def center(category):
database = DataGetter.get__db()
appIds = database.get_app_ids()
c = center.Center()
for appId in appIds:
c.set_property(category, appId)
data = c.calculate()
c.record_data(data)
def cluster_data(category, Minpts=2, e=0.6):
# 获取应用id
database = DataGetter.get__db()
appIds = database.get_app_ids()
d = dbscan.DBSCAN()
for appId in appIds:
# dbscan算法聚簇
d.set_property(category, appId)
clusters = d.dbscan(Minpts, e)
# 持久化数据
d.record_cluster(clusters)
def classify_data(lower, quantity):
database = DataGetter.get__db()
# 从原始数据中读取指定数量数据
data = database.load_specified_quantity_data(lower, quantity)
# 初始化预处理器和分类器
p = preprocess.Preprocess()
b = bayes.Bayes()
for i in range(len(data)):
# 将数据进行预处理
p.set_sentence(data[i][1])
sentence_processed = p.preprocess()
if sentence_processed == '':
category = con.USELESS
else:
# 朴素贝叶斯算法分类器对文本进行分类
# print sentence_processed, data[i][2]
b.set_property(sentence_processed, data[i][2])
category = b.bayes_classifier_improved2()
data[i] = [data[i][0], sentence_processed, data[i][2], category]
# print data[i]
# 持久化
database.save_data(data)
def __init__(self):
self.__clusterHelper = DataGetter.get__clusterHelper()
self.__db = DataGetter.get__db()
def __init__(self):
self.__database = DataGetter.get__db()
def __init__(self, category, appId):
self.__category = category
self.__appId = appId
self.__database = DataGetter.get__db()
self.__clusterHelper = DataGetter.get__clusterHelper()
self.__isAborted = False