def main(category_id):
reload(sys)
sys.setdefaultencoding('utf-8')
file_utils.createDirs(['internal'])
category_set = common.getCandidateCategory(category_id)
inclusionRelation(category_id, category_set)
def main(category_id):
reload(sys)
sys.setdefaultencoding('utf-8')
jieba.load_userdict("../../../data/jieba_userdict.txt")
file_utils.createDirs(['wiki_search'])
category_set = common.getCandidateCategory(category_id)
category_crawl_dict =readJosn(category_id)
clean(category_id,category_crawl_dict,category_set)
def main(category_id):
reload(sys)
sys.setdefaultencoding('utf-8')
jieba.load_userdict("../../../data/jieba_userdict.txt")
file_utils.createDirs(['wiki_search'])
category_set = common.getCandidateCategory(category_id)
category_crawl_dict = readJosn(category_id)
clean(category_id, category_crawl_dict, category_set)
def main(category_path):
reload(sys)
sys.setdefaultencoding('utf-8')
category_path_list = category_path.split('_')
category_id = int(category_path_list[0])
query_category = ""
if len(category_path_list) >= 2:
query_category = category_path_list[-1].decode('utf-8')
main_category_list = [query_category]
file_utils.createDirs(['combine_feature'])
category_set = common.getCandidateCategory(category_id)
combineFeature(category_id, category_path, category_set)
def main(category_path):
reload(sys)
sys.setdefaultencoding('utf-8')
jieba.load_userdict(data_path+"jieba_userdict.txt")
file_utils.createDirs(['wikipedia'])
category_path_list = category_path.split('_')
category_id = int(category_path_list[0])
query_category = ""
if len(category_path_list) >= 2:
query_category = category_path_list[-1].decode('utf-8')
main_category_list = [query_category]
category_set = common.getCandidateCategory(category_id)
extractFeatureFromWikiCategory(category_id,category_path,main_category_list,category_set)
def main(category_path):
reload(sys)
sys.setdefaultencoding('utf-8')
jieba.load_userdict(data_path + "jieba_userdict.txt")
file_utils.createDirs(['wikipedia'])
category_path_list = category_path.split('_')
category_id = int(category_path_list[0])
query_category = ""
if len(category_path_list) >= 2:
query_category = category_path_list[-1].decode('utf-8')
main_category_list = [query_category]
category_set = common.getCandidateCategory(category_id)
extractFeatureFromWikiCategory(category_id, category_path,
main_category_list, category_set)
def main(category_path):
reload(sys)
sys.setdefaultencoding('utf-8')
print '-loading preparation file'
jieba.load_userdict(data_path+"jieba_userdict.txt")
app_tag_dict = pickle.load(open(data_path+'app_tag.dict','rb'))
app_category_dict = pickle.load(open(data_path+'app_category.dict','rb'))
file_utils.createDirs(['tag_tf','title_tf'])
category_path_list = category_path.split('_')
category_id = int(category_path_list[0])
query_category = ""
if len(category_path_list) >= 2:
query_category = category_path_list[-1].decode('utf-8')
category_set = common.getCandidateCategory(category_id)
tf(category_id,category_path,query_category,category_set,app_category_dict,app_tag_dict)
def main(category_path):
reload(sys)
sys.setdefaultencoding('utf-8')
print '-loading preparation file'
jieba.load_userdict(data_path + "jieba_userdict.txt")
app_tag_dict = pickle.load(open(data_path + 'app_tag.dict', 'rb'))
app_category_dict = pickle.load(open(data_path + 'app_category.dict',
'rb'))
file_utils.createDirs(['tag_tf', 'title_tf'])
category_path_list = category_path.split('_')
category_id = int(category_path_list[0])
query_category = ""
if len(category_path_list) >= 2:
query_category = category_path_list[-1].decode('utf-8')
category_set = common.getCandidateCategory(category_id)
tf(category_id, category_path, query_category, category_set,
app_category_dict, app_tag_dict)
