Set up your ML Model for Deployment

In my previous article, First Steps into Building Your Data Science Portfolio Website, where I mentioned what type of projects should be displayed on the portfolio section of your website, to tell how you are well vast with all the skills highlighted in the About section. Remember I said, links to deployed projects, end-to-end machine learning projects.

Deployment of an ML model simply means the integration of the finalized model into a production environment and getting results to make business decisions.

This article is dedicated to those that’d like to learn how to build end-to-end data science and machine learning projects.

The prior condition or prerequisite to go ahead with this tutorial is that you must be already comfortable with all that is listed below as we wouldn't be going through each of them in this article.

• Data Collection.
• Exploratory Data Analysis with numpy and pandas
• Data Visualization.
• Sklearn for building and training models.

Now, we assume you’ve done everything above on a particular dataset and all you are left with is to host this model as a RestAPI.

I feel examples always make things clearer, so I will be explaining this using the popular titanic dataset…