This project demonstrates a simple linear regression model built from scratch using a small two-dimensional dataset.

Dataset: 99 observations, 2 numerical variables (feature and target).

Goal: Predict the target variable based on the feature input using a best fit linear model.

Process:

    Cleaned and prepared raw data

    Applied linear regression manually (without using high level libraries like scikit-learn)

    Visualized the best fit line against the data points

    Evaluated model performance using basic error metrics (such as Mean Squared Error, R-squared)

This project highlights the fundamental concepts of supervised machine learning and regression analysis, with a focus on core algorithm understanding rather than automated library functions.