Deployment of Machine Learning Models

Focused View

Soledad Galli,Christopher Samiullah

9:55:11

49 View

01 - Introduction

001 Introduction to the course.mp4

02:39

002 Course curriculum overview.mp4

05:18

003 Course requirements.mp4

03:51

004 Setting up your computer.html

005 Course Material.mp4

01:47

006 The code.html

007 Presentations.html

008 Download Dataset.html

009 Additional Resources for the required skills.html

010 How to approach the course.mp4

05:16

02 - Overview of Model Deployment

001 Deployments of Machine Learning Models.mp4

03:32

002 Deployment of Machine Learning Pipelines.mp4

04:15

003 Research and Production Environment.mp4

01:55

004 Building Reproducible Machine Learning Pipelines.mp4

05:01

005 Challenges to Reproducibility.mp4

10:07

006 Streamlining Model Deployment with Open-Source.mp4

06:07

007 Additional Reading Resources.html

03 - Machine Learning System Architecture

001 Machine Learning System Architecture and Why it Matters.mp4

02:35

002 03.2-Notes.pdf

002 Specific Challenges of Machine Learning Systems.mp4

03:42

003 03.3-Notes.pdf

003 Principles for Machine Learning Systems.mp4

06:43

004 03.4-Notes.pdf

004 Machine Learning System Architecture Approaches.mp4

06:40

005 Machine Learning System Component Breakdown.mp4

05:17

006 Additional Reading Resources.html

04 - Research Environment - Developing a Machine Learning Model

001 Research Environment - Process Overview.mp4

05:32

002 Machine Learning Pipeline Overview.mp4

05:14

003 Feature Engineering - Variable Characteristics.mp4

06:34

004 Feature Engineering Techniques.mp4

05:58

005 Feature Selection.mp4

09:47

006 Training a Machine Learning Model.mp4

02:49

007 Research environment - second part.html

008 Code covered in this section.html

009 Python library versions.html

010 Data analysis demo - missing data.mp4

10:09

011 Data analysis demo - temporal variables.mp4

04:21

012 Data analysis demo - numerical variables.mp4

07:16

013 Data analysis demo - categorical variables.mp4

06:58

014 Feature engineering demo 1.mp4

08:02

015 Feature engineering demo 2.mp4

07:50

016 Feature selection demo.mp4

04:29

017 Model training demo.mp4

03:54

018 Scoring new data with our model.mp4

09:44

019 Research environment - third part.html

020 Python Open Source for Machine Learning.mp4

11:19

021 Open Source Libraries for Feature Engineering.mp4

06:28

022 Feature engineering with open source demo.mp4

09:39

023 Research environment - fourth part.html

024 Intro to Object Oriented Programing.mp4

07:00

025 Inheritance and the Scikit-learn API.mp4

05:08

026 Create Scikit-Learn compatible transformers.mp4

05:42

027 Create transformers that learn parameters.mp4

06:10

028 Feature engineering pipeline demo.mp4

07:05

029 Should feature selection be part of the pipeline.mp4

03:14

030 Research environment - final section.html

031 Getting Ready for Deployment - Final Pipeline.mp4

05:39

032 Bonus Additional Resources on Scikit-Learn.html

external-links.txt

