Sentence sentiment analysis

[sofiapinto]

---

Description

Using Flair's model to compute sentence based sentiment analysis for sentences mentioning HPs/boilers in MSE and Buildhub (but script also allows for other sources to be read). Then we create a count of pos/neg sentences per year.

Fixes #28

Instructions for Reviewer

Hey Aidan, could please check if the logic makes sense on the following scripts:

• sentiment_analysis.py - main script to review
• sentiment_analysis_utils.py - utils for computing sentiment. This consists of one function for now (but my guess is that this will get bigger, because we want to use a different model in the future that also outputs a neutral category);
• getter_utils.py - updated with a function that allows for reading BH/MSE or another source of data
• text_cleaning_utils.py - utils for cleaning text data prior to applying the sentiment model. A lot of these will be useful for other parts of the codebase too.
• README.md - readme markdown for this subfolder.

Thanks a lot.

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 this PR above
• I have requested a code review