Write a function linearModelFit to fit a linear model. The function should take as its first argument the design matrix $x$ as a $2d-$array,

as its second argument a $1$d$-$array $y$ of outcomes, and as its third argument a function loss $fcn$ which returns as a tuple the value of the

loss, as well as the gradient of the loss. As a result, it should return the estimated betas and the R$2.$

Test the function with these values:

$x=np.$array$(\left[\begin{array}{cccc}1& 0& -1& 2\end{array}\right]$

$1$

$1$

$1)$

$y=np.$array$([0,0\mathrm{.}4,2])$

It must return:

Betas: $\left[\begin{array}{cc}0\mathrm{.}6& 0\mathrm{.}6\end{array}\right]$

R$2$: $0\mathrm{.}75$