https://github.com/jean-baptiste-camps/wauchier_stylo

Stylometric analysis of Old French légendiers
https://github.com/jean-baptiste-camps/wauchier_stylo

Last synced: about 1 month ago
JSON representation

Stylometric analysis of Old French légendiers

• Host: GitHub
• URL: https://github.com/jean-baptiste-camps/wauchier_stylo
• Owner: Jean-Baptiste-Camps
• Created: 2019-10-11T12:50:21.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2021-03-08T09:13:14.000Z (almost 4 years ago)
• Last Synced: 2024-10-12T21:44:05.244Z (2 months ago)
• Language: HTML
• Homepage:
• Size: 85.8 MB
• Stars: 0
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Wauchier_stylo

Stylometric analysis of Old French _légendiers_.

N.B.: the `data` folder contains data generated with `stylo` from the raw text data.

If you need to generate new data, you will need to run the (commented-out) commands using stylo, 

and then use `write.csv` to save them / `read.csv` to load them.

**/!\ WORKFLOW IS POSSIBLY BUGGED. THERE IS A FIX IN THE newComputs branch**

## Generate analysis data

To generate the analysis, you need to clone: https://github.com/PonteIneptique/dh-meier-data

### Generate lemma and pos data

Use `generate_lemma_pos.py`:

```shell

python3 generate_lemma_pos.py [PrefixNameOfTheOutput] [Path to the directory containing texts]

```

For example, `python3 generate_lemma_pos.py transkribus ../dh-meier-data/output/transkribus/lemmatized/ocr/` will produce 

`./data/transkribus_lemmas.csv` and `./data/transkribus_pos3.csv`.

### Generate the Character 3-Grams 

Done with the Rmd files in the first few cells

### Generate the comparison between Gold and output data

ToDo