Kaggle: Titanic Challenge
This is my take on the Kaggle Titanic Challenge, I used Sklearn's Logistic Regression to produce an accuracy of 76.5%. I performed mild preprocessing on the data, which included dividing the fares and ages into 4 categories, allowing for a competely numerical dataset. I dropped Name, Cabin, Ticket, and Embarked from the data, proving either too challenging or irrelevant for our purposes. The name could have potential to be used, and I plan to change that in later revisions.
- Pandas (Data handling)
- Numpy (General Operations)
- Scikit-Learn (Logistic Regression Model)
All the data and code for the project can be found in this repo, as well as my output.