This repository is an accumulation of analysis that I have been running on the Titanic dataset, from the Kaggle Titanic competition.
I started off by writing my own analysis and visualization scripts, and gradually incorporated more established ML methods.
I will be writing up from time to time some explanatory entries, of what I did. For now, you can refer to the titanic_class.py file, which contains the main Titanic class I wrote that loads the data and offers methods to analyze them. There are also a few run*.py files which contain scripts for doing one analysis or another, using the Titanic class.