After a long time, I’m back! 🎉 I spent most of my time doing some CS courses, including CS50, and I even got the CS50 certificate. Besides that, I worked on some really cool projects! One of them is an AI interview project—it’s not that complex, but it was such an awesome experience to build. You can check out the video down below!

I recently added another variable to my project, but I ran into an issue. As I started collecting data for this new variable over time, I lost track of which apartment corresponded to which page 😂 . As a result, I’ll need to start the data collection process from scratch 🤦‍♂️ . On the bright side, I’ve created additional visualizations and will continue gathering more data. Once I have enough, I’ll perform exploratory data analysis (EDA) and then train the model. Finally, I’ll compare the new model’s predictions to the previous one to evaluate improvements

I performed an EDA (Exploratory Data Analysis) and decided to delete house sizes that are above 300 sqm. Then, I stored the output in a new CSV file to use for my model. You can see in the picture the before and after, as well as the code I used to sort the data and store it. the code is pretty simple

Glad that Gradio exists so I can make a quick user interface for my ML project.

Great, it looks much better now! This time, I've added more data and used a quadratic function, also known as a polynomial of degree 2. Explanation of Polynomial Functions: A polynomial function is a mathematical expression that consists of terms made up of a variable raised to non-negative integer powers and coefficients. For example, a polynomial of degree 2 (quadratic) takes the form: y=ax2+bx+c In this case: a, b, and c are constants (coefficients), x is the variable (input feature), The highest power of x is 2, making it a quadratic function. Polynomial regression extends linear regression by fitting a model that can capture more complex relationships between variables by incorporating these higher-degree terms. A quadratic (second-degree) polynomial, for example, can fit data with a curved relationship, while a linear model can only fit a straight line. By using polynomial regression, you allow the model to fit curves rather than just straight lines, which can help in situations where the relationship between the input and output is nonlinear.