
address = ""
beggining = '/static/mirc/Thumbnails/'
jpg = '.jpg'
#p = '/home/cocky/thesite/mirc/static/mirc/Thumbnails/'
for i in range(0, len(data)):
temp = data[i][2]
address = beggining + data[i][0] + jpg
#address = 'http://www.extremetech.com/wp-content/uploads/2013/08/bitcoin1.jpg'
temp['imgAdr'] = address
screen.append(temp)
a = Assemble(screen, width, height)
a.do_the_work()
finished = a.to_list()
print finished
form = SearchForm()
return render(request, 'mirc/dashboard.html',{'data':json.dumps(finished),'form':form})
class SearchServer:
def __init__(self):
self.service = SessionServer('SearchServer/')
def generate_index(self):
def page_text():
for page_file in os.listdir('CrawlData'):
content = open('CrawlData/'+page_file, 'r')
page_content = content.read()
content.close()
page_url = re.sub('\s', '/', page_file)
yield page_url, page_content
corpus = [{'id': '%s' % url, 'tokens': utils.simple_preprocess(text)}
for url, text in page_text()]
self.service.train(corpus, method='lsi')
self.service.index(corpus)
def query(self):
user_string = raw_input('Enter query: ')
doc = {'tokens': utils.simple_preprocess(user_string)}
for results in self.service.find_similar(doc, min_score=0.4, max_results=50):
print results[0]
corpus = [{'id
corpus = [{'id':link, 'tokens':content.cleaned_text} for link, content in maincontent.iteritems()]
len(corpus)
corpus[1]
from gensim import utils
service.train(corpus, method='lsi')
server.train(corpus, method='lsi')
corpus = [{'id':link, 'tokens':(content.cleaned_text,)} for link, content in maincontent.iteritems()]
corpus[1]
server.train(corpus, method='lsi')
server.index(corpus)
corpus = [{'id':link, 'tokens':utils.simple_preprocess(content.cleaned_text,)} for link, content in maincontent.iteritems()]
server.train(corpus, method='lsi')
server.index(corpus)
originaldoc = {'tokens': utils.simple_preprocess(originaldoc_maincontent.cleaned_text)}
result = server.find_similar(originaldoc, min_score=0.5)
len(result)
result
result = server.find_similar(originaldoc, min_score=0.9)
result
url
service.delete(corpus)
server.delete(corpus)
result = server.find_similar(originaldoc)
len(result)
result
result = server.find_similar(originaldoc, min_score=0.9)
result
server.delete([c.id for c in corpus])
corpus[1]
corpus[1].id
#let just index the corpus
texts=['如果 也 没有 的话 。 这个 确实 没有 办法 了 。 我 个人 建议您 重装 一遍 这个 软件 看看 是否 还是 一样 卸载 程序 里 也 没有 呢',
'我能 直接 删掉 这些 文件 吗 ？',
'不 建议 呢 。 因为 不 确定 这些 文件 中 是否 有 其他软件 的 文件 呢',
'好 的 ， 使用 看看 会断 么',
'它 只是 有时 自动 掉 ， 以后 看看 怎么样',
'这个 是 您 无线 驱动 ： http : / / driverdl . lenovo . com . cn / lenovo / driverfilesuploadfloder / 32228 / wlan _ win8 . 1 . exe',
'要是 问题 还是 出现 您 可以 安装 这个 试试',
'10 几个 版本 都 试过 了 么']
corpus=[{'id': 'doc_%i' % num, 'tokens': text.split()} for num, text in enumerate(texts)]
server.index(corpus)
server.delete(['doc_5']) # try to del one doc
server.commit()
texts=['如果 也 没有 的话 。 这个 确实 没有 办法 了 。 我 个人 建议您 重装 一遍 这个 软件 看看 是否 还是 一样 卸载 程序 里 也 没有 呢',
'我能 直接 删掉 这些 文件 吗 ？',
'不 建议 呢 。 因为 不 确定 这些 文件 中 是否 有 其他软件 的 文件 呢',
'好 的 ， 使用 看看 会断 么']
corpus=[{'id': 'eval_%i' % num, 'tokens': text.split()} for num, text in enumerate(texts)]
#and find_similar for each documents, which should return doc_0, doc_1 doc_2.
