A Jupyter notebook for the Kaggle Titanic Challenge competition.
Based on a passenger list and some known characteristics (Sex, Age, Embarkment Port etc.), create a model to predict whether a passenger survived the sinking of the Titanic.
This random forest model with engineered Title and FamilySize features scored at 80.86% for 641st place out of 8974 entries.
More performance could be squeezed out with feature engineering (for example, ticket letters may add value. My NaN 'age' filling solution could probably be done better, etc.), but I don't know if I'll get around to it. If I do, I'll update it.
{% notebook notebooks/KaggleTitanic.ipynb %}