Upload 2 files

app.py

@@ -5,6 +5,8 @@ import gradio as gr
 import ast
 from functools import lru_cache
 from collections import Counter
+import requests
+import os
 
 # --- Constants and Mappings (Unchanged) ---
 BODY_ORDER = ['Very light-bodied', 'Light-bodied', 'Medium-bodied', 'Full-bodied', 'Very full-bodied']
@@ -27,14 +29,42 @@ FOOD_EMOJIS = {
 }
 
 
+# --- Data Download Function ---
+def download_data():
+    """Downloads the dataset from Google Drive if not already present."""
+    csv_filename = 'XWines_Full_100K_wines.csv'
+    
+    if os.path.exists(csv_filename):
+        return csv_filename
+    
+    # Convert Google Drive share link to direct download link
+    file_id = '1uEEipmKNxdiKUAhjH-K14JOSQ2BLRFss'
+    download_url = f'https://drive.google.com/uc?export=download&id={file_id}'
+    
+    print(f"Downloading dataset from Google Drive...")
+    try:
+        response = requests.get(download_url, stream=True)
+        response.raise_for_status()
+        
+        with open(csv_filename, 'wb') as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+        
+        print(f"Dataset downloaded successfully: {csv_filename}")
+        return csv_filename
+    except Exception as e:
+        raise Exception(f"Failed to download dataset: {str(e)}")
+
 # --- OPTIMIZATION 1: Data Loading & Pre-processing ---
 @lru_cache(maxsize=1)
 def load_and_preprocess_data():
     """Loads and performs expensive one-time preprocessing on the dataset."""
+    csv_filename = download_data()
+    
     try:
-        df = pd.read_csv('XWines_Full_100K_wines.csv')
+        df = pd.read_csv(csv_filename)
     except FileNotFoundError:
-        raise FileNotFoundError("CSV file 'XWines_Full_100K_wines.csv' not found.")
+        raise FileNotFoundError(f"CSV file '{csv_filename}' not found.")
 
     def parse_list_string(s):
         try:

requirements.txt

@@ -0,0 +1,6 @@
+pandas
+plotly
+gradio
+numpy
+scipy
+requests