timini / hansard

Analysis of the hansard archive materials
7 stars 0 forks source link

Resolve #14 #16

Open timini opened 8 years ago

timini commented 8 years ago

This PR s for work related to #14

New plan.

It would be good to get topics and then try to associate MPs with different topics.

to proceed with this:

  1. [ ] Scrape all the comments from the last 10 years
  2. [ ] Save the comments in a data structure which allows it to be segmented by
    • [ ] date
    • [ ] house
    • [ ] speaker
    • [ ] member
  3. [ ] Find all the topics for the last 10 years using gensim
    • [ ] for each house
    • [ ] for each member
  4. Is it possible to identify topics from the last 10 years? Is it possible to map members onto those topics?
  5. [ ] create a django model and API endpoint for topics