Upload folder using huggingface_hub

app.py

@@ -1,10 +1,11 @@
 import gradio as gr
 import pandas as pd
+import numpy as np
 import requests
 
-# Function to handle single prediction
-def predict_sales_single(product_weight, product_sugar_content, product_allocated_area, product_type, product_mrp, 
-                        store_establishment_year, store_size, store_location_city_type, store_type):
+def predict_sales(product_weight, product_sugar_content, product_allocated_area, product_type, product_mrp, 
+                  store_establishment_year, store_size, store_location_city_type, store_type):
+    # Create input dictionary
     sample = {
         'Product_Weight': product_weight,
         'Product_Sugar_Content': product_sugar_content,
@@ -16,71 +17,58 @@ def predict_sales_single(product_weight, product_sugar_content, product_allocate
         'Store_Location_City_Type': store_location_city_type,
         'Store_Type': store_type
     }
-    backend_url = "https://hugo014-totalsalespredictionbackend.hf.space/v1/sales"
+
+    # Convert to DataFrame
+    features_df = pd.DataFrame([sample])
+
+    # Apply one-hot encoding for nominal columns (matching backend)
+    features_df = pd.get_dummies(features_df, columns=['Product_Type', 'Store_Type'], drop_first=True)
+
+    # Apply ordinal encoding (based on backend mappings)
+    sugar_mapping = {'No Sugar': 0, 'Low Sugar': 1, 'Regular': 2}
+    size_mapping = {'Small': 0, 'Medium': 1, 'High': 2}
+    city_mapping = {'Tier 3': 0, 'Tier 2': 1, 'Tier 1': 2}
+
+    features_df['Product_Sugar_Content'] = features_df['Product_Sugar_Content'].map(sugar_mapping)
+    features_df['Store_Size'] = features_df['Store_Size'].map(size_mapping)
+    features_df['Store_Location_City_Type'] = features_df['Store_Location_City_Type'].map(city_mapping)
+
+    # Call the backend API
+    backend_url = "https://Hugo014-TotalSalesPredictionBackend.hf.space/v1/sales"
     try:
         response = requests.post(backend_url, json=sample)
         if response.status_code == 200:
             result = response.json()
             predicted_sales = result['Predicted Sales Total (in dollars)']
-            return f"Predicted Sales: ${predicted_sales:.2f}"
-        else:
-            return f"Backend error: {response.status_code} - {response.text}"
-    except Exception as e:
-        return f"Error calling backend: {str(e)}"
-
-# Function to handle batch prediction via CSV upload
-def predict_sales_batch(csv_file):
-    if csv_file is None:
-        return "Please upload a CSV file."
-    files = {"file": (csv_file.name, csv_file.getvalue(), "text/csv")}
-    backend_url = "https://hugo014-totalsalespredictionbackend.hf.space/v1/salesbatch"
-    try:
-        response = requests.post(backend_url, files=files)
-        if response.status_code == 200:
-            result = response.json()
-            return result  # Returns dict like {"0": 123.45, "1": 678.90}
+            return f"The predicted sales total for the product is ${predicted_sales:.2f}."
         else:
             return f"Backend error: {response.status_code} - {response.text}"
     except Exception as e:
         return f"Error calling backend: {str(e)}"
 
