app.py

app.py

@@ -124,7 +124,7 @@ def predict_lifecycle(Category, ProductName, Price, Rating, NumReviews, StockQua
         return f"Error: {str(e)}"
 
 # Load dataset for dynamic pricing
-df_pricing = pd.read_csv("dynamic_pricing_data.csv")  # Update this path with the correct one
+df_pricing = pd.read_csv("/content/dynamic_pricing_data_5000.csv")  # Update this path with the correct one
 
 # Encode categorical variables for dynamic pricing
 label_encoders = {}
@@ -176,7 +176,7 @@ def predict_price(product_name, category, base_price, competitor_price, demand,
     return f"Optimal Price: ₹{round(predicted_price, 2)}"
 
 # Load dataset for product recommendation
-df_recommendation = pd.read_csv("synthetic_product_data.csv")  # Update this path with the correct one
+df_recommendation = pd.read_csv("/content/synthetic_product_data_5000.csv")  # Update this path with the correct one
 
 # Preprocessing for product recommendation
 categorical_features_recommendation = ['product_condition', 'category']
@@ -207,7 +207,7 @@ def recommend_products(category):
 
 # Circular Economy Analytics Dashboard
 def load_data():
-    return pd.read_csv("marketplace_data.csv")
+    return pd.read_csv("/content/synthetic_marketplace_data_2000.csv")
 
 def update_live_data():
     df = load_data()
@@ -218,7 +218,7 @@ def update_live_data():
         "NumReviews": np.random.randint(0, 1000)
     }
     df = df.append(new_entry, ignore_index=True)
-    df.to_csv("marketplace_data.csv", index=False)
+    df.to_csv("/content/synthetic_marketplace_data_2000.csv", index=False)
 
 def generate_dashboard():
     df = load_data()
@@ -331,4 +331,6 @@ def live_update():
 threading.Thread(target=live_update, daemon=True).start()
 
 # Launch the app
-app.launch()
+app.launch()
+
+