Visual Diagnostics for More Informed Machine Learning

I recently watched Rebecca Bilbro’s presentation at PyCon 2016 and thought I’d share a few of my short notes from her interesting presentation. Model Selection Triple When selecting a model, rather than going with your default favourite method, take 3 things into account: Feature analysis: intelligent feature selection and engineering Model selection: model that makes …

Read More
Never trust your factors

I recently helped a friend out with a dataset – she was struggling to merge the CSV files from two dataframes in R into one dataframe. I thought this would be quite simple and yet could not get it to work with merge or dplyr – it just kept giving me weird results. The problem was …

Read More
Python hmmlearn installation issues

I’ve recently started learning how to apply a Hidden Markov Model (HMM) to some states of honeybee behaviour in my data and have been trying to install Python’s hmmlearn library. Unfortunately I kept getting this frustrating error due to it being unable to locate NumPy headers: After a bit of searching I found the solution in a …

Read More
Hover Fly Mistaken For Bee
Mistakes in machine learning datasets

One of the things you realise once you start learning about machine learning is just how important a well-annotated dataset is that you can use for training. Your predictive model will only ever be as good as the labelled data you originally gave it. A little while back when I was trying to learn how …

Read More
Compiling C++ Code Using Caffe

As part of my PhD project, I have been writing a program in C++ to track hundreds of bees that I have tagged and to identify the pattern on the tags. Initially, I had thought that recognising the tags would be rather simplistic – I could threshold out the tags that are reflective under IR …

Read More
Interesting Readings

Work has kept me pretty busy lately but I’ve been meaning to try put together another post with some of the interesting readings I’ve come across. The first thing I’ll mention is that the IEEE (Institute of Electrical and Electronics Engineers) have released their rankings for programming language popularity. Python (ranked #4) and R (ranked #6) …

Read More
Image processing with scikit-image

I’ve been using OpenCV over the past couple of years for all my image processing work. It’s a really extensive and useful library, and just recently, OpenCV 3.0 was released, which included bindings for Python 3! Finally one of my last reasons to continue using Python 2 has disappeared. However, there is another image processing …

Read More
Machine Learning Graphics from Melanie Warrick’s PyCon 2014 Presentation

Recently, I watched Melanie Warrick’s great talk on getting started with machine learning at PyCon 2014. I linked to it in my post on materials to learn machine learning, however I wanted to write another post with pictures of some slides I took from her presentation which I found incredibly helpful. I strongly recommend watching the video and …

Read More
PyCon 2015 Talks I Found Interesting

Here are some of the PyCon 2015 talks I found rather interesting, please note that some of the talks that refer to machine learning have been linked to in my post here.

Read More
Materials for Learning Machine Learning

Lately, myself and a friend have become rather interested in learning more about machine learning. I’ve been trying to start a collection of learning materials that I either found useful or mean to go through at some point, and thought I’d write a post about it. I’m hoping this can help people who are just …

Read More