Upload folder using huggingface_hub

app.py

@@ -16,10 +16,10 @@ with col1:
     # Product Features
     st.markdown("**Product Details**")
     product_weight = st.slider("Product Weight (kg)", 4.0, 22.0, 12.66, 0.01)
-    product_sugar = st.selectbox("Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
+    product_sugar = st.selectbox("Sugar Content", ["Low", "Medium", "High"])
     product_area = st.slider("Allocated Area (sqm)", 0.004, 0.3, 0.05, 0.001)
     product_type = st.selectbox("Product Type", [
-        "Frozen Foods", "Dairy", "Canned", "Baking Goods", 
+        "Frozen Foods", "Dairy", "Canned", "Baking Goods",
         "Health and Hygiene", "Snack Foods", "Meat", "Household"
     ])
     product_mrp = st.slider("Product MRP (price)", 31.0, 266.0, 147.0, 0.5)
@@ -27,26 +27,23 @@ with col1:
 with col2:
     # Store Features
     st.markdown("**Store Details**")
-    store_id = st.selectbox("Store ID", ["OUT001", "OUT002", "OUT003", "OUT004"])
-    current_year = datetime.now().year
-    establishment_year = st.slider("Store Establishment Year", 
-                                1987, current_year, 2002)
-    store_size = st.selectbox("Store Size", ["Small", "Medium", "High"])
+    establishment_year = st.slider("Store Establishment Year",
+                                1987, datetime.now().year, 2002)
+    store_size = st.selectbox("Store Size", ["Small", "Medium", "Large"])
     city_type = st.selectbox("City Tier", ["Tier 1", "Tier 2", "Tier 3"])
     store_type = st.selectbox("Store Type", [
-        "Supermarket Type1", "Supermarket Type2", 
+        "Supermarket Type1", "Supermarket Type2",
         "Departmental Store", "Food Mart"
     ])
 
-# Prepare input data
+# Prepare input data (only including features used in the backend)
 input_data = {
     "product_weight": product_weight,
-    "product_sugar_content": product_sugar,
     "product_allocated_area": product_area,
-    "product_type": product_type,
     "product_mrp": product_mrp,
-    "store_id": store_id,
     "store_establishment_year": establishment_year,
+    "product_sugar_content": product_sugar,
+    "product_type": product_type,
     "store_size": store_size,
     "store_location_city_type": city_type,
     "store_type": store_type
@@ -55,16 +52,14 @@ input_data = {
 # Make prediction when the "Predict" button is clicked
 if st.button("Predict Sales"):
     try:
-        response = requests.post("http://DD009-SuperKartBackend.hf.space/v1/sales", json=input_data)
+        response = requests.post("http://localhost:5000/v1/sales", json=input_data)
         if response.status_code == 200:
             result = response.json()
             st.success(f"Predicted Sales Total: ${result['predicted_sales']}")
             
-            # Display additional metrics
-            st.markdown("**Additional Metrics**")
-            st.write(f"- Store Age: {result['store_age']} years")
-            st.write(f"- Product Density: {result['product_density']} kg/sqm")
-            st.write(f"- Price per Unit Weight: ${result['price_per_weight']}/kg")
+            # Display features used
+            st.markdown("**Features Used**")
+            st.write(", ".join(result['features_used']))
         else:
             st.error(f"Error making prediction: {response.json().get('error', 'Unknown error')}")
     except Exception as e:
@@ -74,22 +69,31 @@ if st.button("Predict Sales"):
 st.subheader("Batch Prediction")
 st.write("Upload a CSV file containing multiple product-store combinations")
 
+# Instructions for CSV format
+st.markdown("""
+**CSV File Requirements:**
+- Must contain these exact columns:
+  - Product_Weight, Product_Allocated_Area, Product_MRP
+  - Store_Establishment_Year, Product_Sugar_Content, Product_Type
+  - Store_Size, Store_Location_City_Type, Store_Type
+""")
+
 # File uploader for batch predictions
 uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
 
 if uploaded_file is not None:
     if st.button("Predict Batch Sales"):
         try:
-            files = {'file': uploaded_file.getvalue()}
-            response = requests.post("http://DD009-SuperKartBackend.hf.space/v1/salesbatch", files=files)
-            
+            files = {'file': uploaded_file}
+            response = requests.post("http://localhost:5000/v1/salesbatch", files=files)
+
             if response.status_code == 200:
                 results = response.json()['predictions']
                 results_df = pd.DataFrame(results)
-                
+
                 st.success("Batch predictions completed!")
                 st.dataframe(results_df)
-                
+
                 # Download button for results
                 csv = results_df.to_csv(index=False)
                 st.download_button(
@@ -105,20 +109,18 @@ if uploaded_file is not None:
 
 # Add sample data section
 st.sidebar.markdown("### Sample Data")
-if st.sidebar.button("Load Sample Data"):
+if st.sidebar.button("Show Sample Input"):
     sample_data = {
         "product_weight": 12.66,
-        "product_sugar_content": "Low Sugar",
         "product_allocated_area": 0.027,
-        "product_type": "Frozen Foods",
         "product_mrp": 117.08,
-        "store_id": "OUT004",
         "store_establishment_year": 2009,
+        "product_sugar_content": "Low",
+        "product_type": "Frozen Foods",
         "store_size": "Medium",
         "store_location_city_type": "Tier 2",
         "store_type": "Supermarket Type2"
     }
     
-    # Update all widgets with sample data
-    st.experimental_set_query_params(**sample_data)
-    st.experimental_rerun()
+    st.sidebar.json(sample_data)
+