The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
fit_gazepoint_gca() test robust to
platform-specific mixed-model fallback behavior observed under CRAN
no-long-double checks.CITATION.cff and
inst/CITATION.inst/extdata/gazepoint_realistic_demo_exports/.data-raw/create_gazepoint_realistic_demo_exports.R.Added run_gazepoint_workflow() for one-command
Gazepoint folder analysis.
Added folder-level import with
read_gazepoint_folder().
Added check_gazepoint_file_pairs() for checking
whether Gazepoint all-gaze and fixation export files are correctly
paired.
Added flag_tracking_quality() for identifying
recordings requiring review.
Added diagnostic plotting functions:
plot_tracking_quality()plot_sampling_rate()Added save_gazepoint_plots() for automatic
diagnostic plot export.
Added create_gazepoint_report() for lightweight HTML
diagnostic reports.
Integrated optional HTML report creation into
run_gazepoint_workflow() with
create_report = TRUE.
Added standard CSV export helpers:
export_gazepoint_tables()write_gazepoint_outputs()Added summarise_gazepoint_workflow() for creating a
compact one-row summary of a completed workflow result object.
as_gazepoint_master() for converting Gazepoint
all-gaze exports into a standard sample-level master table with time,
gaze coordinates, pupil values, validity flags, missingness flags,
off-screen gaze flags, AOI state, event labels, and fixation-related
fields.create_gazepoint_master() as the advanced
Gazepoint master-table constructor for creating analysis-ready
sample-level data with participant, media, timing, gaze, pupil, AOI,
screen, event, response, and metadata fields.audit_gazepoint_master() for producing compact
quality-audit tables from Gazepoint master tables, including overview,
subject-level, media-level, AOI-state, pupil, and coordinate
summaries.validate_gazepoint_master() as a formal
validation gate before pupil preprocessing, AOI modelling, or advanced
statistical analysis.export_gazepoint_master_audit() for exporting the
master table, audit tables, and validation tables to CSV files.summarise_gazepoint_pupil() as the first
pupil-preprocessing gate for Gazepoint master tables. The function
summarises pupil availability, missing-pupil percentages, valid-pupil
percentages, pupil distributions, plausible-value checks, and IQR-based
outlier counts by subject, media, subject-by-media, or overall.flag_gazepoint_pupil() for marking missing,
non-finite, implausible, and IQR-outlying pupil samples in Gazepoint
master tables. The function preserves the original master table, adds
explicit pupil-quality flags, records the selected pupil/time columns
and plausible-value thresholds, and creates
pupil_for_preprocessing, where invalid pupil samples are
set to NA before interpolation, filtering, or baseline
correction.create_gazepoint_preprocessing_registry() for
storing reusable preprocessing parameters, including blink/artifact
padding, interpolation gap thresholds, smoothing window size, baseline
windows, physiological pupil thresholds, speed-outlier thresholds,
binocular-disagreement thresholds, baseline-quality thresholds, and
overlap-risk settings.flag_gazepoint_pupil_artifacts() for conservative
pupil artifact cleaning before interpolation. The function flags
blink/trackloss contamination, missing pupil samples, non-finite and
non-positive values, pupil-speed outliers, binocular left-right pupil
disagreement, and temporal padding around bad samples. It also includes
a scale-safety rule that suppresses millimetre-based physiological
thresholds when they would remove nearly all non-missing samples, which
protects Gazepoint raw-unit exports from being silently erased.interpolate_gazepoint_pupil() for linearly
interpolating short internal gaps in pupil time series. The function
automatically prefers pupil_clean when available, followed
by pupil_for_preprocessing, preserves leading/trailing
gaps, avoids long gaps, respects grouping by subject/media/trial,
records interpolation status, gap size, gap duration, and produces
pupil_interpolated for later filtering or baseline
correction.baseline_correct_gazepoint_pupil() for flexible
baseline correction of Gazepoint pupil data after flagging and
interpolation. The function supports window-based baselines such as
c(-200, 0) or c(0, 200), as well as
user-defined logical baseline/pre-stimulus flag columns. It produces
absolute baseline-corrected values, percent change, ratio, z-scored
baseline correction, baseline availability flags, baseline sample