05 - Packaging The Model for Production

001 Introduction to Production Code.mp4

02:52

002 Repo for this section.html

003 Code Overview.mp4

12:02

003 dmlm-notebook-to-code-diagram.zip

004 Understanding the Reasoning Behind the Prod Code Structure.mp4

10:51

005 Reminder Download the Kaggle Data.html

006 Package Requirements Files.mp4

04:18

007 Working with tox [Do NOT skip - important].mp4

10:15

008 Migrating from Tox 3 to Tox 4.html

009 Troubleshooting Tox.html

010 Package Config.mp4

07:52

011 The Model Training Script & Pipeline.mp4

06:59

012 Introduction to Pytest [Optional].mp4

11:49

013 Feature Engineering Code in the Package.mp4

07:28

014 Making Predictions with the Package.mp4

09:06

015 Building the Package.mp4

06:28

016 Tooling.mp4

03:40

017 Section Notes & Further Reading.html

06 - Serving and Deploying the model via REST API

001 Running the API Locally.mp4

05:08

002 Understanding the Architecture of the API.mp4

04:18

003 Introduction to FastAPI.mp4

06:55

004 The API Endpoints.mp4

10:05

005 Using Schemas in our API.mp4

06:28

006 Logging in our Application.mp4

05:49

007 The Uvicorn Web Server.mp4

03:17

008 Introducing Railway App and Platform as a Service.mp4

00:27

009 What Is a Platform as a Service (PaaS).mp4

02:37

010 Why Use Railway as Our PaaS.mp4

03:27

011 Railway Links.html

012 Deploying our ML Application to Railway - Hands On.mp4

08:36

013 Limitations to Be Aware Of & Wrap Up.mp4

01:26

014 Section Notes & Further Reading.html

07 - Continuous Integration and Deployment Pipelines

001 Introduction to CICD.mp4

03:46

002 Setting up CircleCI.mp4

01:31

003 CICD Automation Overview Part 1.mp4

02:33

004 CICD Config Explanation.mp4

08:39

005 CICD Automation Overview Part 2.mp4

05:50

006 Using a Private Index Server (Gemfury).mp4

07:03

007 Hands on Run the CI Tests in your own Github Fork.mp4

04:13

008 Hands on Run the CI Deploy on Your Own Github Fork.mp4

07:18

009 Hands on Run the CI Publish on Your Own Github Fork.mp4

02:37

010 Section Notes & Further Reading.html

08 - Deploying The ML API With Containers

001 Docker Refresher [Optional - For those unfamiliarrusty with Docker].mp4

06:17

001 docker-notes.pdf

002 The Value of Docker and Containers.mp4

07:10

003 Understanding The Container Deployment Process.mp4

02:23

004 Docker Install Setup.html

005 Hands On Containerising the App Locally.mp4

04:28

006 Updating the CI Pipeline for a Container Deployment.mp4

06:48

007 Section Notes & Further Reading.html

09 - Differential Testing

001 Attention !!! - This section still works with old version of code.html

002 How to Use the Course Resources.mp4

03:46

002 Section5.3a-Notes.pdf

003 9.1 - Introduction.mp4

02:15

004 9.2 - Setting up Differential Tests.mp4

04:29

004 Section9.2-Notes.pdf

005 9.3 - Differential Tests in CI (Part 1 of 2).mp4

03:01

006 9.4 - Differential Tests in CI (Part 2 of 2).mp4

04:01

006 Section9.4-Notes.pdf

007 9.5 Wrap Up.mp4

01:41

007 Section9.5-Notes.pdf

10 - Deploying to IaaS (AWS ECS)

