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")