def readSegFile():
jieba.load_userdict("../../data/jieba_userdict.txt")
infile = open('../../data/all_cn_seg_nwi_clean.txt','rb')
outfile = open('../../data/all_word.txt','wb')
stopword_set = text_process.getStopword('../../data/stopword.txt')
word_set = set([])
word_fre_dict = {}
row_counter = 0
for row in infile:
row_counter += 1
print row_counter
row = row.strip().decode('utf-8')
items = row.split('<@>')
app_name = items[1]
brief_seg = items[2].split()
title_seg = jieba.cut(app_name)
for title in title_seg:
if text_process.isChinese(title) and title not in stopword_set:
word_set.add(title)
word_fre_dict.setdefault(title,0)
word_fre_dict[title] += 1
for brief in brief_seg:
if text_process.isChinese(brief) and brief not in stopword_set:
word_set.add(brief)
word_fre_dict.setdefault(brief,0)
word_fre_dict[brief] += 1
sorted_list = sorted(word_fre_dict.items(),key=lambda p:p[1],reverse=True)
for val in sorted_list:
if val[1] >= 10:
outfile.write(val[0]+','+str(val[1])+'\r\n')
def readSegFile():
jieba.load_userdict("../../data/jieba_userdict.txt")
infile = open('../../data/all_cn_seg_nwi_clean.txt', 'rb')
outfile = open('../../data/all_word.txt', 'wb')
stopword_set = text_process.getStopword('../../data/stopword.txt')
word_set = set([])
word_fre_dict = {}
row_counter = 0
for row in infile:
row_counter += 1
print row_counter
row = row.strip().decode('utf-8')
items = row.split('<@>')
app_name = items[1]
brief_seg = items[2].split()
title_seg = jieba.cut(app_name)
for title in title_seg:
if text_process.isChinese(title) and title not in stopword_set:
word_set.add(title)
word_fre_dict.setdefault(title, 0)
word_fre_dict[title] += 1
for brief in brief_seg:
if text_process.isChinese(brief) and brief not in stopword_set:
word_set.add(brief)
word_fre_dict.setdefault(brief, 0)
word_fre_dict[brief] += 1
sorted_list = sorted(word_fre_dict.items(),
key=lambda p: p[1],
reverse=True)
for val in sorted_list:
if val[1] >= 10:
outfile.write(val[0] + ',' + str(val[1]) + '\r\n')
def generateCandidateCategory(category_path):
print 'loading file'
jieba.load_userdict(data_path + "jieba_userdict.txt")
stopword_set = text_process.getStopword('../../../data/stopword.txt')
print 'reading file'
word_title_dict = {}
word_brief_dict = {}
word_all_dict = {}
infile = open('../data/' + category_path + '.json', 'rb')
outfile = open('candidate_category/' + str(category_path) + '.txt', 'wb')
for row in infile:
json_obj = json.loads(row.strip())
app_name = json_obj["soft_name"]
app_brief = json_obj["soft_brief"]
seg_title_list = jieba.cut(app_name)
seg_brief_list = jieba.cut(app_brief)
for seg_title in seg_title_list:
if text_process.isChinese(
seg_title) and seg_title not in stopword_set:
word_title_dict.setdefault(seg_title, 0)
word_title_dict[seg_title] += 1
for seg_brief in seg_brief_list:
if text_process.isChinese(
seg_brief) and seg_brief not in stopword_set:
word_brief_dict.setdefault(seg_brief, 0)
word_brief_dict[seg_brief] += 1
print 'sorting'
sorted_list = sorted(word_title_dict.items(),
key=lambda p: p[1],
reverse=True)
for item in sorted_list:
if item[1] >= 10:
word_all_dict.setdefault(item[0], 0)
word_all_dict[item[0]] += item[1]
# outfile.write(item[0]+','+str(item[1])+'\r\n')
sorted_list = sorted(word_brief_dict.items(),
key=lambda p: p[1],
reverse=True)
for item in sorted_list:
if item[1] >= 50:
word_all_dict.setdefault(item[0], 0)
word_all_dict[item[0]] += item[1]
# outfile.write(item[0]+','+str(item[1])+'\r\n')
sorted_list = sorted(word_all_dict.items(),
key=lambda p: p[1],
