Predictive Web Browsing

University of Leuven – Machine Learning Project

Setup instructions

Make sure you are running Python 3.

Run pip install -r requirements.txt.

Add and enable the user script urlStreamHandler.user.js in your browser. (Using Greasemonkey in Firefox, for example).

Run python urlStreamHandler.py.

Now after a while, when you are on a page that you have already visited, the app will start suggesting pages you might want to go to.

If you want to pre-train the app with historical web usage data, call for example:
python urlStreamHandler.py --csv log1.csv log2.csv.

The preprocessing and prediction code can be found in url_predictor.py.
The code used to validate the model can be found in model_validator.py.

The hours we worked on this project can be found here.

Name		Name	Last commit message	Last commit date
Latest commit History 106 Commits
.ipynb_checkpoints		.ipynb_checkpoints
Experiments		Experiments
Literature		Literature
Report		Report
.gitignore		.gitignore
KUL_README		KUL_README
README.md		README.md
Time management sheet link.rtf		Time management sheet link.rtf
Untitled.ipynb		Untitled.ipynb
Untitled1.ipynb		Untitled1.ipynb
Untitled2.ipynb		Untitled2.ipynb
Untitled3.ipynb		Untitled3.ipynb
Untitled4.ipynb		Untitled4.ipynb
Untitled5.ipynb		Untitled5.ipynb
Untitled6.ipynb		Untitled6.ipynb
Untitled7.ipynb		Untitled7.ipynb
Untitled8.ipynb		Untitled8.ipynb
graph_vis		graph_vis
graph_vis.py		graph_vis.py
model_validator.py		model_validator.py
requirements.txt		requirements.txt
research.bib		research.bib
urlStreamHandler.py		urlStreamHandler.py
urlStreamHandler.user.js		urlStreamHandler.user.js
url_predictor.py		url_predictor.py