Lets do Clustering! (Unsupervised machine learning) theory + practical!

GITHUB REPO - https://github.com/central-ldn-data-sci/CLDSPN-lets-do-clustering

Clustering is a staple in any data scientist's toolbox! It's used to help find if there are any hidden groups within a data set. It's most commonly used in customer segmentation for targeted marketing, but can also be applied to things like movie descriptions to automatically find genre's.

Come along and learn about how one of the most popular clustering algorithms works, along with how to use it, and then of course get your hands dirty using it on different data sets!

Meetup structure:

• We will start with a short talk on how K-mean's clustering works

• Then how to use it (choosing the correct number of clusters)

• Finally you get your hands dirty clustering some interesting data sets

Learning Outcomes:

We aim to get everyone to the level were they have good intuition around clustering with k-means and be able to comfortably implement it.

Software Requirements:

Please ensure that you have Annaconda Navigator (https://www.anaconda.com/download/) installed with Python 3.

---

As usual this meetup will be very relaxed and we encourage people of all skills in python and R to come along and learn from each other. We'll work on the problem for a few hours then have some pizza and drinks thanks to our new sponsor Pivigo.

---

Topics:

• Un-supervised machine learning

• K-means clustering

• Elbow analysis (for finding the right number of clusters)

• Sci-Kit Learn (python machine learning package)

Bring:

• Laptops, Charging Cords, an Inquisitive Spirit

HOW TO FIND IT

Please head to norfolk place (W2 1PE - see below #1), and its at the faculty of medicine. The entrance (see below #2) is opposite the cambridge wing and might be behind the mobile MRI scanner (it moves so it might not!). On the day I will be meeting people at the door to take them through to the room, however if I am not outside when you arrive either wait and I will be out shortly, or go in and speak to the security guard. If you explain you are here for a data science meetup they will hopefully let you in and explain where to go.

#1

https://secure.meetupstatic.com/photos/event/6/e/5/7/600_456268247.jpeg

#2

https://a248.e.akamai.net/secure.meetupstatic.com/photos/event/a/7/5/5/600_452682837.jpeg