counts, and baseline-status labels.smooth_gazepoint_pupil() for sample-based rolling
smoothing of Gazepoint pupil time series after interpolation and
optional baseline correction. The function supports mean or median
smoothing, centred/right/left-aligned windows, custom grouping by
subject/media/trial or other columns, optional preservation of missing
input rows, and records smoothing status, window size, input column,
method, alignment, and minimum valid-points settings.summarise_gazepoint_pupil_windows() for
aggregating processed Gazepoint pupil data into user-defined analysis
windows. The function supports numeric window breakpoints and labelled
custom window tables, flexible grouping by subject, media, trial,
condition, AOI, or other columns, and produces analysis-ready summaries
including valid/missing pupil counts, percentages, mean, median, SD,
quantiles, min/max, AUC, time span, and window-validity status.audit_gazepoint_pupil_gaps() for summarising
pupil interpolation and missing-gap structure after
interpolate_gazepoint_pupil().audit_gazepoint_pupil_baseline() for checking
baseline-correction quality after
baseline_correct_gazepoint_pupil().audit_gazepoint_pupil_imbalance() for checking
whether preprocessing loss differs across conditions or other
groups.audit_gazepoint_pupil_drift() for assessing tonic
pupil/time-on-task drift.audit_gazepoint_pupil_overlap_risk() as an
event-response overlap and deconvolution-readiness gate.summarise_gazepoint_pupil_trial_features() for
converting processed pupil time series into trial-level feature
summaries.plot_gazepoint_pupil_status() for visualising
observed, interpolated, missing, artifact, and other pupil-sample
statuses over time or as grouped percentages.plot_gazepoint_pupil_timecourse() for plotting
binned pupil time courses with mean lines and confidence bands.plot_gazepoint_pupil_preprocessing() for
single-trial visual audit plots of pupil preprocessing stages.prepare_gazepoint_pupil_window_model_data() for
preparing pupil-window summaries or pupil trial-feature tables for
confirmatory window-level modelling. The function standardises outcome,
subject, condition, window, trial/media identifiers, valid-sample
counts, total-sample counts, valid-sample proportions, weights,
model-readiness status, and settings. It also supports common Gazepoint
pupil-window aliases such as media_id,
MEDIA_ID, n_valid_pupil,
n_valid_samples, and n_samples.fit_gazepoint_pupil_window_lmm() for fitting
confirmatory pupil-window linear mixed models with
lme4::lmer(). The function supports condition, window, and
condition-by-window fixed effects when available; automatic fallback for
single-condition or single-window data; subject random intercepts;
optional random window slopes; optional valid-sample weighting;
singular-fit detection; fallback models; fixed-effect tables;
model-comparison tables; fitted formulas; status labels; and
settings.fit_gazepoint_pupil_window_sensitivity() for
confirmatory pupil-window model-family sensitivity checks. The function
compares unweighted LMMs, weighted LMMs, fixed-effects LMs, and weighted
LMs without adding heavy robust-model dependencies, and returns fitted
models, formulas, comparison tables, fixed-effect tables, model-status
labels, error messages, and settings.summarise_gazepoint_aoi_entries() for converting
sample-level AOI states into ordered AOI-entry episodes.prepare_gazepoint_aoi_sequences() for creating
transition-ready AOI sequences from sample-level data or AOI-entry
tables.summarise_gazepoint_aoi_transitions() for
trial-level AOI transition summaries.compute_gazepoint_aoi_transition_matrix() for
producing AOI transition count matrices, probability matrices, grouped
matrices, and long-form transition tables.plot_gazepoint_aoi_transition_matrix() for
plotting AOI transition count or probability heatmaps.summarise_gazepoint_aoi_trial_features() for
trial-level AOI feature extraction.summarise_gazepoint_fixation_trials() for
trial-level fixation feature extraction from Gazepoint fixation
exports.summarise_gazepoint_aoi_windows() for converting
sample-level AOI states into predefined AOI time-window summaries. The
function supports numeric window breakpoints, labelled window tables,
target/distractor AOI definitions, valid/all/AOI-only denominators,
condition fallback to all_data, chronological window
ordering, and status labels for target-observed and target-not-observed
windows.audit_gazepoint_aoi_window_denominators() for
checking denominator adequacy before binomial or logistic mixed-effects