-# # Create Gradio UI with tabs for single and batch
-# with gr.Blocks() as demo:
-#     gr.Markdown("# Super Kart Product Sales Prediction App")
-    
-#     with gr.Tab("Single Prediction"):
-#         product_weight = gr.Number(label="Product Weight", value=10.0, minimum=0.0, step=0.1)
-#         product_sugar_content = gr.Dropdown(label="Product Sugar Content", choices=["No Sugar", "Low Sugar", "Regular"], value="Low Sugar")
-#         product_allocated_area = gr.Number(label="Product Allocated Area (sq ft)", value=500.0, minimum=0.0, step=1.0)
-#         product_type = gr.Dropdown(label="Product Type", choices=[
-#             "Dairy", "Soft Drinks", "Meat", "Fruits and Vegetables", "Snack Foods", "Household",
-#             "Frozen Foods", "Baking Goods", "Canned", "Health and Hygiene", "Hard Drinks",
-#             "Breads", "Starchy Foods", "Breakfast", "Seafood", "Others"
-#         ], value="Dairy")
-#         product_mrp = gr.Number(label="Product MRP (price)", value=100.0, minimum=0.0, step=1.0)
-#         store_establishment_year = gr.Number(label="Store Establishment Year", value=2000, minimum=1900, maximum=2025, step=1)
-#         store_size = gr.Dropdown(label="Store Size", choices=["Small", "Medium", "High"], value="Medium")
-#         store_location_city_type = gr.Dropdown(label="Store Location City Type", choices=["Tier 3", "Tier 2", "Tier 1"], value="Tier 1")
-#         store_type = gr.Dropdown(label="Store Type", choices=[
-#             "Grocery Store", "Supermarket Type1", "Supermarket Type2", "Supermarket Type3"
-#         ], value="Supermarket Type1")
-#         output_single = gr.Textbox(label="Prediction Result")
-#         predict_button = gr.Button("Predict")
-#         predict_button.click(
-#             fn=predict_sales_single,
-#             inputs=[product_weight, product_sugar_content, product_allocated_area, product_type, product_mrp, 
-#                     store_establishment_year, store_size, store_location_city_type, store_type],
-#             outputs=output_single
-#         )
-    
-#     with gr.Tab("Batch Prediction"):
-#         csv_file = gr.File(label="Upload CSV for Batch Prediction", file_types=[".csv"])
-#         output_batch = gr.JSON(label="Batch Prediction Results")  # Better for displaying dict output
-#         batch_button = gr.Button("Predict Batch")
-#         batch_button.click(
-#             fn=predict_sales_batch,
-#             inputs=csv_file,
-#             outputs=output_batch
-#         )
+# Gradio interface
+demo = gr.Interface(
+    fn=predict_sales,
+    inputs=[
+        gr.Number(label="Product Weight", value=10.0, minimum=0.0, step=0.1),
+        gr.Dropdown(label="Product Sugar Content", choices=["No Sugar", "Low Sugar", "Regular"], value="Low Sugar"),
+        gr.Number(label="Product Allocated Area (sq ft)", value=500.0, minimum=0.0, step=1.0),
+        gr.Dropdown(label="Product Type", choices=[
+            "Dairy", "Soft Drinks", "Meat", "Fruits and Vegetables", "Snack Foods", "Household",
+            "Frozen Foods", "Baking Goods", "Canned", "Health and Hygiene", "Hard Drinks",
+            "Breads", "Starchy Foods", "Breakfast", "Seafood", "Others"
+        ], value="Dairy"),
+        gr.Number(label="Product MRP (price)", value=100.0, minimum=0.0, step=1.0),
+        gr.Number(label="Store Establishment Year", value=2000, minimum=1900, maximum=2025, step=1),
+        gr.Dropdown(label="Store Size", choices=["Small", "Medium", "High"], value="Medium"),
+        gr.Dropdown(label="Store Location City Type", choices=["Tier 3", "Tier 2", "Tier 1"], value="Tier 1"),
+        gr.Dropdown(label="Store Type", choices=[
+            "Grocery Store", "Supermarket Type1", "Supermarket Type2", "Supermarket Type3"
+        ], value="Supermarket Type1")
+    ],
+    outputs=gr.Textbox(label="Prediction Result"),
+    title="Super Kart Product Sales Prediction App",
+    description="This tool predicts the total sales for a product based on store and product details."
+)
 
-demo.launch(share=True)  # Added share=True to avoid localhost error in restricted environments like Colab
+demo.launch()