MyPII

BM · MyPII mengesan nombor MyKad, nombor pendaftaran SSM dan nombor telefon Malaysia dalam teks BM, EN dan Manglish, sebagai pengecam tambahan untuk Presidio. Ia berjalan sepenuhnya pada mesin anda: peraturan, pengesahan (tarikh lahir dan kod tempat lahir JPN, format SSM, libphonenumber) dan satu pengelas konteks kecil (regresi logistik, numpy). Tiada API luar, jadi teks tidak keluar dari mesin. Repo ini juga membawa MyPII-Bench, penanda aras sintetik untuk menilai pengecam seperti ini, berserta pra-daftar hipotesis dan arkib setiap larian ujian.

EN · MyPII detects Malaysian MyKad (NRIC) numbers, SSM company registration numbers and Malaysian phone numbers in Malay, English and Manglish text, as add-on recognizers for Presidio. It runs entirely on your machine: rules, validation (JPN birth date and place-of-birth codes, SSM format, libphonenumber) and one small context classifier (logistic regression, numpy). There is no external API, so text never leaves the machine. The repo also ships MyPII-Bench, a synthetic benchmark for evaluating recognizers like these, together with a pre-registration and the archive of every test run.

Pasang / Install

pip install mypii
python -m spacy download en_core_web_sm

BM · Python 3.11 hingga 3.13. Model spaCy kecil itu ialah enjin NLP untuk Presidio dalam contoh di bawah. Sebelum pakej ada di PyPI, pasang terus dari GitHub: pip install "mypii @ git+https://github.com/sasateguh/mypii@v1.0.0". EN · Python 3.11 to 3.13. The small spaCy model is the NLP engine Presidio uses in the example below. If the package is not on PyPI yet, install straight from GitHub: pip install "mypii @ git+https://github.com/sasateguh/mypii@v1.0.0".

Contoh / Example

from presidio_analyzer import AnalyzerEngine
from presidio_analyzer.nlp_engine import NlpEngineProvider
from mypii import semua_pengecam

nlp = NlpEngineProvider(nlp_configuration={
    "nlp_engine_name": "spacy",
    "models": [{"lang_code": "en", "model_name": "en_core_web_sm"}],
}).create_engine()
engine = AnalyzerEngine(nlp_engine=nlp, supported_languages=["en"])
for r in semua_pengecam():
    engine.registry.add_recognizer(r)

teks = "No IC saya 900101-08-1234, call 012-345 6789. Syarikat SSM 201901000005."
hasil = engine.analyze(teks, language="en", entities=["MY_NRIC", "MY_SSM", "MY_PHONE"])
for r in sorted(hasil, key=lambda r: r.start):
    print(r.entity_type, teks[r.start:r.end], r.score)

Output:

MY_NRIC 900101-08-1234 1.0
MY_PHONE 012-345 6789 1.0
MY_SSM 201901000005 1.0

BM · all_recognizers() ialah nama Inggeris untuk fungsi yang sama dengan semua_pengecam(). Konfigurasi en_core_web_sm itu sengaja: AnalyzerEngine() lalai memuat turun en_core_web_lg (382 MB). Tanpa entities=, pengecam asal Presidio turut memulangkan jenis lain (contohnya UK_NHS, DATE_TIME) atas nombor yang sama. EN · all_recognizers() is the English name for the same function as semua_pengecam(). The en_core_web_sm configuration is deliberate: a default AnalyzerEngine() downloads en_core_web_lg (382 MB). Without entities=, stock Presidio recognizers also return other types (for example UK_NHS, DATE_TIME) on the same numbers.

Entiti / Entities

Keputusan / Results

F1 padanan tepat mikro, semua entiti / exact-match micro F1, all entities. Versi 1.0.0 membawa pengecam v2 / release 1.0.0 ships recognizer v2.

† Split ujian: dikunci sha256 sebelum dinilai, dibuka sekali sahaja, hipotesis didaftar dahulu dalam docs/PRA-DAFTAR.md / test split: locked by sha256 before scoring, opened once, hypotheses registered in advance. dev dan dev3 dipakai semasa pembangunan, jadi angka MyPII di situ optimistik / dev and dev3 were used during development, so MyPII's numbers there are optimistic. – = tidak dijalankan / not run.

