End to End Machine Learning Tutorial — From Data Collection to Deployment

Disclaimer: code and demo at the end of the article.

This started out as a challenge. I wanted with a friend of mine to see if it was possible to build something from scratch and push it to production. In 3 weeks. This is our story. Here for more posts like this.

In this post, we’ll go through the necessary steps to build and deploy a machine learning application. This starts from data collection to deployment and the journey, as you’ll see it, is exciting and fun.

As you see, this web app allows a user to evaluate random brands by writing reviews. While writing, the user will see the sentiment score of his input updating in real-time along with a proposed rating from 1 to 5.

The user can then change the rating in case the suggested one does not reflect his views, and submit.

You can think of this as a crowdsourcing app of brand reviews with a sentiment analysis model that suggests ratings that the user can tweak and adapt afterward.

To build this application we’ll follow these steps:

1. Collecting and scraping ? customer reviews data using Selenium and Scrapy
2. Training a deep learning sentiment classifier ? on this data using PyTorch
3. Building an interactive web app using Dash ?
4. Setting a REST API and a Postgres database ?
5. Dockerizing the app using Docker Compose ?
6. Deploying to AWS ?

All the code is available in our Github repository and organized in independent directories, so you can check it, run it and improve it.

Let’s get started!