NLP/nlp_xiaojiang
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix sample

Browse Source
This commit is contained in:
yongzhuo 2021-04-16 22:37:04 +08:00
parent da4cba7fb8
commit d7ee3fd6cc
3 changed files with 60 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
AugmentText/augment_translate/translate_web/translate_google.py
View File

@ -4,14 +4,23 @@
# @author :Mo
# @function :回译调用谷歌翻译，模拟google token访问
# 适配linux
import sys
import os
path_root = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../.."))
sys.path.append(path_root)
print(path_root)
import logging as logger
import urllib.parse as parse
import execjs
import requests
from nlp_xiaojiang.conf.augment_constant import language_short_google
from nlp_xiaojiang.utils.text_tools import judge_translate_english
from conf.augment_constant import language_short_google
from utils.text_tools import judge_translate_english
class GoogleToken:

30
ChatBot/chatbot_search/chatbot_sentence_vec_by_char.py
View File

@ -4,7 +4,14 @@
# @author :Mo
# @function :chatbot based search, encode sentence_vec by char
# 适配linux
import sys
import os
path_root = os.path.abspath(os.path.join(os.path.dirname(__file__), "../.."))
sys.path.append(path_root)
print(path_root)
import pickle
import gensim
@ -12,10 +19,10 @@ import numpy as np
from gensim import matutils
from numpy import float32 as numpy_type
from nlp_xiaojiang.conf.path_config import matrix_ques_part_path_char
from nlp_xiaojiang.conf.path_config import projectdir, chicken_and_gossip_path
from nlp_xiaojiang.conf.path_config import w2v_model_char_path
from nlp_xiaojiang.utils.text_tools import txtRead, getChinese
from conf.path_config import matrix_ques_part_path_char
from conf.path_config import projectdir, chicken_and_gossip_path
from conf.path_config import w2v_model_char_path
from utils.text_tools import txtRead, getChinese
def load_word2vec_model(path, bin=False, limit=None):
@ -143,6 +150,21 @@ if __name__ == '__main__':
# 标准问句矩阵初始化和预处理
matrix_org_norm, matrix_org_index, top_vec = basic_questions_matrix_init(matrix_ques, top_vec=20)
### 测试一个例子
ques_clean = getChinese("小姜机器人是谁呀")
char_list = [ques_char for ques_char in ques_clean]
sentence_vec = question_encoding(word2vec_model, char_list)
top_20_qid = calculate_text_similar(sentence_vec, matrix_org_norm, matrix_org_index, top_vec=top_vec)
try:
print("小姜机器人: " + syn_qa_dails[top_20_qid[0][0]].strip().split("\t")[1])
print([(syn_qa_dails[top_20_qid[i][0]].strip().split("\t")[0],
syn_qa_dails[top_20_qid[i][0]].strip().split("\t")[1]) for i in range(len(top_20_qid))])
except Exception as e:
# 有的字符可能打不出来
print(str(e))
while True:
print("你问: ")
ques_ask = input()

27
ChatBot/chatbot_search/chatbot_sentence_vec_by_word.py
View File

@ -5,7 +5,14 @@
# @function :chatbot based search, encode sentence_vec by word
# 适配linux
import sys
import os
path_root = os.path.abspath(os.path.join(os.path.dirname(__file__), "../.."))
sys.path.append(path_root)
print(path_root)
import pickle
import gensim
@ -15,10 +22,10 @@ import numpy as np
from gensim import matutils
from numpy import float32 as numpy_type
from nlp_xiaojiang.conf.path_config import matrix_ques_part_path
from nlp_xiaojiang.conf.path_config import projectdir, chicken_and_gossip_path
from nlp_xiaojiang.conf.path_config import w2v_model_merge_short_path, w2v_model_wiki_word_path
from nlp_xiaojiang.utils.text_tools import txtRead, getChinese
from conf.path_config import matrix_ques_part_path
from conf.path_config import projectdir, chicken_and_gossip_path
from conf.path_config import w2v_model_merge_short_path, w2v_model_wiki_word_path
from utils.text_tools import txtRead, getChinese
def load_word2vec_model(path, bin=False, limit=None):
@ -203,6 +210,18 @@ if __name__ == '__main__':
# 标准问句矩阵初始化和预处理
matrix_org_norm, matrix_org_index, top_vec = basic_questions_matrix_init(matrix_ques, top_vec=20)
ques_clean = getChinese("小姜机器人叫什么呀")
word_list, flag_list = word_flag_cut(ques_clean)
sentence_vec = basic_questions_encoding(word2vec_model, word_list, flag_list)
top_20_qid = calculate_text_similar(sentence_vec, matrix_org_norm, matrix_org_index, top_vec=top_vec)
try:
print("小姜机器人: " + syn_qa_dails[top_20_qid[0][0]].strip().split("\t")[1])
print([(syn_qa_dails[top_20_qid[i][0]].strip().split("\t")[0],
syn_qa_dails[top_20_qid[i][0]].strip().split("\t")[1]) for i in range(len(top_20_qid))])
except Exception as e:
# 有的字符可能打不出来
print(str(e))
while True:
print("你: ")
ques_ask = input()