This repository is for exploring the Udemy Courses dataset (Reference 1) and building NLP models around it. Also, it is used for AI & Advanced Analytics (tech stream) in the Microsoft Student Accelerator (MSA) Program - Australia 2020.
- What are popular topics on Udemy? Why?
In this project, NLP models will be built to find the answer for questions above. This project uses the Udemy Course dataset which is given in the Kaggle website (reference 1). With the first question, some procedures such as data analytic and natural language processing will be done.
- Clearning data
- Feature engineering - Keep meaningful columns or aggregate new meaninful columns
- Generating statistical information for finding the definition of popularity.
- Generating topics for each course by using NLP
- Finding popular topics in the dataset
- Python version: 3.7.3
- Cloning the project
git clone https://github.com/peterdu98/udemy-courses-analytics.git
- Using the following commands in your virtual environment to install necessary packages
pip install -r requirements.txt
python -m nltk.downloader stopwords
- Udemy Courses dataset on Kaggle - https://www.kaggle.com/andrewmvd/udemy-courses