sklearn-nature-inspired-algorithms 0.2.0

Search using nature inspired algorithms over specified parameter values for an sklearn estimator.

Nature Inspired Algorithms for scikit-learn

Nature inspired algorithms for hyper-parameter tuning of scikit-learn models. This package uses algorithms implementation from NiaPy.

Installation

pip install sklearn-nature-inspired-algorithms

Usage

The usage is similar to using sklearn's GridSearchCV.

from sklearn_nature_inspired_algorithms.model_selection import NatureInspiredSearchCV
from sklearn.ensemble import RandomForestClassifier

param_grid = { 
    'n_estimators': range(20, 100, 20), 
    'max_depth': range(2, 20, 2),
    'min_samples_split': range(2, 20, 2), 
}

clf = RandomForestClassifier(random_state=42)

nia_search = NatureInspiredSearchCV(
    clf,
    param_grid,
    algorithm='ba', # bat algorithm
    population_size='15',
    max_n_gen=30,
    max_stagnating_gen=2,
)

nia_search.fit(X_train, y_train)

Jupyter notebooks with full examples are available in here.

Using custom nature inspired algorithm

If you do not want to use ony of the pre-defined algorithm configurations, you can use any algorithm from the NiaPy collection. This will allow you to have more control of the algorithm behaviour. Refer to their documentation and examples for the usage.

from NiaPy.algorithms.basic import GeneticAlgorithm

algorithm = GeneticAlgorithm()
algorithm.setParameters(NP=50, Ts=5, Mr=0.25)

nia_search = NatureInspiredSearchCV(
    clf,
    param_grid,
    algorithm=algorithm,
    population_size='15',
    max_n_gen=30,
    max_stagnating_gen=2,
)

nia_search.fit(X_train, y_train)

Contributing

Detailed information on the contribution guidelines are in the CONTRIBUTING.md.