Add dataset download functionality

.gitignore

@@ -0,0 +1 @@
+song_dataset.csv

README.md

@@ -1,6 +1,6 @@
 ---
 title: Not Spotify But Close
-emoji: 📊
+emoji: 🎵
 colorFrom: blue
 colorTo: pink
 sdk: gradio
@@ -8,7 +8,33 @@ sdk_version: 5.5.0
 app_file: app.py
 pinned: false
 license: mit
-short_description: 🎵 Your Personal Music Matchmaker🎧
+short_description: Your Personal Music Matchmaker 🎧
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🎵 Not Spotify But Close
+
+Ever wished you had a friend with impeccable music taste who just *gets* your vibe? Meet your AI-powered music recommendation companion!
+
+## 🎧 What's Cooking?
+Using the power of collaborative filtering, we analyze over 100,000 real listening patterns to suggest music that's perfectly paired with your taste.
+
+## 🎮 How to Use
+1. 🔍 Search for songs you love
+2. ✨ Pick up to 5 of your favorites
+3. 🎯 Hit "Get Recommendations" and watch the magic happen!
+
+## 🎼 Features
+- Lightning-fast song search
+- Detailed recommendations including artist and release year
+- Clean, intuitive interface
+- No account needed - just search and discover!
+
+## 🛠 Technical Stack
+- Built with Python, Gradio, and scikit-learn
+- Powered by collaborative filtering algorithms
+- Trained on real-world listening data
+
+Made with ❤️ for music lovers, by music lovers.
+
+---
+*Note: This is a demo project and not affiliated with any music streaming service.*

app.py

@@ -3,7 +3,18 @@ import numpy as np
 import pandas as pd
 from sklearn.metrics.pairwise import cosine_similarity
 import gradio as gr
+import gdown
+import os
 
+# Add this at the start of your script
+def download_dataset():
+    if not os.path.exists('song_dataset.csv'):
+        # Replace with your Google Drive file ID
+        url = "https://docs.google.com/spreadsheets/d/1MKqJmWQ1PxKHDkpIdbQEeTz_ohpjOsYPyVp6esEZsq4/"
+        gdown.download(url, 'song_dataset.csv', quiet=False)
+
+# Add this line before loading the dataset
+download_dataset()
 # Load the data
 df = pd.read_csv('song_dataset.csv')
 

requirements.txt

@@ -0,0 +1,8 @@
+numpy>=1.21.0
+pandas>=1.3.0
+matplotlib>=3.4.0
+seaborn>=0.11.0
+plotly>=5.0.0
+scikit-learn>=0.24.0
+gradio>=5.5.0
+gdown>=4.7.0