File size: 2,596 Bytes
8810d44
f462bd2
4ff8b83
 
7676e0a
8810d44
86f6efe
f462bd2
 
 
 
 
 
 
17eec93
f462bd2
 
17eec93
f462bd2
 
17eec93
f462bd2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17eec93
f462bd2
 
17eec93
f462bd2
e941c48
f462bd2
 
b213fb9
 
e941c48
0c235c9
86f6efe
 
 
4ff8b83
86f6efe
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
import gradio as gr
import random

import fomula
from utils import *

def final_result(input_text):
    total_change = 0
    num_change = 0
    list_do = random.sample(range(10), 10)
    input_text_process = input_text
    for i in list_do:
        if i == 0:
            ##character_replacement
            input_text_process, num_change = character_replacement(input_text_process, total_change / len(input_text), error_rate=0.01)
        elif i == 1:
            ##character_insertion
            input_text_process, num_change = character_insertion(input_text_process,total_change / len(input_text), error_rate=0.01)
        elif i == 2:
            ##character_deletion
            input_text_process, num_change = character_deletion(input_text_process,total_change / len(input_text), error_rate=0.01)
        elif i == 3:
            ##character_transposition
            input_text_process, num_change = character_transposition(input_text_process,total_change / len(input_text), error_rate=0.01)
        elif i == 4:
            ##homophone_replacement
            input_text_process, num_change = homophone_replacement(input_text_process,total_change / len(input_text), error_rate=0.01)
        elif i == 5:
            ## common_misspelling_replacement
            input_text_process, num_change = common_misspelling_replacement(input_text_process,total_change / len(input_text), error_rate=0.01)
        elif i == 6:
            ##similar_character_replacement
            input_text_process, num_change = similar_character_replacement(input_text_process,total_change / len(input_text), error_rate=0.01)
        elif i == 7:
            ##random_space_insertion
            input_text_process, num_change = random_space_insertion(input_text_process,total_change / len(input_text), error_rate=0.01)
        elif i == 8:
            ##random_space_removal
            input_text_process, num_change = random_space_removal(input_text_process, total_change / len(input_text), error_rate=0.01)
        elif i == 9:
            ##remove_vietnamese_accents
            input_text_process, num_change = remove_vietnamese_accents(input_text_process, total_change / len(input_text), error_rate=0.01)
        total_change = total_change + num_change

    print("Total change: ", total_change)
    print("Tỷ lệ", total_change / len(input_text))

    string_text_response = input_text_process
    return str(string_text_response)

demo = gr.Interface(fn=final_result, inputs="textbox", outputs="textbox")

if __name__ == "__main__":
    print(fomula.AP_fomula(error_rate=0.12))
    demo.launch()