Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/timzatko/sklearn-nature-inspired-algorithms
Nature-inspired algorithms for hyper-parameter tuning of Scikit-Learn models.
https://github.com/timzatko/sklearn-nature-inspired-algorithms
data-science hyper-parameter-optimization hyper-parameter-tuning nature-inspired-algorithms python scikit-learn
Last synced: 6 days ago
JSON representation
Nature-inspired algorithms for hyper-parameter tuning of Scikit-Learn models.
- Host: GitHub
- URL: https://github.com/timzatko/sklearn-nature-inspired-algorithms
- Owner: timzatko
- License: mit
- Created: 2020-05-11T10:28:58.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2023-10-03T20:38:06.000Z (almost 1 year ago)
- Last Synced: 2024-09-24T07:31:14.549Z (9 days ago)
- Topics: data-science, hyper-parameter-optimization, hyper-parameter-tuning, nature-inspired-algorithms, python, scikit-learn
- Language: Python
- Homepage: https://sklearn-nature-inspired-algorithms.readthedocs.io/en/stable/
- Size: 475 KB
- Stars: 28
- Watchers: 3
- Forks: 9
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
README
# Nature-Inspired Algorithms for scikit-learn
[](https://github.com/timzatko/Sklearn-Nature-Inspired-Algorithms/actions?query=workflow:CI+branch:master)
[](https://codeclimate.com/github/timzatko/Sklearn-Nature-Inspired-Algorithms/maintainability)
[](https://pypi.org/project/sklearn-nature-inspired-algorithms/)
[](https://pypi.org/project/sklearn-nature-inspired-algorithms/)
[](https://src.fedoraproject.org/rpms/python-sklearn-nature-inspired-algorithms)
Nature-inspired algorithms for hyper-parameter tuning of [scikit-learn](https://github.com/scikit-learn/scikit-learn) models. This package uses algorithms implementation from [NiaPy](https://github.com/NiaOrg/NiaPy).
## Installation
```shell script
$ pip install sklearn-nature-inspired-algorithms
```
To install this package on Fedora, run:
```sh
$ dnf install python3-sklearn-nature-inspired-algorithms
```
## Usage
The usage is similar to using sklearn's `GridSearchCV`. Refer to the [documentation](https://sklearn-nature-inspired-algorithms.readthedocs.io/en/stable/) for more detailed guides and more examples.
```python
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, 40, 2),
'min_samples_split': range(2, 20, 2),
'max_features': ["auto", "sqrt", "log2"],
}
clf = RandomForestClassifier(random_state=42)
nia_search = NatureInspiredSearchCV(
clf,
param_grid,
algorithm='hba', # hybrid bat algorithm
population_size=50,
max_n_gen=100,
max_stagnating_gen=10,
runs=3,
random_state=None, # or any number if you want same results on each run
)
nia_search.fit(X_train, y_train)
# the best params are stored in nia_search.best_params_
# finally you can train your model with best params from nia search
new_clf = RandomForestClassifier(**nia_search.best_params_, random_state=42)
```
Also you plot the search process with _line plot_ or _violin plot_.
```python
from sklearn_nature_inspired_algorithms.helpers import score_by_generation_lineplot, score_by_generation_violinplot
# line plot will plot all of the runs, you can specify the metric to be plotted ('min', 'max', 'median', 'mean')
score_by_generation_lineplot(nia_search, metric='max')
# in violin plot you need to specify the run to be plotted
score_by_generation_violinplot(nia_search, run=0)
```
Jupyter notebooks with full examples are available in [here](examples/notebooks).
### Using a Custom Nature-Inspired Algorithm
If you do not want to use any of the pre-defined algorithm configurations, you can use any algorithm from the [NiaPy](https://github.com/NiaOrg/NiaPy) collection.
This will allow you to have more control of the algorithm behavior.
Refer to their [documentation](https://niapy.readthedocs.io/en/latest/) and [examples](https://github.com/NiaOrg/NiaPy/tree/master/examples) for the usage.
__Note:__ Use version >2.x.x of NiaPy package
```python
from niapy.algorithms.basic import GeneticAlgorithm
algorithm = GeneticAlgorithm() # when custom algorithm is provided random_state is ignored
algorithm.set_parameters(NP=50, Ts=5, Mr=0.25)
nia_search = NatureInspiredSearchCV(
clf,
param_grid,
algorithm=algorithm,
population_size=50,
max_n_gen=100,
max_stagnating_gen=20,
runs=3,
)
nia_search.fit(X_train, y_train)
```
## Contributing
Detailed information on the contribution guidelines are in the [CONTRIBUTING.md](./CONTRIBUTING.md).