for s in corpus:
print server.find_similar(s)
#service.index(corpus[:3]) # overall index size unchanged (just 3 docs overwritten)
##print(service.find_similar('doc_0'))
##print(service.find_similar('02456-deep-learning'))
#print(service.find_similar('02456-deep-learning', min_score=0.5, max_results=11))
##[('doc_0', 1.0000001192092896, None), ('doc_2', 0.11294259130954742, None), ('doc_1', 0.09881371259689331, None), ('doc_3', 0.08786647021770477, None)]
'''[('02456-deep-learning', 1.0, None), ('deep-docker', 0.8198882937431335, None),
('nvidia-docker-compose', 0.8188392519950867, None), ('introtodeeplearning_labs', 0.8047046661376953, None),
('dl-docker', 0.8002966642379761, None), ('pydocker-template', 0.7893627285957336, None),
('nvidia-docker', 0.7853963375091553, None), ('-deep-deep', 0.7793657779693604, None),
('DockerFiles-tdeboissiere', 0.7759870290756226, None), ('dockerfiles--Kaixhin', 0.7693668007850647, None),
('play-with-docker', 0.7634270191192627, None)]'''
print(
"Similar: ",
service.find_similar('02456-deep-learning', min_score=0.5, max_results=11))
#Similar: [('02456-deep-learning', 1.0, None), ('awesome-docker', 0.7814108729362488, None), ('alpine-minikube', 0.7373288869857788, None), ('baseimage-docker', 0.7281696796417236, None), ('attalos', 0.69722580909729, None), ('bazel-docker', 0.6071430444717407, None), ('basic-docker-agent-build', 0.5810653567314148, None), ('async-deep-rl', 0.5226494073867798, None), ('altair-Lab41', 0.5212352275848389, None)]
print(
"DisSimilar: ",
service.find_dissimilar('02456-deep-learning',
max_score=0.5,
max_results=10))
#DisSimilar: [('attention-is-all-you-need-divyanshj16', 4.366040229797363e-05, None), ('allen', 0.00011094659566879272, None), ('bemkl', 0.00014548376202583313, None), ('backo', 0.00017013587057590485, None), ('aeropy-AeroPython', 0.000325517263263464, None), ('arduino-projects', 0.00038177333772182465, None), ('Asymmetric-Hashing-ANN', 0.000621844083070755, None), ('active-testing', 0.0006259661167860031, None), ('adaptive-neural-compilation', 0.0008356906473636627, None), ('amen', 0.0008382126688957214, None)]
#sys.exit(0)
#print(service.find_similar('doc_5')) # we deleted doc_5 and doc_8, remember?
#ValueError: document 'doc_5' not in index
doc = {
'tokens':
import os
from gensim import utils
from simserver import SessionServer
server = SessionServer('myserver')
w = open('data/1/549518.txt').read()
docin = {'id': '549518', 'tokens' : utils.simple_preprocess(w)}
print server.find_similar(docin)
def test_Gensim(texts):
gsDir = os.getcwd()
logger.debug(u"GSDir %s" % gsDir)
gss = gsDir + os.sep + u"gensim_server" + os.sep
logger.debug(u"%s" % gss)
server = SessionServer(gss)
u""" texts = [u"Human machine interface for lab abc computer applications",
u"A survey of user opinion of computer system response time",
u"The EPS user interface management system",
u"System and human system engineering testing of EPS",
u"Relation of user perceived response time to error measurement",
u"The generation of random binary unordered trees",
u"The intersection graph of paths in trees",
u"Graph minors IV Widths of trees and well quasi ordering",
u"Graph minors A survey",
u"Why use a computer"]
"""
logger.info(u"%s" % server.status())
corpus = [{u"id": u"doc_%i" % num, u"tokens": utils.simple_preprocess(text)} for num, text in enumerate(texts)]
# send 1k docs at a time
utils.upload_chunked(server, corpus, chunksize=1000)
server.train(corpus, method=u"lsi")