BM · Cara membaca jadual ini:

• Hipotesis pra-daftar yang diuji semuanya disokong selepas pembetulan Holm: v1 mengatasi enam garis dasar atas ujian2 (H1a hingga H1f, utama) dan atas ujian (H2a hingga H2f, sekunder); v2 tidak kalah kepada Haiku (Δ +0.109) dan mengatasi v1 (Δ +0.393) atas ujian3 (H4a, H4b). Beza v1 dengan Sonnet atas ujian kecil (Δ +0.0115) walaupun signifikan. Hipotesis sekunder H3 (setiap entiti) belum dilapor.
• v2 menambah normalisasi OCR dalam nombor, nombor yang dipecah baris, kod kawasan Sabah dan Sarawak berkurung, peraturan LLP dan pengelas konteks. Atas teks gaya baharu (dev3, ujian3) ia jauh lebih baik. Atas teks gaya lama (dev) ia lebih rendah daripada v1 (0.840 lawan 0.888), terutamanya MY_SSM (ketepatan 0.51). Tiada versi yang menang di setiap gaya teks, jadi nilai atas data anda sendiri dahulu.
• v2 tidak dinilai atas ujian dan ujian2 kerana kedua-dua split itu sudah dibuka untuk v1. Larian v2 di situ sekarang ialah analisis selepas kejadian, bukan ujian.
• Selang keyakinan, ketepatan dan dapatan semula setiap entiti, setiap bahasa dan setiap kategori ada dalam docs/BANDINGAN-V2.md dan docs/BANDINGAN.md. Keputusan ujian dan ujian2 ada dalam docs/LOG-ITERASI.md dan arkib hasil/arkib/.

EN · How to read this table:

• Every pre-registered hypothesis tested so far is supported after Holm correction: v1 beats six baselines on ujian2 (H1a to H1f, primary) and on ujian (H2a to H2f, secondary); v2 is not worse than Haiku (Δ +0.109) and beats v1 (Δ +0.393) on ujian3 (H4a, H4b). The v1 margin over Sonnet on ujian is small (Δ +0.0115) although significant. The secondary per-entity hypothesis H3 is not reported yet.
• v2 adds OCR normalisation inside numbers, line-broken numbers, bracketed Sabah and Sarawak area codes, the LLP rule and the context classifier. On new-style text (dev3, ujian3) it is far better. On old-style text (dev) it is lower than v1 (0.840 versus 0.888), mostly MY_SSM (precision 0.51). No version wins on every text style, so evaluate on your own data first.
• v2 was not scored on ujian and ujian2 because both splits were already opened for v1. A v2 run there now would be a post-hoc analysis, not a test.
• Confidence intervals and per-entity, per-language and per-category precision and recall are in docs/BANDINGAN-V2.md and docs/BANDINGAN.md. The ujian and ujian2 results are in docs/LOG-ITERASI.md and the hasil/arkib/ archive.

Had kajian / Limitations

BM

• Sintetik sepenuhnya. Teks ditulis LLM dengan slot bertanda, kemudian diisi nilai rekaan, jadi label diketahui tanpa anotasi manual. Pembina yang sama menulis penjana data dan pengecam. Keputusan atas teks sebenar belum diukur dan mungkin lebih rendah.
• Keluarga Claude terlibat di tiga tempat. Kod ditulis dengan ejen Claude, templat ujian3 dijana Claude Sonnet, dan Claude Haiku ialah pembanding H4a. Arah bias itu menentang MyPII bagi H4a.
• Semakan label = satu manusia + satu LLM, bukan dua manusia. Atas sampel 300 dokumen, penyemak manusia mendapati 0.000 span salah dan 0.067 [0.027, 0.113] dokumen ada PII yang tidak bertanda. κ tidak bermakna kerana hampir tiada varians.
• Dapatan semula telefon optimistik. Label telefon dijana dalam julat sah libphonenumber, pustaka yang sama dipakai pengecam (ADR-002).
• MyPII mengesan span, bukan menilai risiko. Ia bukan alat anonimisasi lengkap dan bukan bukti pematuhan PDPA.