001 Attention!!! We are currently updating this section.html

002 12.1 - Introduction to AWS.mp4

02:55

003 12.2 - AWS Costs and Caution.mp4

02:37

003 Section12.2-Notes.pdf

004 12.3a - Intro to AWS ECS.mp4

04:09

004 Section12.3-Notes.pdf

005 12.3b - Container Orchestration Options Kubernetes, ECS, Docker Swarm.mp4

03:31

005 Section12.3-Notes.pdf

006 12.4 - Create an AWS Account.mp4

00:35

006 Section12.4-Notes.pdf

007 12.5 - Setting Permissions with IAM.mp4

03:24

007 Section12.5-Notes.pdf

008 12.6 - Installing the AWS CLI.mp4

03:01

008 Section12.6-Notes.pdf

009 12.7 - Configuring the AWS CLI.mp4

02:57

009 Section12.7-Notes.pdf

010 12.8 - Intro the Elastic Container Registry (ECR).mp4

01:16

010 Section12.8-Notes.pdf

011 12.9 - Uploading Images to the Elastic Container Registry (ECR).mp4

05:23

011 Section12.9-Notes.pdf

012 12.10 - Creating the ECS Cluster with Fargate Launch Method.mp4

04:43

012 Section12.10-Notes.pdf

013 12.11 - Updating the Cluster Containers.mp4

04:20

013 Section12.12-Notes.pdf

014 12.12 - Tearing down the ECS Cluster.mp4

00:53

014 Section12.13-Notes.pdf

015 12.13 - Deploying to ECS via the CI pipeline.mp4

02:42

015 Section12.14-Notes.pdf

016 12.14 - Wrap Up.mp4

01:34

016 Section12.15-Notes.pdf

11 - A Deep Learning Model with Big Data

001 Challenges of using Big Data in Machine Learning.mp4

02:09

002 Installing Keras.html

003 Download the data set.html

004 Introduction to a Large Dataset - Plant Seedlings Images.mp4

01:48

005 Building a CNN in the Research Environment.mp4

09:55

005 CNN-Analysis-and-Model.zip

006 CNNProdCode.zip

006 Production Code for a CNN Learning Pipeline.mp4

08:39

007 Reproducibility in Neural Networks.mp4

03:21

008 Setting the Seed for Keras.html

009 Seed for Neural Networks - Additional reading resources.html

010 13.8 - Packaging the CNN.mp4

07:05

010 Section13.8-Notes.pdf

011 13.9 - Adding the CNN to the API.mp4

04:01

011 Section13.9-Notes.pdf

012 13.10 - Additional Considerations and Wrap Up.mp4

02:53

012 Section13.10-Notes.pdf

12 - Common Issues found during deployment

001 Troubleshooting.html

001 Troubleshooting.pdf

13 - Appendix Former Section Serving the model via REST API

001 Appendix - PLEASE READ.html

002 7.1 - Introduction.mp4

03:18

002 Section7.1-Notes.pdf

003 Primer on Monorepos.mp4

01:53

003 Section5.3c-Notes.pdf

004 7.2 - Creating the API Skeleton.mp4

04:35

004 Section7.2-Notes.pdf

005 7.2b - Note On Flask.html

006 7.3 - Adding Config and Logging.mp4

04:10

006 Section7.3-Notes.pdf

007 7.4 - Adding the Prediction Endpoint.mp4

04:09

007 Section7.4-Notes.pdf

008 7.5 - Adding a Version Endpoint.mp4

02:05

008 Section7.5-Notes.pdf

009 7.6 - API Schema Validation.mp4

07:19

009 Section7.6-Notes.pdf

010 7.7 - Wrap Up.mp4

01:03

14 - Final Section

001 Congratulations.html

002 Bonus lecture.html

Description

Learn how to integrate robust and reliable Machine Learning Pipelines in Production

What You'll Learn?

Build machine learning model APIs and deploy models into the cloud
Send and receive requests from deployed machine learning models
Design testable, version controlled and reproducible production code for model deployment
Create continuous and automated integrations to deploy your models
Understand the optimal machine learning architecture
Understand the different resources available to productionise your models
Identify and mitigate the challenges of putting models in production

Who is this for?

Data scientists who want to deploy their first machine learning model

Data scientists who want to learn best practices model deployment

Software developers who want to transition into machine learning

What You Need to Know?

A Python installation

A Git installation

Confidence in Python programming, including familiarity with Numpy, Pandas and Scikit-learn

Familiarity with the use of IDEs, like Pycharm, Sublime, Spyder or similar

Familiarity with writing Python scripts and running them from the command line interface

Knowledge of basic git commands, including clone, fork, branch creation and branch checkout

Knowledge of basic git commands, including git status, git add, git commit, git pull, git push

Knowledge of basic CLI commands, including navigating folders and using Git and Python from the CLI

Knowledge of Linear Regression and model evaluation metrics like the MSE and R2

More details

Description
Welcome to Deployment of Machine Learning Models, the most comprehensive machine learning deployments online course available to date. This course will show you how to take your machine learning models from the research environment to a fully integrated production environment.

What is model deployment?
Deployment of machine learning models, or simply, putting models into production, means making your models available to other systems within the organization or the web, so that they can receive data and return their predictions. Through the deployment of machine learning models, you can begin to take full advantage of the model you built.

Who is this course for?
If youâ€™ve just built your first machine learning models and would like to know how to take them to production or deploy them into an API,
If you deployed a few models within your organization and would like to learn more about best practices on model deployment,
If you are an avid software developer who would like to step into deployment of fully integrated machine learning pipelines,
this course will show you how.

