This repository is made to build the pipeline for the NLP models that we would like to test for our bachelor project.
-
data
- This is where we store the data that has been preprocessed. This is in order for the preprocessing not having to run at every run of the model.
-
"NewPipeline"
- This is the most recent pipeline
-
"oldpipeline"
- This is the first version of our pipeline
-
raw_data
- Contains the raw data recieved from the supervisor. There are no changes to the data at this location.
-
Results
- This contains the final results as csv files. They can also be found on the webpage
-
Webpage
- This contains the pictures for the webpage
-
index.html
- Contains the webpage itself for Github to host it it needs to be named "index.html"
-
parameters.yaml
- This is where all the parameters for all code can be found. If something has to be "hard coded" it should be added here, because then we have one central place to change parameters.
-
Pipeline.png
- Contains a graph of the pipeline
-
Readme.md
- readme file
