def test_2DNormalDist_variance(self):
# prepare data
U = dists.J(
[dists.Normal(2.0, .5, -1, 4),
dists.Normal(1.0, .5, -1, 3)])
# U = dists.J([dists.Normal(0.5, .5, -1, 2),
# dists.Normal(0.5, .4, -1, 2)])
# define linear transformation
trans = JointTransformation()
for a, b in U.getBounds():
trans.add(LinearTransformation(a, b))
# get a sparse grid approximation
grid = Grid.createPolyGrid(U.getDim(), 10)
grid.getGenerator().regular(5)
gs = grid.getStorage()
# now refine adaptively 5 times
p = DataVector(gs.getDimension())
nodalValues = np.ndarray(gs.getSize())
# set function values in alpha
for i in range(gs.getSize()):
gs.getPoint(i).getStandardCoordinates(p)
nodalValues[i] = U.pdf(trans.unitToProbabilistic(p.array()))
# hierarchize
alpha = hierarchize(grid, nodalValues)
# # make positive
# alpha_vec = DataVector(alpha)
# createOperationMakePositive().makePositive(grid, alpha_vec)
# alpha = alpha_vec.array()
dist = SGDEdist(grid, alpha, bounds=U.getBounds())
fig = plt.figure()
plotDensity2d(U)
fig.show()
fig = plt.figure()
plotSG2d(dist.grid,
dist.alpha,
addContour=True,
show_negative=True,
show_grid_points=True)
fig.show()
print("2d: mean = %g ~ %g" % (U.mean(), dist.mean()))
print("2d: var = %g ~ %g" % (U.var(), dist.var()))
plt.show()
def testExp2d(self):
trainSamples = np.loadtxt("exp_2d.csv").T
# build parameter set
dist = SGDEdist.byLearnerSGDEConfig(
trainSamples,
config={
"grid_level": 7,
"grid_type": "linear",
"grid_maxDegree": 1,
"refinement_numSteps": 0,
"refinement_numPoints": 10,
"solver_threshold": 1e-10,
"solver_verbose": False,
"regularization_type": "Laplace",
"crossValidation_lambda": 0.000562341,
"crossValidation_enable": False,
"crossValidation_kfold": 5,
"crossValidation_silent": False,
"sgde_makePositive": True,
"sgde_makePositive_candidateSearchAlgorithm": "joined",
"sgde_makePositive_interpolationAlgorithm":
"interpolateBoundaries1d",
"sgde_unitIntegrand": True
})
fig, ax, _ = plotDensity3d(dist)
ax.scatter(trainSamples[:, 0], trainSamples[:, 1],
np.zeros(trainSamples.shape[0]))
ax.set_title("vol=%.12f" % dist.vol)
fig.show()
plt.show()
def withSGDEConfig(self, config, *args, **kws):
"""
Estimates the density from training data
@param config: configuration file for density estimation
@return: self
"""
self._dist = SGDEdist(config, *args, **kws)
return self
def test_1DNormalDist_variance(self):
# prepare data
U = dists.Normal(1, 2, -8, 8)
# U = dists.Normal(0.5, .2, 0, 1)
# define linear transformation
trans = JointTransformation()
a, b = U.getBounds()
trans.add(LinearTransformation(a, b))
# get a sparse grid approximation
grid = Grid.createPolyGrid(U.getDim(), 10)
grid.getGenerator().regular(5)
gs = grid.getStorage()
# now refine adaptively 5 times
p = DataVector(gs.getDimension())
nodalValues = np.ndarray(gs.getSize())
# set function values in alpha
for i in range(gs.getSize()):
gs.getPoint(i).getStandardCoordinates(p)
nodalValues[i] = U.pdf(trans.unitToProbabilistic(p.array()))
# hierarchize
alpha = hierarchize(grid, nodalValues)
dist = SGDEdist(grid, alpha, bounds=U.getBounds())
fig = plt.figure()
plotDensity1d(U,
alpha_value=0.1,
mean_label="$\mathbb{E}",
interval_label="$\alpha=0.1$")
fig.show()
fig = plt.figure()
plotDensity1d(dist,
alpha_value=0.1,
mean_label="$\mathbb{E}",