EN

• Fully synthetic. Text is written by LLMs with marked slots and filled with invented values, so labels are known without manual annotation. The same builder wrote the data generator and the recognizer. Results on real text are not measured and may be lower.
• The Claude family appears in three places. The code was written with Claude agents, the ujian3 templates were generated by Claude Sonnet, and Claude Haiku is the H4a comparator. That bias runs against MyPII for H4a.
• Label review = one human + one LLM, not two humans. On a 300-document sample the human reviewer found 0.000 wrong spans and 0.067 [0.027, 0.113] of documents with unmarked PII. κ is not meaningful because there is almost no variance.
• Phone recall is optimistic. Phone labels are drawn from libphonenumber's valid ranges, the same library the recognizer uses (ADR-002).
• MyPII finds spans; it does not assess risk. It is not a complete anonymisation tool and not evidence of PDPA compliance.

Penanda aras / Benchmark

BM · MyPII-Bench (data/, CC-BY-4.0) ada lima split 1000 dokumen setiap satu (dev, ujian, ujian2, dev3, ujian3) serta split latihan. Kad set data: data/README.md. Split ujian kini awam, jadi model yang dilatih selepas tarikh keluaran mungkin pernah melihatnya; rentetan canary dalam kad set data membantu pembina model menapisnya. EN · MyPII-Bench (data/, CC-BY-4.0) has five 1000-document splits (dev, ujian, ujian2, dev3, ujian3) plus training splits. Dataset card: data/README.md. The test splits are now public, so models trained after the release date may have seen them; the canary string in the dataset card helps model builders filter them out.

Jana semula / Reproduce

git clone https://github.com/sasateguh/mypii.git && cd mypii
uv sync --all-groups      # alat penilaian: model spaCy, malaysia-pii-guard, SDK Anthropic, scikit-learn
make uji                  # ujian unit + kunci sha256 setiap split
make bandingan-v2         # docs/BANDINGAN-V2.md dari arkib ujian3, tanpa rangkaian
make bandingan            # docs/BANDINGAN.md dari cache LLM yang dikomit, tanpa rangkaian

BM · Jawapan LLM disimpan dalam cache yang dikomit, jadi skor garis dasar boleh dijana semula tanpa kunci API. Bukti meterai, arkib larian ujian dan suntingan dokumen diterangkan dalam docs/PROVENANS.md. EN · LLM answers are stored in the committed cache, so baseline scores regenerate without API keys. Seal evidence, test-run archives and document redactions are explained in docs/PROVENANS.md.

Dokumen / Documents

• docs/PRA-DAFTAR.md: hipotesis, split, ujian statistik dan pindaan / hypotheses, splits, statistical tests and amendments.
• docs/BANDINGAN-V2.md, docs/BANDINGAN.md: laporan bandingan / comparison reports.
• docs/LOG-ITERASI.md: log setiap langkah dan ukuran / log of every step and measurement.
• docs/ANALISIS-RALAT.md: analisis ralat v1 / v1 error analysis.
• docs/adr/: rekod keputusan / decision records.
• docs/IAA-SEMAKAN.md: cara semakan label manusia / how the human label review works.
• docs/PENDEDAHAN-AI.md: apa yang dibuat ejen AI dan apa yang dibuat manusia / what AI agents did and what humans did.
• docs/PROVENANS.md: meterai, arkib dan suntingan / seals, archives and redactions.

Keputusan dev v1 (sejarah) / v1 dev results (history)

BM · Jadual ini dijana sebelum v2 wujud, jadi baris mypii ialah MyPII v1. Enam garis dasar ialah pengesahan (Holm k = 6); Mistral Small 3.1 dan GLM-5.3-Flash ialah eksplorasi (ADR-017), bukan dakwaan. EN · This table was generated before v2 existed, so the mypii row is MyPII v1. Six baselines are confirmatory (Holm k = 6); Mistral Small 3.1 and GLM-5.3-Flash are exploratory (ADR-017), not claims.

Split dev, 1000 dokumen / documents, padanan tepat / exact match, semua|*. Selang = bootstrap 95% (1000 ulangan / resamples, unit dokumen). Δ = F1 MyPII tolak F1 sistem / MyPII minus system (negatif = sistem lebih baik / negative = system is better). P/R: docs/BANDINGAN.md.

Petik / Cite

BM · Metadata petikan ada dalam CITATION.cff (GitHub memaparkannya sebagai "Cite this repository"). DOI Zenodo ditambah di sini selepas keluaran pertama. EN · Citation metadata lives in CITATION.cff (GitHub shows it as "Cite this repository"). The Zenodo DOI is added here after the first release.

Lesen / License

Kod / code: MIT (LICENSE). Set data / dataset (data/): CC-BY-4.0. © 2026 Aiman Malib (Sasa Teguh).