reverse=True)
for item in sorted_list:
outfile.write(item[0] + ',' + str(item[1]) + '\r\n')
def mineKeywordCombination(category_id, query_keyword):
#主类目名称
main_category = idToName(category_id)
jieba.load_userdict('../../../data/jieba_userdict.txt')
stopword_set = text_process.getStopword('../../../data/stopword.txt')
combination_fre_dict = {}
outfile = open('keyword_combination.txt', 'wb')
#遍历主类目下的app
infile = open('../data/' + str(category_id) + '.json', 'rb')
for row in infile:
json_obj = json.loads(row.strip())
app_id = int(json_obj["id"])
app_name = json_obj["title"]
app_brief = json_obj["brief"]
app_download = int(json_obj["download_times"])
app_name_seg = [
word for word in jieba.cut(app_name)
if word not in stopword_set and text_process.isChinese(word)
]
app_brief_seg = [
word for word in jieba.cut(app_brief)
if word not in stopword_set and text_process.isChinese(word)
]
app_name_brief = app_name + " " + app_brief
app_name_combination_dict = combineNeighborWord(
app_name_seg, query_keyword)
for word in app_name_combination_dict.keys():
combination_fre_dict.setdefault(word, 0)
combination_fre_dict[word] += app_name_combination_dict[word]
app_brief_combination_dict = combineNeighborWord(
app_brief_seg, query_keyword)
for word in app_brief_combination_dict.keys():
combination_fre_dict.setdefault(word, 0)
combination_fre_dict[word] += app_brief_combination_dict[word]
sorted_list = sorted(combination_fre_dict.items(),
key=lambda p: p[1],
reverse=True)
for val in sorted_list:
if val[1] >= 2:
print val[0] + ',' + str(val[1])
outfile.write(val[0] + ',' + str(val[1]) + '\r\n')
def readSegFile():
infile = open('../../data/all_cn_seg_nwi_clean.txt','rb')
outfile = open('../../data/candidate_title_word.txt','wb')
stopword_set = text_process.getStopword('../../data/stopword.txt')
word_set = set([])
word_fre_dict = {}
row_counter = 0
for row in infile:
row_counter += 1
print row_counter
row = row.strip().decode('utf-8')
items = row.split('<@>')
app_name = items[1]
brief_seg = items[2].split()
title_seg = jieba.cut(app_name)
for title in title_seg:
if text_process.isChinese(title) and title not in stopword_set:
word_set.add(title)
word_fre_dict.setdefault(title,0)
word_fre_dict[title] += 1
# for brief in brief_seg:
# word_set.add(brief)
for word in word_fre_dict.keys():
if word_fre_dict[word] >= 10:
outfile.write(word+'\r\n')
def generateCandidateCategory(category_path):
print 'loading file'
jieba.load_userdict(data_path+"jieba_userdict.txt")
stopword_set = text_process.getStopword('../../../data/stopword.txt')
print 'reading file'
word_title_dict = {}
word_brief_dict = {}
word_all_dict = {}
infile = open('../data/'+category_path+'.json','rb')
outfile = open('candidate_category/'+str(category_path)+'.txt','wb')
for row in infile:
json_obj = json.loads(row.strip())
app_name = json_obj["soft_name"]
app_brief = json_obj["soft_brief"]
seg_title_list = jieba.cut(app_name)
seg_brief_list = jieba.cut(app_brief)
for seg_title in seg_title_list:
if text_process.isChinese(seg_title) and seg_title not in stopword_set:
word_title_dict.setdefault(seg_title,0)
word_title_dict[seg_title] += 1
for seg_brief in seg_brief_list:
if text_process.isChinese(seg_brief) and seg_brief not in stopword_set:
word_brief_dict.setdefault(seg_brief,0)
word_brief_dict[seg_brief] += 1
print 'sorting'
sorted_list = sorted(word_title_dict.items(),key=lambda p:p[1],reverse=True)
for item in sorted_list:
if item[1] >= 10:
word_all_dict.setdefault(item[0],0)
word_all_dict[item[0]] += item[1]
