Introductory project to Linear Models, Decision Trees and Ensemble Methods. It includes various ways to train a model and covers the most significant theories of basic machine learning, such as:
- Overfitting: the most common ways to face this issue are provided, with detailed explanation and documentation.
- Model-tuning: finding the best parameters for the model, while avoiding overfitting.
- Evaluation: various evaluation methods such as cross-validation.
- Data-preprocessing: handling of missing and categorical values, one hot encoding and normalization.
Instructions: To run each demo, you will need a dataset, which can be found under the data directory and inside the folder corresponding to the demo you are running.