app.py

import streamlit as st
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer
import pandas as pd
import numpy as np
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score


df = pd.read_csv("spam.csv")
st.title(":red[Email Spam or Ham Classification]")

x = df["Message"]
y = df["Category"]
ham = df[df["Category"] == "ham"]


bow = CountVectorizer(stop_words = "english")

final_X = pd.DataFrame(bow.fit_transform(x).toarray(), columns = bow.get_feature_names_out())

X_train, X_test, y_train, y_test = train_test_split(final_X, y , test_size= 0.25, random_state = 23)

nav_base = MultinomialNB()

nav_base.fit(X_train, y_train)

y_pred = nav_base.predict(X_test)

res = st.button("predict_score")
if res:
    st.write(accuracy_score(y_test,y_pred))
    st.snow()

input = st.text_input("enter email")

def fun(email):
    data = bow.transform([email]).toarray()
    st.write(nav_base.predict(data)[0])

if st.button("predict"):
    fun(input)
    st.balloons()