This paper uses fake Facebook data on friend's birthdays to explore how these birthdays are distributed. It demonstrates some ggplot visualisations, lubridate functionalities for working with date variables and dplyr functions for manipulating datasets.

This paper uses data from www.gapminder.org to perform a exploratory analysis of the evolution of life expectancy at birth and DTP3 Immunization among 1-year-old Infants accross the world. We then introduce GDP/capita to identify correlations.

This is the capstone project for the JHU Data Science specialization.

This is the slide deck for the JHU Capstone project. It pitches my Shiny application for a next word predictor.

This is the interim report for the captone project at the end of JHU's Data Science Specialization on Coursera. I describe the basic pre-processing tasks and general data distribution.

This is a 5-slide pitch for the Shiny App that I developed as part of the Coursera Developing Data Products course: https://lucfrachon-ds.shinyapps.io/TitanicLightDataset/ The application is based on the Titanic light dataset provided in R, of which a more elaborate version can be found on Kaggle.

This is the final project for the Practical Machine Learning course from John Hopkins University on Coursera. Using data collected through accelerometers worn by a group of people performing weight lifting, we fit classification algorithms to the data to predict whether the exercise was performed correcty or with different types of typical errors.