v0.3.0 — Full Matlab Parity

What's New in v0.3.0

This release achieves full method-level parity with the Matlab nSTAT toolbox across all 16 audited classes (484 methods).

New Methods

• SignalObj: MTMspectrum(), spectrogram(), periodogram(), findPeaks(), findMaxima(), findMinima(), findGlobalPeak(), shift(), shiftMe(), alignTime(), power(), sqrt(), xcov()
• DecodingAlgorithms: Full SSGLM EM suite (PPSS_EStep, PPSS_MStep, PPSS_EM, PPSS_EMFB, estimateInfoMat, prepareEMResults), UKF methods (ukf, ukf_ut, ukf_sigmas)
• SpikeTrainCollection: ssglm(), ssglmFB() entry points
• FitResSummary: plotAllCoeffs(), plot3dCoeffSummary(), plot2dCoeffSummary(), plotKSSummary()

Paper Examples

All 5 paper examples rewritten as self-contained, documented scripts matching the Matlab workflow:

1. mEPSC Poisson analysis (constant vs piecewise-rate)
2. Whisker stimulus thalamus (lag search, nested model comparison)
3. PSTH and SSGLM (CIF simulation, GLM-PSTH, state-space learning)
4. Place cells (Gaussian + Zernike receptive fields, population statistics)
5. Decoding (PPAF, goal-directed reach, hybrid filter)

Fidelity Summary

• Classes: 11 exact, 7 high fidelity, 1 N/A (19 total)
• Notebooks: 8 exact, 5 high fidelity (13 total)
• Tests: 198 passed, 2 skipped

Install

pip install nstat-toolbox==0.3.0

Full changelog: v0.2.0...v0.3.0

v0.2.0 — Matlab API Parity

nSTAT Python v0.2.0 — Matlab API Parity

Complete functional parity with the Matlab nSTAT toolbox.

New Methods

State-Space GLM (SSGLM) EM Algorithm

• PPSS_EMFB, PPSS_EStep, PPSS_MStep, PPSS_EM
• estimateInfoMat, prepareEMResults, _ComputeStimulusCIs_MC
• nstColl.ssglm(), nstColl.ssglmFB()

Unscented Kalman Filter

• ukf, ukf_ut, ukf_sigmas

SignalObj Spectral Analysis

• MTMspectrum, spectrogram, periodogram

SignalObj Utilities

• shift, shiftMe, alignTime, power, sqrt, xcov

SignalObj Peak-Finding

• findPeaks, findMaxima, findMinima, findGlobalPeak

FitResSummary Visualization

• plotAllCoeffs, plot3dCoeffSummary, plot2dCoeffSummary, plotKSSummary

Paper Examples

All 5 paper examples (Sections 2.3–2.6 of Cajigas et al. 2012) rewritten as self-contained documented scripts with --export-figures support.

Documentation

• Complete help files with grouped method listings for all 16 classes
• Paper overview with SSGLM workflow, decoding, and signal processing sections
• README aligned with Matlab nSTAT repo structure

Bug Fixes (vs Matlab)

• findPeaks minima branch: now correctly negates data (nSTAT#12)
• findGlobalPeak: fixed sOBj → sObj typo (nSTAT#13)
• shiftMe: now updates minTime/maxTime (nSTAT#14)
• nspikeTrain.plot(): accepts handle kwarg for API consistency

Verification

• 180 tests pass across Python 3.11 and 3.12
• All 5 paper examples verified end-to-end (24 figures generated)
• 13/13 CI checks green

Full Changelog: v0.1.0...v0.2.0

v1.0.0-rc1

Release candidate baseline for MATLAB-equivalent parity in nSTAT-python.\n\nHighlights:\n- Parity snapshot at release commit 8b69adf: high=0, medium=0, low=0\n- CI now enforces high/medium parity gate in test-and-build\n- Green workflows on release commit: test-and-build, pages, notebooks-full\n- Canonical validation artifact attached: nstat_python_validation_report_20260301_212022.pdf\n

nSTAT-python v1.0.0-rc5

nSTAT-python v1.0.0-rc5

Automated release-candidate notes generated from parity, functional, and numeric-drift artifacts.

