import streamlit as st
import pickle
import re
import nltk
import numpy as np

from nltk.corpus import stopwords
from textblob import TextBlob

st.title("YouTube Comment Analysis")
st.video("https://www.youtube.com/watch?v=iCvmsMzlF7o")

nltk.download('stopwords')
stop_words = set(stopwords.words('english'))

# Load saved model and vectorizer
with open('sentiment_model.pkl', 'rb') as f:
    model = pickle.load(f)

with open('tfidf_vectorizer.pkl', 'rb') as f:
    vectorizer = pickle.load(f)

# Text cleaning function
def clean_text(text):
    text = text.lower()
    text = re.sub(r"http\S+|www\S+|https\S+", '', text)
    text = re.sub(r'[^a-z\s]', '', text)
    text = re.sub(r'\s+', ' ', text).strip()
    text = ' '.join([word for word in text.split() if word not in stop_words])
    return text

# Streamlit UI
st.title("🎯 YouTube Comment Sentiment Classifier")

comment_input = st.text_area("Enter your YouTube comment here:")

if st.button("Predict Sentiment"):
    if comment_input.strip() == "":
        st.warning("Please enter a comment.")
    else:
        cleaned = clean_text(comment_input)
        features = vectorizer.transform([cleaned])
        prediction = model.predict(features)[0]

        st.subheader("🔍 Sentiment Prediction:")
        if prediction == "Positive":
            st.success("😊 Positive Comment")
        elif prediction == "Negative":
            st.error("😠 Negative Comment")
        else:
            st.info("😐 Neutral Comment")