1+ # -*- coding: utf-8 -*-
2+
3+ # Copyright © 2017 Roberto Alsina and others.
4+
5+ # Permission is hereby granted, free of charge, to any
6+ # person obtaining a copy of this software and associated
7+ # documentation files (the "Software"), to deal in the
8+ # Software without restriction, including without limitation
9+ # the rights to use, copy, modify, merge, publish,
10+ # distribute, sublicense, and/or sell copies of the
11+ # Software, and to permit persons to whom the Software is
12+ # furnished to do so, subject to the following conditions:
13+ #
14+ # The above copyright notice and this permission notice
15+ # shall be included in all copies or substantial portions of
16+ # the Software.
17+ #
18+ # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
19+ # KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
20+ # WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
21+ # PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS
22+ # OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
23+ # OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
24+ # OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
25+ # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
26+
27+ from __future__ import print_function , unicode_literals
28+
29+ import gensim
30+
31+ from nikola .plugin_categories import Task
32+
33+ class Similarity (Task ):
34+ """Calculate post similarity."""
35+ name = "similarity"
36+
37+ def set_site (self , site ):
38+ self .site = site
39+
40+ def gen_tasks (self ):
41+ """Build similarity data for each post."""
42+ self .site .scan_posts ()
43+
44+ texts = []
45+
46+ for p in self .site .timeline :
47+ texts .append (p .text (strip_html = True ).lower ().split ())
48+
49+ dictionary = gensim .corpora .Dictionary (texts )
50+ corpus = [dictionary .doc2bow (text ) for text in texts ]
51+ lsi = gensim .models .LsiModel (corpus , id2word = dictionary , num_topics = 2 )
52+ index = gensim .similarities .MatrixSimilarity (lsi [corpus ])
53+
54+ for i , post in enumerate (self .site .timeline ):
55+ doc = texts [i ]
56+ vec_bow = dictionary .doc2bow (doc )
57+ vec_lsi = lsi [vec_bow ]
58+ sims = index [vec_lsi ]
59+ sims = sorted (enumerate (sims ), key = lambda item : - item [1 ])
60+ print (i , sims [:10 ])
61+
62+
0 commit comments