Upload folder using huggingface_hub

Dockerfile

@@ -1,16 +1,16 @@
-# Use a minimal base image with Python 3.9 installed
 FROM python:3.9-slim
 
-# Set the working directory inside the container to /app
-WORKDIR /app
+# Set the working directory inside the container
+WORKDIR /app 
 
-# Copy all files from the current directory on the host to the container's /app directory
+# Copy all files from the current directory to the container's working directory
 COPY . .
 
-# Install Python dependencies listed in requirements.txt
-RUN pip3 install -r requirements.txt
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
-# Define the command to run the Streamlit app on port 8501 and make it accessible externally
-CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]
-
-# NOTE: Disable XSRF protection for easier external access in order to make batch predictions
+# Define the command to start the application using Gunicorn with 4 worker processes
+# - `-w 4`: Uses 4 worker processes for handling requests
+# - `-b 0.0.0.0:7860`: Binds the server to port 7860 on all network interfaces
+# - `app:app`: Runs the Flask app (assuming `app.py` contains the Flask instance named `app`)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:superkart_sales_prediction_api"]

app.py

@@ -1,69 +1,91 @@
-import streamlit as st
-import pandas as pd
-import requests
-
-# Set the title of the Streamlit app
-st.title("🛒 SuperKart Sales Prediction App")
-
-st.write("Predict sales revenue based on product and customer details.")
-
-# Section: Online prediction
-st.subheader("📦 Online Prediction")
-
-# Sample input fields (must match features used in your trained model)
-product_category = st.selectbox("Product Category", ["Electronics", "Clothing", "Home", "Sports", "Others"])
-product_price = st.number_input("Product Price ($)", min_value=0.0, step=10.0, value=100.0)
-discount_applied = st.selectbox("Discount Applied", ["Yes", "No"])
-customer_age = st.slider("Customer Age", 18, 70, 30)
-customer_gender = st.selectbox("Customer Gender", ["Male", "Female"])
-customer_income = st.number_input("Customer Income ($)", min_value=0.0, step=1000.0, value=50000.0)
-store_region = st.selectbox("Store Region", ["North", "South", "East", "West"])
-units_sold = st.number_input("Units Sold", min_value=1, value=1)
-
-# Prepare the input as a dictionary
-input_data = pd.DataFrame([{
-    "product_category": product_category,
-    "product_price": product_price,
-    "discount_applied": discount_applied,
-    "customer_age": customer_age,
-    "customer_gender": customer_gender,
-    "customer_income": customer_income,
-    "store_region": store_region,
-    "units_sold": units_sold
-}])
-
-# API call to Hugging Face backend
-if st.button("Predict Sales"):
+
+# Import necessary libraries
+import numpy as np
+import joblib  # For loading the serialized model
+import pandas as pd  # For data manipulation
+from flask import Flask, request, jsonify  # For creating the Flask API
+
+# Initialize the Flask application
+superkart_sales_prediction_api = Flask("SuperKart Sales Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("superkart_sales_prediction_model_v1_0.joblib")
+
+# Define the required feature columns
+REQUIRED_FEATURES = [
+    'Product_Weight',
+    'Product_Sugar_Content',
+    'Product_Allocated_Area',
+    'Product_MRP',
+    'Store_Size',
+    'Store_Location_City_Type',
+    'Store_Type',
+    'Product_Id_Group',
+    'Store_Age',
+    'Product_Type_Category',
+    'Store_Id'
+]
+
+# Define a route for the home page (GET request)
+@superkart_sales_prediction_api.get('/')
+def home():
+    return "Welcome to the SuperKart Sales Prediction API!"
+
+# Define an endpoint for single product prediction (POST request)
+@superkart_sales_prediction_api.post('/v1/sales')
+def predict_sales():
     try:
-        response = requests.post(
-            "https://vamsikrishna1516-SuperKartSalesPredictionBackend.hf.space/v1/sales",
-            json=input_data.to_dict(orient='records')[0]
-        )
-        if response.status_code == 200:
-            predicted = response.json()['Predicted Sales']
-            st.success(f"💰 Predicted Sales: ${predicted}")
-        else:
-            st.error("❌ Error from backend. Please try again.")
+        data = request.get_json()
+
+        # Validate input fields
+        missing_fields = [field for field in REQUIRED_FEATURES if field not in data]
+        if missing_fields:
+            return jsonify({
+                "error": "Missing required fields",
+                "missing_fields": missing_fields
+            }), 400
+
+        # Prepare input data
+        input_data = pd.DataFrame([{key: data[key] for key in REQUIRED_FEATURES}])
+
+        # Make prediction
+        prediction = model.predict(input_data).tolist()[0]
+
+        return jsonify({'Sales': prediction})
+
     except Exception as e:
-        st.error(f"⚠️ Request failed: {e}")
-
-# Section: Batch prediction
-st.subheader("📄 Batch Prediction (CSV Upload)")
-
-uploaded_file = st.file_uploader("Upload CSV file for batch prediction", type=["csv"])
-
-if uploaded_file is not None:
-    if st.button("Predict Batch Sales"):
-        try:
-            response = requests.post(
-                "https://vamsikrishna1516-SuperKartSalesPredictionBackend.hf.space/v1/salesbatch",
-                files={"file": uploaded_file}
-            )
-            if response.status_code == 200:
-                results = response.json()
-                st.success("✅ Batch predictions received!")
-                st.write(pd.DataFrame(results.items(), columns=["ID", "Predicted Sales ($)"]))
-            else:
-                st.error("❌ Failed to get predictions from backend.")
-        except Exception as e:
-            st.error(f"⚠️ Request failed: {e}")
+        return jsonify({"error": "Internal server error", "message": str(e)}), 500
+
+# Define an endpoint for batch prediction (POST request)
+@superkart_sales_prediction_api.post('/v1/salesbatch')
+def predict_sales_batch():
+    try:
+        file = request.files.get('file')
+        if file is None:
+            return jsonify({"error": "CSV file not provided"}), 400
+
+        input_data = pd.read_csv(file)
+
+        # Check for missing columns
+        missing_cols = [col for col in REQUIRED_FEATURES if col not in input_data.columns]
+        if missing_cols:
+            return jsonify({
+                "error": "Missing columns in CSV file",
+                "missing_columns": missing_cols
+            }), 400
+
+        # Predict
+        predictions = model.predict(input_data[REQUIRED_FEATURES]).tolist()
+        predicted_sales = [round(float(pred), 2) for pred in predictions]
+
+        ids = input_data['id'].tolist() if 'id' in input_data.columns else list(range(1, len(predicted_sales) + 1))
+        output_dict = dict(zip(ids, predicted_sales))
+
+        return jsonify(output_dict)
+
+    except Exception as e:
+        return jsonify({"error": "Internal server error", "message": str(e)}), 500
+
+# Run the API
+if __name__ == '__main__':
+    superkart_sales_prediction_api.run(debug=True)

requirements.txt

@@ -1,3 +1,11 @@
+pandas==2.2.2
 numpy==2.0.2
-requests==2.32.3
+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==2.28.1
+uvicorn[standard]
 streamlit==1.43.2