def analyze(self, adjust=False, plot=False, learn=False, adjustparams={}, learnparams={'feature_opt':'1storder', 'coeforder':1}):
dataman = DataIO(self.case)
fu, gridvars, ICparams = dataman.loadSolution(self.loadnamenpy, array_opt='marginal')
##Make fu smaller (in time)
if adjust:
fu, gridvars = self.adjust(fu, gridvars, adjustparams)
grid = PdfGrid(gridvars)
if plot:
V = Visualize(grid)
V.plot_fu3D(fu)
V.plot_fu(fu, dim='t', steps=5)
V.plot_fu(fu, dim='x', steps=5)
V.show()
if learn:
t0 = time.time()
print('fu dimension: ', fu.shape)
print('fu num elem.: ', np.prod(fu.shape))
feature_opt = learnparams['feature_opt']
coeforder = learnparams['coeforder']
sindy_alpha = learnparams['sindy_alpha']
RegCoef = learnparams['RegCoef']
nzthresh = learnparams['nzthresh']
# Learn
difflearn = PDElearn(grid=grid, fu=fu, ICparams=ICparams, scase=self.case, trainratio=0.8, debug=False, verbose=True)
difflearn.fit_sparse(feature_opt=feature_opt, variableCoef=True, variableCoefBasis='simple_polynomial', \
variableCoefOrder=coeforder, use_sindy=True, sindy_alpha=sindy_alpha, RegCoef=RegCoef, nzthresh=nzthresh)
print('learning took t = ', str(t0 - time.time()))
def burgers():
loadnamenpy = 'burgersMC_9601.npy' # PDF - triangles
loadnamenpy = 'burgersMC_6095.npy' # CDF - triangles
loadnamenpy = 'burgersMC_4147.npy' # PDF - gaussians
#loadnamenpy = 'burgersMC_5042.npy' # CDF - gaussians
case = loadnamenpy.split('_')[0]
dataman = DataIO(case)
fu, gridvars, ICparams = dataman.loadSolution(loadnamenpy)
grid = PdfGrid(gridvars)
# Learn
difflearn = PDElearn(grid=grid,
fu=fu,
ICparams=ICparams,
scase=case,
trainratio=0.7,
debug=False,
verbose=True)
difflearn.fit_sparse(feature_opt='1storder',
variableCoef=True,
variableCoefBasis='simple_polynomial',
variableCoefOrder=1,
use_sindy=True,
sindy_alpha=0.01,
shuffle=False)
def advection():
#loadnamenpy = 'advection_marginal_7397.npy'
loadnamenpy = 'advection_marginal_6328.npy'
loadnamenpy = 'advection_marginal_8028.npy'
loadnamenpy = 'advection_marginal_5765.npy'
#loadnamenpy = 'advection_marginal_4527.npy'
case = '_'.join(loadnamenpy.split('_')[:2])
dataman = DataIO(case)
fuk, fu, gridvars, ICparams = dataman.loadSolution(loadnamenpy)
grid = PdfGrid(gridvars)
V = Visualize(grid)
V.plot_fuk3D(fuk)
V.plot_fu3D(fu)
V.plot_fu(fu, dim='t', steps=5)
V.plot_fu(fu, dim='x', steps=5)
V.show()
# Learn
difflearn = PDElearn(fuk,
grid,
fu=fu,
ICparams=ICparams,
scase=case,
trainratio=0.8,
debug=False,
verbose=True)
difflearn.fit_sparse(feature_opt='2ndorder',
variableCoef=True,
variableCoefBasis='simple_polynomial',
variableCoefOrder=3,
use_sindy=True,
sindy_alpha=0.001)
def advection_reaction():
loadnamenpy = 'advection_reaction_9987.npy' # PDF - gaussians
#loadnamenpy = 'advection_reaction_5739.npy' # PDF - gaussians
case = '_'.join(loadnamenpy.split('_')[:2])
dataman = DataIO(case)
fu, gridvars, ICparams = dataman.loadSolution(loadnamenpy)
# Make fu smaller (in time)
tt = np.linspace(
gridvars['t'][0], gridvars['t'][1],
round((gridvars['t'][1] - gridvars['t'][0]) / gridvars['t'][2]))
period = 6
indexes = np.array([i * period for i in range((len(tt)) // period)])
ttnew = tt[indexes]
fu = fu[:, :, indexes]
gridvars['t'][1] = ttnew[-1]
gridvars['t'][2] = (ttnew[-1] - ttnew[0]) / len(ttnew)
grid = PdfGrid(gridvars)
# Learn
difflearn = PDElearn(grid=grid,
fu=fu,
ICparams=ICparams,
scase=case,
trainratio=0.8,
debug=False,
verbose=True)
difflearn.fit_sparse(feature_opt='1storder',
variableCoef=True,
variableCoefBasis='simple_polynomial',
variableCoefOrder=2,
use_sindy=True,
sindy_alpha=0.005,
shuffle=False)
def reaction():
#loadnamenpy = 'reaction_linear_2204.npy'
#loadnamenpy = 'reaction_linear_6632.npy'
loadnamenpy = 'reaction_linear_5966.npy'
case = '_'.join(loadnamenpy.split('_')[:2])