# outfile.write(item[0]+','+str(item[1])+'\r\n')
sorted_list = sorted(word_brief_dict.items(),key=lambda p:p[1],reverse=True)
for item in sorted_list:
if item[1] >= 50:
word_all_dict.setdefault(item[0],0)
word_all_dict[item[0]] += item[1]
# outfile.write(item[0]+','+str(item[1])+'\r\n')
sorted_list = sorted(word_all_dict.items(),key=lambda p:p[1],reverse=True)
for item in sorted_list:
outfile.write(item[0]+','+str(item[1])+'\r\n')
def formatText(text): format_text = "" for val in text: if text_process.isChinese(val) or val == '[' or val == ']': continue format_text += val format_text = format_text.strip() return format_text
def formatText(text): format_text = "" for val in text: if text_process.isChinese(val) or val == '[' or val == ']': continue format_text += val format_text = format_text.strip() return format_text
def calculateCoverage(category_stat_dict, synonyms_set_list):
print 'loading file'
jieba.load_userdict(data_path + "jieba_userdict.txt")
stopword_set = text_process.getStopword('../../../data/stopword.txt')
print 'reading file'
infile = open('../data/' + category_path + '.json', 'rb')
all_app_counter = 0
for row in infile:
json_obj = json.loads(row.strip())
app_id = int(json_obj["soft_id"])
app_name = json_obj["soft_name"]
app_brief = json_obj["soft_brief"]
app_download = int(json_obj["download_times"])
if app_download < 100:
continue
all_app_counter += 1
seg_title_list = jieba.cut(app_name)
seg_brief_list = jieba.cut(app_brief)
for seg_title in seg_title_list:
if text_process.isChinese(
seg_title) and seg_title not in stopword_set:
for main_category in category_stat_dict.keys():
if seg_title in category_stat_dict[main_category][0]:
category_stat_dict[main_category][1].add(app_id)
for seg_brief in seg_brief_list:
if text_process.isChinese(
seg_brief) and seg_brief not in stopword_set:
for main_category in category_stat_dict.keys():
if seg_brief in category_stat_dict[main_category][0]:
category_stat_dict[main_category][1].add(app_id)
top_coverage_category_info_dict = {}
for iter_num in range(20):
stat(top_coverage_category_info_dict, category_stat_dict,
all_app_counter, synonyms_set_list)
def calculateCoverage(category_stat_dict,synonyms_set_list):
print 'loading file'
jieba.load_userdict(data_path+"jieba_userdict.txt")
stopword_set = text_process.getStopword('../../../data/stopword.txt')
print 'reading file'
infile = open('../data/'+category_path+'.json','rb')
all_app_counter = 0
for row in infile:
json_obj = json.loads(row.strip())
app_id = int(json_obj["soft_id"])
app_name = json_obj["soft_name"]
app_brief = json_obj["soft_brief"]
app_download = int(json_obj["download_times"])
if app_download < 100:
continue
all_app_counter += 1
seg_title_list = jieba.cut(app_name)
seg_brief_list = jieba.cut(app_brief)
for seg_title in seg_title_list:
if text_process.isChinese(seg_title) and seg_title not in stopword_set:
for main_category in category_stat_dict.keys():
if seg_title in category_stat_dict[main_category][0]:
category_stat_dict[main_category][1].add(app_id)
for seg_brief in seg_brief_list:
if text_process.isChinese(seg_brief) and seg_brief not in stopword_set:
for main_category in category_stat_dict.keys():
if seg_brief in category_stat_dict[main_category][0]:
category_stat_dict[main_category][1].add(app_id)
top_coverage_category_info_dict = {}
for iter_num in range(20):
stat(top_coverage_category_info_dict,category_stat_dict,all_app_counter,synonyms_set_list)
def recommendTag(category_name, category_parent_dict, category_child_dict,
category_synonyms_dict, indicator_set, comment_category_set,
