Update to latest model

[lizgzil]

Fixes #197 and #212

• Update references to the old model (20220825) to the new model (20230808)
• Added the new model to a public zipped folder. This is currently in ojd_daps_skills_data_new.zip since it will break things if it replaces ojd_daps_skills_data.zip just yet
• Add info to model cards
• Optimize bertvectorizer

To do:

• Rename the old public zipped file to ojd_daps_skills_data_old.zip and change ojd_daps_skills_data_new.zip to ojd_daps_skills_data.zip. DO THIS AFTER THIS PR IS MERGED?

Important. I have created a new public S3 zipped file (s3://open-jobs-indicators/escoe_extension/ojd_daps_skills_data_new.zip) which has the new model (20230808) rather than the old one (20220825).

For the meantime, I have kept s3://open-jobs-indicators/escoe_extension/ojd_daps_skills_data.zip as it is (i.e. with the old model). This is because whilst this code is still in a PR, dev won't work with the new zipped file (it will try to look for the 20220825 model but it won't exist).

This is how I updated the zipped file:

# Move over the new model
aws s3 cp --recursive s3://open-jobs-lake/escoe_extension/outputs/models/ner_model/20230808/ s3://open-jobs-indicators/escoe_extension/outputs/models/ner_model/20230808/

# Delete the old model
aws s3 rm s3://open-jobs-indicators/escoe_extension/outputs/models/ner_model/[20220825/](https://s3.console.aws.amazon.com/s3/buckets/open-jobs-indicators?region=eu-west-1&prefix=escoe_extension/outputs/models/ner_model/20220825/&showversions=false) --recursive

# Download the whole folder locally
aws s3 cp --recursive s3://open-jobs-indicators/escoe_extension/outputs/ ojd_daps_skills_data/outputs/

# zip
zip -r ojd_daps_skills_data.zip ojd_daps_skills_data/

# Upload the zipped file
aws s3 cp ojd_daps_skills_data.zip  s3://open-jobs-indicators/escoe_extension/ojd_daps_skills_data_new.zip

---

Thanks for contributing to Nesta's Skills Extractor Library 🙏!

If you have suggested changes to code anywhere outside of the ExtractSkills class, please consult the checklist below.

Checklist ✔️🐍:

• I have refactored my code out from notebooks/
• I have checked the code runs
• I have tested the code
• I have run pre-commit and addressed any issues not automatically fixed
• I have merged any new changes from dev
• I have documented the code
  • Major functions have docstrings
  • Appropriate information has been added to READMEs
• I have explained the feature in this PR or (better) in output/reports/
• I have requested a code review

If you have suggested changes to documentation (and/or the ExtractSkills class), please ALSO consult the checklist below.

Documentation Checklist ✔️📚:

• I have run make html in docs
• I have manually reviewed the docs/build/*.html files locally to ensure they have formatted correctly
• I have pushed both relevant files AND their corresponding docs/build/*.html files

[lizgzil]

@india-kerle - no rush on this - but I've tried to update everything with the new model details. Hope I haven't missed something?

[india-kerle]

Suggested change

	We labelled another batch of job adverts using [Prodigy](https://prodi.gy/). This was to avail of their active learning capabilities. Details of how we labelled job adverts this way are given in [the Prodigy labelling README](./ojd_daps_skills/ojd_daps_skills/pipeline/skill_ner/prodigy/README.md).
	We labelled another batch of job adverts using [Prodigy](https://prodi.gy/). This was to make use of their active learning capabilities. Details of how we labelled job adverts this way are given in [the Prodigy labelling README](./ojd_daps_skills/ojd_daps_skills/pipeline/skill_ner/prodigy/README.md).

[india-kerle]

Suggested change

To train the NER model we needed labelled data. First we created a random sample of job adverts and got them into a form needed for labelling using [Label Studio](https://labelstud.io/), we then did a second batch of labelled using [Prodigy](https://prodi.gy/). More about this labelling process can be found in the `skill_ner` pipeline [README.md](./ojd_daps_skills/ojd_daps_skills/pipeline/skill_ner/README.md).

To train the NER model we needed labelled data. First we created a random sample of job adverts and got them into a form needed for labelling using [Label Studio](https://labelstud.io/). We then did a second batch of labelled using [Prodigy](https://prodi.gy/). More about this labelling process can be found in the `skill_ner` pipeline [README.md](./ojd_daps_skills/ojd_daps_skills/pipeline/skill_ner/README.md).

[india-kerle]

Looks great! thanks for these changes :)