This is a project for Udacity's Machine Learning Nanodegree. It's a Jupyter notebook, along with supporting Python code, that looks at data from who survived the sinking of the Titanic, and explores a manual decision-tree algorithm for predicting whether or someone survived based on features like sex, age, etc. The goal was to get a predictve accuracy greater than 80%.
Concepts explored in this project:
- basic decision tree algorithm
- pandas, numpy, scikit-learn, and matplotlib Python libraries
- iPython and Jupyter notebooks
Relevant classes:
To get started:
- Download/clone the repository
- To view the finished product, open
Titanic_Survival_Exploration.html
in a web browser - To view the Jupyter notebook, it's recommended you install Jupyter and Anaconda. Once those are installed, navigate to the project root directory and run the following command:
jupyter notebook titanic_survival_exploration.ipynb
This will open the Jupyter Notebook software and project file in your web browser.