app.py

import streamlit as st
from surprise import Dataset, Reader, SVD
from surprise.model_selection import train_test_split
import pandas as pd

# Sample user-item rating data for collaborative filtering
data = {'user_id': [1, 1, 1, 2, 2, 3, 3, 4, 4],
        'item_id': [1, 2, 3, 1, 4, 2, 3, 1, 4],
        'rating': [5, 3, 4, 4, 5, 5, 2, 4, 4]}

df = pd.DataFrame(data)
reader = Reader(rating_scale=(1, 5))
dataset = Dataset.load_from_df(df[['user_id', 'item_id', 'rating']], reader)
trainset, testset = train_test_split(dataset, test_size=0.25)

algo = SVD()
algo.fit(trainset)

# UI Elements
st.title("🌟 Personalized Entertainment Recommendations")

# Input for user genre preference
user_genre = st.selectbox(
    "Choose your favorite genre", 
    ["Action 🎬", "Drama 🎭", "Comedy 😂", "Sci-Fi 🚀"]
)

# Define genre mapping
genre_mapping = {
    "Action 🎬": 1,
    "Drama 🎭": 2,
    "Comedy 😂": 3,
    "Sci-Fi 🚀": 4
}

# Example mapping of genre to item_id
recommendations = {
    1: ["Die Hard", "Mad Max"], 
    2: ["The Shawshank Redemption", "Forrest Gump"],
    3: ["Superbad", "Step Brothers"], 
    4: ["Inception", "Interstellar"]
}

# Provide recommendation based on collaborative filtering
selected_genre_id = genre_mapping[user_genre]

# Predict ratings for the selected genre items
predicted_ratings = [(id, algo.predict(5, id).est) for id in [1, 2, 3, 4] if id == selected_genre_id]

# Sort recommendations by predicted ratings
predicted_ratings.sort(key=lambda x: x[1], reverse=True)

st.subheader("🎯 Recommendations for you:")
for item_id, rating in predicted_ratings:
    for rec in recommendations[item_id]:
        st.write(f"{rec} - Predicted Rating: {rating:.2f} ⭐")

# Provide visual feedback for actions
if predicted_ratings:
    st.button("👍 Like", key="like_button")
    st.button("👎 Dislike", key="dislike_button")
else:
    st.write("No recommendations available for your selected genre.")