Method __init__

mla/linear_models.py:15–44

Basic class for implementing continuous regression estimators which are trained with gradient descent optimization on their particular loss function. Parameters ---------- lr : float, default 0.001 Learning rate. penalty : str, {'l1', 'l2'

(
        self, lr=0.001, penalty="None", C=0.01, tolerance=0.0001, max_iters=1000
    )

class BasicRegression(BaseEstimator):
    def __init__(
        self, lr=0.001, penalty="None", C=0.01, tolerance=0.0001, max_iters=1000
    ):
        """Basic class for implementing continuous regression estimators which
        are trained with gradient descent optimization on their particular loss
        function.

        Parameters
        ----------
        lr : float, default 0.001
            Learning rate.
        penalty : str, {'l1', 'l2', None'}, default None
            Regularization function name.
        C : float, default 0.01
            The regularization coefficient.
        tolerance : float, default 0.0001
            If the gradient descent updates are smaller than `tolerance`, then
            stop optimization process.
        max_iters : int, default 10000
            The maximum number of iterations.
        """
        self.C = C
        self.penalty = penalty
        self.tolerance = tolerance
        self.lr = lr
        self.max_iters = max_iters
        self.errors = []
        self.theta = []
        self.n_samples, self.n_features = None, None
        self.cost_func = None

    def _loss(self, w):
        raise NotImplementedError()