Write group-aware resampling tables to CSV

Usage

write_gazepoint_group_folds_csv(
  x,
  directory,
  prefix = "gazepoint_group_folds",
  tables = c("assignments", "fold_summary", "group_counts", "group_mapping",
    "validation_checks", "validation_issues", "audit_summary", "audit_checks",
    "audit_issues"),
  include_fold_data = FALSE,
  overwrite = FALSE,
  na = ""
)

Arguments

x: A gazepoint_group_folds object.
directory: Output directory.
prefix: Non-empty filename prefix.
tables: Character vector selecting summary tables.
include_fold_data: Logical. Whether every materialized fold partition should also be written.
overwrite: Logical. Whether existing files may be replaced.
na: Character representation of missing values.

Value

A named character vector of normalized output paths, invisibly.

Examples

example_data <- expand.grid(
  participant_id = sprintf("P%02d", 1:6),
  stimulus_id = sprintf("S%02d", 1:4),
  repetition = 1:2,
  KEEP.OUT.ATTRS = FALSE,
  stringsAsFactors = FALSE
)
example_data$trial_id <- paste0(
  example_data$stimulus_id,
  "_T",
  example_data$repetition
)
participant_number <- as.integer(
  sub("P", "", example_data$participant_id)
)
stimulus_number <- as.integer(
  sub("S", "", example_data$stimulus_id)
)
example_data$outcome <- factor(
  ifelse(
    (participant_number + stimulus_number) %% 2L == 0L,
    "review",
    "pass"
  ),
  levels = c("pass", "review")
)
row_index <- seq_len(nrow(example_data))
example_data$fixation_duration <- 180 + row_index
example_data$pupil_change <- round(
  sin(row_index / 7),
  4
)
example_data$repetition <- NULL
manifest <- create_gazepoint_feature_manifest(
  features = c("fixation_duration", "pupil_change"),
  scientific_source = c(
    "Gazepoint fixation export",
    "Gazepoint pupil export"
  ),
  source_table = c("fixations", "pupil"),
  transformation = c(
    "Trial-level mean",
    "Trial-level change"
  ),
  availability_stage = "during_exposure",
  prediction_time_available = TRUE,
  preprocessing_scope = "none",
  fold_local_required = FALSE
)
folds <- create_gazepoint_group_folds(
  data = example_data,
  outcome = "outcome",
  predictors = c("fixation_duration", "pupil_change"),
  feature_manifest = manifest,
  generalization_target = "new_participants",
  participant_id = "participant_id",
  trial_id = "trial_id",
  stimulus_id = "stimulus_id",
  v = 3L,
  repeats = 1L,
  seed = 101L
)
output_directory <- tempfile()
paths <- write_gazepoint_group_folds_csv(
  x = folds,
  directory = output_directory,
  tables = c("fold_summary", "group_counts")
)
paths
#>                                                                                                 fold_summary 
#> "C:/Users/Stefanos-PC/AppData/Local/Temp/RtmpacJaCe/file75482d7f564e/gazepoint_group_folds_fold_summary.csv" 
#>                                                                                                 group_counts 
#> "C:/Users/Stefanos-PC/AppData/Local/Temp/RtmpacJaCe/file75482d7f564e/gazepoint_group_folds_group_counts.csv" 
unlink(output_directory, recursive = TRUE)