Hugging Face's logo

AVAIYA
/
python-test

Model card Files Community
python-test
File size: 4,663 Bytes 
e228e17
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
 
#pip install GoogleNews
#pip install --upgrade GoogleNews

import streamlit as st
from GoogleNews import GoogleNews
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
import pandas as pd
import numpy as np
import string
import re
from nltk.corpus import stopwords
from sklearn.metrics.pairwise import cosine_similarity
import sklearn
import time


googlenews = GoogleNews()
googlenews = GoogleNews(lang='ar')
googlenews.clear()



st.write("""
Arabic Fake News Detection System
A system designed as a part of master project
done by Reem AlFouzan
Supervised by : Dr, Abdulla al mutairi
""")
#df = pd.read_csv('News.csv')
text_input = st.text_input (''' **Enter the text** ''')
if len(text_input) != 0:
    inputt = []
    inputt = pd.DataFrame([text_input])

    googlenews.search(inputt.iloc[0,0])
    googlenews.get_news(inputt.iloc[0,0])

    result_0 = googlenews.page_at(1)
    print("Data")
    print(result_0, "data 2")
    # time.sleep(100)
    if len(result_0) == 0:
      desc_1 = ['لا يوجد نتائج للخبر ']
      link_1 = ['لا يوجد مصدر']
    if len(result_0) != 0:
        desc_1 = googlenews.get_texts()
        link_1 = googlenews.get_links()
        for i in list(range(2, 70)):
    
            result = googlenews.page_at(i)
            desc = googlenews.get_texts()
            link = googlenews.get_links()
    
            desc_1 = desc_1 + desc
            link_1 = link_1 + link
    
    column_names = ["text", 'link']
    df = pd.DataFrame(columns = column_names)
    
    df['text'] = desc_1
    df['link'] = link_1
    
    for letter in '#.][!XR':
        df['text'] = df['text'].astype(str).str.replace(letter,'')
        inputt[0] = inputt[0].astype(str).str.replace(letter,'')
        
    arabic_punctuations = '''`÷×؛<>_()*&^%][ـ،/:"؟.,'{}~¦+|!”…“–ـ'''
    english_punctuations = string.punctuation
    punctuations_list = arabic_punctuations + english_punctuations
    
    def remove_punctuations(text):
        translator = str.maketrans('', '', punctuations_list)
        return text.translate(translator)
    
    def normalize_arabic(text):
        text = re.sub("[إأآا]", "ا", text)
        text = re.sub("ى", "ي", text)
        text = re.sub("ة", "ه", text)
        text = re.sub("گ", "ك", text)
        return text
        
        
    def remove_repeating_char(text):
        return re.sub(r'(.)\1+', r'\1', text)  
            
    def processPost(text): 
        
        #Replace @username with empty string
        text = re.sub('@[^\s]+', ' ', text)
            
        #Convert www.* or https?://* to " "
        text = re.sub('((www\.[^\s]+)|(https?://[^\s]+))',' ',text)
            
        #Replace #word with word
        text = re.sub(r'#([^\s]+)', r'\1', text)
        
        # remove punctuations
        text= remove_punctuations(text)
            
        # normalize the text
        text= normalize_arabic(text)
            
        # remove repeated letters
        text=remove_repeating_char(text)
            
        return text  
            
        
    df['text'] = df['text'].apply(lambda x: processPost(x))
    inputt[0] = inputt[0].apply(lambda x: processPost(x))
        
    st.markdown(f"my input is : { inputt.iloc[0,0] }")
    #input=input.apply(lambda x: processPost(x))
        
        
    vectorizer = TfidfVectorizer()
    vectors = vectorizer.fit_transform(df['text'])
        
    text_tfidf = pd.DataFrame(vectors.toarray())
        
    traninput = vectorizer.transform(inputt[0])
    traninput = traninput.toarray()
    cosine_sim = cosine_similarity(traninput,text_tfidf)
    top = np.max(cosine_sim)
        
        
    if top >= .85 :
        prediction = 'الخبر صحيح'
    elif (top < .85) and (top >= .6) :
        prediction = 'الخبر مظلل '
    elif top < .6 :
        prediction = 'الخبر كاذب '
        
        
    st.markdown(f"most similar news is: { df['text'].iloc[np.argmax(np.array(cosine_sim[0]))] }")
    st.markdown(f"Source url : {df['link'].iloc[np.argmax(np.array(cosine_sim[0]))]}")
    st.markdown(f"Credibility rate : { np.max(cosine_sim)}")
    st.markdown(f"system prediction: { prediction}")
    df.to_csv('Students.csv', sep ='\t')    
    
    
st.sidebar.markdown('مواقع اخباريه معتمده ')
st.sidebar.markdown("[العربية](https://www.alarabiya.net/)")
st.sidebar.markdown("[الجزيرة نت](https://www.aljazeera.net/news/)")
st.sidebar.markdown("[وكالة الانباء الكويتية](https://www.kuna.net.kw/Default.aspx?language=ar)")
    
    #st.markdown('test')