1. CTPF goes negative on first iteration
2. pre-compute ELBOs, or derive formula for various M and K
3. decide on fixmodel! function
4. camelCase to under_score
5. new to temp
6. change UTF8String in README to String
7. put package back in official listing
8. smooth out fLDA and fCTM
9. figure out way to preserve ordering of documents so showdocs() is comprehensible
10. Use feather or paraquet or some fead read-in binary file format for default corpora in order to speed up their loading times.
11. tab align C code
12. write run tests for package, see issue #3
13. write detect topic code, see issue #2
14. save/load trained models see issue #13
15. change comments to new style formatting
16. fix checkcorp! situation
17. make extended integers datatype so that chkelbo can be Z U {Inf}
18. when different lex keys map to the same word, need to merge these in fixcorp functions
19. fix DTM
20. make 1.0 compatible
21. deal with counts situation