A step-by-step guide that goes through data exploration, feature engineering, model training, and fine-tuning — You’ve probably heard about the Titanic challenge on Kaggle. No? Don’t worry: it’s a competition where the goal is to predict a given passenger’s survival or death based on a set of variables (i.e. features). These variables include information such as age, gender, or class on the boat.

An overview of the latest release of Tweepy — Accessing external data from social networks like Twitter is valuable in many situations. Whether you’re a big company or an individual, this helps conduct and enrich analyses on particular topics, monitor the competition, evaluate the social reputation of a given product, analyze customer reviews, follow reactions to recent events, etc. …

Towards building, shipping, and deploying your apps with a peace of mind — Docker is a great tool to easily develop your applications, ship them into containers and deploy them everywhere. In my job as a data scientist, I frequently use Docker whenever I need to package an application that has multiple services underneath (such as a back-end, a database, a front-end, etc)…

Don’t let these files overshadow other important languages of your project — If you’re a Github user like me, you probably know this little nifty section at the right-side of your repository: Languages. This section lists the programming languages that are involved in the project as well as the percentages at which they’re used: this gives a rough idea of the stack…

3-month condensed general best practices to make your siamese networks behave well and produce high-quality embeddings — A while ago, I participated in a data science challenge that took place at my previous company. The goal was to help marine researchers better identify whales based on the appearance of their flukes. More specifically, we were asked to predict for each image of a test set, the top…

A crazy Github functionality I overlooked for a long time — You’re probably familiar with Github. It’s an amazing platform to build software, collaborate with teammates and contribute to open-source projects. Github provides many functionalities that make your life easier as a developer. In this post, I’d like to introduce one killer Github product that is very powerful and yet less…

Remove these silent errors that may occur — The assertstatement in Python allows you to run internal unit tests and provides debugging aid that tests a condition. syntax: assert condition [, Error Message] If the condition is true, nothing happens. Otherwise, an AssertionError exception with an optional error message is raised. An example where the assert statement is useful Let’s say you want to compute a…

How to apply some ideas from the 12-factor app manifesto — In a recent video that covers DevOps best practices for launching a SaaS platform, ArjanCodes briefly discusses the 12-factor app, a manifesto written by Heroku engineering teams about building and scaling cloud-based applications. I was intrigued by the content of this document so I immediately looked it up on Google…

Learn about MLBox to quickly and efficiently train an automated machine learning pipeline for a classification problem in python — Today’s post is very special. It’s written in collaboration with Axel De Romblay, the author of the MLBox Auto-ML package that has gained a lot of popularity these last years. If you haven’t heard about this library, go and check it out on Github: It encompasses interesting features, it’s gaining…