modelling. The function reports zero, low, missing, imbalanced, and
variable denominators by row, window, and condition, and returns
overview, row-audit, window-summary, condition-window, imbalance, and
flagged-row tables.prepare_gazepoint_aoi_glmm_data() for preparing
AOI-window summaries as binomial success/failure data. The function
supports valid, all-sample, AOI-only, and custom denominators; creates
success, failure, denominator, proportion, weight, subject, condition,
and window columns; and records row-level GLMM-readiness status.fit_gazepoint_aoi_window_glmm() for fitting
confirmatory AOI-window binomial mixed-effects logistic regression
models using lme4::glmer(). The function supports
condition, window, and condition-by-window fixed effects, subject random
intercepts, optional random window slopes, singular-fit detection,
fallback models, model comparison tables, and explicit model-status
reporting.fit_gazepoint_aoi_model_sensitivity() for
AOI-window model-family sensitivity checks. The function compares the
main binomial GLMM against empirical-logit LMM, weighted proportion LMM,
and fixed-effects quasibinomial GLM specifications, returning model
comparisons, formulas, fixed effects, status labels, and settings.prepare_gazepoint_pupil_gamm_data() for preparing
binned pupil time-course data for mgcv::bam() models.fit_gazepoint_pupil_gamm() for fitting pupil
time-course GAMMs with mgcv::bam().fit_gazepoint_pupil_pfe_gamm() for
gaze-position-adjusted pupil GAMM sensitivity analysis.prepare_gazepoint_gca_data() for Growth Curve
Analysis preparation.fit_gazepoint_gca() for fitting GCA mixed models
with lme4::lmer().plot_gazepoint_gca() for plotting observed and
fitted GCA trajectories.prepare_gazepoint_cluster_data() for preparing
sample-level or binned Gazepoint time-course data for cluster-based
permutation testing. The function standardises subject, condition,
time-bin, outcome, sample-count, trial-count, status, outcome-label,
aggregation, bin-size, paired-design, and condition-status fields. It
supports pupil time courses, AOI target-looking indicators, and other
numeric or logical time-course outcomes.run_gazepoint_cluster_permutation() for paired
within-subject cluster-based permutation testing of two-condition
time-course divergence. The function uses sign-flip permutations,
time-wise paired t-statistics, configurable cluster-forming thresholds,
two-sided or directional tests, multiple cluster-statistic options,
complete-subject filtering, permutation maximum-cluster distributions,
cluster-level p-values, model-status labels, and explicit circularity
warnings.summarise_gazepoint_clusters() for converting
cluster-permutation results into compact reporting tables, including
overview, all observed clusters, significant clusters, time-course
summary, permutation-distribution summary, settings, and circularity
warning tables.plot_gazepoint_cluster_results() for plotting
cluster-permutation results. The function supports mean-difference,
test-statistic, or two-panel plots; optional cluster shading;
candidate-bin markers; threshold lines; zero-reference lines; custom
titles and labels; and publication-ready ggplot2
output.prepare_gazepoint_aoi_gamm_data() for preparing
sample-level or binned AOI data for AOI time-course GAMM analysis. The
function creates subject-by-condition-by-time-bin binomial
success/failure summaries for target-AOI looking, supports AOI-column
and logical/numeric indicator workflows, valid/all/AOI-only denominator
definitions, condition fallback to all_data, custom time
bins, denominator filtering, and model-readiness status fields.fit_gazepoint_aoi_gamm() for fitting binomial AOI
target-looking GAMMs using mgcv::bam(). The function models
target-AOI looking over time using success/failure counts, supports
condition fixed effects when available, condition-specific smooths,
subject random-effect smooths, optional subject-specific time smooths,
automatic single-condition fallback, model diagnostics, formula
reporting, parametric and smooth tables, and captured model
warnings.plot_gazepoint_aoi_gamm() for plotting observed
AOI target-looking proportions and fitted AOI-GAMM trajectories. The
function supports single-condition and multi-condition plots,
observed-only and fitted-only views, confidence ribbons,
population-level predictions with subject random effects excluded by
default, custom labels, and publication-ready ggplot2
output.check_gazepoint_model_convergence() for compact
convergence diagnostics across fitted models used in
