Deploying salary prediction ML model inside a Docker container hosted on an EC2 instance:

Deploying your salary prediction ML model inside a Docker container hosted on an EC2 instance

A step-by-step guide to deploying your salary prediction ML model inside a Docker container hosted on an EC2 instance:

Step 1: Prepare the ML Model

1. Train your model: Make sure your salary prediction model is trained and saved as a serialized file (e.g., model.pkl).
2. Create a Flask API: If you haven't already, create a Flask API to serve the model predictions.

   from flask import Flask, request, jsonify
   import pickle
   
   app = Flask(__name__)
   
   # Load the model
   model = pickle.load(open('model.pkl', 'rb'))
   
   @app.route('/predict', methods=['POST'])
   def predict():
       data = request.get_json()
       prediction = model.predict([data['features']])
       return jsonify({'prediction': prediction.tolist()})
   
   if __name__ == '__main__':
       app.run(host='0.0.0.0', port=5000)
   

3. Test the API locally: Run the Flask application locally to ensure it works as expected.

Step 2: Create a Dockerfile

1. Create a Dockerfile in the same directory as your Flask app. Here's an example:

   # Use an official Python runtime as a parent image
   FROM python:3.8-slim
   
   # Set the working directory in the container
   WORKDIR /app
   
   # Copy the current directory contents into the container at /app
   COPY . /app
   
   # Install any needed packages specified in requirements.txt
   RUN pip install --no-cache-dir -r requirements.txt
   
   # Make port 5000 available to the world outside this container
   EXPOSE 5000
   
   # Run app.py when the container launches
   CMD ["python", "app.py"]
   

2. Create a requirements.txt file to list the dependencies
3. Flask

   scikit-learn
   

Step 3: Build and Test the Docker Image Locally

1. Build the Docker image:

   docker build -t salary-prediction-app .

2. Run the Docker container locally:

   docker run -p 5000:5000 salary-prediction-app

3. Test the API: Use Postman or curl to test your API endpoint (http://localhost:5000/predict).

Step 4: Set Up an EC2 Instance

1. Launch an EC2 instance: Go to the AWS Management Console, launch an EC2 instance, and choose an appropriate AMI (e.g., Amazon Linux 2).
2. Connect to the EC2 instance:

   ssh -i /path/to/your-key.pem ec2-user@your-ec2-public-dns

3. Install Docker on the EC2 instance:

   sudo yum update -y
   sudo amazon-linux-extras install docker
   sudo service docker start
   sudo usermod -a -G docker ec2-user
   

Step 5: Deploy the Docker Container on EC2

1. Copy your Docker image to the EC2 instance:

   • You can use docker save and docker load commands to transfer the Docker image, or you can push the image to a Docker registry (e.g., Docker Hub) and pull it on the EC2 instance.

   docker save salary-prediction-app | gzip > salary-prediction-app.tar.gz
   scp -i /path/to/your-key.pem salary-prediction-app.tar.gz ec2-user@your-ec2-public-dns:/home/ec2-user/
   ssh -i /path/to/your-key.pem ec2-user@your-ec2-public-dns
   gunzip -c salary-prediction-app.tar.gz | docker load
   

2. Run the Docker container on EC2:

   docker run -d -p 80:5000 salary-prediction-app

Step 6: Access Your Application

• Access your app: The app should now be running on your EC2 instance. You can access it using the public DNS of your EC2 instance:

  http://your-ec2-public-dns/

Step 7: Secure Your Application

• Security groups: Make sure your EC2 instance security group allows inbound traffic on port 80 (HTTP).
• Optional: Set up a domain name and SSL for better security and accessibility

Your Application

• Security groups: Make sure your EC2 instance security group allows inbound traffic on port 80 (HTTP).
• Optional: Set up a domain name and SSL for better security and accessibility