def retrive_word(self, word):
# 找出 DocID 对应的 url
manager = documentManager()
collection = manager.connect_mongo()
id_list = []
for word in self.word_dictionary[word]:
url = collection.find_one({"DocID": int(word[0])})["url"]
id_list.append(int(word[0]))
return id_list
def caculate_BM25(self, query_words):
manager = documentManager()
collection = manager.connect_mongo()
score_dictionary = {}
b = 0.5 #参数调节因子
k = 10 # 调节因子
avdl = 800 # 文档平均长度
# query_words 中至少一个单元词出现的所有文档
DocId_of_query_words = set([])
for word in query_words.split(' '):
if not self.word_dictionary.has_key(word):
continue
for posting in self.word_dictionary[word]:
DocID = posting[0]
DocId_of_query_words.add(DocID)
for id in DocId_of_query_words:
BM25_score = 0
for word in query_words.split(' '):
content = collection.find_one({"DocID": int(id)})["content"]
freq = self.get_wordcount_in_document(word ,content)
doc_len = len(self.word_dictionary[word])
idf = math.log(float(100) / doc_len)
normalizer = 1 - b + b * (doc_len / avdl)
BM25_score += (float)((k + 1) * freq) / (freq + k * normalizer) * idf
# 计算某个文档对 Query 的 BM25 分数
score_dictionary[id] = BM25_score
score = sorted(score_dictionary.iteritems(), key=lambda d:d[1], reverse = True)
for i in score:
print self.DocID2Doc(int(i[0]))
def process_all_documents(self):
manager = documentManager()
collection = manager.connect_mongo()
for loop in range(1, 101):
text = collection.find_one({"DocID": loop})["content"]
self.count_words(text, loop)
def process_all_documents(self):
manager = documentManager()
collection = manager.connect_mongo()
for loop in range(1, 101):
text = collection.find_one({"DocID": loop})["content"]
self.count_words(text, loop)
def DocID2Doc(self, DocID):
manager = documentManager()
collection = manager.connect_mongo()
url = collection.find_one({"DocID": DocID})["url"]
return url
