A visual demonstration of how the machine "learns" with a linear regression model using python and matplotlib.
You can see also a video that i've posted on linkedin about this project if you speak portuguese: Linear Regression Demo Linkedin
- Understood how a linear regression model works and how the model fits the data
- Learnt how to customize plots in matplotlib
- Created a function to generate data with a linear shape
- Calculated the accuracy of the model using MAE (mean absolute error)
- Clone the repository
- Install required dependencies with 'pip install -r requirements.txt'
- Run 'main.py'
After executing the file, a matplotlib window will appear, to interact with it you can click on the 'next iteration' button.
When you click on this button the model will use one more data point each time, so if you click 3 times, it will use 3 data points to fit.
It's possible to see that when the model progressively uses more data, the error indicator (MAE) will dicrease and the model function will be closer to the real function.
Beyond that, the line that the model creates will follow better the generated data.