Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.9-slim
+
+# Set working directory
+WORKDIR /app
+
+# Copy backend files into container
+COPY . .
+
+# Install dependencies
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Start the SmartKart API using Gunicorn
+# -w 4  → 4 worker processes
+# -b 0.0.0.0:7860 → required port for Hugging Face Spaces
+# app:smartkart_api → Flask instance name inside app.py
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:app"]

app.py

@@ -0,0 +1,56 @@
+
+# Import necessary libraries
+import numpy as np
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+app = Flask(__name__)   # ← THIS MUST EXIST
+
+# Initialize the Flask application
+smartkart_api = Flask("SmartKart Total Sales Predictor")
+
+# Load the trained SmartKart model
+model = joblib.load("smartkart_model_v1_0.joblib")
+
+# Home route
+@smartkart_api.get('/')
+def home():
+    return "Welcome to the SmartKart Total Sales Prediction API!"
+
+# Endpoint for single prediction
+@smartkart_api.post('/v1/predict')
+def predict_total_sales():
+    """
+    Handles POST requests to /v1/predict.
+    Expects JSON with SmartKart product/store features.
+    Returns predicted total sales.
+    """
+
+    data = request.get_json()
+
+    # Extract the SmartKart model features from the JSON payload
+    sample = {
+        'Product_Weight': data['Product_Weight'],
+        'Product_Allocated_Area': data['Product_Allocated_Area'],
+        'Product_MRP': data['Product_MRP'],
+        'Store_Age': data['Store_Age'],
+        'Product_Sugar_Content_Ord': data['Product_Sugar_Content_Ord'],
+        'Store_Size_Ord': data['Store_Size_Ord'],
+        'Store_Location_City_Type_Ord': data['Store_Location_City_Type_Ord'],
+        # One-hot encoded or target-encoded fields:
+        'Store_Type': data['Store_Type'],
+        'Product_Type': data['Product_Type']
+    }
+
+    # Convert to DataFrame
+    input_df = pd.DataFrame([sample])
+
+    # Predict total sales
+    predicted_sales = model.predict(input_df)[0]
+
+    # Convert to Python float
+    predicted_sales = round(float(predicted_sales), 2)
+
+    return jsonify({'Predicted_Total_Sales': predicted_sales})
+
+app.run(host="0.0.0.0", port=7860)

requirements.txt

@@ -0,0 +1,12 @@
+joblib
+pandas==2.2.2
+numpy==1.26.4
+scikit-learn==1.6.1
+xgboost==2.1.4
+joblib==1.4.2
+Werkzeug==2.2.2
+flask==2.2.2
+gunicorn==20.1.0
+requests>=2.31
+uvicorn[standard]
+streamlit==1.43.2

smartkart_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcf37fa829ad125ae78dbae40f3715715c6e960fbe1cdaa415047a07a3c80cc0
+size 645339