MnCSSJ4x / IIITB-Course-Recommendation-System Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

A course recommendation system based on K Means Clustering and SVD along with comparisions with user based collaborative filtering on a dataset of IIITB students. Given the ratings of core subjects by students, we give the top 5 subjects to take as an elective

0 stars 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 44 Commits
.ipynb_checkpoints		.ipynb_checkpoints
Notebooks		Notebooks
Plots		Plots
Problem Statement		Problem Statement
Resources		Resources
__pycache__		__pycache__
flagged		flagged
.DS_Store		.DS_Store
Colaborative Filtering.ipynb		Colaborative Filtering.ipynb
Course Recommendation System.xlsx		Course Recommendation System.xlsx
Kmeans.py		Kmeans.py
Presentation.pdf		Presentation.pdf
README.md		README.md
SVD.py		SVD.py
SVD_fixed.py		SVD_fixed.py
main.ipynb		main.ipynb
mainWithMean.ipynb		mainWithMean.ipynb
main_SVD_KMeans.ipynb		main_SVD_KMeans.ipynb
main_withoutDM.ipynb		main_withoutDM.ipynb

Repository files navigation

Course Recommendation System

Submitted by:

IMT2020001 - Srinivas Manda
IMT2020003 - Karanjit Saha
IMT2020084 - Arya Kondawar
IMT2020502 - Monjoy Narayan Choudhury

Files Submitted

Inside the zip following files are present:

Readme.md : This readme file.
Presentation.pdf: The presentation file used for the oral presentations.
Code: A folder that consist of:
- Colaborative Filtering.ipynb: A jupyter notebook where colaborative filtering user based is implemented.
- KMeans.py: is the python file that contains our KMeans implementation to be used by the other notebooks
- SVD.py: is the python file that contains our SVD and reduced SVD implementation to be used by the other notebooks
- Course Recommendation System.xlsx: The dataset
- mainWithMean.ipynb: This implements approach 1 in presentation with NaNs replaced as mean of the subject.
- main_SVD_KMeans.ipynb: This implements SVD followed by KMeans(approach 2).
- Notebooks: Consist of jupyter notebooks for various trials we tried to do. These notebooks are mostly to play around and verify our results with sklearn KMeans and SVD. Also consist of the notebook used to the initial Exploratory Data Analysis (EDA.ipynb)

Instructions to run

User must have a valid jupyter notebook setups and environment setup. Other than that one must have pandas, numpy installed as a bare minimum.

About

A course recommendation system based on K Means Clustering and SVD along with comparisions with user based collaborative filtering on a dataset of IIITB students. Given the ratings of core subjects by students, we give the top 5 subjects to take as an elective

Report repository

Releases

No releases published

Packages

No packages published

Contributors 2

Languages