Skip to content

Latest commit

 

History

History
147 lines (92 loc) · 4.54 KB

README.md

File metadata and controls

147 lines (92 loc) · 4.54 KB
Raw

Student Admission Prediction (SAP-Project)

Project Idea

This is a student project about predicting the chance of admission. For this project we are using Graduate Admission Dataset from Kaggle. We will use machine learning to analyze the data, find a model to predict the University Ranking and then visualize the result.

Requirments and Preparation

  • Required Libraries

  • Start Server

    • Create a virtual environment for the project: python -m venv venv
    • Activate the virtual environment for windows: venv\Scripts\activate
      • Activate the virtual environment for Linux/macOS: source venv/bin/activate
    • Install required libraries in the project: pip install dash pandas numpy joblib
    • Start server: python app.py

Implementation approach

Dataset:

https://www.kaggle.com/mohansacharya/graduate-admissions?select=Admission_Predict_Ver1.1.csv

Algorithms:

  • Regression
    • DecisionTree
    • Linear Regression
    • RandomForest
    • KNeighbours
    • SVM
    • AdaBoostClassifier
    • GradientBoostingClassifier
    • Ridge
    • BayesianRidge
    • ElasticNet
    • HuberRegressor

Tools:

  • DASH/Plotly

Project Arcithecture:

  • Machine learning model: regression with RandonForestRegressor
  • Backend: Flask which is embedded in Dash
  • Frontend: Dash/Plotly

Visualization:

Home

Home

Dataset

Dataset

Dashboard

Dashboard'

Machine Learning

ML

Prediction

Prediction

SAP-Project on GitHub:

https://github.com/LameesKadhim/SAP-project

SAP-Project on Heroku:

https://predict-student-admission.herokuapp.com/

SAP-Project Video Trailer:

https://youtu.be/rXDHiqIxYuQ

Deployment steps on Heroku

  • Step 1. Create a new folder for your project:

    $ mkdir sap-project

    $ cd sap-project

  • Step 2. Initialize the folder with git and a virtualenv

    $ git init // initializes an empty git repo

    $ virtualenv venv // creates a virtualenv called "venv"

    $ venv\Scripts\activate // Activate the virtual environment for windows

    -uses the virtualenv for linux and Macos: $ source venv/bin/activate

    You will need to reinstall your app's dependencies with this virtualenv:

    $ pip install dash

    $ pip install plotly

    You will also need a new dependency, gunicorn, for deploying the app:

    $ pip install gunicorn

  • Step 3. Initialize the folder with the (app.py), requirements.txt, and a Procfile for deployment

    content of Procfile is --> web: gunicorn app:server

    creation of requirements.txt file:

    requirements.txt describes your Python dependencies. You can fill this file in automatically with:

    $ pip freeze > requirements.txt

  • Step 4 Initialize Heroku, add files to Git, and deploy

    $ heroku create my-dash-app # change my-dash-app to a unique name

    $ git add . # add all files to git

    $ git commit -m 'Initial app boilerplate'

    $ git push heroku master # deploy code to heroku

Contributors