ambiguation_dict):
#主类目名称
main_category = category_name
#未被匹配到的app
others_app = {}
outfile_json = open('tag_recommend_result.json', 'wb')
jieba.load_userdict('../../../data/jieba_userdict.txt')
stopword_set = text_process.getStopword('../../../data/stopword.txt')
node_children_dict = rule_base.createNodeChildrenDict(category_child_dict)
candidate_tag_set, candidate_delegate_tag_set = rule_base.getCandidateTag(
main_category, node_children_dict, category_synonyms_dict)
level_category_dict = rule_base.createLevelCategoryDict(
main_category, candidate_tag_set, category_parent_dict,
category_child_dict, category_synonyms_dict)
# level_category_dict[0] = set([main_category])
for level in level_category_dict.keys():
print level
print ' '.join(level_category_dict[level])
match_counter = 0
all_app_counter = 0
#遍历主类目下的app
infile = open('../data/' + category_name + '.json', 'rb')
outfile_match = open('../data/' + category_name + '_match.json', 'wb')
outfile_unmatch = open('../data/' + category_name + '_unmatch.json', 'wb')
for row in infile:
all_app_counter += 1
json_obj = json.loads(row.strip())
app_id = int(json_obj["id"])
app_name = json_obj["title"]
app_brief = json_obj["brief"]
app_download = int(json_obj["download_times"])
app_brief_seg = [
word for word in jieba.cut(app_brief)
if word not in stopword_set and text_process.isChinese(word)
]
app_name_brief = app_name + " " + app_brief
app_name_brief += " " + rule_base.grabEnglish(app_name_brief)
output_dict = {}
output_dict["id"] = app_id
output_dict["content"] = {}
tag_recommend_set = set([])
#情感词匹配，暂时不处理情感词的同义关系
for comment_word in [
comment_word for comment_word in comment_category_set
if comment_word in app_name_brief
]:
output_dict.setdefault("character", []).append(comment_word)
#自下而上匹配
for depth in reversed(range(0, max(level_category_dict.keys()) + 1)):
if depth not in level_category_dict.keys():
continue
current_level_category_set = level_category_dict[depth]
for current_level_category in current_level_category_set:
if current_level_category in app_name_brief and not rule_base.isAmbiguous(
current_level_category, ambiguation_dict,
app_name_brief):
category_delegate = category_synonyms_dict[
current_level_category][0]
tag_recommend_set.add(category_delegate)
#强规则
strong_parent_set = rule_base.getNodeListOnStrongPath(
category_parent_dict[category_delegate],
category_parent_dict, set([]))
tag_recommend_set = tag_recommend_set | (
strong_parent_set & candidate_tag_set)
current_level_unmatch_category_set = current_level_category_set - tag_recommend_set
for unmatch_category in current_level_unmatch_category_set:
if unmatch_category in indicator_set:
continue
unmatch_category = category_synonyms_dict[unmatch_category][0]
unmatch_category_children = node_children_dict[
unmatch_category]
match_children = unmatch_category_children & tag_recommend_set
if len(match_children) >= 3:
tag_recommend_set.add(unmatch_category)
#隐节点
for tag in tag_recommend_set:
if u'(' in tag and u')' in tag:
hidden_node_next_level = rule_base.getNextLevelCategorySet(
category_synonyms_dict, category_child_dict, tag)
for hidden_node_next_level_item in hidden_node_next_level:
hidden_node_next_level_item = category_synonyms_dict[
hidden_node_next_level_item][0]
if hidden_node_next_level_item in tag_recommend_set:
output_dict.setdefault(
tag, []).append(hidden_node_next_level_item)
#去除推导词
tag_recommend_set = tag_recommend_set - indicator_set
#构建输出字典
content = outputJson(main_category, category_parent_dict,
