post_classification/main.py at master · Nguonchhay/post_classification · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
from functions import *
from operator import itemgetter, attrgetter


# Read from files for more sentences
def get_search_sentences():
    search_sentences = []
    f = open('test.txt')
    if f is not None:
        content = f.read()
        search_sentences = content.splitlines()
    return search_sentences


# search_sentences = get_search_sentences()
# for sentence in search_sentences:
#     features = convert_to_features(dictionary, sentence)
#     result = predict_category(features)
#     print(result[0] + ' => ' + result[1])

# ss = 'កីឡាកររមណីដ្ឋាននៃប្រទេសកម្ពុជានៅខេត្តមណ្ឌលគិរី'
# ss = 'រមណីដ្ឋាន'
# ss = 'រមណីយដ្ឋានធម្មជាតិ'
# ss = 'ធម្មជាតិ'
# ss = 'កីឡាករធម្មជាតិ'
# ss = 'ធម្មជាតិកីឡាករ'
ss = 'afsfsdfsd'
words = ss.split('')

# Clean words
adjust_words = []
for i in range(0, len(words)):
    word = clean_word(words[i])
    if word != '':
        adjust_words.append(word)

words = adjust_words
print(words)

# Do not forget to re-train in case there are new keywords
dictionary = make_keywords_dictionary()
features = sentence_to_features(dictionary, words)
result = predict_category(features)
print('Predict result: ' + str(result[0]) + ' => ' + result[1] + '\n')

if result[0] > 0:
    # Display related posts
    keyword_posts = []
    for keyword in words:
        posts = get_posts_by_category_and_keyword(result[0], keyword)
        keyword_posts.append([len(posts), keyword, posts])

    # sort keyword_posts
    sort_keyword_posts = sorted(keyword_posts, key=itemgetter(0), reverse=True)

    # Display posts
    for sort_keyword_post in sort_keyword_posts:
        print('* ' + sort_keyword_post[1] + ':')
        for post in sort_keyword_post[2]:
            print('\t - ' + str(post[0]) + ' | ' + post[2])

        print('---------------------------------------------------------------------------------------------------------')

    print('\n Update keywords frequency')
    # Update keyword frequency of found category
    for keyword in words:
        print('- ' + keyword)
        update_keyword_frequency(result[0], keyword, True)