Structural parity

• High gaps: 0
• Medium gaps: 0
• Low gaps: 0
• Total gaps: 0

Functional parity

• Total methods: 501
• Contract-verified methods: 480
• Contract-explicit verified methods: 480
• Probe-verified methods: 0
• Excluded methods: 21
• Missing symbol methods: 0
• Unverified behavior methods: 0

Example parity

• Total topics: 30
• Validated topics: 26
• MATLAB doc-only topics: 4
• Pending manual review topics: 0
• Out-of-scope topics:
  • DocumentationSetup2025b
  • FitResSummaryExamples
  • FitResultExamples
  • FitResultReference

Numeric drift

• Topics checked: 31
• Topics passed: 31
• Topics failed: 0
• Metrics checked: 180
• Metrics failed: 0

RC delta vs v1.0.0-rc4

• Structural high gaps: 0 -> 0 (+0)
• Structural medium gaps: 0 -> 0 (+0)
• Validated example topics: 26 -> 26 (+0)
• MATLAB doc-only topics: 4 -> 4 (+0)
• Contract-explicit verified methods: 480 -> 480 (+0)
• Probe-verified methods: 0 -> 0 (+0)
• Unverified behavior methods: 0 -> 0 (+0)
• Numeric topics checked: 31 -> 31 (+0)
• Numeric topics passed: 31 -> 31 (+0)
• Numeric topics failed: 0 -> 0 (+0)
• Numeric metrics checked: 126 -> 180 (+54)
• Numeric metrics failed: 0 -> 0 (+0)

Frozen MATLAB snapshot

• Snapshot id: matlab_gold_20260302 (2026-03-02)
• Source manifest: data/shared/matlab_source_20260302.manifest.json (sha256 578a20db6433efed11466eb64ab23d77a1f106f3a2da8937c28849511e9385e7)
• Mirror manifest: data/shared/matlab_gold_20260302.manifest.json (sha256 b980cb16f5872b53e841f360e9a81a34c9e6b4a5149a9ef3b7fd96314899bfe4)
• File count: 42
• Total size bytes: 504513862

Validation asset

• PDF: nstat_python_validation_report_20260302_224759.pdf

Build metadata

• Commit: aa7c0ccb87a868512bc5bf490d970a12baeab778
• Workflow run: https://github.com/cajigaslab/nSTAT-python/actions/runs/22599268208

nSTAT-python v1.0.0-rc4

nSTAT-python v1.0.0-rc4

Automated release-candidate notes generated from parity, functional, and numeric-drift artifacts.

Structural parity

• High gaps: 0
• Medium gaps: 0
• Low gaps: 0
• Total gaps: 0

Functional parity

• Total methods: 501
• Contract-verified methods: 480
• Contract-explicit verified methods: 480
• Probe-verified methods: 0
• Excluded methods: 21
• Missing symbol methods: 0
• Unverified behavior methods: 0

Example parity

• Total topics: 30
• Validated topics: 26
• MATLAB doc-only topics: 4
• Pending manual review topics: 0
• Out-of-scope topics:
  • DocumentationSetup2025b
  • FitResSummaryExamples
  • FitResultExamples
  • FitResultReference

Numeric drift

• Topics checked: 31
• Topics passed: 31
• Topics failed: 0
• Metrics checked: 126
• Metrics failed: 0

Frozen MATLAB snapshot

• Snapshot id: matlab_gold_20260302 (2026-03-02)
• Source manifest: data/shared/matlab_source_20260302.manifest.json (sha256 578a20db6433efed11466eb64ab23d77a1f106f3a2da8937c28849511e9385e7)
• Mirror manifest: data/shared/matlab_gold_20260302.manifest.json (sha256 b980cb16f5872b53e841f360e9a81a34c9e6b4a5149a9ef3b7fd96314899bfe4)
• File count: 42
• Total size bytes: 504513862

Validation asset

• PDF: nstat_python_validation_report_20260302_221606.pdf

Build metadata

• Commit: cf36c2f1978a640948cb0d937d3230d8ee73e162
• Workflow run: https://github.com/cajigaslab/nSTAT-python/actions/runs/22598121674

nSTAT-python v1.0.0-rc3

nSTAT-python v1.0.0-rc3

Automated release-candidate notes generated from parity, functional, and numeric-drift artifacts.

