Package: kollaR 1.1.4

kollaR: Event Classification, Visualization and Analysis of Eye Tracking Data

Functions for analysing eye tracking data, including event detection, visualizations and area of interest (AOI) based analyses. The package includes implementations of the IV-T, I-DT, adaptive velocity threshold, and Identification by two means clustering (I2MC) algorithms. See separate documentation for each function. The principles underlying I-VT and I-DT algorithms are described in Salvucci & Goldberg (2000) <doi:10.1145/355017.355028>. Two-means clustering is described in Hessels et al. (2017), <doi:10.3758/s13428-016-0822-1>. The adaptive velocity threshold algorithm is described in Nyström & Holmqvist (2010),<doi:10.3758/BRM.42.1.188>. A documentation of the 'kollaR' can be found in Kleberg et al (2026) <doi:10.3758/s13428-025-02903-z>. Cite this paper when using 'kollaR' See a demonstration in the URL.

Authors:Johan Lundin Kleberg [aut, cre]

kollaR_1.1.4.tar.gz
kollaR_1.1.4.zip(r-4.7-any)kollaR_1.1.4.zip(r-4.6-any)kollaR_1.1.4.zip(r-4.5-any)
kollaR_1.1.4.tgz(r-4.6-any)kollaR_1.1.4.tgz(r-4.5-any)
kollaR_1.1.4.tar.gz(r-4.7-any)kollaR_1.1.4.tar.gz(r-4.6-any)
kollaR_1.1.4.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION
card.svg |card.png
kollaR/json (API)

# Install 'kollaR' in R:
install.packages('kollaR', repos = c('https://drjohanlk.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/drjohanlk/kollar/issues

Datasets:

On CRAN:

Conda:

1.30 score 1 stars 1 scripts 466 downloads 34 exports 106 dependencies

Last updated from:f3d1b082b5. Checks:9 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-develOK155
source / vignettesOK224
linux-releaseOK180
macos-releaseOK187
macos-oldrelOK192
windows-develOK112
windows-releaseOK126
windows-oldrelOK108
wasm-releaseOK137

Exports:adjust_fixation_timingalgorithm_adaptivealgorithm_i2mcalgorithm_idtalgorithm_ivtanimated_fixation_plotaoi_testcalculate_rmscluster2mdownsample_gazedraw_aoisfilt_plot_2dfilt_plot_temporalfind.transition.weightsfind.valid.periodsfixation_plot_2dfixation_plot_temporalfixation_plot_tsidt_filterinterpolate_with_marginivt_filtermerge_adjacent_fixationsmovmean.filterplot_algorithm_resultsplot_filter_resultsplot_sample_velocityplot_velocity_profilespreprocess_gazeprocess_gazestatic_plotstatic_plot_minimalsuggest_thresholdsummarize_fixation_metricstrim_fixations

Dependencies:abindbackportsbase64encbootbroombslibcachemcarcarDataclicolorspacecommonmarkcorrplotcowplotcpp11curlDerivdigestdoBydplyrfarverfastmapfontawesomeforecastFormulafracdifffsgenericsggforceggplot2ggpubrggrepelggsciggsignifgluegridExtragtablehtmltoolshttpuvisobandjpegjquerylibjsonlitelabelinglaterlatticelifecyclelme4lmtestmagickmagrittrMASSMatrixMatrixModelsmemoisemgcvmimeminqamodelrnlmenloptrnnetnumDerivotelpatchworkpbkrtestpillarpkgconfigpolyclippolynompromisespurrrquantregR6rappdirsrbibutilsRColorBrewerRcppRcppArmadilloRcppEigenRdpackreformulasrlangrstatixS7sassscalesshinysourcetoolsSparseMstringistringrsurvivalsystemfontstibbletidyrtidyselecttimeDatetweenrurcautf8vctrsviridisLitewithrxtablezoo

