Skip to main content

(partial) pure Python HistFactory implementation

Project description

pyhf logo

pure-python fitting/limit-setting/interval estimation HistFactory-style

GitHub Project DOI Scikit-HEP NSF Award Number

GitHub Actions Status: CI GitHub Actions Status: Publish Docker Automated Code Coverage Language grade: Python CodeFactor Code style: black

Docs Binder

PyPI version Conda-forge version Supported Python versions Docker Stars Docker Pulls

The HistFactory p.d.f. template [CERN-OPEN-2012-016] is per-se independent of its implementation in ROOT and sometimes, it’s useful to be able to run statistical analysis outside of ROOT, RooFit, RooStats framework.

This repo is a pure-python implementation of that statistical model for multi-bin histogram-based analysis and its interval estimation is based on the asymptotic formulas of “Asymptotic formulae for likelihood-based tests of new physics” [arXiv:1007.1727]. The aim is also to support modern computational graph libraries such as PyTorch and TensorFlow in order to make use of features such as autodifferentiation and GPU acceleration.

Hello World

>>> import pyhf
>>> model = pyhf.simplemodels.hepdata_like(signal_data=[12.0, 11.0], bkg_data=[50.0, 52.0], bkg_uncerts=[3.0, 7.0])
>>> data = [51, 48] + model.config.auxdata
>>> test_mu = 1.0
>>> CLs_obs, CLs_exp = pyhf.infer.hypotest(test_mu, data, model, qtilde=True, return_expected=True)
>>> print(f"Observed: {CLs_obs}, Expected: {CLs_exp}")
Observed: 0.05251497423736956, Expected: 0.06445320535890459

What does it support

Implemented variations:
  • ☑ HistoSys

  • ☑ OverallSys

  • ☑ ShapeSys

  • ☑ NormFactor

  • ☑ Multiple Channels

  • ☑ Import from XML + ROOT via uproot

  • ☑ ShapeFactor

  • ☑ StatError

  • ☑ Lumi Uncertainty

Computational Backends:
  • ☑ NumPy

  • ☑ PyTorch

  • ☑ TensorFlow

  • ☑ JAX

Optimizers:
  • ☑ SciPy (scipy.optimize)

  • ☑ MINUIT (iminuit)

All backends can be used in combination with all optimizers. Custom user backends and optimizers can be used as well.

Todo

  • ☐ StatConfig

  • ☐ Non-asymptotic calculators

results obtained from this package are validated against output computed from HistFactory workspaces

A one bin example

import pyhf
import numpy as np
import matplotlib.pyplot as plt
import pyhf.contrib.viz.brazil

pyhf.set_backend("numpy")
model = pyhf.simplemodels.hepdata_like(
    signal_data=[10.0], bkg_data=[50.0], bkg_uncerts=[7.0]
)
data = [55.0] + model.config.auxdata

poi_vals = np.linspace(0, 5, 41)
results = [
    pyhf.infer.hypotest(test_poi, data, model, qtilde=True, return_expected_set=True)
    for test_poi in poi_vals
]

fig, ax = plt.subplots()
fig.set_size_inches(7, 5)
ax.set_xlabel(r"$\mu$ (POI)")
ax.set_ylabel(r"$\mathrm{CL}_{s}$")
pyhf.contrib.viz.brazil.plot_results(ax, poi_vals, results)

pyhf

manual

ROOT

manual

A two bin example

import pyhf
import numpy as np
import matplotlib.pyplot as plt
import pyhf.contrib.viz.brazil

pyhf.set_backend("numpy")
model = pyhf.simplemodels.hepdata_like(
    signal_data=[30.0, 45.0], bkg_data=[100.0, 150.0], bkg_uncerts=[15.0, 20.0]
)
data = [100.0, 145.0] + model.config.auxdata

poi_vals = np.linspace(0, 5, 41)
results = [
    pyhf.infer.hypotest(test_poi, data, model, qtilde=True, return_expected_set=True)
    for test_poi in poi_vals
]

fig, ax = plt.subplots()
fig.set_size_inches(7, 5)
ax.set_xlabel(r"$\mu$ (POI)")
ax.set_ylabel(r"$\mathrm{CL}_{s}$")
pyhf.contrib.viz.brazil.plot_results(ax, poi_vals, results)

pyhf

manual

ROOT

manual

Installation

To install pyhf from PyPI with the NumPy backend run

python -m pip install pyhf

and to install pyhf with all additional backends run

python -m pip install pyhf[backends]

or a subset of the options.

To uninstall run

python -m pip uninstall pyhf

Questions

If you have a question about the use of pyhf not covered in the documentation, please ask a question on Stack Overflow with the [pyhf] tag, which the pyhf dev team watches.

Stack Overflow pyhf tag

If you believe you have found a bug in pyhf, please report it in the GitHub Issues.

Citation

As noted in Use and Citations, the preferred BibTeX entry for citation of pyhf is

@software{pyhf,
  author = "{Heinrich, Lukas and Feickert, Matthew and Stark, Giordon}",
  title = "{pyhf: v0.5.2}",
  version = {0.5.2},
  doi = {10.5281/zenodo.1169739},
  url = {https://github.com/scikit-hep/pyhf},
}

Authors

pyhf is openly developed by Lukas Heinrich, Matthew Feickert, and Giordon Stark.

Please check the contribution statistics for a list of contributors.

Milestones

  • 2020-07-28: 1000 GitHub issues and pull requests. (See PR #1000)

Acknowledgements

Matthew Feickert has received support to work on pyhf provided by NSF cooperative agreement OAC-1836650 (IRIS-HEP) and grant OAC-1450377 (DIANA/HEP).

Project details


Download files

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

Source Distribution

pyhf-0.5.2.tar.gz (90.8 kB view hashes)

Uploaded Source

Built Distribution

pyhf-0.5.2-py2.py3-none-any.whl (118.0 kB view hashes)

Uploaded Python 2 Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page