simpful
A Python library for fuzzy logic reasoning, designed to provide a simple and lightweight API, as close as possible to natural language. Simpful supports Mamdani and Sugeno reasoning of any order, parsing any complex fuzzy rules involving AND, OR, and NOT operators, using arbitrarily shaped fuzzy sets.
Installation
pip install simpful
Citing Simpful
If you find Simpful useful for your research, please cite our work as follows:
Spolaor S., Fuchs C., Cazzaniga P., Kaymak U., Besozzi D., Nobile M.S.: Simpful: a user-friendly Python library for fuzzy logic, International Journal of Computational Intelligence Systems, 13(1):1687–1698, 2020 DOI:10.2991/ijcis.d.201012.002
Usage example 1: tipping with Sugeno
This example shows how to specify the information about the linguistic variables, fuzzy sets, fuzzy rules, and input values to Simpful. The last line of code prints the result of the fuzzy reasoning.
import simpful as sf
# A simple fuzzy model describing how the heating power of a gas burner depends on the oxygen supply.
FS = sf.FuzzySystem()
# Define a linguistic variable.
S_1 = sf.FuzzySet( points=[[0, 1.], [1., 1.], [1.5, 0]], term="low_flow" )
S_2 = sf.FuzzySet( points=[[0.5, 0], [1.5, 1.], [2.5, 1], [3., 0]], term="medium_flow" )
S_3 = sf.FuzzySet( points=[[2., 0], [2.5, 1.], [3., 1.]], term="high_flow" )
FS.add_linguistic_variable("OXI", sf.LinguisticVariable( [S_1, S_2, S_3] ))
# Define consequents.
FS.set_crisp_output_value("LOW_POWER", 0)
FS.set_crisp_output_value("MEDIUM_POWER", 25)
FS.set_output_function("HIGH_FUN", "OXI**2")
# Define fuzzy rules.
RULE1 = "IF (OXI IS low_flow) THEN (POWER IS LOW_POWER)"
RULE2 = "IF (OXI IS medium_flow) THEN (POWER IS MEDIUM_POWER)"
RULE3 = "IF (NOT (OXI IS low_flow)) THEN (POWER IS HIGH_FUN)"
FS.add_rules([RULE1, RULE2, RULE3])
# Set antecedents values, perform Sugeno inference and print output values.
FS.set_variable("OXI", .51)
print (FS.Sugeno_inference(['POWER']))
Usage example 2: tipping with Mamdani
This second example shows how to model a FIS using Mamdani inference. It also shows some facilities that make modeling more concise and clear: automatic Triangles (i.e., pre-baked linguistic variables with equally spaced triangular fuzzy sets) and the automatic detection of the inference method.
from simpful import *
FS = FuzzySystem()
TLV = AutoTriangle(3, terms=['poor', 'average', 'good'], universe_of_discourse=[0,10])
FS.add_linguistic_variable("service", TLV)
FS.add_linguistic_variable("quality", TLV)
O1 = TriangleFuzzySet(0,0,13, term="low")
O2 = TriangleFuzzySet(0,13,25, term="medium")
O3 = TriangleFuzzySet(13,25,25, term="high")
FS.add_linguistic_variable("tip", LinguisticVariable([O1, O2, O3], universe_of_discourse=[0,25]))
FS.add_rules([
"IF (quality IS poor) OR (service IS poor) THEN (tip IS low)",
"IF (service IS average) THEN (tip IS medium)",
"IF (quality IS good) OR (quality IS good) THEN (tip IS high)"
])
FS.set_variable("quality", 6.5)
FS.set_variable("service", 9.8)
tip = FS.inference()
Additional examples
Additional example scripts are available in our Code Ocean capsule.
Further info
Created by Marco S. Nobile at the Eindhoven University of Technology and Simone Spolaor at the University of Milano-Bicocca.
If you need further information, please write an e-mail at: m.s.nobile@tue.nl.
Release files for simpful 2.3.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| simpful-2.3.2.tar.gz | 14.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| simpful-2.3.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 42.3 kB
Release files / simpful-2.3.2.tar.gz
| Download URL | simpful-2.3.2.tar.gz |
|---|---|
| Size | 14.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6b448dca304770e6b3df5a2157b33ff95a590a4fe5e41e0989e197e38831a680
|
|
BLAKE2b-256 checksum How to use checksums |
cdded36d276afddc0482166be63c0c9c386853fe5f4d086250e27ec0ddd230bd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.2.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/50.3.2 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.7.4
|
Release files / simpful-2.3.2-py3-none-any.whl
| Download URL | simpful-2.3.2-py3-none-any.whl |
|---|---|
| Size | 27.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
30e632b3aab9180a765aa21038796d23cef3f4849065b37b8152c70d3069523a
|
|
BLAKE2b-256 checksum How to use checksums |
ab4b73df51aa7146c8a9079cff819b0d6d347823eeee23ceb1a28a168b545af9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.2.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/50.3.2 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.7.4
|