# index the same documents that we trained on...
server.index(corpus)
# supply a list of document ids to be removed from the index
# server.delete(["doc_5", "doc_8"])
# overall index size unchanged (just 3 docs overwritten)
server.index(corpus[:3])
# Option Ons
for n in range(0, len(texts)):
doc = u"doc_%d" % n
logger.info(u"Find similar doc_%d to %s" % (n, corpus[n][u"tokens"]))
for sim in server.find_similar(doc):
m = int(sim[0][-1:])
if m != n:
logger.info(u"\t%s \t %3.2f : %s" % (sim[0], float(sim[1]), corpus[m][u"tokens"]))
d = [unicode(x) for x in corpus[n][u"tokens"]]
e = [unicode(y) for y in corpus[m][u"tokens"]]
s1 = set(e)
s2 = set(d)
common = s1 & s2
lc = [x for x in common]
logger.info(u"\tCommon Topics : %s\n" % (lc))
if False:
# Option two
doc = {u"tokens": utils.simple_preprocess(u"Graph and minors and humans and trees.")}
logger.info(u"%s" % server.find_similar(doc, min_score=0.4, max_results=50))
import os
from gensim import utils
from simserver import SessionServer
server = SessionServer("myserver")
w = open("data/1/549518.txt").read()
docin = {"id": "549518", "tokens": utils.simple_preprocess(w)}
print server.find_similar(docin)
class Simple_resume_similarity_app_tk(Tkinter.Tk):
def __init__(self):
Tkinter.Tk.__init__(self)
self.initialize()
def initialize(self):
button = Tkinter.Button(self,text=u"Click Me!", command = self.resume_scoring)
button.grid(row = 1, column = 1)
self.label1 = Tkinter.Label(self, text = "Click Button To Generate Similarity Score")
self.label1.grid(row = 2, column = 1)
#self.img = Image.open('C:\\temp\\Resume_Similarity\\Resume_GUI\\wellsfargologo2.gif')
#self.img_path = r"C:/temp/Resume_Similarity/Resume_GUI/wellsfargologo2.gif"
#self.im = Image.open(self.img_path)
#self.ph = PIL.ImageTk.PhotoImage(self.im)
#self.label1 = Label(self, image=self.ph)
#self.label1.image = self.ph
#self.label1.pack(side = "left")
#logo = PhotoImage("C:/temp/Resume_Similarity/Resume_match_score/logo.jpg")
#label.config(image = logo)
def resume_scoring(self):
""""
Cleanes the data and runs the resume matching code. User is
requested to pass the job description name, session_name and
final output file name. Final output is an excel file.
