check_classification: A function to check automatic classifications

In ctross/DieTryin: A package for running network-structured economic games

A function to check automatic classifications

Description

This is a helper function to plot infered connections. Run this for each game, and it will plot predicted tokens on the real images. If model performance is not good, then tweak parameters until classification is accurate. Photos are saved in the "ClassifiedPhotos" folder.

Usage

check_classification(
  path,
  dat,
  n_panels = 2,
  n_rows = 4,
  n_cols = 5,
  ID = "BS1",
  game = "Friend"
)

Arguments

path	Full path to main folder.
dat	Classification output.
n_panels	Number of frames/panels/blocks of photos to be output. I use four big panels and randomize their order at each game.
n_rows	Number of rows per panel. With 7cm x 10cm photos, I use five rows of photos per panel.
n_cols	Number of cols per panel. With 7cm x 10cm photos, I use six to eight cols of photos per panel.
ID	ID code of focal individual.
game	ID code for game/case/question: e.g., "GivingGame".

Examples

## Not run: 
 check_classification(path=path, dat[[1]], n_panels = 2, n_rows=4, n_cols=5, 
                      ID="SK1", game="FriendshipsData")
                   
## End(Not run)

ctross/DieTryin documentation built on Sept. 8, 2024, 8:07 p.m.