How to use the bonsai.core.bonsaic.Bonsai function in bonsai

"""
This class implements the regression tree in CART that uses
the minimum variance criterion.
"""

# Authors: Yubin Park 
# License: Apache License 2.0

from bonsai.core.bonsaic import Bonsai
import numpy as np
import logging

class RegTree(Bonsai):
    def __init__(self, 
                max_depth=5, 
                min_samples_split=2,
                min_samples_leaf=1,
                min_varsum_decrease=0.0, 
                subsample=1.0,
                random_state=1234,
                n_jobs=-1,
                **kwarg):

        self.max_depth=max_depth
        self.min_samples_split = min_samples_split
        self.min_samples_leaf = min_samples_leaf
        self.min_varsum_decrease = min_varsum_decrease

        def find_split(avc):

"""
This class implements a modified version of Alpha Tree that appeared in
- the origial: https://ieeexplore.ieee.org/document/6399474/
- closer to the implementation: https://arxiv.org/abs/1606.05325
"""

# Authors: Yubin Park 
# License: Apache License 2.0

from bonsai.core.bonsaic import Bonsai
import numpy as np


class AlphaTree(Bonsai):

    def __init__(self,
                alpha=1.0, 
                max_depth=5, 
                min_samples_split=2,
                min_samples_leaf=1, 
                **kwarg):

        self.alpha = alpha
        self.max_depth=max_depth
        self.min_samples_split = min_samples_split
        self.min_samples_leaf = min_samples_leaf

        def find_split(avc):

            PRECISION = 1e-12

"""
This class implements a tree with the Friedman's splitting criterion
that appeared in: 
- https://statweb.stanford.edu/~jhf/ftp/trebst.pdf
FYI, this is the default splitting criterion for Scikit-Learn GBM.
"""

# Authors: Yubin Park 
# License: Apache License 2.0

from bonsai.core.bonsaic import Bonsai
import numpy as np
import logging

class FriedmanTree(Bonsai):
    def __init__(self, 
                max_depth=5, 
                min_samples_split=2,
                min_samples_leaf=1,
                subsample=1.0,
                random_state=1234,
                n_jobs=-1,
                **kwarg):

        self.max_depth=max_depth
        self.min_samples_split = min_samples_split
        self.min_samples_leaf = min_samples_leaf
 
        def find_split(avc):

            if avc.shape[0] == 0:

"""
This class implements the XGBoost base tree that appeared in:
- https://arxiv.org/abs/1603.02754 
"""

# Authors: Yubin Park 
# License: Apache License 2.0

from bonsai.core.bonsaic import Bonsai
import numpy as np

class XGBTree(Bonsai):
    def __init__(self, 
                max_depth=5, 
                min_samples_split=2,
                min_samples_leaf=1,
                subsample=1.0,
                subsample_splts=1.0,
                reg_lambda=1e-2,            # regularization
                obj_tolerance=1e-2,
                random_state=1234,
                distribution="gaussian",
                n_jobs=-1,
                **kwarg):
        
        self.max_depth=max_depth
        self.min_samples_split = min_samples_split
        self.min_samples_leaf = min_samples_leaf