@param: job_description - string
@param: session_name - string
@param: output_filename - string
Once you run this code it will prompt you to select the path of the
directory
"""
self.job_description = self.select_job_description()
if len(self.job_description) > 0:
#self.job_description_path = os.path.join( self.job_description_path + "/" + job_description)
self.raw_resumes_path =self.select_resume_path()
if len(self.raw_resumes_path) > 0:
self.save_text_files_path = self.select_rawtext_path()
self.raw_resumes_to_text()
self.jd_to_text()
self.file_list_text = glob.glob(self.save_text_files_path + "/*.*")
print self.file_list_text
self.resume_id = []
for i in range(0, len(self.file_list_text)):
self.resume_id.append([int(s) for s in self.file_list_text[i].split() if s.isdigit()])
self.documents = []
for filename in self.file_list_text:
with open(filename, 'r') as f:
#d = f.read()
#print d
self.documents.append(f.read())
self.corpus = [{'id': 'doc_%s' % num, 'tokens': utils.simple_preprocess(text)}
for num, text in enumerate(self.documents)]
self.count = 0
while self.count < len(self.resume_id):
for item in self.corpus:
if self.resume_id[self.count] == []:
item['id'] = 'doc_jd'
else:
item['id'] = str(self.resume_id[self.count])
self.count = self.count + 1
self.regex = re.compile('[%s]' % re.escape(string.punctuation)) #see documentation here: http://docs.python.org/2/library/string.html
self.tokenized_corpus_no_punctuation = []
for review in self.corpus:
self.new_corpus = []
for token in review:
self.new_token = self.regex.sub(u'', token)
if not self.new_token == u'':
self.new_corpus.append(self.new_token)
self.tokenized_corpus_no_punctuation.append(self.new_corpus)
self.dir_name = self.setting_up_server_session_dir()
self.server = SessionServer(self.dir_name)
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
self.server.train(self.corpus, method='lsi')
self.server.index(self.corpus)
self.lst = self.server.find_similar('doc_jd')
self.series = pd.DataFrame(self.lst)
self.series.columns = ['Resume_ID', 'Score', 'none']
self.series.index.names = ['Rank']
self.series = self.series.drop(self.series.columns[2], axis = 1)
self.final_excel_path()
def setting_up_server_session_dir(self):
self.dir = 'C:/temp/resume_server_script_server_logs'
if not os.path.exists(self.dir):
os.makedirs(self.dir)
else:
shutil.rmtree(self.dir) #removes all the subdirectories!
os.makedirs(self.dir)
return self.dir
def convert(self,fname, pages=None):
if not pages:
pagenums = set()
else:
pagenums = set(pages)
output = StringIO()
manager = PDFResourceManager()
converter = TextConverter(manager, output, laparams=LAParams())
interpreter = PDFPageInterpreter(manager, converter)
infile = file(fname, 'rb')
for page in PDFPage.get_pages(infile, pagenums):
interpreter.process_page(page)
infile.close()
converter.close()
text = output.getvalue()
output.close
return text
def select_job_description(self):
root = Tkinter.Tk()
root.withdraw() #use to hide tkinter window
currdir = os.getcwd()
self.tempdir = tkFileDialog.askopenfilename(parent=root,
initialdir=currdir,
title="Select Job Description file")
if len(self.tempdir) > 0:
return self.tempdir
def select_resume_path(self):
root = Tkinter.Tk()
root.withdraw() #use to hide tkinter window
currdir = os.getcwd()
tempdir = tkFileDialog.askdirectory(parent=root,
initialdir=currdir,
title="Select Resume Description Path")
if len(tempdir) > 0:
return tempdir
def select_rawtext_path(self):
root = Tkinter.Tk()
root.withdraw() #use to hide tkinter window
currdir = os.getcwd()
tempdir = tkFileDialog.askdirectory(parent=root,
initialdir=currdir,
title="Select Path Where You Want To Save Text Files.")
if len(tempdir) > 0:
return tempdir
def final_excel_path(self):
root = Tkinter.Tk()
root.withdraw() #use to hide tkinter window
currdir = os.getcwd()
savefile = tkFileDialog.asksaveasfilename(filetypes=(("Excel files", "*.xlsx"),
("All files", "*.*") ),
parent=root,
initialdir=currdir,
title="Final Excel Output Path")
if len(savefile) > 0:
self.series.to_excel(savefile + ".xlsx", index=True, sheet_name="Results")
def raw_resumes_to_text(self):
## Reading the files path
file_list_raw = glob.glob(self.raw_resumes_path + "/*.*")
for fp in file_list_raw:
# print fp
ext = os.path.splitext(fp)[-1].lower()
base = os.path.basename(fp)
file_name = os.path.splitext(base)[0]
#print ext
if ext == ".docx":
text = textract.process(fp)
complte_name = os.path.join(self.save_text_files_path + "/" + file_name + ".txt")
with open(complte_name, 'w') as f:
f.write(text)
elif ext == ".pdf":
text = self.convert(fp)
complte_name = os.path.join(self.save_text_files_path + "/" + file_name + ".txt")
with open(complte_name, 'w') as f:
f.write(text)
elif ext == ".txt":
shutil.copy(os.path.join(self.raw_resumes_path + str("/") + file_name + ".txt"), os.path.join(self.save_text_files_path + str("/") + file_name + ".txt"))
else:
print "Unable to recognise this format."
