Workshop Ancient Text Analysis with Python

This repository contains materials for the Workshop Ancient Text Analysis with Python which will be held at the University of Copenhagen in May and June 2022.

We cover the following topics:

1. Querying the Hebrew Bible using Text Fabric Browser.
2. Querying the New Testament and the Quran.
3. Making data visualizations with Seaborn.
4. Making data visualizations with Seaborn, part 2.
5. Annotating Latin Genesis with CLTK.
6. Annotating raw text with Spacy or Clustering the texts of many manuscripts of the Greek Letter of Jude.

===========================================================================

Documentation Text-Fabric

Example corpora

Search documentation

===========================================================================

Set up everything:

• Download and install Anaconda.
• Download and install Git if needed.
• Clone this repo: git clone https://github.com/DT-UCPH/workshop_ancient_text_analysis
• Create an environment for this workshop in Anaconda and activate it.
• Install the dependencies in the environment with: pip install -r requirements.txt.
• If you want to use the BHSA dataset in Text-Fabric browser: text-fabric etcbc/bhsa.

===========================================================================

Corpora we will explore:

1. BHSA

• Data
• Tutorials
• BHSA feature docs
• Inspection of the text, features, and lexicon

2. SBLGNT

• Data

3. Quran

• Data
• Feature documentation
• Tutorials

===========================================================================

Other relevant packages we will use:

• Classical Language Toolkit
• spaCy
• scikit-learn