How can I use python packages to fit a polynomial model that connects between data set x: xa1 xb1 xc1 xa2 xb2 xc2 ... . . to a data set y: ya1 yb1 yc1 ya2 yb2 yc2 ... . . . I am trying to fit a second degree polynomial with a,b,c features: y=f(a,a^2,b,b^2,c,c^2,ab,ac,bc) by using coefficients=np.linalg.lstsq(A,y)[0]. However I am not sure how to build the matrix A. I understand it should be composed of len(x) rows, 10 columns, and should yield 10 coefficients. is there a known method to build this matrix? Continue reading...
