app.py

import pandas as pd
import gradio as gr

# Load the dataset
df = pd.read_csv("TeluguMovies_dataset.csv")

# Get unique genres
genres = df['Genre'].unique().tolist()

def recommend_movie(genre, min_rating):
    # Filter the movies by genre and rating
    if 'Genre' not in df.columns or 'Rating' not in df.columns:
        return "Dataset is missing 'Genre' or 'Rating' columns."

    recommendations = df[df['Genre'].str.contains(genre, case=False, na=False) & (df['Rating'] >= min_rating)]
    if recommendations.empty:
        return "No movies found with the specified criteria."
    
    # Sort by rating
    recommendations = recommendations.sort_values(by='Rating', ascending=False)
    
    # Format the response
    response = []
    for idx, row in recommendations.iterrows():
        response.append(f"**{row['Movie']} ({row['Year']})**\nRating: {row['Rating']}\nOverview: {row['Overview']}\n")
    
    return "\n\n".join(response)

# Define the Gradio interface
iface = gr.Interface(
    fn=recommend_movie,
    inputs=[
        gr.Dropdown(choices=genres, label="Genre"),
        gr.Slider(1.0, 10.0, step=0.1, value=7.0, label="Minimum Rating")
    ],
    outputs="markdown",
    title="Movie Recommendation Chatbot",
    description="Get movie recommendations based on genre and rating."
)

# Launch the interface
iface.launch()