def _fit_k_lin(nlds, k, kf_i=[]):
data = nlds.data
fn = nlds.fn
# linear fit (KF)
if (kf_i == []):
kf = KF(data, k) # without init params
else:
kf = kf_i # with init params
kf.em(ITER, ITERe) # em algorithm
nlds.setKFParams(kf)
# fit si
nlds = nlds.fit_si()
if (DBG): nlds.plot("%s_%d" % (fn, k))
(Sta, Obs) = nlds.gen(len(data))
err = tl.RMSE(Obs, data)
if (DBG): print("nlds:fit_k_lin (k:%d):rmse: %f" % (k, err))
return (nlds, err)
observations = 20 * (np.sin(x) + 0.005 * np.random.random(n))
data[:,0]=observations
return (data)
#----------------------------------#
# main
#----------------------------------#
if __name__ == "__main__":
from kf import KF
tl.comment("kf.py -- example ")
tl.msg("create synthetic sequence (1-dim)")
(data)=_example1()
fn='../output/tmp/kf_sample'
k=2 #4
tl.msg("k=%d: # of latent variables"%(k))
tl.msg("init params")
mykf=KF(data,k)
tl.msg("em algorithm -- START")
tic = tl.time.clock()
mykf.em(ITER=2, iter_each=10)
toc = tl.time.clock(); fittime= toc-tic;
tl.msg("em algorithm -- END (%f sec.)"%(fittime))
tl.msg("plot/save models")
mykf.plot(fn)
mykf.printParams(fn)