category_child_dict, category_synonyms_dict,
tag_recommend_set)
output_dict['content'] = content
if len(content.keys()) != 0:
outfile_match.write(row)
match_counter += 1
if app_download >= 10000000:
continue
outfile_json.write(
json.dumps(output_dict, ensure_ascii=False) + '\r\n')
else:
outfile_unmatch.write(row)
if app_download <= 500:
continue
others_app.setdefault(app_name,
[app_download, ' '.join(app_brief_seg)])
print "覆盖率: " + str(1.0 * match_counter / all_app_counter)
#剩下没有匹配到的按下载量排序，输出
other_title_fre = {}
sorted_list = sorted(others_app.items(),
key=lambda p: p[1][0],
reverse=True)
outfile_others = open('others.txt', 'wb')
for val in sorted_list:
title_seg = jieba.cut(val[0])
for title in title_seg:
if text_process.isChinese(title) and title not in stopword_set:
other_title_fre.setdefault(title, 0)
other_title_fre[title] += 1
outfile_others.write(val[0] + '<@>' + val[1][1] + '\r\n')
sorted_list = sorted(other_title_fre.items(),
key=lambda p: p[1],
reverse=True)
outfile_others_title = open('others_title.txt', 'wb')
for val in sorted_list:
outfile_others_title.write(val[0] + '<@>' + str(val[1]) + '\r\n')
def getCorpus(category_name):
app_lable_dict = {
10743: 1,
1002128: 1,
47: 1,
498: 1,
550: -1,
48: -1,
490: -1,
761: -1,
101108: -1,
101916: -1
}
x_train = []
y_train = []
x_test = []
jieba.load_userdict('../../../data/jieba_userdict.txt')
stopword_set = text_process.getStopword('../../../data/stopword.txt')
doc_app_id = []
docs = []
id_name_dict = {}
infile = open('corpus/' + category_name + '.json', 'rb')
for row in infile:
json_obj = json.loads(row.strip())
app_id = int(json_obj["id"])
app_name = json_obj["title"]
app_brief = json_obj["brief"]
app_download = int(json_obj["download_times"])
app_brief_seg = [
word for word in jieba.cut(app_name + " " + app_brief)
if word not in stopword_set and text_process.isChinese(word)
]
if len(app_brief_seg) <= 10 and app_download <= 100:
continue
doc_app_id.append(app_id)
id_name_dict[app_id] = app_name
docs.append(app_brief_seg)
dictionary = corpora.Dictionary(docs)
corpus = [dictionary.doc2bow(text) for text in docs]
for i in range(len(corpus)):
doc = corpus[i]
x = [0 for n in range(len(dictionary))]
for val in doc:
x[val[0]] = val[1]
app_id = doc_app_id[i]
if app_id in app_lable_dict.keys():
x_train.append(x)
if app_lable_dict[app_id] == 1:
y_train.append(1)
else:
y_train.append(-1)
else:
x_test.append(x)
return x_train, x_test, y_train, doc_app_id, id_name_dict
def recommendTag(
category_name,
category_parent_dict,
category_child_dict,
category_synonyms_dict,
indicator_set,
comment_category_set,
ambiguation_dict,
):
# 主类目名称
main_category = category_name
# 未被匹配到的app
others_app = {}
outfile_json = open("tag_recommend_result.json", "wb")
jieba.load_userdict("../../../data/jieba_userdict.txt")
stopword_set = text_process.getStopword("../../../data/stopword.txt")
node_children_dict = rule_base.createNodeChildrenDict(category_child_dict)
candidate_tag_set, candidate_delegate_tag_set = rule_base.getCandidateTag(
main_category, node_children_dict, category_synonyms_dict
)
level_category_dict = rule_base.createLevelCategoryDict(
main_category, candidate_tag_set, category_parent_dict, category_child_dict, category_synonyms_dict
)
# level_category_dict[0] = set([main_category])
for level in level_category_dict.keys():
print level
print " ".join(level_category_dict[level])
match_counter = 0
all_app_counter = 0
# 遍历主类目下的app
infile = open("../data/" + category_name + ".json", "rb")
outfile_match = open("../data/" + category_name + "_match.json", "wb")
