Machine Learning DevOps Engineer training
The Machine Learning DevOps Engineer training focuses on the software engineering fundamentals required to successfully streamline the deployment of data and machine-learning models in a production-level environment. Students will build the DevOps skills required to automate the various aspects and stages of machine learning model building and monitoring over time.
Skills you'll learn
Git ? Machine learning ops troubleshooting ? Dvc ? Automated machine learning
Prerequisite Details
To optimize your success in this program, we've created a list of prerequisites and recommendations to help you prepare for the curriculum. Prior to enrolling, you should have the following knowledge:
Welcome to the Machine Learning DevOps Engineer
We're excited to share more about and start this journey with you! In this course, you will learn more about the pre-requisites, structure of the program, and getting started!
An Introduction to Machine Learning DevOps Engineer
Welcome! We're so glad you're here. Join us in learning a bit more about what to expect and ways to succeed.
Getting Help
You are starting a challenging but rewarding journey! Take 5 minutes to read how to get help with projects and content.
Clean Code Principles
Develop skills that are essential for deploying production machine learning models. First, you will put your coding best practices on auto-pilot by learning how to use PyLint and AutoPEP8. Then you will further expand your git and Github skills to work with teams. Finally, you will learn best practices associated with testing and logging used in production settings in order to ensure your models can stand the test of time.
Introduction
Get introduced to clean code principles, why and when to use them, and the history of clean code. Then, see what you'll be able to build by the end of the course!
Coding Best Practices
Learn coding best practices, such as clean and modular code, code efficiency, refactoring, documentation, and linting.
Working with Others Using Version Control
Version control is crucial for any coding project, but becomes even more important when working in teams. Another new area in working with teams is the code review, which you'll also learn about here.
Production Ready Code
Find more coding best practices here, such as handling errors, testing and logging, as well as addressing model drift in machine learning models.
Predict Customer Churn with Clean Code
Take a colleague's messy juypter notebook for building a customer churn prediction model and implement all of the clean code principles you have learned throughout the course!
Building a Reproducible Model Workflow
This course empowers the students to be more efficient, effective, and productive in modern, real-world ML projects by adopting best practices around reproducible workflows. In particular, it teaches the fundamentals of MLops and how to: a) create a clean, organized, reproducible, end-to-end machine learning pipeline from scratch using MLflow b) clean and validate the data using pytest c) track experiments, code, and results using GitHub and Weights & Biases d) select the best-performing model for production and e) deploy a model using MLflow. Along the way, it also touches on other technologies like Kubernetes, Kubeflow, and Great Expectations and how they relate to the content of the class.
Introduction to Reproducible Model Workflows
Dive into reproducible model workflows and machine learning operations, learning about use cases, its history, and what you'll build at the end of the course.
Machine Learning Pipelines
Build out machine learning pipelines, as well as learning how to version data and model artifacts.
Data Exploration and Preparation
Come up with re-usable processes for performing exploratory data analysis (EDA), cleaning and pre-processing data, and segregating/splitting data.
Data Validation
Validate data through deterministic and non-deterministic testing, and look at handling different parameters with PyTest.
领英推荐
Training, Validation and Experiment Tracking
Write an inference pipeline, validate and choose your best performing models from experiments, and test your final model artifacts.
Final Pipeline, Release and Deploy
Write a full end-to-end pipeline, release the pipeline, and deploy with MLflow.
Build an ML Pipeline for Short-term Rental Prices in NYC
Create a re-usable end-to-end pipeline for predicting short-term rental prices in New York City!
ML Model Scoring and Monitoring
This course will help students automate the devops processes required to score and re-deploy ML models. Students will automate model training and deployment. They will set up regular scoring processes to be performed after model deployment, and also learn to reason carefully about model drift, and whether models need to be retrained and re-deployed. Students will learn to diagnose operational issues with models, including data integrity and stability problems, timing problems, and dependency issues. Finally, students will learn to set up automated reporting with API’s.
Welcome to ML Model Scoring and Monitoring
This lesson will talk about goals for the course, when to use ML model scoring and monitoring, stakeholders, the history of the field, and the tools and dependencies you need to be aware of.
Model Training and Deployment
This lesson will talk about model training and deployment. We’ll focus on automating the training and deployment process and making sure that the trained, deployed models are ready to be monitored.
Model Scoring and Model Drift
This lesson will discuss model scoring and model drift, an important part of the continuous monitoring that makes sure your deployed model remains as accurate as possible.
Diagnosing and Fixing Operational Problems
There are problems that can come up in deployed projects. So this lesson will talk about diagnosing and fixing operational problems, a crucial part of the post-deployment machine learning process.
Model Reporting and Monitoring with API's
This lesson will discuss model reporting and monitoring with APIs which can be used as an automatic interface with your ML project.
Project: A Dynamic Risk Assessment System
The final project for this course will be a dynamic risk assessment system in which you will build and monitor an ML model to predict attrition risk.
Deploying a Scalable ML Pipeline in Production
This course teaches students how to robustly deploy a machine learning model into production. En route to that goal students will learn how to put the finishing touches on a model by taking a fine grained approach to model performance, checking bias, and ultimately writing a model card. Students will also learn how to version control their data and models using Data Version Control (DVC). The last piece in preparation for deployment will be learning Continuous Integration and Continuous Deployment which will be accomplished using GitHub Actions and Heroku, respectively. Finally, students will learn how to write a fast, type-checked, and auto-documented API using FastAPI.
Introduction to Deploying a Scalable ML Pipeline in Production
We'll introduce you to the course concepts of operationalizing our model, focusing on the ecosystem surrounding that model to successfully deploy it, and easily maintain it in production.
Performance Testing and Preparing a Model for Production
In this lesson, we will cover performance testing and preparing a model for production.
Data and Model Versioning
In this lesson, we will review git and then delve into Data Version Control (DVC) and the concepts of data provenance.
CI/CD
We cover the software engineering principles of automation, testing, and versioning. We put these into action using Continuous Integration and Continuous Delivery with Heroku and Github Actions.
API Deployment with FastAPI
Delve into FastAPI which leverages type hints to build a robust and self-documenting REST API. First, build out our API locally, test it, and the deploy to Heroku where you'll test it again live.
Deploying a ML Model to Cloud Application Platform
contact us
email - [email protected]