Training and Deploying an ML Model as a Microservice

ML as a Service, Sentiment Analysis, NLTK, FaaS, Docker Container
Jon Peck
5 weeks · 5-10 hours per week
In this liveProject, you’ll fill the shoes of a developer for an ecommerce company. Customers provide reviews of your company’s products, which are used to give a product rating. Until now, assigning a rating has been manual: contractors read each review, decide whether it’s positive or negative, and assign a score. Your boss has decided that this is too expensive and time consuming. Your mission is to automate this process, dramatically increasing the speed of rating calculations, and decreasing the cost to your company. To complete this project you will have to train a machine learning model to recognize and rank positive and negative reviews, expose this model to an API so your website and partner sites can benefit from automatic ratings, and build a small webpage using FaaS, containers, and microservices that can run your model for demonstration.

Prerequisites

This liveProject will benefit both full-stack web developers and data scientists. If you’re a web developer, you’ll expand your skill set with valuable data science knowledge. If you’re a data scientist, you’ll develop techniques for deploying and demonstrating your models. To begin this liveProject, you will need to be familiar with the basics of Python. It would be helpful, but not essential, to know

TOOLS
  • Basics of Lambda or another FaaS
  • Basics of Docker
  • Basics of HTML & JavaScript
  • Basics of AWS or another IaaS provider
TECHNIQUES
  • Basics of NLP

you will learn

In this liveProject, you’ll learn the diverse skill set necessary to design, create, host, and give a live demonstration of a machine learning model. You’ll learn how all parts of machine learning tie together, and how to effectively deploy a model to production.

  • Determine the tools and frameworks for your machine learning projects
  • Compare the capabilities of off-the-shelf solutions with those of a self-trained model
  • Train and evaluate your own Sentiment Analysis model in Python using NLTK
  • Host your model as a callable API endpoint
  • Write a simple HTML and JavaScript site to connect to your model’s API

features

Self-paced
You choose the schedule and decide how much time to invest as you build your project.
Project roadmap
Each project is divided into several achievable steps.
Peer support
Chat with other participants within the liveProject platform.
Compare with others
For each step, compare your deliverable to the solutions by the author and other participants.
Book and video resources
Excerpts from Manning books and videos are included, as well as references to other resources.

project outline

Introduction

about this liveProject

1. Existing Machine Learning Services

1.1. Existing Machine Learning Services

1.2. The Absolute Python Basics

1.3. Exploratory Data Analysis

1.4. Submit Your Work

Solution

2. Training Your Own ML Model

2.1. Training Your Own ML Model

2.2. Implementing Your Own Spam Filter

2.3. Text Mining and Text Analytics

2.4. Submit Your Work

Solution

3. Deploying as a FaaS

3.1. Deploying as a FaaS

3.2. Your First Lambda Function

3.3. Submit Your Work

Solution

4. Deploying as a Container Service

4.1. Deploying as a Container Service

4.2. Discovering Docker

4.3. Building Your Own Docker Images

4.4. Submit Your Work

Solution

5. Integrating Your Microservice

5.1. Integrating Your Microservice

5.2. Review of the XMLHttpRequest API

5.3. Debugging CORS Requests

5.4. Submit Your Work

Solution

Summary

Project Conclusions

FAQs

placing your order...

Don't refresh or navigate away from the page.
liveProject $25.00 $50.00 self-paced learning
Training and Deploying an ML Model as a Microservice (liveProject) added to cart
continue shopping
go to cart
Prices displayed in rupees will be charged in USD when you check out.

project author

Jonathan Peck
Jon Peck is a full-stack developer and educator with a focus on DevOps and machine learning. Jon currently works as a technology advocate for GitHub. His prior positions include Algorithmia (a Seattle-based MLOps company backed by Google's AI fund), Massachusetts General Hospital, Cornell University, a bevy of small startups, and independent consulting. He constantly strives to make technical concepts digestible, demonstrating the value of new technology at every level, from developers through execs, and has been honored to speak at AI Next, API World, DeveloperWeek, O'Reilly AI, ODSC, and OSCON.