import streamlit as st 
import pickle 
import numpy as np
import pandas as pd 
import nltk
import re
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
from nltk.stem import WordNetLemmatizer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer

model = pickle.load(open('spam_model.sav','rb'))
tf = pickle.load(open('vectorizer.pkl','rb'))

st.title('Spam classifier')
input = st.text_area('Enter sms here')
ps = PorterStemmer()
review = re.sub('[^a-zA-Z]', ' ', input) # to remove punctuation
review = review.lower()
review = review.split()
review = [ps.stem(word) for word in review if not word in stopwords.words('english')]
review = ' '.join(review)


X = tf.fit_transform(review).toarray()



if input:
    output = model.predict(X)
    st.json(output)