MEDS Random Task Sampler

Python 3.11+ License: MIT

Model-independent generation of query-based task rows from MEDS datasets.

The package provides two separate workflows:

  • random_sample: random (code, duration) specifications paired with random patient contexts; and
  • dense_grid: explicit code x duration grids at sampled patient prediction times.

These names describe how rows are sampled, not how a downstream model must use them. For example, either output could be used for training, validation, benchmarking, probing, or analysis.

Both workflows follow payalchandak/EveryQuery@9bd85a1. The package owns the shared task schema, code-source resolution, future-occurrence labeling, death and censoring semantics, deterministic seeds, and atomic output writes. It does not depend on Hydra or a model framework.

Random task samples

from meds_random_task_sampler import RandomTaskSamplerConfig, sample_random_tasks

config = RandomTaskSamplerConfig(
    num_queries=1024,
    num_contexts_per_query=1,
    min_prediction_times_per_subject=50,
    query_codes="/path/to/MEDS",  # resolves metadata/codes.parquet
    min_duration=1,
    max_duration=731,
    duration_distribution="log-uniform",
)

result = sample_random_tasks(
    data_dir="/path/to/MEDS",
    output_dir="/path/to/random_tasks",
    split="train",
    config=config,
)

Output is partitioned under random_tasks/{split}/*.parquet; restartable intermediate artifacts use the sibling random_tasks_artifacts/{split}/ directory. Machine-readable summary statistics are written to random_tasks_artifacts/{split}/_summary.json.

Dense task grids

from meds_random_task_sampler import (
    TaskGridGeneratorConfig,
    generate_task_grid,
)

config = TaskGridGeneratorConfig(
    prediction_times_per_subject=1,
    min_context_per_subject=50,
    query_codes=["CODE_A", "CODE_B"],
    durations=[30, 90, 180, 365, 731],
    write_unique_prediction_times=True,
    censored_rows="keep",  # or "drop" for current EveryQuery evaluation behavior
)

result = generate_task_grid(
    data_dir="/path/to/MEDS",
    output_dir="/path/to/task_grid",
    split="held_out",
    input_shard="0",
    config=config,
)

Grid rows are written to task_grid/{split}/{shard}.parquet. Optional unique prediction times use the sibling task_grid_unique/ root and per-shard summaries use task_grid_summary/. Nullable/censored labels are retained by default; use censored_rows="drop" to reproduce current EveryQuery evaluation output.

See DESIGN.md for the behavioral contract and planned EveryQuery adapter boundary.

Development

uv sync --group dev
uv run pytest -v
uv run pre-commit run --all-files

This repository retains the McDermottHealthAI/MHAL-template project structure.

Project links

Data verified by PyPI on Jul 23, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.2.0)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for florian6973 from gravatar.com florian6973

Credits

Author: florian6973

GitHub Statistics

Data verified by PyPI on Jul 23, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

MIT License

Requires

Python >=3.11

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

meds_random_task_sampler-0.1.0.tar.gz (132.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

meds_random_task_sampler-0.1.0-py3-none-any.whl (39.9 kB view details)

Uploaded Python 3

File details

Details for the file meds_random_task_sampler-0.1.0.tar.gz.

File metadata

  • Download URL: meds_random_task_sampler-0.1.0.tar.gz
  • Upload date:
  • Size: 132.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for meds_random_task_sampler-0.1.0.tar.gz
Algorithm Hash digest
SHA256 598e269d8a201879c11db185fb4ec3cb9f922b4f4faa02dd4e7ce139533c7865
MD5 ea33bb0dc4e50dc85cdde103663ebd5c
BLAKE2b-256 b18df05de0843d180a575c6c6a6015ae5043bbc0e270da0e71d6530d638a5148

See more details on using hashes here.

Provenance

The following attestation bundles were made for meds_random_task_sampler-0.1.0.tar.gz:

Publisher: python-build.yaml on florian6973/meds-random-task-sampler

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file meds_random_task_sampler-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for meds_random_task_sampler-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d1d64d519ca30a5bd383f2dbefe7551289b496470256801a8f430179b992e699
MD5 156672207e37183506cca41d32b40cce
BLAKE2b-256 5ada1b28bd1b375d46354733fe8a70272807e05b46391ce7da898dcb9f989676

See more details on using hashes here.

Provenance

The following attestation bundles were made for meds_random_task_sampler-0.1.0-py3-none-any.whl:

Publisher: python-build.yaml on florian6973/meds-random-task-sampler

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.2.0

2 files

This release

0.1.0 This release

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page