gp3tools workflows. The helper supports lme4
mixed models, mgcv GAM/BAM objects, glm
objects, and ordinary lm objects where applicable, and
returns a tidy diagnostic table with convergence status, model class,
diagnostic status, and message.check_gazepoint_model_singularity() for checking
singular random-effects structures in lme4 mixed models
using lme4::isSingular(). The helper reports singular fits
as structured diagnostic output rather than package failures, and
returns not_applicable for model classes where singularity
is not meaningful.check_gazepoint_model_overdispersion() for
Pearson-residual overdispersion diagnostics in binomial, quasibinomial,
Poisson, quasipoisson, and negative-binomial-like models. The helper
returns dispersion ratios, Pearson chi-square values, residual degrees
of freedom, threshold-based overdispersion flags, and diagnostic
messages.diagnose_gazepoint_glmm() as a reusable
diagnostics bundle for GLMM, LMM, and GLM workflows. The function
combines convergence, singularity, overdispersion, and optional DHARMa
simulation-based residual diagnostics into a structured
gp3_model_diagnostics object with overview, convergence,
singularity, overdispersion, DHARMa, and settings tables.diagnose_gazepoint_gamm() as a reusable
diagnostics bundle for mgcv::gam() and
mgcv::bam() workflows. The function combines convergence
checks, mgcv::k.check() basis-dimension diagnostics,
overdispersion checks when meaningful, and optional DHARMa diagnostics
into a structured gp3_model_diagnostics object.DHARMa is listed in Suggests, not
Imports, and diagnostics skip cleanly with
skipped_missing_package when DHARMa is not installed.summarise_gazepoint_fixed_effects() for creating
manuscript-ready fixed-effect summary tables from lm,
glm, lme4 mixed models, and mgcv
GAM/BAM models. The function supports gp3tools fit objects
containing a $model element, Wald confidence intervals,
optional exponentiation for odds ratios or rate ratios, intercept
filtering, significance stars, and structured diagnostic status
fields.tidy_gazepoint_model_summary() for combining
model metadata, fixed-effect summaries, and optional model diagnostics
into a structured gp3_model_summary object. The returned
object contains overview, model_info,
fixed_effects, diagnostics, and
settings components.summarise_gazepoint_emmeans() for estimated
marginal means and pairwise contrasts using optional
emmeans. The function returns structured
overview, emmeans, contrasts, and
settings tables and skips cleanly with
skipped_missing_package if emmeans is not
installed.export_gazepoint_model_tables() for exporting
manuscript-ready model summaries, fixed effects, diagnostics, estimated
marginal means, contrasts, settings, and export-index tables to CSV
files.emmeans support in Suggests
for estimated marginal means and pairwise contrasts without making it a
required package dependency.create_gazepoint_analysis_decision_audit() for
creating a final analysis-decision audit across completed Gazepoint
analysis branches. The function records which branches were run,
classifies each branch as confirmatory, sensitivity, exploratory,
diagnostic, preprocessing, reporting, or unknown, summarises available
diagnostics, flags interpretation cautions, and creates a final
analysis-readiness table.gp3_analysis_decision_audit object with
overview, branch_audit,
diagnostics_summary, interpretation_cautions,
readiness, and settings components.create_gazepoint_preprocessing_multiverse() for
defining preprocessing multiverse specifications across pupil and AOI
workflows. The function creates structured pupil, AOI, and combined
branch grids for alternative preprocessing decisions such as pupil
interpolation gap thresholds, smoothing windows, baseline windows,
artifact-padding settings, AOI denominator definitions, and minimum
denominator thresholds.run_gazepoint_pupil_multiverse() for running
pupil preprocessing branches from a preprocessing multiverse object. The
runner applies branch-specific artifact flagging, interpolation,
baseline correction, smoothing, and optional pupil-window summarisation,
while recording completed and failed branches.run_gazepoint_aoi_multiverse() for running AOI
preprocessing branches from a preprocessing multiverse object. The
runner creates AOI-window summaries and branch-specific AOI GLMM
preparation tables using alternative denominator and minimum-denominator
decisions.summarise_gazepoint_multiverse_results() for
combining pupil and AOI multiverse results into overview,
