daniel1noble / BACE / 25929232737

Builds Branch Commit Type Ran Committer Via Coverage
25929232737 main Add smoke/production mode toggle to sim-reference benchmark workflow Wires a workflow_dispatch `mode` input (default: smoke) to the existing BACE_NITT/BURNIN/THIN/RUNS/NFINAL env-var hooks in the evaluator, and passes `1` as the second CLI arg in... push daniel1noble github
91.15
25929072426 main Reference dataset scripts push daniel1noble github
91.15
25907501234 main Udpated ignore push daniel1noble github
91.15
25362969520 main Bump n_final default 10 -> 50; add simulated-benchmark vignette section Why default n_final = 50: with only 10 imputations the empirical [2.5%, 97.5%] quantile of per-cell imputed values is closer to [min, max] of 10 draws than to a true 95% pred... push daniel1noble github
91.15
25341195972 main Add per-level multinomial Pagel-style lambda to phylo_signal_summary For categorical traits, phylo_signal_summary() now reports both: - H2_* trace-based heritability on MCMCglmm's working scale (existing behaviour, ... push daniel1noble github
91.15
25340715961 main sim_bace: scale default sigmas down for non-gaussian variables When response_type is gaussian, default sigma_species = sigma_residual = 1 is innocuous: the response is on a linear scale. For variables passed through a non-linear link (poisson via... push daniel1noble github
91.17
25339511135 main Re-run accuracy benchmark at n_final=50 — coverage now well-calibrated The single-rep "poor coverage" (~0.62 for gaussian) was a benchmark design artifact, not a BACE problem: with n_final=5 the empirical [2.5%, 97.5%] quantile is essentially [mi... push daniel1noble github
91.16
25338302573 main Per-type accuracy benchmark on simulated data with known truth dev/sim_accuracy_benchmark.R: per-type sweep across all 5 BACE response types {gaussian, poisson, binary, K=3 categorical, K=4 ordinal}. For each, simulates 60 species / 120 cases via... push daniel1noble github
91.16
25337507009 main Coverage push v2: 87.76% -> 91.19% (past 90% target, 1251 tests) Two new test files focused on remaining model_functions.R gaps and the parallel/plot-helper paths. - test-pred_cat_threshold.R: direct mock-based unit tests for .pred_cat / .pred... push daniel1noble github
91.16
25336882118 main Coverage push: 80.6% -> 87.76% (1214 tests) Five new test files target previously-uncovered orchestration paths: - test-verbose_orchestration.R: bace()/bace_imp()/bace_final_imp() verbose=TRUE cat() lines + nitt_cat_mult + ovr_categorical=FALS... push daniel1noble github
87.76
25335689570 main Pred helpers + final_imp orchestration tests (1140 tests, 80.6% coverage) tests/testthat/test-pred_helpers.R (48 tests): Direct unit tests for .pred_cont and .pred_count with hand-built mock MCMCglmm-like objects. Asserts numerical correctnes... push daniel1noble github
80.35
25335321784 main Push past 1000 tests + 80% coverage milestone Adds two batches of tests: tests/testthat/test-simulate.R (additions, 14 new test_thats): Response-type variants: response_type='threshold3' : 3-level ordered factor response_type='thresho... push daniel1noble github
79.67
25334877583 main 1000-test milestone: simulate_aux_helpers tests (now 1011 passing) Adds tests/testthat/test-simulate_aux_helpers.R with 76 tests on the helper functions in simulate_auxiliary.r: var_name_gen : naming convention sweep n=1..5 apply_miss... push daniel1noble github
77.66
25334583911 main Add validation/properties/build_functions tests + .build_formula source fix Pushing toward the 1000-test / 90%-coverage target. After this commit: test PASS : 538 -> 935 (+397 this commit set) coverage : 74.4% -> 76.3% R CMD check ... push daniel1noble github
76.27
25334172491 main Add per-type imputation accuracy tests + pipeline numerical assertions Adds two more test files driving toward the ambitious 1000-test / 90%-coverage target. Local: 570 PASS / 0 FAIL. tests/testthat/test-imputation_accuracy.R (6 tests, all skip_... push daniel1noble github
76.02