This release is a pre-release and may not be stable for production use.
Model
This repository contains the implementation of the MetaRisk Model Infrastructure.
Related Document: Revisiting_MetaRisk_V2.pdf
Quality-aware observations
OrganAgeMetaRisk configures each observation channel as a (value_column, quality_column) pair. For an available
channel, the observation standard deviation is phi_group / sqrt(Q), where Q is the raw, dimensionless quality score
in [MIN_OBSERVATION_QUALITY, 1]. Q=1 is the reference-quality anchor for phi_group.
Quality columns are required in every dataframe passed to fit(), predict(), or log_likelihood(). Quality is not
included in observation preconditioning and does not add a likelihood correction. If preprocessing cannot provide a
valid score for an observation, it must mark that observation missing before passing the dataframe to the model.
Models are persisted as format-v3 payloads. Older v1/v2 payloads are rejected by metarisk.models.load() and must be
converted explicitly with metarisk.utils.migrate_model_payload(..., quality_column_mapping=...) before they can be
saved and loaded as v3; quality-column names are never inferred.
Metadata
Release files for metarisk 1.7.0rc1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| metarisk-1.7.0rc1.tar.gz | 117.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| metarisk-1.7.0rc1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 175.4 kB
Release files / metarisk-1.7.0rc1.tar.gz
| Download URL | metarisk-1.7.0rc1.tar.gz |
|---|---|
| Size | 117.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
07bcf7b0c6a75953d30c1267260762ef68656846140bcda28c6f8027c0d54389
|
|
BLAKE2b-256 checksum How to use checksums |
aafb4a6f037a9922cb9ced53d3abd9de54af0348376020e4038ea98d22ab2c06
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.4
|
Release files / metarisk-1.7.0rc1-py3-none-any.whl
| Download URL | metarisk-1.7.0rc1-py3-none-any.whl |
|---|---|
| Size | 57.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
04baf473be855831ddc1344d4ddd944af324d21985e33122dfc11089c2667ad9
|
|
BLAKE2b-256 checksum How to use checksums |
107fe13d111dd67728237eb4969177bd2c6d00465c18be83a6e2f656bc426c29
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.4
|