$"""$

Linear Regression model

$"""$

import numpy as np

class Linear$($object$)$:

def $\_\_$init$\_\_($self$,$ n$\_$class: int, lr: float, epochs: int, weight$\_$decay: float$)$:

$"""$Initialize a new classifier.

Parameters:

n$\_$class: the number of classes

lr: the learning rate

epochs: the number of epochs to train for

$"""$

self.w $=$ None # Initialize in train

self.lr $=$ lr

self.epochs $=$ epochs

self.n$\_$class $=$ n$\_$class

self.weight$\_$decay $=$ weight$\_$decay

def train$($self$,$ X$\_$train: np$.$ndarray, y$\_$train: np$.$ndarray, weights: np$.$ndarray$)->$ np$.$ndarray:

$"""$Train the classifier.

Use the linear regression update rule as introduced in the Lecture.

Parameters:

X$\_$train: a number array of shape $($N$,$ D$)$ containing training data;

N examples with D dimensions

y$\_$train: a numpy array of shape $($N$,)$ containing training labels

$"""$

N$,$ D $=$ X$\_$train.shape

self.w $=$ weights

# TODO: implement me

return self.w

def predict$($self$,$ X$\_$test: np$.$ndarray$)->$ np$.$ndarray:

$"""$Use the trained weights to predict labels for test data points.

Parameters:

X$\_$test: a numpy array of shape $($N$,$ D$)$ containing testing data;

N examples with D dimensions

Returns:

predicted labels for the data in X$\_$test; a $1-$dimensional array of

length N$,$ where each element is an integer giving the predicted

class.

$"""$

# TODO: implement me

pass