Upload 4 files

Backed of Project 5 is set

Dockerfile

@@ -0,0 +1,26 @@
+# Dockerfile
+
+# Use a specific Python base image for stability and size optimization
+FROM python:3.12-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy the requirements file and install dependencies
+# Use --no-cache-dir to keep the image size small
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the Flask application and the serialized model
+COPY app.py .
+COPY tuned_xgb_sales_forecaster.pkl . 
+
+# Expose the port the Flask app will run on
+EXPOSE 5000
+
+# Set the environment variable for Flask
+ENV FLASK_APP=app.py
+
+# Command to run the application when the container starts
+# Use gunicorn or a similar WSGI server for production, but Flask's built-in server is fine for this context
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,56 @@
+# app.py
+
+import joblib
+import numpy as np
+import pandas as pd
+from flask import Flask, request, jsonify
+
+# Define the model filename
+MODEL_FILE = 'tuned_xgb_sales_forecaster.pkl'
+
+# Define the 10 feature columns expected by the model pipeline
+FEATURE_COLS = [
+    'Product_Weight', 'Product_Sugar_Content', 'Product_Allocated_Area',
+    'Product_Type', 'Product_MRP', 'Store_Size',
+    'Store_Location_City_Type', 'Store_Type', 'Store_Age',
+    'Product_Category_Simplified'
+]
+
+# --- Load the Model Pipeline ---
+try:
+    model_pipeline = joblib.load(MODEL_FILE)
+    print("Model loaded successfully.")
+except Exception as e:
+    print(f"CRITICAL ERROR: Model not found: {e}. Check Dockerfile.")
+    model_pipeline = None
+
+app = Flask(__name__)
+
+@app.route('/predict', methods=['POST'])
+def predict_sales():
+    if model_pipeline is None:
+        return jsonify({'error': 'Server setup error: Model not loaded.'}), 500
+
+    try:
+        data = request.get_json(force=True)
+        # Ensure input data matches the feature columns
+        input_df = pd.DataFrame(data, columns=FEATURE_COLS)
+
+        # Prediction on log scale
+        log_prediction = model_pipeline.predict(input_df)
+
+        # Inverse transformation: sales = exp(y) - 1
+        prediction_original_scale = np.expm1(log_prediction)
+
+        response = {
+            'status': 'success',
+            'predicted_sales_revenue': round(prediction_original_scale[0], 2)
+        }
+        return jsonify(response)
+
+    except Exception as e:
+        return jsonify({'error': f'Prediction logic failed: {str(e)}'}), 400
+
+if __name__ == '__main__':
+    # This runs the server inside the Docker container
+    app.run(host='0.0.0.0', port=5000)

requirements.txt

@@ -0,0 +1,6 @@
+Flask==3.0.3
+pandas==2.2.2
+numpy==1.26.4
+scikit-learn==1.6.1
+joblib==1.4.2
+xgboost==2.1.4

tuned_xgb_sales_forecaster.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e94ad83c2cb59138fd0addc972f5484caad0c21455161edb6465fafe8f24ae
+size 612275