outfile_unmatch = open("../data/" + category_name + "_unmatch.json", "wb")
for row in infile:
all_app_counter += 1
json_obj = json.loads(row.strip())
app_id = int(json_obj["id"])
app_name = json_obj["title"]
app_brief = json_obj["brief"]
app_download = int(json_obj["download_times"])
app_brief_seg = [
word for word in jieba.cut(app_brief) if word not in stopword_set and text_process.isChinese(word)
]
app_name_brief = app_name + " " + app_brief
app_name_brief += " " + rule_base.grabEnglish(app_name_brief)
output_dict = {}
output_dict["id"] = app_id
output_dict["content"] = {}
tag_recommend_set = set([])
# 情感词匹配，暂时不处理情感词的同义关系
for comment_word in [comment_word for comment_word in comment_category_set if comment_word in app_name_brief]:
output_dict.setdefault("character", []).append(comment_word)
# 自下而上匹配
for depth in reversed(range(0, max(level_category_dict.keys()) + 1)):
if depth not in level_category_dict.keys():
continue
current_level_category_set = level_category_dict[depth]
for current_level_category in current_level_category_set:
if current_level_category in app_name_brief and not rule_base.isAmbiguous(
current_level_category, ambiguation_dict, app_name_brief
):
category_delegate = category_synonyms_dict[current_level_category][0]
tag_recommend_set.add(category_delegate)
# 强规则
strong_parent_set = rule_base.getNodeListOnStrongPath(
category_parent_dict[category_delegate], category_parent_dict, set([])
)
tag_recommend_set = tag_recommend_set | (strong_parent_set & candidate_tag_set)
current_level_unmatch_category_set = current_level_category_set - tag_recommend_set
for unmatch_category in current_level_unmatch_category_set:
if unmatch_category in indicator_set:
continue
unmatch_category = category_synonyms_dict[unmatch_category][0]
unmatch_category_children = node_children_dict[unmatch_category]
match_children = unmatch_category_children & tag_recommend_set
if len(match_children) >= 3:
tag_recommend_set.add(unmatch_category)
# 隐节点
for tag in tag_recommend_set:
if u"(" in tag and u")" in tag:
hidden_node_next_level = rule_base.getNextLevelCategorySet(
category_synonyms_dict, category_child_dict, tag
)
for hidden_node_next_level_item in hidden_node_next_level:
hidden_node_next_level_item = category_synonyms_dict[hidden_node_next_level_item][0]
if hidden_node_next_level_item in tag_recommend_set:
output_dict.setdefault(tag, []).append(hidden_node_next_level_item)
# 去除推导词
tag_recommend_set = tag_recommend_set - indicator_set
# 构建输出字典
content = outputJson(
main_category, category_parent_dict, category_child_dict, category_synonyms_dict, tag_recommend_set
)
output_dict["content"] = content
if len(content.keys()) != 0:
outfile_match.write(row)
match_counter += 1
if app_download >= 10000000:
continue
outfile_json.write(json.dumps(output_dict, ensure_ascii=False) + "\r\n")
else:
outfile_unmatch.write(row)
if app_download <= 500:
continue
others_app.setdefault(app_name, [app_download, " ".join(app_brief_seg)])
print "覆盖率: " + str(1.0 * match_counter / all_app_counter)
# 剩下没有匹配到的按下载量排序，输出
other_title_fre = {}
sorted_list = sorted(others_app.items(), key=lambda p: p[1][0], reverse=True)
outfile_others = open("others.txt", "wb")
for val in sorted_list:
title_seg = jieba.cut(val[0])
for title in title_seg:
if text_process.isChinese(title) and title not in stopword_set:
other_title_fre.setdefault(title, 0)
other_title_fre[title] += 1
outfile_others.write(val[0] + "<@>" + val[1][1] + "\r\n")
sorted_list = sorted(other_title_fre.items(), key=lambda p: p[1], reverse=True)