Readme and manuals

Help Manual

Help pageTopics
Fixation and Saccade Detection, Visualization, and Analysis of Eye Tracking DatakollaR
Adjust the onset and offset of fixations to avoid misclassification of saccade samples as belonging to fixationsadjust_fixation_timing
Adaptive velocity-based algorithm for saccade and fixation detectionalgorithm_adaptive
Fixation detection by two-means clusteringalgorithm_i2mc
Dispersion-based fixation detection algorithm '(I-DT)'algorithm_idt
I-VT algorithm for fixation and saccade detectionalgorithm_ivt
Create GIF animation of fixations on a stimulus imagesanimated_fixation_plot
Test whether a gaze coordinates are within or outside a rectangular or elliptical AOI. The data fram aois must contain variables with minimum x, minimum y, maximum x, and maximum y values and type where rect or rectangle means that the AOI is a rectangle and ellipse or circle that the AOI is an ellipse The coordinate variables must be named: x0 OR xmin: minimum x value x1 OR xmax: maximum x value y0 OR ymin: minimum y value y1 OR ymax: maximum y value If a column called name is present, the output for each AOI will be labelled accordingly. Otherwise, the output will be labelled according to the order of the AOI in the data frame. The df 'gaze' must contain the variables onset, duration, x, and y. Latency will be defined as the value in onset of the first detected gaze coordinate in the AOI Make sure that the timestamps are correct! The function can be used with gaze data either fixations, saccades, or single samples. Note that the output variables are not equally relevant for all types of gaze data. For example, both total duration and latency are relevant in many analyses focusing on fixations, but total duration may be less relevant in analyses of saccades.aoi_test
Calculate sample-to-sample root mean squared deviations (RMS) of subsequent samples in a data segmentcalculate_rms
Fixation detection by two-means clusteringcluster2m
Downsample gazedownsample_gaze
Draw one or more areas of interest, AOIs, on one or more stimulus images and save the coordinates to the R prompt. The function returns a data frame with all saved AOIs. By default, AOIs are drawn in a coordinate system where y is 0 in the lower extreme of the image, e.g., an ascending y axis. Tobii eye trackers use a coordinate system with a descending y-axis, e.g., x and y are 0 in the upper left corner of the image. Make sure that your AOIS match the coordinate system of your eye tracker output. By setting the parameter reverse.y.axis to TRUE, the saved AOIs will be reformatted to fit a coordinate system with a descending y-axis. All AOIS have the variables xmin, xmax, ymin and ymax. xmin is the minimum x value, ymin the minimum y value. xmax the maximum x value. ymax the maximum y value. Major updates to this function were made in version 1.1.4draw_aois
Plot fixations vs. individual sample coordinates in 2D space. In the current release, filt_plot_2d is a wrapper around fixation_plot_2d which accepts the same arguments.filt_plot_2d
Plot fixation filtered vs. raw gaze coordinates. This function will be replaced by fixation_plot_temporal in future releases. It is currently a wrapper around fixation_plot_temporal accepting the same arguments.filt_plot_temporal
Find transition weights for each sample in a gaze matrix.find.transition.weights
Find subsequent periods in a vector with values below a threshold. Used internally by the function suggest_thresholdfind.valid.periods
Plot fixations vs. individual sample coordinates in 2D space.fixation_plot_2d
Plot fixation classified vs. raw gaze coordinatesfixation_plot_temporal
Plot fixation classified vs. raw gaze coordinate time seriesfixation_plot_ts
Dispersion-based fixation detection algorithm '(I-DT)'idt_filter
Interpolate over gaps (subsequent NAs) in vector.interpolate_with_margin
I-VT algorithm for fixation and saccade detectionivt_filter
Merge adjacent fixationsmerge_adjacent_fixations
Calculate the moving mean of a vectormovmean.filter
Plot vdescriptives one or more fixation detection algorithmsplot_algorithm_results
Plot descriptives from one or more fixation detection algorithmsplot_filter_results
Plot the sample-to-sample velocity of eye tracking data.plot_sample_velocity
Create ggplot of saccade velocity profilesplot_velocity_profiles
Interpolation and smoothing of gaze-vectorpreprocess_gaze
Interpolation and smoothing of gaze-vector. This function will be replaced by preprocess_gaze in future versions. process_gaze is a wrapper around preprocess gaze (the two functions produce the same result)process_gaze
Sample-to-sample raw and fixation classified data from 1 individualsample.data.classified
Fixations from 1 individualsample.data.fixation1
Fixations from 7 individualssample.data.fixations
Pre-processed sample-by-sample example datasample.data.processed
Saccades from 3 individualssample.data.saccades
Unprocessed sample-by-sample example datasample.data.unprocessed
Plot fixations in 2D space on a stimulus image (with visible x and y axis labels and ticks)static_plot
Plot fixations in 2D space on a stimulus image (minimalistic plot)static_plot_minimal
Data-driven identification of threshold parameters for adaptive veloctity-based saccade detection.suggest_threshold
Summarize fixation statisticssummarize_fixation_metrics
Adjust the onset and offset of fixations to avoid misclassification of saccade samples as belonging to fixationstrim_fixations