Notebooks, Datasets and Code for my Udacity Data Analyst Nanodegree Projects
There are 3 main projects covering data investigation, wrangling, and visualisation respectively.
Here, I analysed data containing information about 100,000 patient appointments in Brazil with a view to identifying what factors were most important in predicting whether a patient showed up for the appointment or not.
I gathered and used data from various sources including the Twitter API, performed cleaning tasks and provided insights on tweets from the WeRateDogs Archive.
I analysed the Prosper Loans Dataset and generated visualisations depicting distribution of singular variables and bivariate and multivariate relationships between variables.