branch-summary, failure-summary, and settings tables.plot_gazepoint_multiverse_results() for
visualising multiverse branch status, retained rows, pupil preprocessing
settings, and AOI denominator settings.audit_gazepoint_event_sync() for checking
event-marker availability, expected event labels, duplicate timestamps,
sparse units, and unusually large time gaps.audit_gazepoint_design_balance() for auditing
observed subject-by-condition design balance before exclusions.audit_gazepoint_exclusion_flow() for summarising
retained versus excluded analysis units, exclusion reasons,
condition-level retention, and subject-level retention.audit_gazepoint_gaze_signal_quality() for
auditing gaze-coordinate availability, validity columns, missing gaze,
off-screen gaze, and optional pupil availability.audit_gazepoint_condition_quality_imbalance() for
checking whether quality metrics differ across experimental
conditions.audit_gazepoint_post_exclusion_balance() for
checking whether retained analysis units remain balanced across subjects
and conditions after exclusions.audit_gazepoint_aoi_geometry() for checking AOI
size, area, coordinate validity, screen-bound status, and duplicate AOI
geometry.audit_gazepoint_aoi_overlap() for identifying
pairwise AOI overlap within each stimulus or media item.audit_gazepoint_aoi_margin_sensitivity() for
auditing whether AOI assignments are sensitive to small boundary
expansions or shrinkages.audit_gazepoint_aoi_coding_matrix() for
validating observed AOI labels against geometry-derived AOI labels and
producing coding/confusion matrices.plot_gazepoint_aoi_verification() for visual AOI
verification with optional gaze-point overlays.Added advanced AOI/state sequence-model preparation helpers:
create_gazepoint_markovchain_object()prepare_gazepoint_semimarkov_data()prepare_gazepoint_hmm_data()Added create_gazepoint_markovchain_object() for
creating dependency-free Markov-chain-style AOI/state objects with
transition counts, transition probabilities, transition matrices,
sequence-level transition data, state ordering, optional state
exclusion, optional missing-state labelling, optional self-transition
handling, and Laplace smoothing.
Added prepare_gazepoint_semimarkov_data() for
converting ordered AOI/state observations into semi-Markov-ready
state-visit and transition tables with dwell durations, next-state
labels, terminal-state handling, sequence summaries, state summaries,
transition summaries, optional covariate carry-through, and optional
repeated-state collapsing.
Added prepare_gazepoint_hmm_data() for creating
dependency-free HMM-ready AOI/state sequence structures with ordered
observation data, initial-state probabilities, transition
count/probability matrices, transition tables, observation summaries,
emission-format data, optional numeric observation scaling, optional
terminal-state transitions, optional covariate carry-through, and
optional missing-state labelling.
Added dependency-free package-adapter helpers for exporting
gp3tools master/sample tables to external R eye-tracking
workflows:
prepare_gazepoint_eyetrackingr_data()prepare_gazepoint_pupillometryr_data()prepare_gazepoint_gazer_data()prepare_gazepoint_eyetools_data()These helpers create clean, package-friendly tibbles without importing or depending on the external packages directly.
Added eyetrackingR-style sample-level export with participant, trial, time, gaze coordinates, AOI labels, AOI indicator columns, trackloss status, and adapter metadata.
Added pupillometryR-style sample-level export with participant, trial, time, pupil, event, baseline, pupil-validity, trackloss, and adapter metadata.
Added gazer-style sample-level export with participant, trial, time, gaze coordinates, optional pupil, AOI labels, fixation IDs, validity flags, off-screen detection, trackloss status, and adapter metadata.
Added eyetools-style sample-level export with participant, trial, time, primary and binocular gaze coordinates, pupil columns, AOI labels, fixation IDs, event labels, validity flags, off-screen detection, trackloss status, and adapter metadata.
Added estimate_gazepoint_divergence_point() for
estimating the earliest reliable divergence between two condition time
courses using bootstrap confidence intervals. The helper supports
participant-, trial-, and row-level bootstrap units, mean or median
summaries, directional testing, consecutive-point onset rules,
no-divergence handling, optional bootstrap-output retention, and
onset-time uncertainty summaries.
