Skip to content

Analyzed trending youtube videos to establish a correlation between certain attributes of the videos to the likelihood of trending

Notifications You must be signed in to change notification settings

filipopo/youtube-model

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

youtube-model

This Python project contains a youtube.ipynb Jupyter notebook in which videos from the youtube trending 2017 dataset were analyzed with pandas and visualisations were made using matplotlib

image

In the last section of the notebook a one class classifier ML model was made in Scikit-learn which predicts will a new video be trending

The dataset is saved under the dataset folder but it can also be found here: https://www.kaggle.com/datasets/elmarico/youtube-trending-2017

In the report folder, there's a graphical report of the findings in the Serbian langauge made in PyQT5 for which the interface was made using QT designer

You can install the requirements for the entire project with pip install -r requirements.txt

Then you can view the PyQT5 report

python izvestaj.py

The resources for the report were compiled by running pyrcc5 resursi.qrc -o resursi_rc.py

About

Analyzed trending youtube videos to establish a correlation between certain attributes of the videos to the likelihood of trending

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published