interval_label="$\alpha=0.1$")
fig.show()
print("1d: mean = %g ~ %g" % (U.mean(), dist.mean()))
print("1d: var = %g ~ %g" % (U.var(), dist.var()))
plt.show()
def test1DNormalDist(self):
# prepare data
U = dists.TNormal(0.5, .2, -1, 2)
np.random.seed(1234567)
trainSamples = np.array([U.rvs(1000)]).T
testSamples = np.array([U.rvs(1000)]).T
# build parameter set
dist = SGDEdist.byLearnerSGDEConfig(
trainSamples,
config={
"grid_level": 6,
"grid_type": "modlinear",
"grid_maxDegree": 3,
"refinement_numSteps": 0,
"refinement_numPoints": 10,
"solver_threshold": 1e-10,
"solver_verbose": True,
"regularization_type": "Laplace",
"crossValidation_enable": True,
"crossValidation_kfold": 5,
"crossValidation_silent": False,
"sgde_makePositive": False,
"sgde_makePositive_candidateSearchAlgorithm": "fullGrid",
"sgde_makePositive_interpolationAlgorithm": "setToZero",
"sgde_makePositive_verbose": True,
"sgde_unitIntegrand": False
},
bounds=np.array([U.getBounds()]))
fig = plt.figure()
plotDensity1d(U, label="analytic")
plotDensity1d(dist, label="sgde")
plt.legend()
# plt.title("mean = %g ~ %g (err=%g), var = %g ~ %g (err=%g)" % (np.mean(trainSamples),
# dist.mean(),
# np.abs(np.mean(trainSamples) - dist.mean()) / np.mean(trainSamples),
# np.var(trainSamples),
# dist.var(),
# np.abs(np.var(trainSamples) - dist.var()) / np.var(trainSamples)
# ))
print("1d: mean = %g ~ %g (err=%g)" %
(np.mean(trainSamples), dist.mean(),
(np.abs(np.mean(trainSamples) - dist.mean()) /
np.mean(trainSamples))))
print("1d: var = %g ~ %g (err=%g)" %
(np.var(trainSamples), dist.var(),
(np.abs(np.var(trainSamples) - dist.var()) /
np.var(trainSamples))))
print("KL = %g" % U.klDivergence(dist, testSamples, testSamples))
print("CE = %g" % dist.crossEntropy(testSamples))
print("MSE = %g" % dist.l2error(U, testSamples, testSamples))
plt.show()
def test2DNormalDist(self):
# prepare data
U = dists.J(
[dists.Normal(2.0, .5, -1, 4),
dists.Normal(1.0, .5, -1, 3)])
U = dists.J(
[dists.Normal(0.5, .5, -1, 2),
dists.Normal(0.5, .4, -1, 2)])
np.random.seed(1234567)
trainSamples = U.rvs(300)
testSamples = U.rvs(1000)
# build parameter set
dist = SGDEdist.byLearnerSGDEConfig(
trainSamples,
config={
"grid_level": 5,
"grid_type": "modlinear",
"refinement_numSteps": 0,
"refinement_numPoints": 10,
"regularization_type": "Laplace",
"crossValidation_lambda": 0.000562341,
"crossValidation_enable": False,
"crossValidation_kfold": 5,
"crossValidation_silent": False,
"sgde_makePositive": False,
"sgde_makePositive_candidateSearchAlgorithm": "joined",
"sgde_makePositive_interpolationAlgorithm": "setToZero",
"sgde_makePositive_generateConsistentGrid": False,
"sgde_makePositive_verbose": True,
"sgde_unitIntegrand": True
},
bounds=U.getBounds())
fig = plt.figure()
plotDensity2d(U)
fig.show()
fig = plt.figure()
plotSG2d(dist.grid,
dist.alpha,
addContour=True,
show_negative=True,
show_grid_points=True)
fig.show()
print("2d: mean = %g ~ %g" % (U.mean(), dist.mean()))
print("2d: var = %g ~ %g" % (U.var(), dist.var()))
plt.show()
print("KL = %g" % U.klDivergence(dist, testSamples, testSamples))
print("CE = %g" % dist.crossEntropy(testSamples))
print("MSE = %g" % dist.l2error(U, testSamples, testSamples))
def test2DPPF(self):
# prepare data
C = np.array([[0.1, 0.08], [0.08, 0.1]]) / 10.
