Post-Graduation Admission Predictor

Kaggle Dataset Card: Kaggle

Objective

• Develop a predictive model to estimate the likelihood of a student's post-graduation application being accepted.

• Identify the key factors that can enhance a student's chances of acceptance.

• Determine if there is a singular decisive factor that can influence the acceptance or rejection of a student's application.

Getting the Dataset

1. Visit Kaggle

2. Sign Up or Sign In to your Kaggle Account and simply download the CSV file named Admission_Predict_Ver1.1.csv.

3. (Optional) Rename the dataset to something simple like dataset.csv

About the Dataset

The CSV file contains 500 rows columns with 9 columns. First column is the Serial Number of the application so we can discard it. The remaining 8 columns are as follows:

1. GRE Score (out of 340)
2. TOEFL Score (out of 120)
3. University Rating (out of 5)
4. Statement of Puropose Rating (out of 5)
5. Letter of Recommendation Rating (out of 5)
6. GPA Score (out of 10)
7. Research Experience (0 for No and 1 for Yes)
8. Chance of Admit (a decimal value between 0 and 1)

Columns 1 through 7 are the predictors or features of our model and Column 8 is our target variable.

Tip

You can change the datatypes of the features to reduce your memory footprint while developing the model.

Notebooks

Notebook	Description
scikit-learn	Using only scikit-learn package
flaml	Using FLAML library

Setup Environment

I have used Python 3.11 on a Ubuntu 22.04 machine.

Method 1: Setup environment on your local machine

1. Clone the repository:

git clone https://github.com/arnabd64/Graduate-Admission-Prediction.git
cd Graduate-Admission-Prediction

2. Setup a python virtual environment using virtualenv or conda.

# using virtualenv
python -m venv .venv

# using conda
conda create -n predict python=3.11

# activate the environment
conda activate predict      # when using conda
source .venv/bin/activate   # virtualenv on GNU/Linux or MacOS
.venv/Scripts/Activate.ps1  # virtualenv on Windows

3. Install the python packages from requirements.txt by executing pip install -r requirements.txt

4. Your environment is ready

Method 2: Using Google Colab or Kaggle

At the beginning of the notebook, add the following command in a new cell and execute it:

!pip install scikit-learn seaborn

Method 3: Using Dev Containers on VS Code

Important

This method requires the following prerequisites:

• Docker installed on your local machine.
• Extensions: GitHub and Dev Containers installed on your Visual Studio Code.
• Your Visual Studio Code installation being connected with your Github account for seamless git pull/push operations.

1. Open VS Code and press: Ctrl + Shift + P and type in Clone Repository in a Named Container.
2. First select Github as the source and then arnabd64/Graduate-Admission-Prediction as the name of the repo.
3. Follow the steps provided by VS code and environment will be setup for you.