Upload folder using huggingface_hub

app.py

@@ -54,105 +54,46 @@ with tab1:
                 "Store_Establishment_Year": est_year
             }
 
-            url = "https://Pushpak21-SuperKart-Sales-Forecast-Backend.hf.space/predict"
-            response = requests.post(url, json=payload)
-            result = response.json()
-
-            if response.status_code == 200:
-                st.success(f"📈 Predicted Sales: ₹{result['prediction'][0]:,.2f}")
-            else:
-                st.error(f"❌ Error: {result.get('error', 'Unknown error')}")
-        
-        except Exception as e:
-            st.error(f"⚠️ Request failed: {e}")
+            try:
+                prediction = get_single_prediction(payload)
+                st.success(f"✅ Predicted Sales: ₹{prediction:,.2f}")
+                st.json({**payload, "Predicted_Sales": prediction})
+            except Exception as e:
+                st.error(f"⚠️ Error during prediction: {e}")
 
 # ----------------- Tab 2: Batch Prediction -----------------
+# 📄 TAB 2: Batch Prediction
 with tab2:
     st.subheader("📄 Upload CSV for Batch Prediction")
     uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
 
-    if uploaded_file is not None:
+    if uploaded_file:
         try:
             df = pd.read_csv(uploaded_file)
 
             if df.empty:
-                st.warning("Uploaded file is empty!")
+                st.warning("Uploaded file is empty.")
             else:
                 st.write("📋 Uploaded Data Preview:")
                 st.dataframe(df.head())
 
-                # Convert DataFrame to list of records
-                records = df.to_dict(orient="records")
-
-                # Make prediction API call
-                response = requests.post(
-                    "https://Pushpak21-SuperKart-Sales-Forecast-Backend.hf.space/predict_batch",
-                    json=records
-                )
-
-                if response.status_code == 200:
-                    predictions = response.json().get("predictions", [])
-                    df["Predicted_Sales"] = predictions
-
-                    # Reorder columns: move actual & predicted sales to front
-                    priority_cols = ["Product_Store_Sales_Total", "Predicted_Sales"]
-                    other_cols = [col for col in df.columns if col not in priority_cols]
-                    df = df[priority_cols + other_cols]
-
-                    st.success("✅ Batch prediction complete!")
-
-                    # Header + Download button aligned
-                    col1, col2 = st.columns([6, 1])
-                    with col1:
-                        st.subheader("📈 Prediction Results:")
-                    with col2:
-                        csv = df.to_csv(index=False).encode('utf-8')
-                        st.download_button(
-                            label="📥 Download CSV",
-                            data=csv,
-                            file_name="batch_predictions.csv",
-                            mime="text/csv",
-                            use_container_width=True
-                        )
-
-                    # Display result table
-                    st.dataframe(df)
-
-                    # 📉 Altair Line Chart: Actual vs Predicted
-                    if "Product_Store_Sales_Total" in df.columns:
-                        plot_df = df[["Product_Store_Sales_Total", "Predicted_Sales"]].dropna()
-
-                        if not plot_df.empty:
-                            st.subheader("📉 Actual vs Predicted Sales")
-
-                            # Prepare long-format dataframe for Altair
-                            plot_df = plot_df.reset_index().rename(columns={
-                                "Product_Store_Sales_Total": "Actual Sales",
-                                "Predicted_Sales": "Predicted Sales",
-                                "index": "Index"
-                            })
-
-                            plot_df_melted = plot_df.melt(
-                                id_vars="Index",
-                                var_name="Type",
-                                value_name="Sales"
-                            )
-
-                            line_chart = alt.Chart(plot_df_melted).mark_line(point=True).encode(
-                                x=alt.X("Index:O", title="Record Index"),
-                                y=alt.Y("Sales:Q", title="Sales Value"),
-                                color=alt.Color("Type:N", title="Sales Type"),
-                                tooltip=["Index", "Type", "Sales"]
-                            ).properties(
-                                width=700,
-                                height=400
-                            )
-
-                            st.altair_chart(line_chart, use_container_width=True)
-                        else:
-                            st.info("ℹ️ Not enough valid rows for plotting.")
-                else:
-                    st.error(f"❌ API Error {response.status_code}: {response.text}")
+                df = get_predictions(df)
+                df = reorder_columns(df, ["Product_Store_Sales_Total", "Predicted_Sales"])
+
+                col1, col2 = st.columns([6, 1])
+                with col1:
+                    st.subheader("📈 Prediction Results:")
+                with col2:
+                    st.download_button(
+                        label="📥 Download CSV",
+                        data=get_csv_download(df),
+                        file_name="batch_predictions.csv",
+                        mime="text/csv",
+                        use_container_width=True
+                    )
+
+                st.dataframe(df)
+                plot_actual_vs_predicted(df)
 
         except Exception as e:
             st.error(f"⚠️ Error while processing the file: {e}")