def getLabeledHudongItem(self, filename):
labels = readCSV2(filename)
List = []
i = 0
for line in labels:
ctx = self.graph.find_one(label="HudongItem",property_key="title",property_value=line[0])
if ctx == None:
continue;
cur = HudongItem(ctx)
cur.label = line[1]
List.append(cur)
print('load LabeledHudongItem over ...')
return List
def getLabeledHudongItem(self, filename):
labels = readCSV2(filename)
List = []
i = 0
for line in labels:
ctx = self.graph.find_one(label="HudongItem",property_key="title",property_value=line[0])
if ctx == None:
continue;
cur = HudongItem(ctx)
cur.label = line[1]
List.append(cur)
print('load LabeledHudongItem over ...')
return List
def create_predict(HudongItem_csv):
# 读取neo4j内容
db = Neo4j()
db.connectDB()
predict_List = readCSVbyColumn(HudongItem_csv, 'title')
file_object = open('vector.txt', 'a')
model = FastText('wiki.zh.bin')
count = 0
vis = set()
for p in predict_List:
cur = HudongItem(db.matchHudongItembyTitle(p))
count += 1
title = cur.title
if title in vis:
continue
vis.add(title)
wv_list = model[title]
strr = str(title)
print('===============')
print(strr)
for p in wv_list:
strr += ' ' + str(p)[:7]
print('===============')
print(strr)
print('===============')
file_object.write(strr + "\n")
print(str(count) + ' / ' + str(len(predict_List)))
file_object.close()
def create_predict(HudongItem_csv):
# 读取neo4j内容
db = Neo4j()
db.connectDB()
data_set = db.getLabeledHudongItem('labels.txt')
classifier = Classifier('wiki.zh.bin')
classifier.load_trainSet(data_set)
classifier.set_parameter(weight=[1.0, 3.0, 0.2, 4.0, 0],k=10)
predict_List = readCSVbyColumn(HudongItem_csv, 'title')
file_object = open('predict_labels2.txt','a')
count = 0
vis = set()
for p in predict_List:
cur = HudongItem(db.matchHudongItembyTitle(p))
if count > 200:
break
count += 1
if count <140 :
continue
title = cur.title
if title in vis:
continue
vis.add(title)
label = classifier.KNN_predict(cur)
print(str(title)+" "+str(label)+": "+str(count)+"/"+str(len(predict_List)))
file_object.write(str(title)+" "+str(label)+"\n")
file_object.close()
def getAllHudongItem(self, limitnum):
List = []
ge = self.graph.find(label="HudongItem", limit=limitnum)
for g in ge:
List.append(HudongItem(g))
print('load AllHudongItem over ...')
return List
def getAllHudongItem(self, limitnum):
List = []
matcher = NodeMatcher(self.graph)
ge = matcher.match("hudongItem").limit(limitnum)
#ge = self.graph.find(label="HudongItem", limit=limitnum)
for g in ge:
List.append(HudongItem(g))
print('load AllHudongItem over ...')
return List
def getAllHudongItem(self, limitnum):
List = []
ge = self.graph.find(label="HudongItem", limit=limitnum)
for g in ge:
List.append(HudongItem(g))
print('load AllHudongItem over ...')
return List
#test = Neo4j()
#test.connectDB()
#a = test.getLabeledHudongItem('labels.txt')
#print(a[10].openTypeList)
def getAllHudongItem(self, limitnum):
List = []
ge = self.graph.find(label="HudongItem", limit=limitnum)
for g in ge:
List.append(HudongItem(g))
print('load AllHudongItem over ...')
return List
#test = Neo4j()
#test.connectDB()
#answer = test.graph.find_one(label="HudongItem",property_key="title",property_value='火龙果')
#print(answer)
#a = test.getLabeledHudongItem('labels.txt')
#print(a[10].openTypeList)
