third_codes/jieba
1
0
Fork 0
mirror of https://github.com/fxsjy/jieba.git synced 2025-07-10 00:01:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

make extract_tags behavior compatiable with previous version

Browse Source
This commit is contained in:
fxsjy 2015-02-14 21:23:58 +08:00
parent abcaf3e475
commit 49657c976d
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
jieba/analyse/__init__.py
View File

@ -60,14 +60,14 @@ def set_stop_words(stop_words_path):
for line in lines: for line in lines:
STOP_WORDS.add(line) STOP_WORDS.add(line)
def extract_tags(sentence, topK=20, withWeight=False, allowPOS=['ns', 'n', 'vn', 'v']): def extract_tags(sentence, topK=20, withWeight=False, allowPOS=[]):
""" """
Extract keywords from sentence using TF-IDF algorithm. Extract keywords from sentence using TF-IDF algorithm.
Parameter: Parameter:
- topK: return how many top keywords. `None` for all possible words. - topK: return how many top keywords. `None` for all possible words.
- withWeight: if True, return a list of (word, weight); - withWeight: if True, return a list of (word, weight);
if False, return a list of words. if False, return a list of words.
- allowPOS: the allowed POS list eg. ['ns', 'n', 'vn', 'v']. - allowPOS: the allowed POS list eg. ['ns', 'n', 'vn', 'v','nr'].
if the POS of w is not in this list,it will be filtered. if the POS of w is not in this list,it will be filtered.
""" """
global STOP_WORDS, idf_loader global STOP_WORDS, idf_loader