SALib/SALib: Sensitivity Analysis Library in Python. Contains Sobol, Morris, FAST, and other methods. · GitHub

Python implementations of commonly used sensitivity analysis methods. Useful in systems modeling to calculate the effects of model inputs or exogenous factors on outputs of interest.

Documentation: ReadTheDocs

Requirements: NumPy, SciPy, matplotlib, pandas, Python 3 (from SALib v1.2 onwards SALib does not officially support Python 2)

Installation: pip install SALib or pip install . or conda install SALib

Build Status: Test Coverage:

• Sobol Sensitivity Analysis (Sobol 2001, Saltelli 2002, Saltelli et al. 2010)
• Method of Morris, including groups and optimal trajectories (Morris 1991, Ruano et al. 2012)
• Radial OAT (Campolongo et al. 2007, Campolongo et al. 2011)
• extended Fourier Amplitude Sensitivity Test (eFAST) (Cukier et al. 1973, Saltelli et al. 1999, Pujol (2006) in Iooss et al., (2021))
• Random Balance Designs - Fourier Amplitude Sensitivity Test (RBD-FAST) (Tarantola et al. 2006, Plischke 2010, Tissot et al. 2012)
• Delta Moment-Independent Measure (Borgonovo 2007, Plischke et al. 2013)
• Derivative-based Global Sensitivity Measure (DGSM) (Sobol and Kucherenko 2009)
• Shapley Effects (Goda 2021)
• Fractional Factorial Sensitivity Analysis (Saltelli et al. 2008)
• High-Dimensional Model Representation (HDMR) (Rabitz et al. 1999, Li et al. 2010)
• PAWN (Pianosi and Wagener 2018, Pianosi and Wagener 2015)
• Regional Sensitivity Analysis (based on Hornberger and Spear, 1981, Saltelli et al. 2008, Pianosi et al., 2016)

Contributing: see here

from SALib.sample import saltelli
from SALib.analyze import sobol
from SALib.test_functions import Ishigami
import numpy as np

problem = {
  'num_vars': 3,
  'names': ['x1', 'x2', 'x3'],
  'bounds': [[-np.pi, np.pi]]*3
}

# Generate samples
param_values = saltelli.sample(problem, 1024)

# Run model (example)
Y = Ishigami.evaluate(param_values)

# Perform analysis
Si = sobol.analyze(problem, Y, print_to_console=True)
# Returns a dictionary with keys 'S1', 'S1_conf', 'ST', and 'ST_conf'
# (first and total-order indices with bootstrap confidence intervals)

It's also possible to specify the parameter bounds in a file with 3 columns:

# name lower_bound upper_bound
P1 0.0 1.0
P2 0.0 5.0
...etc.

Then the problem dictionary above can be created from the read_param_file function:

from SALib.util import read_param_file
problem = read_param_file('/path/to/file.txt')
# ... same as above

Lots of other options are included for parameter files, as well as a command-line interface. See the advanced section in the documentation.

Chaining calls is supported from SALib v1.4

from SALib import ProblemSpec
from SALib.test_functions import Ishigami

import numpy as np


# By convention, we assign to "sp" (for "SALib Problem")
sp = ProblemSpec({
  'names': ['x1', 'x2', 'x3'],   # Name of each parameter
  'bounds': [[-np.pi, np.pi]]*3,  # bounds of each parameter
  'outputs': ['Y']               # name of outputs in expected order
})

(sp.sample_saltelli(1024, calc_second_order=True)
   .evaluate(Ishigami.evaluate)
   .analyze_sobol(print_to_console=True))

print(sp)

# Samples, model results and analyses can be extracted:
print(sp.samples)
print(sp.results)
print(sp.analysis)

# Basic plotting functionality is also provided
sp.plot()

The above is equivalent to the procedural approach shown previously.

Also check out the FAQ and examples for a full description of options for each method.

If you would like to use our software, please cite it using the following:

Iwanaga, T., Usher, W., & Herman, J. (2022). Toward SALib 2.0: Advancing the accessibility and interpretability of global sensitivity analyses. Socio-Environmental Systems Modelling, 4, 18155. doi:10.18174/sesmo.18155

Herman, J. and Usher, W. (2017) SALib: An open-source Python library for sensitivity analysis. Journal of Open Source Software, 2(9). doi:10.21105/joss.00097

If you use BibTeX, cite using the following entries:

@article{Iwanaga2022,
  title = {Toward {SALib} 2.0: {Advancing} the accessibility and interpretability of global sensitivity analyses},
  volume = {4},
  url = {https://sesmo.org/article/view/18155},
  doi = {10.18174/sesmo.18155},
  journal = {Socio-Environmental Systems Modelling},
  author = {Iwanaga, Takuya and Usher, William and Herman, Jonathan},
  month = may,
  year = {2022},
  pages = {18155},
}

@article{Herman2017,
  doi = {10.21105/joss.00097},
  url = {https://doi.org/10.21105/joss.00097},
  year  = {2017},
  month = {jan},
  publisher = {The Open Journal},
  volume = {2},
  number = {9},
  author = {Jon Herman and Will Usher},
  title = {{SALib}: An open-source Python library for Sensitivity Analysis},
  journal = {The Journal of Open Source Software}
}

Many projects now use the Global Sensitivity Analysis features provided by SALib. Here is a selection:

• The City Energy Analyst
• pynoddy
• savvy
• rhodium
• pySur
• EMA workbench
• Brain/Circulation Model Developer
• DAE Tools
• agentpy
• uncertainpy
• CLIMADA

• Sensitivity Analysis in Python
• Sensitivity Analysis with SALib
• Running Sobol using SALib
• Extensions of SALib for more complex sensitivity analyses

• PyData Presentation on SALib

If you would like to be added to this list, please submit a pull request, or create an issue.

Many thanks for using SALib.

See here for how to contribute to SALib.

Copyright (C) 2012-2019 Jon Herman, Will Usher, and others. Versions v0.5 and later are released under the MIT license.