Are you planning to support sklearn's API?

[jckkvs]

I think that it will be very convenient if pipeline can be used as follows

from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestRegressor

pipe = Pipeline(steps=[("selector", ParticleSwarmOptimization()), 
                　　　　　　　　　　　　　　("Regressor", RandomForestRegressor())])
pipe.fit(X,y)

[jaswinder9051998]

Seems like a good initiative to take, will check for be compatibility and start working on it

[jckkvs]

Thank you. 　
As you know, to support sklearn.pipeline , we need fit and transform functions.

Also, in order to support sklearn's GridSearchCV and cross_val_predict, I think that the get_params and set_params, get_support functions are also necessary.

As you know,

from sklearn.model_selectiom import cross_val_predict, GridSearchCV
y_pred_cv = cross_val_predict(pipe, X, y)

gcv = GridSearchCV(pipe, param_grid={"population_size" : [20,30,50,]})
gcv.fit(X,y)

# It is just an example,
# whether population_size optimization is necessary is not discussed here.

[jckkvs]

@jaswinder9051998

Apologies for the delay, I have created the code for DragonFlyOptimization. The fundamental algorithm for Dragonfly optimization remains unchanged.

I have modified some argument and variable names to make it compatible with the sklearn API.

If this implementation is acceptable, I will proceed to implement other algorithms from zoofs as well.

https://github.com/jaswinder9051998/zoofs/pull/29/files#diff-f325c536869fad925454821e8290757de9931d07e37c0713fdf1dff283202317