From Design to Deploy: The Whole Lifepath Of A Machine Learning App

From Design to Deploy: The Whole Lifepath Of A Machine Learning App

The whole Lifepath of a Machine Learning app. The step-by-step description to design, develop, deploy and maintain a Machine Learning application. Through an example. With code.

The step-by-step description to design, develop, deploy and maintain a Machine Learning application. Through an example. With code.

Why should you read a 25min reading time medium post? Well, here I tried to condense the complete path of a machine learning project, from data analysis to deployment on AWS EC2.

Introduction

In the age of innocence, after following our first ML courses, we all thought that to be a data scientist, working on notebooks would have been enough.

Once we left kindergarten, we learnt that this is far from the truth.

Nowadays there is plenty of other skills a data scientist must have other than knowledge of machine learning algorithms (or more often library usage).

This post aims to go through an example (I will keep it easy on the model part) of a complete machine learning task example from design to deploy and maintain.

I do this because I have spoken and worked with dozens of data scientists, also not so junior in their career, and I got a picture of great confusion about the role. Data science is a great activity, but often data scientist codes are really difficult to bring in production (and even to read) because they have been written without thinking of the real-world use of the model.

I find this is a matter of respect — for the whole stack of poor devils working on the model after the data scientist — provide a solid and simple model deploy.

Furthermore, these days docker is a skill highly requested in all data science job offers, so why not take some time to see how dockerise a machine learning application?

The ubiquitous image used to illustrate the machine learning project lifecycle. Image by [https://www.jeremyjordan.me/ml-projects-guide/]

The figure above is nice, but I think it may appear a bit too abstract. I will use my poor drawing abilities to redesign it as follows.

A simplified model lifecycle. Image poorly drawn by the author.

The image above is also the schema we are going to follow in this post.

deployment docker machine-learning data-science tensorflow

Bootstrap 5 Complete Course with Examples

Bootstrap 5 Tutorial - Bootstrap 5 Crash Course for Beginners

Nest.JS Tutorial for Beginners

Hello Vue 3: A First Look at Vue 3 and the Composition API

Building a simple Applications with Vue 3

Deno Crash Course: Explore Deno and Create a full REST API with Deno

How to Build a Real-time Chat App with Deno and WebSockets

Convert HTML to Markdown Online

HTML entity encoder decoder Online

Deploy a Machine Learning Model | Data Science | Machine Learning

Deploy a Machine Learning Model | Data Science | Machine Learning . I will train and Deploy a Machine Learning Model using Flask step by step. I will first train a model, then I will work to serve our model, and at the end I will deploy our machine learning model.

How To Build A Data Science Career In 2021

In Conversation With Dr Suman Sanyal, NIIT University,he shares his insights on how universities can contribute to this highly promising sector and what aspirants can do to build a successful data science career.

5 stages of learning Data Science

5 stages of learning Data Science and how to ace each of them

Most popular Data Science and Machine Learning courses — July 2020

Most popular Data Science and Machine Learning courses — August 2020. This list was last updated in August 2020 — and will be updated regularly so as to keep it relevant

How I'd Learn Data Science If I Were To Start All Over Again

A couple of days ago I started thinking if I had to start learning machine learning and data science all over again where would I start?