Regression Datasets & Analysis

This repository contains the implementation of a custom Decision Tree Regressor built from scratch in Python. Below are the details for the datasets used to benchmark the model.

1. Student Performance

Predicts a student's performance index based on study hours, sleep, and previous scores. This dataset is ideal for testing simple linear relationships.

• Source: Kaggle - Student Performance (Multiple Linear Regression)
• Target Variable (y): Performance Index
• Key Features: add

2. Household Income

A dataset designed for predicting household income based on demographic and employment factors. Good for testing the model's ability to handle economic data distributions.

• Source: Kaggle - Household Income Analysis
• Target Variable (y): Income
• Key Features: add

3. Cancer Data

Epidemiological data used to predict cancer mortality rates or incidence based on population demographics.

• Source: Kaggle - Cancer Regression
• Target Variable (y): target_deathrate
• Key Features: add

4. Possum Measurements

Physical measurements of possums caught in Australia. This dataset is excellent for biological regression tasks and handling mixed categorical/numerical data.

• Source: Kaggle - OpenIntro Possum
• Target Variable (y): footlgth
• Key Features: add

---