U = dists.MultivariateNormal([0.5, 0.5], C, 0, 1)
train_samples = U.rvs(1000)
fig = plt.figure()
plotDensity2d(U)
plt.title('true density')
fig.show()
dist = SGDEdist.byLearnerSGDEConfig(train_samples,
config={
"grid_level": 5,
"grid_type": "linear",
"refinement_numSteps": 0,
"refinement_numPoints": 10,
"regularization_type":
"Laplace",
"crossValidation_lambda":
0.000562341,
"crossValidation_enable":
False,
"crossValidation_kfold": 5,
"crossValidation_silent": True
},
bounds=U.getBounds())
fig = plt.figure()
plotDensity2d(dist)
plt.title('estimated SGDE density')
fig.show()
samples = dists.J([dists.Uniform(0, 1), dists.Uniform(0, 1)]).rvs(1000)
fig = plt.figure()
plt.plot(samples[:, 0], samples[:, 1], "o ")
plt.title('uniformly drawn samples')
plt.xlim(0, 1)
plt.ylim(0, 1)
fig.show()
transformed_samples = dist.ppf(samples)
fig = plt.figure()
plt.plot(transformed_samples[:, 0], transformed_samples[:, 1], "o ")
plt.title('transformed samples')
plt.xlim(0, 1)
plt.ylim(0, 1)
fig.show()
plt.show()
def __extractDiscretePDFforMomentEstimation(self, U, T):
dists = U.getDistributions()
vol = 1.
err = 0.
# check if importance sampling has been used for some parameters
for i, trans in enumerate(T.getTransformations()):
# if this is the case replace them by a uniform distribution
if isinstance(trans, InverseCDFTransformation):
grid, alpha, erri = Uniform(0, 1).discretize(level=2)
else:
vol *= trans.vol()
grid, alpha, erri = dists[i].discretize(level=10)
dists[i] = SGDEdist.fromSGFunction(grid, alpha)
err += erri
return vol, J(dists), err
def test1DCDFandPPF(self):
# prepare data
U = Normal(0.5, 0.1, 0, 1)
train_samples = U.rvs(1000).reshape(1000, 1)
dist = SGDEdist.byLearnerSGDEConfig(train_samples,
config={
"grid_level": 5,
"grid_type": "poly",
"refinement_numSteps": 0,
"refinement_numPoints": 10,
"regularization_type":
"Laplace",
"crossValidation_lambda":
0.000562341,
"crossValidation_enable":
False,
"crossValidation_kfold": 5,
"crossValidation_silent": True
},
bounds=U.getBounds())
fig = plt.figure()
plt.hist(train_samples, bins=10, normed=True)
plotDensity1d(U)
plotDensity1d(dist)
plt.title("original space")
fig.show()
transformed_samples = dist.cdf(train_samples)
fig = plt.figure()
plt.hist(transformed_samples, bins=10, normed=True)
plt.title("uniform space")
fig.show()
transformed_samples = dist.ppf(transformed_samples)
fig = plt.figure()
plt.hist(transformed_samples, bins=10, normed=True)
plotDensity1d(U)
plotDensity1d(dist)
plt.title("original space")
fig.show()
plt.show()
def testExpPoly2d(self):
trainSamples = np.loadtxt("exp_2d.csv").T
# build parameter set
dist_sgde = SGDEdist.byLearnerSGDEConfig(
trainSamples,
config={
"grid_level": 4,
"grid_type": "modpoly",
"grid_maxDegree": 6,
"refinement_numSteps": 0,
"refinement_numPoints": 10,
"solver_threshold": 1e-10,
"solver_verbose": True,