def jd_to_text(self):
ext = os.path.splitext(self.job_description)[-1].lower()
file_name_with_ext = os.path.basename(self.job_description)
file_name = os.path.splitext(file_name_with_ext)[0].lower()
if ext == ".docx":
text = textract.process(self.job_description)
complte_name = os.path.join(self.save_text_files_path + "/" + file_name + ".txt")
with open(complte_name, 'w') as f:
f.write(text)
elif ext == ".pdf":
text = convert(self.job_description)
complte_name = os.path.join(self.save_text_files_path + "/" + file_name + ".txt")
with open(complte_name, 'w') as f:
f.write(text)
elif ext == ".txt":
shutil.copy(self.job_description, os.path.join(self.save_text_files_path + str("/") + file_name + ".txt"))
else:
print "This file format is not supported for now."
"The intersection graph of paths in trees",
"Graph minors IV Widths of trees and well quasi ordering",
"Graph minors A survey"]
corpus = [{'id': 'doc_%i' % num, 'tokens': utils.simple_preprocess(text)} for num, text in enumerate(texts)]
utils.upload_chunked(server, corpus, chunksize=1000) # send 1k docs at a time
service = SessionServer('C:/0_afc_working/0_Doc2Vec/gensim-simserver-master/my_server/') # or wherever
logger.info("simberver_local_A: service.train(corpus, method='lsi')" )
service.train(corpus, method='lsi')
service.index(corpus) # index the same documents that we trained on...
service.delete(['doc_5', 'doc_8']) # supply a list of document ids to be removed from the index
service.index(corpus[:3]) # overall index size unchanged (just 3 docs overwritten)
print(service.find_similar('doc_0'))
#[('doc_0', 1.0000001192092896, None), ('doc_2', 0.11294259130954742, None), ('doc_1', 0.09881371259689331, None), ('doc_3', 0.08786647021770477, None)]
#print(service.find_similar('doc_5')) # we deleted doc_5 and doc_8, remember?
#ValueError: document 'doc_5' not in index
doc = {'tokens': gensim.utils.simple_preprocess('Graph and minors and humans and trees.')}
print(service.find_similar(doc, min_score=0.4, max_results=50))
#[('doc_7', 0.7615688443183899, None), ('doc_3', 0.5443614721298218, None)]
class SimService(object):
def __init__(self, path, preprocess, deaccent=True, lowercase=True,
stemmer=None, stopwords=None):
self.service = SessionServer(path)
self.deaccent = deaccent
self.lowercase = lowercase
self.preprocess = preprocess
self.stemmer = stemmer
self.stopwords = stopwords
def find_similar(self, data, min_score, max_results):
if isinstance(data, basestring):
doc = data.strip()
if ' ' in doc:
doc = {'tokens': self.preprocess(data, deacc=self.deaccent,
lowercase=self.lowercase, errors='ignore',
stemmer=self.stemmer, stopwords=self.stopwords)}
try:
return {'status': 'OK', 'response':
self.service.find_similar(doc,
min_score=min_score,
max_results=max_results)}
except ValueError:
return {'status': 'NOTFOUND', 'response':[]}
else:
result = {}
for doc in data:
try:
result[doc] = (self.service.find_similar(
doc,
min_score=min_score,
max_results=max_results))
except ValueError:
pass
if result:
return {'status': 'OK', 'response': result}
else:
return {'status': 'NOTFOUND', 'response':[]}
def _buffer(self, data):
i = 0
for d in data:
if 'tokens' in d:
self.service.buffer([{'id': d['id'], 'tokens': d['tokens']}])
else:
self.service.buffer([{'id': d['id'],
'tokens': list(self.preprocess(d['text'], deacc=self.deaccent,
lowercase=self.lowercase, errors='ignore',
stemmer=self.stemmer, stopwords=self.stopwords))}])
i+=1
return i
def train(self, data):
self.service.set_autosession(False)
