Simple Regression - Anatomy, Scikit-learn vs Math Algorithm

1-Mar 2018 - 18:00

Dearest Barrel AI Monkeys,

Linear regression, we have all been taught about it in primary school but it also happens to be one of the most commonly used types of predictive analysis classified under supervised learning. Regression attempts to model the relationship between two variables by fitting a linear equation to observed data. One variable is considered to be an explanatory variable, and the other is considered to be a dependent variable; eg. relationship between the weights and heights of individuals.

Barrel AI Monkey Melina will during this evening take you back to the basics in regression modeling, demonstrate and compare two "versions" of regression algorithms 1) scikit-learn and 2) model build from scratch based on the math behind; in python. Melina is on her ML evolving journey with Master in Computer Science from Lund University 1999-2005, years when she was for the first time introduced to AI and data structures and algorithms in general.

It will be a hybrid evening - demo & workshop so bring your own laptop and stay tuned here for more information about prerequisites and github link to the source code. If you want your own 2 variables dataset to be tested on the models prepare it in advance and send it in as .csv file to

* Level = Basic/Intermediate
* Other info = Yes, there will be pizza and refreshments during the evening :-)

Please find the code that we will be using, and the most simple datasets.

Make sure you can open the files and that you have some python environment. I am using Python 3.5.2.

J, M & M Monkeys