Update app.py

app.py

@@ -10,7 +10,7 @@ API_URL = "https://molinari135-product-return-prediction-api.hf.space/predict/"
 # Load the inventory dataset from Hugging Face
 hf_token = os.getenv("inventory_data")
 dataset = load_dataset("molinari135/armani-inventory", token=hf_token, data_files="inventory.tsv")
-inventory = pd.DataFrame(dataset['train']).head(15)
+inventory = pd.DataFrame(dataset['train']).sample(n=15, random_state=42)
 
 # Gradio Interface function
 def predict_return(selected_products, total_customer_purchases, total_customer_returns):
@@ -27,7 +27,7 @@ def predict_return(selected_products, total_customer_purchases, total_customer_r
 
     for selected_product in selected_products:
         # Split each selected product into model, fabric, and color
-        product_info = selected_product.split(" \t")
+        product_info = selected_product.split(" \t\t")
         model_fabric_colour = product_info[0]  # Questo è del tipo "Model-Fabric-Colour"
         
         # Dividi il codice prodotto in modello, tessuto e colore
@@ -92,7 +92,7 @@ def predict_return(selected_products, total_customer_purchases, total_customer_r
 # Crea l'interfaccia Gradio con le checkbox a sinistra
 checkbox_choices = [
     f"{row['Item Brand Model']}-{row['Item Brand Fabric']}-{row['Item Brand Colour']}"
-    f" \tType: {row['Product Type']} \tMaterial: {row['Main Material']} \tSales: {round(row['Net Sales (FA)'], 2)} USD"
+    f" \t\tType: {row['Product Type']} \t\tMaterial: {row['Main Material']} \t\tSales: {round(row['Net Sales (FA)'], 2)} USD"
     for _, row in inventory.iterrows()
 ]