Spaces:
Sleeping
Sleeping
File size: 2,100 Bytes
fe5faf3 |
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 |
import streamlit as st
import pickle
import re
import string
import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.stem.porter import PorterStemmer
stemmer = PorterStemmer()
st.set_page_config(
page_title="NLP WEB APP"
)
st.title("LANGUAGE DETECTOR MODEL")
st.sidebar.success("Select a page above")
nltk.download('stopwords')
nltk.download('punkt')
def preprocess(text):
text = text.lower()
text = re.sub(r'\d+', '', text)
translator = str.maketrans('', '', string.punctuation)
text = text.translate(translator)
stop_words = set(stopwords.words("english"))
word_tokens = word_tokenize(text)
filtered_text = [word for word in word_tokens if word not in stop_words]
stems = [stemmer.stem(word) for word in filtered_text]
preprocessed_text = ' '.join(stems)
return preprocessed_text
cv = pickle.load(open('language-detector-models/vectorizer.pkl','rb'))
model = pickle.load(open('language-detector-models/model.pkl','rb'))
message= st.text_input("ENTER THE MESSAGE")
if st.button("PREDICT"):
# PREPROCESS
transformed_text = preprocess(message)
# VECTORIZE
vector_input = cv.transform([message])
# PREDICTION
result = model.predict(vector_input)[0]
# DISPLAY
if result==0:
st.header("ARABIC")
elif result==1:
st.header("DANISH")
elif result==2:
st.header("DUTCH")
elif result==3:
st.header("ENGLISH")
elif result==4:
st.header("FRENCH")
elif result==5:
st.header("GERMAN")
elif result==6:
st.header("GREEK")
elif result==7:
st.header("HINDI")
elif result==8:
st.header("ITALIAN")
elif result==9:
st.header("KANNADA")
elif result==10:
st.header("MALYALAM")
elif result==11:
st.header("PORTUGESE")
elif result==12:
st.header("RUSSIAN")
elif result==13:
st.header("SPANISH")
elif result==14:
st.header("SWEDISH")
elif result==15:
st.header("TAMIL")
else:
st.header("TURKISH") |