"regularization_type": "Laplace",
"crossValidation_lambda": 0.000562341,
"crossValidation_enable": False,
"crossValidation_kfold": 5,
"crossValidation_silent": True,
"sgde_makePositive": False,
"sgde_makePositive_candidateSearchAlgorithm": "joined",
"sgde_makePositive_interpolationAlgorithm": "setToZero",
"sgde_makePositive_verbose": True,
"sgde_unitIntegrand": True
})
# build parameter set
dist_kde = dists.KDEDist(
trainSamples,
kernelType=KernelType_GAUSSIAN,
bandwidthOptimizationType=BandwidthOptimizationType_SILVERMANSRULE)
# fig = plt.figure()
# plotSG2d(dist.grid, dist.alpha, show_grid_points=True)
# plt.scatter(trainSamples[:, 0], trainSamples[:, 1], np.zeros(trainSamples.shape[0]))
# plt.title("%.12f" % dist.vol)
fig, _, _ = plotDensity3d(dist_sgde)
plt.title("SGDE: vol=%g" % dist_sgde.vol)
fig, _, _ = plotDensity3d(dist_kde)
plt.title("KDE: vol=1.0")
plt.show()
def test2DCovarianceMatrix(self):
# prepare data
np.random.seed(1234567)
C = np.array([[0.3, 0.09], [0.09, 0.3]]) / 10.
U = dists.MultivariateNormal([0.5, 0.5], C, 0, 1)
samples = U.rvs(2000)
kde = KDEDist(samples)
sgde = SGDEdist.byLearnerSGDEConfig(
samples,
bounds=U.getBounds(),
config={
"grid_level": 5,
"grid_type": "linear",
"grid_maxDegree": 1,
"refinement_numSteps": 0,
"refinement_numPoints": 10,
"solver_threshold": 1e-10,
"solver_verbose": False,
"regularization_type": "Laplace",
"crossValidation_lambda": 3.16228e-06,
"crossValidation_enable": False,
"crossValidation_kfold": 5,
"crossValidation_silent": False,
"sgde_makePositive": True,
"sgde_makePositive_candidateSearchAlgorithm": "joined",
"sgde_makePositive_interpolationAlgorithm": "setToZero",
"sgde_generateConsistentGrid": True,
"sgde_unitIntegrand": True
})
sgde_x1 = sgde.marginalizeToDimX(0)
sgde_x2 = sgde.marginalizeToDimX(1)
plt.figure()
plotDensity1d(sgde_x1, label="x1")
plotDensity1d(sgde_x2, label="x2")
plt.title(
"mean: x1=%g, x2=%g; var: x1=%g, x2=%g" %
(sgde_x1.mean(), sgde_x2.mean(), sgde_x1.var(), sgde_x2.var()))
plt.legend()
jsonStr = sgde.toJson()
jsonObject = json.loads(jsonStr)
sgde = Dist.fromJson(jsonObject)
fig = plt.figure()
plotDensity2d(U, addContour=True)
plt.title("analytic")
fig = plt.figure()
plotDensity2d(kde, addContour=True)
plt.title("kde")
fig = plt.figure()
plotDensity2d(sgde, addContour=True)
plt.title("sgde (I(f) = %g)" % (doQuadrature(sgde.grid, sgde.alpha), ))
# print the results
print("E(x) ~ %g ~ %g" % (kde.mean(), sgde.mean()))
print("V(x) ~ %g ~ %g" % (kde.var(), sgde.var()))
print("-" * 60)
print(kde.cov())
print(sgde.cov())
self.assertTrue(np.linalg.norm(C - kde.cov()) < 1e-2, "KDE cov wrong")
self.assertTrue(
np.linalg.norm(np.corrcoef(samples.T) - kde.corrcoeff()) < 1e-1,
"KDE corrcoef wrong")
plt.show()
def test2DCDFandPPF(self, plot=True):
# prepare data
C = np.array([[0.1, 0.08], [0.08, 0.1]]) / 10.
