import streamlit as st
import pandas as pd
import re
import string
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.model_selection import train_test_split

# Page config
st.set_page_config(page_title="SMS Spam Detector", layout="centered")
st.title("📩 SMS Spam Detection App")
st.markdown("🔍 Enter a message below to check if it's **Spam** or **Not Spam (Ham)**")

# --- Load dataset ---
csv_url = "https://huggingface.co/spaces/MLDeveloper/Spam_SMS_Detection/resolve/main/spam.csv" 
try:
    df = pd.read_csv(csv_url, encoding='latin-1')[['v1', 'v2']]
    df.columns = ['label', 'message']
    df['label'] = df['label'].map({'ham': 0, 'spam': 1})
except Exception as e:
    st.error(f"Failed to load CSV: {e}")
    st.stop()

# --- Text Cleaning Function ---
def clean_text(text):
    text = text.lower()
    text = re.sub(r"http\S+|www\S+|https\S+", '', text, flags=re.MULTILINE)
    text = re.sub(r'\@w+|\#','', text)
    text = re.sub(r'[^\w\s]', '', text)
    text = re.sub(r'\d+', '', text)
    text = text.translate(str.maketrans('', '', string.punctuation))
    return text.strip()

df['cleaned'] = df['message'].apply(clean_text)

# --- Train model ---
X = df['cleaned']
y = df['label']

vectorizer = TfidfVectorizer()
X_vec = vectorizer.fit_transform(X)

model = MultinomialNB()
model.fit(X_vec, y)

# --- Prediction Function ---
def predict_spam(message):
    cleaned = clean_text(message)
    vector = vectorizer.transform([cleaned])
    prediction = model.predict(vector)
    return "Spam" if prediction[0] == 1 else "Not Spam"

# --- UI ---
user_input = st.text_area("✉️ Enter your SMS message here:")

if st.button("Check Message"):
    if user_input.strip() == "":
        st.warning("⚠️ Please enter a valid message.")
    else:
        result = predict_spam(user_input)
        if result == "Spam":
            st.error("🚫 This message is classified as **SPAM**.")
        else:
            st.success("✅ This message is classified as **NOT SPAM (HAM)**.")

# Optional: View CSV
with st.expander("📄 View sample dataset (CSV)"):
    st.dataframe(df[['label', 'message']].head())

st.markdown("---")
st.markdown("🔒 **Note**: Model is trained in real-time from CSV and not saved for reuse. Ideal for demo purposes.**")