Visual gallery¶

The previews on this page summarize deterministic eyeprocesspy 0.1.0 example outputs. Run python examples/core_gallery.py and python examples/advanced_gallery.py to generate the full Matplotlib figures directly through the package plotting API. The scripts were validated against the CI-built wheel and use no private participant data.

Gaze, fixation and AOI workflows¶

**Gaze trace.** Ordered valid gaze samples in canonical coordinates.

Fixation plot — **Fixations.** Duration-scaled fixation centroids.

Scanpath plot — **Scanpath.** Ordered AOI visits with spatial trajectory.

Gaze density heatmap — **Gaze density.** Two-dimensional histogram over gaze coordinates.

AOI dwell plot — **AOI dwell.** AOI-level dwell features carried in the canonical feature table.

AOI transition matrix — **Transition matrix.** Row-normalized transitions derived from scanpath episodes.

Pupil and data-quality workflows¶

**Pupil time series.** Eye-specific pupil streams on a shared timebase.

Sampling irregularity audit — **Sampling irregularity.** Effective sampling diagnostics with an explicit review threshold.

Calibration error model — **Calibration error.** Empirical horizontal/vertical error cloud used to propagate gaze uncertainty.

Probabilistic AOI assignment — **Probabilistic AOIs.** Membership probabilities after calibration uncertainty is propagated.

Psychometrics and measurement¶

Process reliability Bland Altman plot — **Process reliability.** Bland–Altman diagnostics for repeated process measures.

IRT information curve — **IRT information.** Test information across the latent continuum.

**IRT item fit.** Item-level fit diagnostics against the reference line.

IRT differential item functioning curve — **DIF curve.** Signed focal-reference probability difference across theta.

Dataset overview¶

Canonical eyeprocess dataset overview

The plotting functions retain the underlying plot data on the Matplotlib axes where relevant (ax.eyeprocess_plot_data, and for matrix plots ax.eyeprocess_plot_matrix). This makes the visual output auditable and allows publication styling without losing the numerical payload.

Scientific interpretation

The gallery demonstrates computational capabilities. A gaze, pupil, reliability, or psychometric statistic is not automatically a validated psychological construct. Use the package's evidence, provenance, and guardrail layers alongside an appropriate study design.