self.service.open_session()
i = self._buffer(data)
self.service.train(method='lsi')
logger.info('training complete commit changes')
self.service.commit()
self.service.set_autosession(True)
return {'status': 'OK', 'response':i}
def index(self, data):
self.service.set_autosession(False)
self.service.open_session()
i = self._buffer(data)
self.service.index()
logger.info('indexing complete commit changes')
self.service.commit()
self.service.set_autosession(True)
return {'status': 'OK', 'response':i}
def optimize(self):
self.service.set_autosession(False)
self.service.open_session()
self.service.optimize()
self.service.commit()
self.service.set_autosession(True)
return {'status': 'OK', 'response': 'index optimized'}
def delete(self, data):
self.service.set_autosession(False)
self.service.open_session()
self.service.delete(data)
self.service.commit()
self.service.set_autosession(True)
return {'status': 'OK', 'response': 'documents deleted'}
def status(self):
return {'status': 'OK', 'response': self.service.status()}
def indexed_documents(self):
return {'status': 'OK', 'response': self.service.keys()}
def is_indexed(self, doc):
return {'status': 'OK', 'response': doc in self.service.keys()}
class DocSimServer(object):
def __init__(self):
self.server = SessionServer(settings.SIMSERVER_WORKING_DIR)
if not self.server.stable.model:
self.server.train(self.corpus)
if not self.server.stable.fresh_index:
self.server.index(self.corpus)
def find_similar(self, *args, **kwargs):
return self.server.find_similar(*args, **kwargs)
@property
def corpus(self):
try:
return self._corpus
except AttributeError:
logging.info('creating corpus from DB')
self._corpus = [dict(id=doc.id, tokens=doc.tokens())
for doc in Document.objects.all()]
return self._corpus
@property
def document_ids(self):
try:
return self._document_ids
except AttributeError:
self._document_ids = list(
Document.objects.values_list('id', flat=True).order_by('id'))
return self._document_ids
@property
def index_id(self):
try:
return self._index_id
except AttributeError:
self._index_id = dict(enumerate(self.document_ids))
return self._index_id
@property
def id_index(self):
try:
return self._id_index
except AttributeError:
self._id_index = dict((v, k) for k, v in self.index_id.iteritems())
return self._id_index
def similarity_matrix(self):
logging.info('calculating similarity matrix')
s = identity(len(self.id_index))
for id in self.document_ids:
for sim_id, score, none in self.server.find_similar(
id, min_score=.2, max_results=10000):
if sim_id != id:
s[self.id_index[id]][self.id_index[sim_id]] = score
return s
@property
def distance_matrix(self):
try:
return self._distance_matrix
except AttributeError:
s = self.similarity_matrix()
logging.info('converting similarity matrix to distance matrix')
self._distance_matrix = 2 * (1 - s)
return self._distance_matrix
def dbscan_clusters(self, eps=.4, min_samples=5):
D = self.distance_matrix
logging.info('starting dbscan')
dbscan = DBSCAN(eps=eps, min_samples=min_samples, metric='precomputed')
db = dbscan.fit(D)
labels = db.labels_
clusters = [l for l in set(labels) if l > 0] # outliers are -1
logging.info('found %i clusters' % len(clusters))
for c in clusters:
cluster = Cluster(
parameters=dict(algorithm='DBSCAN', eps=eps,
min_samples=min_samples))
cluster.save()
doc_ids = [self.index_id[i[0]] for i in argwhere(labels == c)]
logging.info(
'cluster %s: %s documents' % (cluster.id, len(doc_ids)))
cluster.documents.add(*doc_ids)
