Data Science Exercises

Predicting obesity levels

Data wrangling and machine learning exercise in Spark using R and SparklyR. RMarkdown document with the workflow available to download.

Pycaret Experiment

Finding an algorithm able to predict whether a single record of meteorological data belongs to a place in the northern, central, or southern area of the UK using historical weather data and Pycaret library. Reproducible Jupyter notebook with workflow

Scikit-Learn Clustering

Analyzing historical weather data with Python - Machine learning clustering with Scikit-Learn + Folium visualization. Reproducible jupyter notebook with the machine learning workflow and cleaning of the data.

Ploting geospatial data with R

Live births in Scotland visualization using Public Health Scotland and Scottish goverment open data. Very easy to follow exercise exploring and plotting spatial data - Reproducible RMarkdown document.

Fetching Stock Data

How to fetch stock data from Yahoo!Finance using Python, R or Julia language. The featured stocks in the exercise are my investment bets for this year.

Health Data Analysis

Analysing Commom causes of unintentional injuries in Scotland. Descriptive statistisc and visualizations on a 100% reproducible RMarkdown document.