outfile_others_title = open("others_title.txt", "wb")
for val in sorted_list:
outfile_others_title.write(val[0] + "<@>" + str(val[1]) + "\r\n")
def getTrainTest(category_name,category_parent_dict,category_child_dict,category_synonyms_dict,indicator_set,comment_category_set,ambiguation_dict):
#主类目名称
main_category = u"软件"
jieba.load_userdict('../../../data/jieba_userdict.txt')
stopword_set = text_process.getStopword('../../../data/stopword.txt')
node_children_dict = rule_base.createNodeChildrenDict(category_child_dict)
candidate_tag_set,candidate_delegate_tag_set = rule_base.getCandidateTag(main_category,node_children_dict,category_synonyms_dict)
level_category_dict = rule_base.createLevelCategoryDict(main_category,candidate_tag_set,category_parent_dict,category_child_dict,category_synonyms_dict)
# for level in level_category_dict.keys():
# print level
# print ' '.join(level_category_dict[level])
dictionary = corpora.Dictionary([list(candidate_delegate_tag_set)])
valcabulary_size = len(dictionary)
#遍历主类目下的app
infile = open('../data/'+category_name+'.json','rb')
X_train = []
X_test = []
X_test_info = []
all_counter = 0
train_counter = 0
for row in infile:
all_counter += 1
json_obj = json.loads(row.strip())
app_id = int(json_obj["id"])
app_name = json_obj["title"]
app_brief = json_obj["brief"]
app_tag = json_obj["tags"]
app_download = int(json_obj["download_times"])
app_brief_seg = [word for word in jieba.cut(app_brief) if word not in stopword_set and text_process.isChinese(word)]
app_name_brief = app_name+" "+app_brief
app_name_brief += " "+rule_base.grabEnglish(app_name_brief)
tag_recommend_set = set([])
for tag in candidate_tag_set:
if tag in app_name_brief:
tag_recommend_set.add(category_synonyms_dict[tag][0])
doc = dictionary.doc2bow(list(tag_recommend_set))
x = [0 for i in range(valcabulary_size)]
for val in doc:
index = val[0]
x[index] = val[1]
if u"视频" in app_tag or u"音乐" in app_tag and app_download >= 1000:
train_counter += 1
X_train.append(x)
else:
X_test.append(x)
X_test_info.append([app_name,' '.join(app_brief_seg)])
print 1.0*train_counter/all_counter
return X_train,X_test,X_test_info
def classify(category_name,category_parent_dict,category_child_dict,category_synonyms_dict,indicator_set,comment_category_set,ambiguation_dict):
#主类目名称
main_category = u"软件"
jieba.load_userdict('../../../data/jieba_userdict.txt')
stopword_set = text_process.getStopword('../../../data/stopword.txt')
node_children_dict = rule_base.createNodeChildrenDict(category_child_dict)
candidate_tag_set,candidate_delegate_tag_set = rule_base.getCandidateTag(main_category,node_children_dict,category_synonyms_dict)
level_category_dict = rule_base.createLevelCategoryDict(main_category,candidate_tag_set,category_parent_dict,category_child_dict,category_synonyms_dict)
for level in level_category_dict.keys():
print level
print ' '.join(level_category_dict[level])
#遍历主类目下的app
infile = open('../data/'+category_name+'.json','rb')
outfile_classification = open('../data/'+ category_name+'_classification.json','wb')
for row in infile:
json_obj = json.loads(row.strip())
app_id = int(json_obj["id"])
app_name = json_obj["title"]
app_brief = json_obj["brief"]
app_download = int(json_obj["download_times"])
app_brief_seg = [word for word in jieba.cut(app_brief) if word not in stopword_set and text_process.isChinese(word)]
app_name_brief = app_name+" "+app_brief
app_name_brief += " "+rule_base.grabEnglish(app_name_brief)
tag_recommend_set = set([])
for tag in candidate_tag_set:
if tag in app_name_brief:
tag_recommend_set.add(category_synonyms_dict[tag][0])
if len(level_category_dict[1] & tag_recommend_set) != 0:
candidate_main_level_set = level_category_dict[1] & tag_recommend_set
candidate_main_level_score_dict = {}
for candidate_main_level in candidate_main_level_set:
score = len(node_children_dict[candidate_main_level] & tag_recommend_set)
candidate_main_level_score_dict.setdefault(score,set([])).add(candidate_main_level)
max_score = max(candidate_main_level_score_dict.keys())
if max_score >= 3:
final_category_list = list(candidate_main_level_score_dict[max_score])
if final_category_list[0] != category_name:
outfile_classification.write(str(app_id)+"->"+final_category_list[0]+"->"+app_name+"<@>"+" ".join(app_brief_seg)+'\r\n')
def getCorpus(category_name):
app_lable_dict = {10743:1,1002128:1,47:1,498:1,550:-1,48:-1,490:-1,761:-1,101108:-1,101916:-1}
x_train = []
y_train = []
x_test = []
jieba.load_userdict('../../../data/jieba_userdict.txt')
stopword_set = text_process.getStopword('../../../data/stopword.txt')
doc_app_id = []
docs = []
id_name_dict = {}
infile = open('corpus/'+category_name+'.json','rb')
for row in infile:
json_obj = json.loads(row.strip())
app_id = int(json_obj["id"])
app_name = json_obj["title"]
app_brief = json_obj["brief"]
app_download = int(json_obj["download_times"])
app_brief_seg = [word for word in jieba.cut(app_name+" "+app_brief) if word not in stopword_set and text_process.isChinese(word)]
if len(app_brief_seg) <= 10 and app_download <= 100:
continue
doc_app_id.append(app_id)
id_name_dict[app_id] = app_name
docs.append(app_brief_seg)
dictionary = corpora.Dictionary(docs)
corpus = [dictionary.doc2bow(text) for text in docs]
for i in range(len(corpus)):
doc = corpus[i]
x = [0 for n in range(len(dictionary))]
for val in doc:
x[val[0]] = val[1]
app_id = doc_app_id[i]
if app_id in app_lable_dict.keys():
x_train.append(x)
if app_lable_dict[app_id] == 1:
y_train.append(1)
else:
y_train.append(-1)
else:
x_test.append(x)
return x_train,x_test,y_train,doc_app_id,id_name_dict
def mineKeywordCombination(category_id,query_keyword):
#主类目名称
main_category = idToName(category_id)
jieba.load_userdict('../../../data/jieba_userdict.txt')
stopword_set = text_process.getStopword('../../../data/stopword.txt')
combination_fre_dict = {}
outfile = open('keyword_combination.txt','wb')
#遍历主类目下的app
infile = open('../data/'+str(category_id)+'.json','rb')
for row in infile:
json_obj = json.loads(row.strip())
app_id = int(json_obj["id"])
app_name = json_obj["title"]
app_brief = json_obj["brief"]
app_download = int(json_obj["download_times"])
app_name_seg = [word for word in jieba.cut(app_name) if word not in stopword_set and text_process.isChinese(word)]
app_brief_seg = [word for word in jieba.cut(app_brief) if word not in stopword_set and text_process.isChinese(word)]
app_name_brief = app_name+" "+app_brief
app_name_combination_dict = combineNeighborWord(app_name_seg,query_keyword)
for word in app_name_combination_dict.keys():
combination_fre_dict.setdefault(word,0)
combination_fre_dict[word] += app_name_combination_dict[word]
app_brief_combination_dict = combineNeighborWord(app_brief_seg,query_keyword)
for word in app_brief_combination_dict.keys():
combination_fre_dict.setdefault(word,0)
combination_fre_dict[word] += app_brief_combination_dict[word]
sorted_list = sorted(combination_fre_dict.items(),key=lambda p:p[1],reverse=True)
for val in sorted_list:
if val[1] >= 2:
print val[0]+','+str(val[1])
outfile.write(val[0]+','+str(val[1])+'\r\n')