“Out of clutter, find simplicity.” — Albert Einstein

Hi all,

I am a freelance data scientist who is interested in various areas spanning from data analysis and data visualization to machine learning and deep learning. For more information, inquiries or collaborations check out the about page.

Featured Projects

Here I have selected a series of articles that are the efforts of projects which I have particularly enjoyed and that I wish to showcase. For more articles have a look at the rest of my blog.
Photo by Konstantin Kolosov on Pixabay

Determining the Causes of Diabetes Readmissions in Hospitals

Diabetes is quickly becoming one of the major causes of mortality in the developing world, due to changing lifestyles and massive urbanization of the population, and is currently affecting over 10% of the US population alone according to the CDC. Millions of deaths could be prevented each year by use of better analytics, such as non-invasive screening, tailor-made solutions and hospital readmissions.

Photo by Sebastian Pena Lambarri on Unsplash

Predicting Earthquake Damage With Ensemble Learners

One of the main appeals of machine learning is that one can immediately start making fairly good data predictions without having estensive domain knowledge on the subject at matter, which at times can produce unexpected and surprising insights. This happens to be the case concerning the machine learning data set available at DrivenData on the Gorkha earthquake in Nepal, which on April 25, 2015 caused thousands of deaths and extreme hardship for all of the survivors, as well as massive damage to the country’s public buildings, infrastructure and private households.

Average weekday public bicycle traffic in London UK at 17:45 pm. The large blue and purple dots show the inflow to King's Cross and Waterloo train stations, while the light green and orange dots show the outflows from central London. There are also sizable, light green dots for dock stations in Hyde Park and Kensington Gardens and Queen Elizabeth Olympic Park.

Bicycle Use Visualization With Bokeh

I’ve dedicated some time to build an interactive scatter plot with Bokeh to show the average weekday bicycle traffic in London UK for 2019. The interactive plot displays the total and net traffic fluxes for 748 docking stations and 12940 bicycles in downtown London. The size of each data point corresponds to the total traffic flux given by the sum of the mean inflow and outflow, and the color shows the net flux given by the difference between the mean inflow and outflow. The blue-shifted colors represent a net inflow of bicycles while the red-shifted colors represent a net outflow.

Photo by Robert Keane on Unsplash

Public Bicycle Use in London During COVID Lockdown

The public bicycle share scheme in London has enjoyed an overwhelming success since its introduction in July 2010. The program is currently at its tenth year and has proven to be very popular among Londoners who now as of July 2020 have access to 781 docking stations and over 12,000 bikes throughout the city. However due to the lockdown caused by the COVID pandemic there has been a distinct change in the frequency of use of public transportion by city residents, and cycling has followed this trend as well.