def gen_zhengzhou_tree(dirname=myconfig.ZZ_STD_ADD,
sav_file=myconfig.zhengzhou_std_word,
sav_file_2=myconfig.zhengzhou_std_tree):
addr_kv_rec = open("./addr_match.txt", 'w+')
print('\n>gen_zhengzhou_tree start')
#pdb.set_trace()
my_tree = trie_tree.Trie()
my_word = trie_tree.Trie()
paths = os.walk(dirname)
sum_lines = []
cnt = 0
for _, _, fs in paths:
for f in fs:
pth = os.path.join(dirname, str(f))
lines = open(pth, 'r').readlines()
np.random.shuffle(lines)
#lines = open(pth,'r').readlines()[:myconfig.TRAIN_DATA]
for line in lines:
if not ',' in line:
continue
_line = line.split(',')[1]
line = utils.pre_trans(_line)
addr_kv_rec.write('%s\t%s\n' % (str(line), str(_line)))
cnt += 1
if cnt % 10000 == 1:
print(cnt)
my_tree.insert(line)
my_word.insert(_line)
utils.save_var(my_word, sav_file)
utils.save_var(my_tree, sav_file_2)
print('\n>my address tree save ok')
addr_kv_rec.close()
def test_format_df():
logger.debug('\n> 树的合并')
from function_ultra import utils
mStandAddrTreeBuilder = StandAddrTreeBuilder() # 实例
my_tree = utils.read_var(myconfig.MY_TREE)
mStandAddrTreeBuilder.format_tree(my_tree.root)
utils.save_var(my_tree, myconfig.MY_TREE)
pdb.set_trace()
logger.debug('\n> 树的合并测试完成')
def gen_address_tree(filename=myconfig.STDTXTPATH, sav_file=myconfig.MY_TREE):
print('\n>gen_address_tree start')
my_tree = trie_tree.Trie()
df = open(filename, 'r')
lines = df.readlines() #pd.read_csv(filename)
for sent in lines:
my_tree.insert(sent)
utils.save_var(my_tree, sav_file)
print('\n>my address tree save ok')
return my_tree
def gen_std_tree_from_dataframe(data_src, sav_file=myconfig.MY_TREE):
# 从dataframe创建标准地址树
print('\n>gen_std_tree_from_dataframe start')
my_tree = trie_tree.Trie()
for item in data_src:
clritem = remove_nan(item)
print(clritem)
pdb.set_trace()
my_tree.part_insert(my_tree.root, clritem)
utils.save_var(my_tree, sav_file)
print('\n>gen_std_tree_from_dataframe ready and save finish')
return myconfig.SUCCESS
def gen_word_tree(filename=myconfig.STDTXTPATH, sav_file=myconfig.MY_WORD):
print('\n>gen_address_tree start')
my_tree = trie_tree.Trie()
df = open(filename, 'r')
lines = df.readlines() #pd.read_csv(filename)
print(len(lines))
for sent in lines:
words = sent.split('/')
for word in words:
my_tree.insert(word)
utils.save_var(my_tree, sav_file)
print('\n>my address tree save ok')
return my_tree
def gen_std_tree(filename=myconfig.STDTXTPATH,
sav_file=myconfig.MY_TREE,
delimeter='/'):
print('\n>gen_std_tree start')
my_tree = trie_tree.Trie()
df = open(filename, 'r')
lines = df.readlines() #pd.read_csv(filename)
for sent in lines:
words = sent.split(delimeter)
my_tree.insert(words)
utils.save_var(my_tree, sav_file)
print('\n>my std tree save ok')
return my_tree
def first_init_DG(self):
my_tree = utils.read_var(myconfig.MY_TREE)
di = nx.DiGraph()
my_tree.trans_tree_2_graph(my_tree.root,di)
utils.save_var(di,myconfig.DIGRAPH)
return my_tree,utils.read_var(myconfig.DIGRAPH)
