Upload 2 files

app.py

@@ -0,0 +1,83 @@
+
+
+import gradio as gr
+import requests
+import json
+
+# --- Configuration ---
+# IMPORTANT: Replace this with the URL of your deployed Flask API
+API_URL = "https://kritish205/supercart-backend/predict"
+
+# --- Prediction Function ---
+# This function takes all the inputs from the UI, sends them to the API, and gets a prediction.
+def predict_sales(
+    product_weight,
+    product_mrp,
+    product_sugar_content,
+    product_allocated_area,
+    product_type,
+    store_age,
+    store_size,
+    store_location_city_type,
+    store_type,
+):
+    """Makes a request to the backend API and returns the prediction."""
+    if "YOUR_BACKEND_API_URL_HERE" in API_URL:
+        return "ERROR: Please update the API_URL in the app.py script."
+
+    # Create the JSON payload for the API
+    payload = {
+        "Product_Weight": product_weight,
+        "Product_MRP": product_mrp,
+        "Product_Sugar_Content": product_sugar_content,
+        "Product_Allocated_Area": product_allocated_area,
+        "Product_Type": product_type,
+        "Store_Age": store_age,
+        "Store_Size": store_size,
+        "Store_Location_City_Type": store_location_city_type,
+        "Store_Type": store_type,
+    }
+
+    try:
+        # Send the request to the Flask API
+        response = requests.post(API_URL, json=payload)
+        response.raise_for_status()  # Raise an exception for bad status codes
+        result = response.json()
+        predicted_sales = result.get('predicted_sales', 'N/A')
+        return f"${predicted_sales:,.2f}"
+    except requests.exceptions.RequestException as e:
+        return f"API Connection Error: {e}"
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+# --- UI Interface ---
+# Define the input and output components for the Gradio UI
+product_type_options = [
+    'Snack Foods', 'Household', 'Frozen Foods', 'Fruits and Vegetables',
+    'Health and Hygiene', 'Dairy', 'Baking Goods', 'Canned', 'Meat',
+    'Soft Drinks', 'Breads', 'Hard Drinks', 'Starchy Foods', 'Breakfast',
+    'Seafood', 'Others'
+]
+
+iface = gr.Interface(
+    fn=predict_sales,
+    inputs=[
+        gr.Number(label="Product Weight (kg)", value=10.0),
+        gr.Number(label="Product MRP ($)", value=150.0),
+        gr.Radio(["No Sugar", "Low Sugar", "Regular"], label="Product Sugar Content", value="Low Sugar"),
+        gr.Slider(0.0, 0.3, value=0.05, label="Product Allocated Area (Ratio)"),
+        gr.Dropdown(product_type_options, label="Product Type", value="Snack Foods"),
+        gr.Number(label="Store Age (Years)", value=15),
+        gr.Radio(["Small", "Medium", "High"], label="Store Size", value="Medium"),
+        gr.Radio(["Tier 1", "Tier 2", "Tier 3"], label="Store Location City Type", value="Tier 2"),
+        gr.Dropdown(["Supermarket Type1", "Supermarket Type2", "Departmental Store", "Food Mart"], label="Store Type", value="Supermarket Type1"),
+    ],
+    outputs=gr.Textbox(label="Predicted Sales"),
+    title="🛒 SuperKart Sales Predictor",
+    description="This app predicts the total sales for a product in a given store. Fill in the details and click 'Submit'.",
+    allow_flagging="never"
+)
+
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()

requirements.txt

@@ -0,0 +1,2 @@
+gradio==4.31.5
+requests==2.31.0