U = dists.MultivariateNormal([0.5, 0.5], C, 0, 1)
train_samples = U.rvs(1000)
if plot:
fig = plt.figure()
plotDensity2d(U)
plt.title('true density')
fig.show()
dist = SGDEdist.byLearnerSGDEConfig(train_samples,
config={
"grid_level": 5,
"grid_type":
"polyClenshawCurtis",
"refinement_numSteps": 0,
"refinement_numPoints": 10,
"regularization_type":
"Laplace",
"crossValidation_lambda":
0.000562341,
"crossValidation_enable":
False,
"crossValidation_kfold": 5,
"crossValidation_silent": True,
"sgde_makePositive": False
},
bounds=U.getBounds())
if plot:
fig = plt.figure()
plotDensity2d(dist)
plt.title('estimated SGDE density')
fig.show()
samples = dists.J([dists.Uniform(0, 1), dists.Uniform(0, 1)]).rvs(500)
if plot:
fig = plt.figure()
plt.plot(samples[:, 0], samples[:, 1], "o ")
plt.title('u space')
plt.xlim(0, 1)
plt.ylim(0, 1)
fig.show()
else:
print("-" * 80)
print(samples)
transformed_samples = dist.ppf(samples, shuffle=False)
if plot:
fig = plt.figure()
plt.plot(transformed_samples[:, 0], transformed_samples[:, 1],
"o ")
plt.title('x space (transformed)')
plt.xlim(0, 1)
plt.ylim(0, 1)
fig.show()
else:
print("-" * 80)
print(transformed_samples)
samples = dist.cdf(transformed_samples, shuffle=False)
if plot:
fig = plt.figure()
plt.plot(samples[:, 0], samples[:, 1], "o ")
plt.title('u space (transformed)')
plt.xlim(0, 1)
plt.ylim(0, 1)
fig.show()
plt.show()
else:
print("-" * 80)
print(samples)
def estimateDensitySGDE(trainSamplesUnit,
testSamplesUnit=None,
testSamplesProb=None,
pathResults="/tmp",
dist=None,
optimization='l2',
iteration=0,
levels=[1, 2, 3, 4, 5],
refNr=0, refPoints=0,
nSamples=1000):
"""
Estimates a sparse grid density for different levels and refinements by
optimizing over a given quantity.
@param trainSamplesUnit:
@param testSamplesUnit:
@param testSamplesProb:
@param pathResults:
@param dist:
@param optimization:
@param iteration:
@param levels:
@param refNr:
@param refPoints:
"""
config = """
[general]
method = dmest
[files]
inFileTrain = %s
usingTrain = %s
inFileTest = %s
outFileTest = %s
usingTest = %s
[dmest]
gridFile = %s
lambda = -1 # 0.01
regType=Laplace
refNr = %i
refPoints = %i
writeGridFile = %s
writeAlphaFile = %s
samp_rejectionTrialMax = 5000
samp_numSamples = %i
samp_outFile = %s
printSurfaceFile = %s
"""
# write the samples to file
if len(trainSamplesUnit.shape) == 1:
n, dim = trainSamplesUnit.shape[0], 1
usingTrainTag = "%i" % dim
else:
n, dim = trainSamplesUnit.shape
usingTrainTag = "1:%i" % dim
trainSamplesUnitFile = os.path.join(pathResults,
"samples_%i_%i_train.csv" % (iteration, n))
np.savetxt(trainSamplesUnitFile, trainSamplesUnit)
testSamplesUnitFile = ""
usingTestTag = ""
if testSamplesUnit is not None:
testSamplesUnitFile = os.path.join(pathResults,
"samples_%i_%i_test.csv" % (iteration, n))
if dim == 1:
usingTestTag = "%i" % dim
else:
usingTestTag = "1:%i" % dim
np.savetxt(testSamplesUnitFile, testSamplesUnit)
# collector arrays
accGridSizes = np.array([])
accLevels = np.array([])
accL2error = np.array([])
accCrossEntropy = np.array([])
accKLDivergence = np.array([])
# best estimation
ans = None
bestMeasure = 1e20
bestSetting = None
for level in levels:
# define output files
gridFile = os.path.join(pathResults,
"samples_%i_%i_l%i.grid" % (iteration, n, level))
