simuci

🇪🇸 Español: Léeme en español

ICU discrete-event simulation engine — distribution sampling, patient clustering, and statistical validation.

Installation

pip install simuci

For development:

git clone https://github.com/coslatte/simuci.git
cd simuci
pip install -e ".[dev]"

Quick Start

from simuci import Experiment, single_run, multiple_replication

# Create an experiment with patient parameters
exp = Experiment(
    age=55,
    diagnosis_admission1=11,
    diagnosis_admission2=0,
    diagnosis_admission3=0,
    diagnosis_admission4=0,
    apache=20,
    respiratory_insufficiency=5,
    artificial_ventilation=1,
    uti_stay=100,
    vam_time=50,
    preuti_stay_time=10,
    percent=3,
)

# Single replication (requires centroids CSV)
result = single_run(exp, centroids_path="path/to/centroids.csv")
print(result)
# {'Tiempo Pre VAM': 5, 'Tiempo VAM': 89, 'Tiempo Post VAM': 168, 'Estadia UCI': 262, 'Estadia Post UCI': 45}

# Multiple replications → DataFrame
df = multiple_replication(exp, n_reps=200, centroids_path="path/to/centroids.csv")
print(df.describe())

Using Your Own Centroid Data

You must pass the path to your centroid CSV explicitly:

from simuci import single_run, Experiment

exp = Experiment(age=55, ..., validate=False)

# Point to your centroids CSV
result = single_run(exp, centroids_path="path/to/real_centroids.csv")

The centroids CSV must have:

  • An index column (cluster IDs: 0, 1, 2)
  • At least 11 numeric columns (features used for nearest-centroid classification)

You can also use the loader directly:

from simuci.io.loaders import CentroidLoader

loader = CentroidLoader()
centroids = loader.load("path/to/centroids.csv")  # returns numpy array

Statistical Validation

import numpy as np
from simuci import SimulationMetrics, Wilcoxon, Friedman

# Compare simulation output to real data
metrics = SimulationMetrics(
    true_data=np.array(...),       # (n_patients, n_variables)
    simulation_data=np.array(...), # (n_patients, n_replicates, n_variables)
)
metrics.evaluate(confidence_level=0.95, result_as_dict=True)

print(metrics.coverage_percentage)
print(metrics.error_margin)
print(metrics.kolmogorov_smirnov_result)
print(metrics.anderson_darling_result)

Input Validation

All Experiment inputs are validated on construction by default:

from simuci import Experiment

# This raises ValueError: age must be between 14 and 100
Experiment(age=200, ...)

Skip validation with validate=False if you've already validated externally.

API Reference

Symbol Description
Experiment Patient parameters + result container
single_run(exp) One simulation replication
multiple_replication(exp, n_reps) N replications → DataFrame
clustering(edad, ...) Nearest-centroid patient classifier
Wilcoxon Paired Wilcoxon signed-rank test
Friedman Friedman chi-square test
SimulationMetrics Full evaluation suite (coverage, RMSE, KS, AD)
StatsUtils Static CI helper
CentroidLoader CSV loader with schema validation
validate_experiment_inputs() Parameter range checking

Architecture

Project map (core vs. validation, I/O, statistics, tooling): docs/architecture.md

License

MIT

Project links

Data verified by PyPI on Feb 13, 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:
Latest release

1 maintainer

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

Credits

Author: SimUCI Team

GitHub Statistics

Data verified by PyPI on Feb 13, 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 (MIT License)

Requires

Python >=3.12

Provides Extra

dev security

Tags

discrete-event healthcare icu simpy simulation

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

simuci-1.0.1.tar.gz (90.5 kB view details)

Uploaded Source

Built Distribution

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

simuci-1.0.1-py3-none-any.whl (27.8 kB view details)

Uploaded Python 3

File details

Details for the file simuci-1.0.1.tar.gz.

File metadata

  • Download URL: simuci-1.0.1.tar.gz
  • Upload date:
  • Size: 90.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for simuci-1.0.1.tar.gz
Algorithm Hash digest
SHA256 379011ab44bcfc690182c0bcf4ce01a1cfe3e4c17e1bbdf553e631d0892fea3b
MD5 7624f5bd6cf1696f509b665fcdc6fd6e
BLAKE2b-256 e60c1297711530b1f4dd3967861f1a4fac712044b506fc2b7a6b56f8e9dc5f90

See more details on using hashes here.

Provenance

The following attestation bundles were made for simuci-1.0.1.tar.gz:

Publisher: python-publish.yml on coslatte/simuci

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

File details

Details for the file simuci-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: simuci-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 27.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for simuci-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 9b590329e0213a74a7b13ca10ae9ec34c92062593ad94a354b0c6f80735ae3de
MD5 9ad8c98e172156bda665c6734443649f
BLAKE2b-256 535e19c2d295188bdcbac8897b3fb9a6c45dbff6664abd30afc98b6ae1889565

See more details on using hashes here.

Provenance

The following attestation bundles were made for simuci-1.0.1-py3-none-any.whl:

Publisher: python-publish.yml on coslatte/simuci

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

Release history Release notifications | RSS feed

This release

1.0.1 This release

2 files

1.0.0

2 files

0.1.5

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