What will you learn?
We'll take you step-by-step through engaging video tutorials and teach you everything you need to know to start creating a model in the research environment, and then transform the Jupyter notebooks into production code, package the code and deploy to an API, and add continuous integration and continuous delivery. We will discuss the concept of reproducibility, why it matters, and how to maximize reproducibility during deployment, through versioning, code repositories and the use of docker. And we will also discuss the tools and platforms available to deploy machine learning models.
Specifically, you will learn:
The steps involved in a typical machine learning pipeline
How a data scientist works in the research environment
How to transform the code in Jupyter notebooks into production code
How to write production code, including introduction to tests, logging and OOP
How to deploy the model and serve predictions from an API
How to create a Python Package
How to deploy into a realistic production environment
How to use docker to control software and model versions
How to add a CI/CD layer
How to determine that the deployed model reproduces the one created in the research environment
By the end of the course you will have a comprehensive overview of the entire research, development and deployment lifecycle of a machine learning model, and understood the best coding practices, and things to consider to put a model in production. You will also have a better understanding of the tools available to you to deploy your models, and will be well placed to take the deployment of the models in any direction that serves the needs of your organization.

What else should you know?
This course will help you take the first steps towards putting your models in production. You will learn how to go from a Jupyter notebook to a fully deployed machine learning model, considering CI/CD, and deploying to cloud platforms and infrastructure.
But, there is a lot more to model deployment, like model monitoring, advanced deployment orchestration with Kubernetes, and scheduled workflows with Airflow, as well as various testing paradigms such as shadow deployments that are not covered in this course.

Want to know more? Read on...
This comprehensive course on deployment of machine learning models includes over 100 lectures spanning about 10 hours of video, and ALL topics include hands-on Python code examples which you can use for reference and re-use in your own projects.
In addition, we have now included in each section an assignment where you get to reproduce what you learnt to deploy a new model.
So what are you waiting for? Enroll today, learn how to put your models in production and begin extracting their true value.
Who this course is for:
Data scientists who want to deploy their first machine learning model
Data scientists who want to learn best practices model deployment
Software developers who want to transition into machine learning

User Reviews

Rating

average 0

Total votes0

Focused display

Hey, I am Sole. I am a data scientist and open-source Python developer with a passion for teaching and programming.I teach intermediate and advanced courses on machine learning, covering topics like how to improve machine learning pipelines, better engineer and select features, optimize models, and deal with imbalanced datasets.I am the developer and maintainer of Feature-engine, an open-source Python library for feature engineering and selection, and the author of Packt's "Python Feature Engineering Cookbook" and the "Feature Selection in Machine Learning with Python" book.I received a Data Science Leaders Award in 2018 and was selected as one of "LinkedIn’s voices" in data science and analytics in 2019.I worked as a data scientist for financial and insurance firms, developing and putting in production machine learning models to assess credit risk, process insurance claims, and prevent fraud.I love sharing knowledge about data science and machine learning. This is why I teach online, create and contribute to open-source software, and also speak at meetups, write blogs, and participate in podcasts.I've got an MSc in Biology, a PhD in Biochemistry, and 8+ years of experience as a research scientist at well-known institutions like University College London and the Max Planck Institute. I've also taught biochemistry for 4+ years at the University of Buenos Aires and mentored MSc and PhD students.Feel free to contact me on LinkedIn, follow me on Twitter, or visit our website for blogs about machine learning.

Christopher Samiullah

Instructor's Courses

My name is Chris. I'm a professional software engineer from the UK. I've been writing code for over a decade, and for the past five years I've focused on scaling machine learning applications. I've done this at fintech and healthtech companies in London, where I've worked on and grown production machine learning applications used by millions of people. I've built and maintained machine learning systems which make credit-risk and fraud detection judgements on over a billion dollars of personal loans per year for the challenger bank Zopa. I previously worked on systems for predicting health risks for patients around the world at Babylon Health. In the past, I've worn a variety of hats. I worked at a global healthcare company, Bupa, which included being a core developer on their flagship website, and three years working in Beijing setting up mobile, web and IT for medical centers in China. Whilst in Beijing, I ran the Python meetup group, mentored a lot of junior developers, and ate a lot of dumplings. I enjoy giving talks at engineering meetups, building systems that create value, and writing software development tutorials and guides. I've written on topics ranging from wearable development, to internet security, to Python web frameworks. I'm passionate about teaching in a way that minimizes the time between "ah hah" moments, but doesn't leave you Googling every other word. Complexity is necessary for application in the real world, but too much complexity is overwhelming and counter-productive. I will help you find the right balance. Feel free to connect on LinkedIn (very active) or Twitter (getting more active in 2022)

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.