Spaces:
Sleeping
Sleeping
File size: 1,173 Bytes
75f6b3f |
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 |
import streamlit as st
import pickle
import string
from nltk.corpus import stopwords
import nltk
nltk.download('punkt')
nltk.download('stopwords')
from nltk.stem.porter import PorterStemmer
ps=PorterStemmer()
def transform_text(text):
text=text.lower()
text=nltk.word_tokenize(text)
y=[]
for i in text:
if i.isalnum():
y.append(i)
text=y[:]
y.clear()
for i in text:
if i not in stopwords.words('english') and i not in string.punctuation:
y.append(i)
text=y[:]
y.clear()
for i in text:
y.append(ps.stem(i))
return " ".join(y)
tfidf=pickle.load(open('vectorizer.pkl','rb'))
model=pickle.load(open('model.pkl','rb'))
st.title("EMAIL/SMS SPAM CLASSIFIER")
#follow documentation for syntax and fn
input_sms=st.text_input("Enter the message :)")
if st.button('predict'):
#1.preprocess
transformed_sms=transform_text(input_sms)
#2.vectorize
vector_input=tfidf.transform([transformed_sms])
#3.predict
result=model.predict(vector_input)[0]
#4.display
if result==1:
st.header("make some friends loner")
else:
st.header("not spam uwu")
|