dataman = DataIO(case)
fu, gridvars, ICparams = dataman.loadSolution(loadnamenpy)
grid = PdfGrid(gridvars)
# Learn
difflearn = PDElearn(grid=grid,
fu=fu,
ICparams=ICparams,
scase=case,
trainratio=0.8,
debug=False,
verbose=True)
difflearn.fit_sparse(feature_opt='1storder',
variableCoef=True,
variableCoefBasis='simple_polynomial',
variableCoefOrder=2,
use_sindy=True,
sindy_alpha=0.1)
def learn(self):
dataman = DataIO(self.case)
fu, gridvars, ICparams = dataman.loadSolution(self.loadnamenpy,
array_opt='marginal')
grid = PdfGrid(gridvars)
feature_opt = '1storder'
coeforder = 2
# Learn
difflearn = PDElearn(grid=grid,
fu=fu,
ICparams=ICparams,
scase=self.case,
trainratio=0.8,
debug=False,
verbose=True)
difflearn.fit_sparse(feature_opt=feature_opt, variableCoef=True, variableCoefBasis='simple_polynomial', \
variableCoefOrder=coeforder, use_sindy=True, sindy_alpha=0.001)
# BUILD PDF
MCprocess = MCprocessing(savenameMC, case=case)
savenamepdf = MCprocess.buildKDE(nu, distribution=distribution, MCcount=MCcount, save=save, u_margin=u_margin, bandwidth=bandwidth)
# LEARN
dataman = DataIO(case, directory=PDFDIR)
fu, gridvars, ICparams = dataman.loadSolution(savenamepdf, array_opt='marginal')
adjustgrid = {'mu':mu, 'mx':mx, 'mt':mt, 'pu':pu, 'px':px, 'pt':pt}
grid = PdfGrid(gridvars)
fu = grid.adjust(fu, adjustgrid)
difflearn = PDElearn(grid=grid, fu=fu, ICparams=ICparams, scase=case, trainratio=trainratio, verbose=printlearning)
filename = difflearn.fit_sparse(feature_opt=feature_opt, variableCoef=variableCoef, variableCoefBasis=variableCoefBasis, \
variableCoefOrder=coeforder, use_rfe=use_rfe, rfe_alpha=rfe_alpha, nzthresh=nzthresh, maxiter=maxiter, \
LassoType=LassoType, RegCoef=RegCoef, cv=cv, criterion=criterion, print_rfeiter=print_rfeiter, shuffle=shuffle, \
basefile=savenamepdf, adjustgrid=adjustgrid, save=save, normalize=normalize, comments=comments)
# Save Learning
D = DataIO(case, directory=LEARNDIR)
output, metadata = D.readLearningResults(filename)
output_vec.append(output)
metadata_vec.append(metadata)
filename_vec.append(filename)
print('files = [')
for f in filename_vec:
print("\'"+f+"\',")
print(']')
RegCoef = 0.000004
maxiter = 10000
if "savenamepdf" not in locals():
# Check if there is already a loadfile (if not load it)
savenamepdf = 'advection_reaction_analytical_717_944.npy'
dataman = DataIO(case)
fu, gridvars, ICparams = dataman.loadSolution(savenamepdf,
array_opt='marginal')
grid = PdfGrid(gridvars)
fu = grid.adjust(fu, aparams)
if plot:
s = 10
V = Visualize(grid)
V.plot_fu3D(fu)
V.plot_fu(fu, dim='t', steps=s)
V.plot_fu(fu, dim='x', steps=s)
V.show()
difflearn = PDElearn(grid=grid,
fu=fu,
ICparams=ICparams,
scase=case,
trainratio=0.8,
debug=False,
verbose=True)
difflearn.fit_sparse(feature_opt=feature_opt, variableCoef=True, variableCoefBasis='simple_polynomial', \
variableCoefOrder=coeforder, use_sindy=True, sindy_alpha=sindy_alpha, RegCoef=RegCoef, nzthresh=nzthresh, maxiter=maxiter)
partial_data=True,
MCcount=MCcount,
save=False,
plot=False,
distribution=distribution)
grid = PdfGrid(gridvars)
difflearn = PDElearn(grid=grid,
fu=fu,
ICparams=ICparams,
scase=case,
trainratio=0.8,
debug=False,
verbose=True)
coef, featurenames, trainRMSE, testRMSE, trainScore, testScore = difflearn.fit_sparse(feature_opt='1storder', \
variableCoef=True, variableCoefBasis='simple_polynomial', variableCoefOrder=1, \
use_sindy=True, sindy_alpha=0.001, shuffle=False)
coefvec.append(coef)
featurenamesvec.append(featurenames)
trainRMSEvec.append(trainRMSE)
testRMSEvec.append(testRMSE)
trainScorevec.append(trainScore)
testScorevec.append(testScore)
savedata = {
'coefvec': coefvec,
'featurenamesvec': featurenamesvec,
'trainRMSEvec': trainRMSEvec,
'testRMSEvec': testRMSEvec,
'trainScorevec': trainScorevec,