Please refer to the description given in the repository to know more about the data set that has been chosen for this project. Apart from that, here are a few more details you may need to know.
This project has been divided into 3 parts:
- Description
- A brief rundown of what will be done, and what is covered in this project.
- Data Cleaning
- Importing libraries, splitting, dropping, or converting features, etc.
- Data Pre-Processing & Model Training and Testing
- Pre-Processing, Normalizing the data, Data Visualization, Regression techniques, and a Summary.
Please view these files in the stated order only.
Each link above takes you to the respective pages of the project. To open the file in Google Colab, please click on the option present in the beginning of the file. Once the notebook is open, please upload the respective files needed for that notebook, which have been provided in the repository.
I will give a brief conclusion here, but to view the summary, please see the final section of the Data Pre-Processing & Model Training and Testing notebook.
After observing many different accuracies and correlations, I observed that for a student to do well in his/her final test, they must do well in the penultimate test as well.
| MODEL TYPE | ACCURACY |
|---|---|
| LINEAR REGRESSION | Data Set -- 1 : 93.09% , Data Set -- 2 : 94.33% |
| MULTIVARIATE POLYNOMIAL REGRESSION | Data Set -- 1 : 93.11% , Data Set -- 2 : 94.33% |