huizezhang-sherry/judgeface

Honours Project: Exploration of Judicial Facial Expression in Videos of Legal Proceedings

judgeface's Issues

need binary imputation for AU01_c missings

final thesis

• Headings and sub-headings need consistent capitalisation: choose title case or sentence case, and make all the same
• Remind reader at beginning of Results section that notation follows that defined in Methods section
• spell check: I still see some spelling issues, eg "theoratically"
• Finish captions: should have three components: (1) what is the plot about, (2) specific details of plot, like what type of display and how variables are mapped, (3) the most important thing that the reader should learn.
• Change heading "Choice of action unit to include", "Filtering action units"
• I see some double sentence endings, like "?." Fix
• Residual plots can go into appendix, with just a short paragraph explaining what's been done in the main thesis
• References have same problem that Headings and sub-headings have, that some have titles in title-case and some are in sentence case. Need to be consistent.
• Bibliography should appear before Appendix
• "Model fitting and ANOVA" should be "Model comparison". Tables 4.2 and 4.3 need a column describing what is in each row, "Model 1", "Model 2", "Model 3". Replace NA with blank text or "-". You need to comment on the numbers, not just p-value, and explain why model 2 is the best choice from a practical or interpretation perspective.
• Fig 4.4 would be best is you have one column of plots, and each one is 100% wide, and 1/6 page high, so they look like time plots, and you can compare the times from judge to judge. Two colour scheme should be changed because this isn't colour-blind proof. Use Dark2 palette perhaps. Your caption needs to say why 2 and is this across all action units or just a selected one.

miss_case_summary for missing

add license: maybe MIT