File size: 704 Bytes
70e2bb0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import pickle
import re
from pathlib import Path

__version__ = "0.1.0"

BASE_DIR = Path(__file__).resolve(strict=True).parent


with open(f"{BASE_DIR}/trained_pipeline-{__version__}.pkl", "rb") as f:
    model = pickle.load(f)


classes = [
    "Arabic",
    "Danish",
    "Dutch",
    "English",
    "French",
    "German",
    "Greek",
    "Hindi",
    "Italian",
    "Kannada",
    "Malayalam",
    "Portugeese",
    "Russian",
    "Spanish",
    "Sweedish",
    "Tamil",
    "Turkish",
]


def predict_pipeline(text):
    text = re.sub(r'[!@#$(),\n"%^*?\:;~`0-9]', " ", text)
    text = re.sub(r"[[]]", " ", text)
    text = text.lower()
    pred = model.predict([text])
    return classes[pred[0]]