Update app.py

app.py

@@ -12,11 +12,26 @@ def load_data():
     print(f"Files in Directory: {os.listdir(cwd)}") 
     lead_time_path = os.path.join(os.getcwd(), "final_cleaned_lead_time_data.csv")
     inventory_path = os.path.join(os.getcwd(), "inventory.csv")
+    optimization_path = os.path.join(os.getcwd(), "inventory_optimization_results.csv")
     lead_time_data = pd.read_csv(lead_time_path)
-    inventory_data = pd.read_csv(inventory_path)  
-    return lead_time_data, inventory_data
+    inventory_data = pd.read_csv(inventory_path)
+    optimization_data=pd.read_csv(optimization_path)
+    return lead_time_data, inventory_data, optimization_data
  
-lead_time_data, inventory_data = load_data()
+lead_time_data, inventory_data, optimization_data = load_data()
+st.header("📊 Inventory Optimization Insights")
+st.write("### Optimization Results Dataset")
+st.dataframe(optimization_data)
+st.write("### Key Metrics Summary")
+st.write(optimization_data.describe())
+st.write("### Optimization Trend")
+if 'Optimization_Score' in optimization_data.columns:
+    fig, ax = plt.subplots()
+    ax.plot(optimization_data.index, optimization_data['Optimization_Score'], marker='o', linestyle='-')
+    ax.set_title("Optimization Score Over Time")
+    ax.set_xlabel("Iteration")
+    ax.set_ylabel("Score")
+    st.pyplot(fig)
 def calculate_safety_stock(demand_std, lead_time_mean, z_score=1.645):
     return z_score * demand_std * np.sqrt(lead_time_mean)
 
@@ -63,5 +78,4 @@ if st.button("Save Results"):
     inventory_data.to_csv("updated_inventory_data.csv", index=False)
     st.success("Results saved to 'updated_inventory_data.csv'")
 if __name__ == "__main__":
-    import streamlit as st
-    st.write("Streamlit app is running!") 
+