import streamlit as st
import pandas as pd
import numpy as np
import sklearn
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score

df = pd.read_csv(r"C:\Users\rajus\Downloads\spam.csv")


st.title("Identifying Spam and Ham Emails")

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

bow = CountVectorizer(stop_words="english")
final_data = 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_data, y, test_size=0.2, random_state=20)


models = {
    "Naive Bayes": MultinomialNB(),
    "KNN": KNeighborsClassifier(),
    "Logistic Regression": LogisticRegression(),
    "Decision Tree": DecisionTreeClassifier(),
    "SVM": SVC()
}

model_choice = st.selectbox("Choose a Classification Algorithm", list(models.keys()))


obj = models[model_choice]
obj.fit(x_train, y_train)
y_pred = obj.predict(x_test)
accuracy = accuracy_score(y_test, y_pred)


if st.button("Show Accuracy"):
    st.write(f"Accuracy of {model_choice}: {accuracy:.4f}")

email_input = st.text_input("Enter an Email for Prediction")


def predict_email(email):
    data = bow.transform([email]).toarray() 
    prediction = obj.predict(data)[0]
    st.write(f"Prediction: {prediction}")


if st.button("Predict Email"):
    if email_input:
        predict_email(email_input)
    else:
        st.write(":red[Please enter an email to classify]")