How to use the mlxtend._base._IterativeModel function in mlxtend

def __init__(self, eta=0.01, epochs=50,
                 minibatches=None, random_seed=None,
                 print_progress=0):

        _BaseModel.__init__(self)
        _IterativeModel.__init__(self)
        _Classifier.__init__(self)

        self.eta = eta
        self.minibatches = minibatches
        self.epochs = epochs
        self.random_seed = random_seed
        self.print_progress = print_progress
        self._is_fitted = False

# mlxtend Machine Learning Library Extensions
#
# Estimator for Linear Regression
# Author: Sebastian Raschka 
#
# License: BSD 3 clause


import numpy as np
from .._base import _Cluster
from .._base import _BaseModel
from .._base import _IterativeModel
# from scipy.spatial.distance import euclidean


class Kmeans(_BaseModel, _Cluster, _IterativeModel):
    """ K-means clustering class.

    Added in 0.4.1dev

    Parameters
    ------------
    k : int
        Number of clusters
    max_iter : int (default: 10)
        Number of iterations during cluster assignment.
        Cluster re-assignment stops automatically when the algorithm
        converged.
    convergence_tolerance : float (default: 1e-05)
        Compares current centroids with centroids of the previous iteration
        using the given tolerance (a small positive float)to determine
        if the algorithm converged early.

# mlxtend Machine Learning Library Extensions
#
# Estimator for Linear Regression
# Author: Sebastian Raschka 
#
# License: BSD 3 clause

import tensorflow as tf
import numpy as np
from time import time
from .._base import _Cluster
from .._base import _BaseModel
from .._base import _IterativeModel


class TfKmeans(_BaseModel, _Cluster, _IterativeModel):
    """ TensorFlow K-means clustering class.

    Added in 0.4.1dev

    Parameters
    ------------
    k : int
        Number of clusters
    max_iter : int (default: 10)
        Number of iterations during cluster assignment.
        Cluster re-assignment stops automatically when the algorithm
        converged.
    convergence_tolerance : float (default: 1e-05)
        Compares current centroids with centroids of the previous iteration
        using the given tolerance (a small positive float)to determine
        if the algorithm converged early.

# mlxtend Machine Learning Library Extensions
#
# Estimator for Linear Regression
# Author: Sebastian Raschka 
#
# License: BSD 3 clause

import numpy as np
import tensorflow as tf
from time import time
from .._base import _BaseModel
from .._base import _IterativeModel
from .._base import _Regressor


class TfLinearRegression(_BaseModel, _IterativeModel, _Regressor):
    """Estimator for Linear Regression in TensorFlow using Gradient Descent.

    Added in version 0.4.1

    """

    def __init__(self, eta=0.1, epochs=50, print_progress=0,
                 random_seed=None, dtype=None):
        """
        Parameters
        ------------
        eta : float (default: 0.01)
            solver rate (between 0.0 and 1.0)
        epochs : int (default: 50)
            Passes over the training dataset.
        print_progress : int (default: 0)

# Implementation of a Multi-layer Perceptron in Tensorflow
# Author: Sebastian Raschka 
#
# License: BSD 3 clause

import numpy as np
from time import time
from scipy.special import expit
from .._base import _BaseModel
from .._base import _IterativeModel
from .._base import _MultiClass
from .._base import _MultiLayer
from .._base import _Classifier


class MultiLayerPerceptron(_BaseModel, _IterativeModel,
                           _MultiClass, _MultiLayer, _Classifier):

    """Multi-layer perceptron classifier with logistic sigmoid activations

    Parameters
    ------------
    eta : float (default: 0.5)
        Learning rate (between 0.0 and 1.0)
    epochs : int (default: 50)
        Passes over the training dataset.
        Prior to each epoch, the dataset is shuffled
        if `minibatches > 1` to prevent cycles in stochastic gradient descent.
    hidden_layers : list (default: [50])
        Number of units per hidden layer. By default 50 units in the
        first hidden layer. At the moment only 1 hidden layer is supported
    n_classes : int (default: None)