Structural parity

• High gaps: 0
• Medium gaps: 0
• Low gaps: 0
• Total gaps: 0

Functional parity

• Total methods: 501
• Contract-verified methods: 480
• Contract-explicit verified methods: 277
• Probe-verified methods: 203
• Excluded methods: 21
• Missing symbol methods: 0
• Unverified behavior methods: 0

Example parity

• Total topics: 30
• Validated topics: 26
• MATLAB doc-only topics: 4
• Pending manual review topics: 0
• Out-of-scope topics:
  • DocumentationSetup2025b
  • FitResSummaryExamples
  • FitResultExamples
  • FitResultReference

Numeric drift

• Topics checked: 13
• Topics passed: 13
• Topics failed: 0
• Metrics checked: 36
• Metrics failed: 0

Frozen MATLAB snapshot

• Snapshot id: matlab_gold_20260302 (2026-03-02)
• Source manifest: data/shared/matlab_source_20260302.manifest.json (sha256 578a20db6433efed11466eb64ab23d77a1f106f3a2da8937c28849511e9385e7)
• Mirror manifest: data/shared/matlab_gold_20260302.manifest.json (sha256 b980cb16f5872b53e841f360e9a81a34c9e6b4a5149a9ef3b7fd96314899bfe4)
• File count: 42
• Total size bytes: 504513862

Validation asset

• PDF: nstat_python_validation_report_20260302_204327.pdf

Build metadata

• Commit: 8675f3d127b454c9b0d84e5449433ee2da95e8f4
• Workflow run: https://github.com/cajigaslab/nSTAT-python/actions/runs/22594829334

nSTAT-python v1.0.0-rc2

nSTAT-python v1.0.0-rc2

This release candidate tightens parity enforcement for in-scope examples and freezes the MATLAB data snapshot used for reproducible validation.

Highlights

• Enforced alignment_status=validated for all in-scope example topics in CI.
• Explicitly documented out-of-scope MATLAB documentation-only topics in parity policy/spec:
  • DocumentationSetup2025b
  • FitResSummaryExamples
  • FitResultExamples
  • FitResultReference
• Added frozen MATLAB gold data snapshot metadata:
  • parity/matlab_gold_snapshot_20260302.yml
• Updated gate-mode PDF parity logic to honor in-scope vs out-of-scope topic policy.

Validation (latest on this release commit)

• test-and-build: 22593954595
• validation-pdf: 22594014785
• pages: 22593954590

Numeric Drift Report

• parity/numeric_drift_report.json

Frozen MATLAB Gold Snapshot

• Mirror manifest: data/shared/matlab_gold_20260302.manifest.json
  • SHA256: b980cb16f5872b53e841f360e9a81a34c9e6b4a5149a9ef3b7fd96314899bfe4
  • Files: 42
  • Total size bytes: 504513862
• Source manifest: data/shared/matlab_source_20260302.manifest.json
  • SHA256: 578a20db6433efed11466eb64ab23d77a1f106f3a2da8937c28849511e9385e7
  • Files: 42
  • Total size bytes: 504513862

PDF Asset

• Attached: nstat_python_validation_report_20260302_151458.pdf

nSTAT-python v0.1.0-split

Split Release: Standalone Python nSTAT

This release establishes nSTAT-python as the standalone Python repository split from nSTAT.

Included

• Standalone package layout at repo root (nstat/, tools/, docs/, notebooks/, tests/)
• Canonical Python APIs (nstat.signal, nstat.spikes, nstat.trial, nstat.analysis, nstat.fit, nstat.cif, nstat.decoding, nstat.datasets)
• Help topic docs generated from helpfiles/helptoc.xml (full topic coverage)
• Example notebook generation and execution gating for all 25 help example topics
• Bundled datasets required for offline example execution
• CI gate requiring:
  • docs coverage verification
  • notebook execution and topic alignment
  • strict offline target-install standalone verification
  • pytest

Migration Guidance

• Python users should now use this repository: cajigaslab/nSTAT-python.
• MATLAB users should use cajigaslab/nSTAT: https://github.com/cajigaslab/nSTAT
• If migrating from monorepo paths, drop the python/ prefix in commands and imports from checkout root.

Related Split PRs

• nSTAT-python bootstrap PR: #1
• nSTAT MATLAB-only cleanup PR: cajigaslab/nSTAT#4