curve fitting - In Java, does an implementation exist for interpolating non-uniformly distributed time series data? -


i have matlab code requires time series data uniformly distributed in time produce answer. driver matlab code reads data file runs interp1( x, y, xi, 'cubic') on data after reads file because data not uniformly distributed in time.

now have port process java add production process. matlab version isn't anemiable large numbers of data files , can't used in production.

my actual question can find java library implements interp1 'cubic' method use when data read process?

according matlab docs, 'cubic' same piecewise cubic hermite interpolating polynomial (pchip) interpolation. 'spline' produces unacceptable results. have looked @ apache commons-math , jama.

drej.

http://www.gregdennis.com/drej/

nonlinear least squares via regression on data sets. can specify lamda value ( goodness of fit) , cheaper fit data.

it interpolate , extrapolate, don't extrapolate far;

if want specific extrapolated far-field behavior add point out there somewhere!

it uses kernel regression can different kinds of fits pretty easily. kardi teknomo has page on kernel regression.

it works.


Comments

Popular posts from this blog

c++ - Convert big endian to little endian when reading from a binary file -

C#: Application without a window or taskbar item (background app) that can still use Console.WriteLine() -

unicode - Are email addresses allowed to contain non-alphanumeric characters? -