getPolyFit(x,y,n)

call:

[Coeffs, yhat, Residuals] = getPolyFit(x,y,n)

Compute polynomial fitting between vectors 'x' and 'y', and return the coefficients of the n-th order polynomial
used to fit the data, the fitting polynomial function (yhat), and the residuals. If the residuals exhibit "non-random" patterns, it
is an indication that the fit is not so good. To check them: bar(x,Residuals), xlabel('x'), ylabel('ŷ - y')
Note: the function ignores non-finite values(-Inf,Inf,NaN).

INPUT

x : independent variable (column vector)
y : dependent variable I want to estimate (column vector)
n : order of the polynomial I use to fit

OUTPUT

Coeffs : Coefficients of the best-fitting line
yhat : fitting polynomial function
Residuals : difference between observations predicted by the best fit and the real ones