anomaly_eval opsignal × signal → tableimport fullseye as fs; fs.ledger.anomaly_image_auroc(scores, labels) (実装を直接呼ぶなら import anomeval; anomeval.anomaly_image_auroc(scores, labels)、台帳から引くなら opsspc.get("anomaly_image_auroc"))Image-level AUROC from one anomaly score per image and a good/defective label per image (table).
scores is a 1-D array (higher = more anomalous), labels the same length with 1 /
True = defective. Exact Mann–Whitney statistic with mid-ranks for ties (Hanley & McNeil
1982): the probability that a random defective image outscores a random good one, ties
counting 1/2. Returns auroc, n_pos, n_neg.
Raises ValueError on empty / mismatched / non-finite input, non-binary labels, or when
all images carry the same label (AUROC undefined).
py -3.11 examples/anomaly_eval_metrics.pypy -3.11 examples/poc_good_sample_variation_model.pypy -3.11 examples/poc_patch_anomaly.pytable を入力に取れる)msa_anova_table · msa_gauge_rr · msa_bias_linearity · msa_attribute_agreement · gum_standard_uncertainty · gum_propagate · gum_expanded · gum_monte_carlo
anomaly_eval)anomaly_pixel_auroc · anomaly_pro · anomaly_region_overlap · anomaly_pixel_f1_max · anomaly_image_f1_max · anomaly_operating_point
Provenance: anomeval.py — SPC operator registry. この per-op ノートは tools/opdocs.py md が自動生成(手編集しない)。
© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.