Added run_gazepoint_model_leave_one_out() for
generic leave-one-unit model sensitivity analysis. The helper refits a
user-supplied model while leaving out one participant, item, stimulus,
trial, or other unit at a time. It supports custom effect extraction,
effect-term filtering, fit/extraction error tracking, optional model
retention, and effect-stability summaries including maximum absolute
change, largest-change unit, percent change, and sign-flip
detection.
Added transform_gazepoint_aoi_empirical_logit() for
transforming bounded AOI proportions into finite empirical logits. The
helper supports numerator/denominator count input, proportion-only input
with pseudo-denominators, correction constants for 0/1 proportions,
custom output columns, overwrite protection, row-level transformation
statuses, and overview/status/settings attributes.
Added prepare_gazepoint_fixation_aligned_data() for
fixation-, saccade-, and AOI-contingent alignment. The helper aligns
observations to first target entry, first fixation to target, first
saccade to AOI, first fixation, or custom event markers, and returns
aligned data, event tables, trial summaries, baseline/analysis-window
flags, pre/post-event phases, target-preexisting flags, and
already-on-target-at-start indicators.
Added plot_gazepoint_model_predictions() for
plotting observed summaries together with model-implied prediction
trajectories. The helper supports model objects for which
predict() works, including lm,
glm, mixed-model, GAMM, and GCA-style workflows, and stores
observed summaries, prediction summaries, overview metadata, and
settings as plot attributes.
Added compare_gazepoint_nested_models() for
comparing ordered nested models. The helper returns model-level AIC,
BIC, log-likelihood, degrees of freedom, likelihood-ratio tests, model
rankings, sequential or against-first comparisons, extraction/comparison
statuses, and fallback support for simple custom list-like model
wrappers.
Added flag_gazepoint_pupil_hampel() as an optional
Hampel-filter pupil artifact helper. The function applies a rolling
Hampel filter to pupil data, supports grouping and time ordering,
configurable window size, threshold multiplier, minimum valid samples,
MAD scaling, optional corrected pupil output, custom output columns,
overwrite protection, row-level statuses, and overview/status/settings
attributes.
Added recalibrate_gazepoint_gaze() for offline gaze
recalibration and drift correction using known target or check-target
coordinates. The helper estimates group-level horizontal and vertical
gaze shifts, applies median or mean drift correction, supports
calibration-row filters, maximum-shift blocking, grouped correction
summaries, row-level statuses, before/after target-error columns, custom
output columns, and overview/status/settings attributes.
Added recommend_gazepoint_exclusions() for creating
explicit trial-level and participant-level exclusion recommendations.
The helper uses validity flags, gaze-coordinate missingness, pupil
missingness, artifact flags, sample-count thresholds, missingness
thresholds, and artifact-rate thresholds to return transparent
participant recommendations, trial recommendations, a combined exclusion
table, overview metadata, and settings. The helper recommends exclusions
only; it does not remove data.
