Language Analytics Exam 2021

Cultural Data Science, Aarhus University

Frida Hæstrup (201805753)

Content

This is my personal repository with code and data related to my exam in the Spring 2021 module Language Analytics as part of the bachelor's tilvalg in Cultural Data Science at Aarhus University. The portfolio contains 5 projects:

Project	Description
1	Keyword collocation across a text corpus
2	Network analysis of entities in documents
3	(Un)supervised machine learning
4	Text classification using Deep Learning
5	Topic Modelling on religious texts

Structure

This repository has the following directory structure:

VisualAnalytics2021/  
├── data/  #data folders for each project
│   └── project1/
│   └── project2/
│   └── project3/
│   └── project4/
│   └── project5/ 
├── src/  #Python scripts for each project
│   └── project1/
│   │   └── out/
│   │   └── collocation.py
│   └── project2/
│   │   └── output/
│   │   └── viz/
│   │   └── network.py
│   └── project3/
│   │   └── out/
│   │   └── LR_philosophicalTexts.py  
│   └── project4/
│   │   └── out/  
│   │   └── LR_GOT.py
│   │   └── DL_GOT.py   
│   └── project5/
│   │   └── out/ 
│   │   └──  religious_topics.py
├── utils/  #utility functions 
│   └── *.py  
├── figures/  #figures to use in READMEs  
│   └── *.png  

Technicalities

Scripts with code for each project can be found in the folder, src, along with a description of how to run them.

To run scripts within this repository, I recommend cloning the repository and installing relevant dependencies in a virtual ennvironment:

$ git clone https://github.com/frillecode/LanguageAnalytics2021
$ cd LanguageAnalytics2021
$ bash ./create_venv.sh #use create_venv_win.sh for windows

If you run into issues with some libraries/modules not being installed correctly when creating the virtual environment, install these manually by running the following:

$ cd LanguageAnalytics2021
$ source cds-lang/bin/activate
$ pip install {module_name}
$ deactivate

Licencse

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgements

Credits for utility scripts and the original repository structure goes to Ross Deans Kristensen-McLachlan.