FPOGS, FPOGD, FPOGX,
FPOGY, FPOGID, FPOGV,
AOI, MEDIA_ID, and informative participant
identifiers such as USER_FILE.all_data fallback in pupil time-course
preparation, GAMM modelling, GCA preparation, GCA plotting, AOI-window
summaries, AOI GLMM preparation, AOI-window mixed modelling,
pupil-window model-data preparation, pupil-window mixed modelling, and
cluster-data preparation.check_gazepoint_real_data_readiness(), an
explicit final readiness gate for real-data analysis. The helper returns
structured overview, gate_decision,
checks, detected_columns,
data_summary, condition_summary, and
settings outputs, with pass/warn/fail readiness
status.run_gazepoint_eyetools_fixation_detection(), an
optional external-detector wrapper for eyetools. The
wrapper prepares Gazepoint data using the expected pID,
trial, time, x, and
y schema, supports dispersion, VTI fixation, and VTI
saccade branches, and records clean skipped, complete, partial-complete,
and error statuses.create_gazepoint_reporting_checklist(), an
auto-generated reporting checklist for manuscript/report preparation. It
summarises reporting readiness across data structure, readiness gates,
import/workflow checks, sampling/tracking quality, AOI reporting, pupil
reporting, model diagnostics, sensitivity analyses, reproducibility, and
optional advanced methods.compute_gazepoint_time_varying_transition_matrix(), a
dedicated helper for transition-count and transition-probability
matrices by time window and grouping variables.fit_gazepoint_transition_count_nb_sensitivity(),
an optional negative-binomial transition-count sensitivity model using
glmmTMB when available.run_gazepoint_gazer_crosscheck(), an optional
external gazeR preprocessing cross-check wrapper.audit_gazepoint_stimulus_luminance(),
audit_gazepoint_pupil_reliability(), and
interpolate_gazepoint_pupil_pchip() for pupil-analysis
robustness and reporting support..env pronoun use
in internal helper functions by replacing dplyr pronoun-based assignment
with explicit local data-frame assignment.Recent focused validations completed successfully for the following advanced helpers:
devtools::test(filter = "estimate_gazepoint_divergence_point")
# [ FAIL 0 | WARN 0 | SKIP 0 | PASS 95 ]
devtools::test(filter = "run_gazepoint_model_leave_one_out")
# [ FAIL 0 | WARN 0 | SKIP 0 | PASS 98 ]
devtools::test(filter = "prepare_gazepoint_fixation_aligned_data")
# [ FAIL 0 | WARN 0 | SKIP 0 | PASS 117 ]
devtools::test(filter = "transform_gazepoint_aoi_empirical_logit")
# [ FAIL 0 | WARN 0 | SKIP 0 | PASS 89 ]
devtools::test(filter = "plot_gazepoint_model_predictions")
# [ FAIL 0 | WARN 0 | SKIP 0 | PASS 83 ]
devtools::test(filter = "compare_gazepoint_nested_models")
# [ FAIL 0 | WARN 0 | SKIP 0 | PASS 95 ]
devtools::test(filter = "flag_gazepoint_pupil_hampel")
# [ FAIL 0 | WARN 0 | SKIP 0 | PASS 77 ]
devtools::test(filter = "recalibrate_gazepoint_gaze")
# [ FAIL 0 | WARN 0 | SKIP 0 | PASS 109 ]
devtools::test(filter = "recommend_gazepoint_exclusions")
# [ FAIL 0 | WARN 0 | SKIP 0 | PASS 89 ]The current full-package validation status after the README, vignette, and example-data branches is:
devtools::test()
# [ FAIL 0 | WARN 0 | SKIP 0 | PASS 6788 ]
devtools::check()
# 0 errors | 0 warnings | 0 notesDuring full tests,
boundary (singular) fit: see help('isSingular') messages
may appear in mixed-model diagnostic contexts. These are expected
diagnostic messages from singular-fit test fixtures and are not package
failures when the final test summary reports
FAIL 0 | WARN 0.
On some Windows systems, a Quarto/TMPDIR message may appear after
devtools::check(). This is harmless when the final
R CMD check results report:
0 errors | 0 warnings | 0 notesAdded lightweight built-in example datasets so README examples, vignettes, tests, and user workflows can run without private Gazepoint files:
gazepoint_example_mastergazepoint_example_fixationsgazepoint_example_aoi_geometrygazepoint_example_aoi_windowsgazepoint_example_pupil_windowsAdded data-raw/create_gazepoint_example_data.R to
regenerate the example datasets reproducibly.
Added dataset documentation in R/data.R.
Added focused tests for the example datasets and their compatibility with core master-table, pupil-window, AOI-window, and AOI-geometry workflows.
Excluded data-raw/ from the built package via
.Rbuildignore to avoid R CMD check top-level file
notes.
Current validation after the example-data branch:
devtools::test() reports
FAIL 0 | WARN 0 | SKIP 0 | PASS 6788.devtools::check() reports
0 errors | 0 warnings | 0 notes.emmeans support, CSV
export of model tables, model-implied prediction visualisation, and
nested model-comparison reporting.devtools::test() passes with 6788
tests, and devtools::check() returns 0 errors, 0 warnings,
and 0 notes.These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.