alphaFile = os.path.join(pathResults,
"samples_%i_%i_l%i.alpha.arff" % (iteration, n, level))
sampleFile = os.path.join(pathResults,
"samples_%i_%i_l%i.csv" % (iteration, n, level))
likelihoodFile = ""
if testSamplesUnit is not None:
likelihoodFile = os.path.join(pathResults,
"samples_%i_%i_l%i_likelihood.csv" % (iteration, n, level))
surfaceFile = ""
if dim == 2:
surfaceFile = os.path.join(pathResults,
"samples_%i_%i_l%i.xyz" % (iteration, n, level))
gnuplotJpegFile = os.path.join(pathResults,
"samples_%i_%i_l%i_gnuplot.jpg" % (iteration, n, level))
sgdeJpegFile = os.path.join(pathResults,
"samples_%i_%i_l%i_sgde.jpg" % (iteration, n, level))
sgdePositiveJpegFile = os.path.join(pathResults,
"samples_%i_%i_l%i_sgdePositive.jpg" % (iteration, n, level))
configFile = os.path.join(pathResults,
"sgde_%i_%i_l%i.cfg" % (iteration, n, level))
gnuplotConfig = os.path.join(pathResults,
"sgde_%i_%i_l%i.gnuplot" % (iteration, n, level))
# generate the grid
grid = Grid.createLinearBoundaryGrid(dim)
grid.createGridGenerator().regular(level)
if grid.getSize() <= n:
print " l=%i" % level,
fd = open(gridFile, "w")
fd.write(grid.serialize())
fd.close()
# write config to file
fd = open(configFile, "w")
fd.write(config % (trainSamplesUnitFile,
usingTrainTag,
testSamplesUnitFile,
likelihoodFile,
usingTestTag,
gridFile,
refNr,
refPoints,
gridFile,
alphaFile,
nSamples,
sampleFile,
surfaceFile))
fd.close()
sgdeDist = SGDEdist.byConfig(configFile)
grid, alpha = sgdeDist.grid, sgdeDist.alpha
# -----------------------------------------------------------
# do some plotting
if dim == 2:
# gnuplot
sgdeDist.gnuplot(gnuplotJpegFile, gnuplotConfig=gnuplotConfig)
# -----------------------------------------------------------
# matplotlib
l2error = np.NAN
kldivergence = np.NAN
crossEntropy = sgdeDist.crossEntropy(testSamplesUnit)
if dist is not None:
l2error = dist.l2error(sgdeDist, testSamplesUnit, testSamplesProb)
kldivergence = dist.klDivergence(sgdeDist, testSamplesUnit, testSamplesProb)
fig = plt.figure()
plotSG2d(grid, alpha)
plt.title("N=%i: vol=%g, kl=%g, log=%g, l2error=%g" % (grid.getSize(),
doQuadrature(grid, alpha),
kldivergence,
crossEntropy,
l2error))
fig.savefig(sgdeJpegFile)
plt.close(fig)
# -----------------------------------------------------------
# copy grid and coefficients
gridFileNew = os.path.join(pathResults,
"samples_%i_%i_sgde.grid" % (iteration, n))
alphaFileNew = os.path.join(pathResults,
"samples_%i_%i_sgde.alpha.arff" % (iteration, n))
sampleFileNew = os.path.join(pathResults,
"samples_%i_%i_sgde.csv" % (iteration, n))
copy2(gridFile, gridFileNew)
copy2(alphaFile, alphaFileNew)
copy2(sampleFile, sampleFileNew)
# -----------------------------------------------------------
# # make it positive and do all over again
# opPositive = OperationMakePositive(sgdeDist.grid)
# alg = EstimateDensityAlgorithm(configFile)
# opPositive.setInterpolationAlgorithm(alg)
# grid, alpha = opPositive.makePositive(sgdeDist.alpha)
# scale to unit integrand
alpha.mult(1. / createOperationQuadrature(grid).doQuadrature(alpha))
sgdeDist.grid = grid
sgdeDist.alpha = alpha
gridFileNew = os.path.join(pathResults,
"samples_%i_%i_l%i_positive.grid" % (iteration, n, level))
alphaFileNew = os.path.join(pathResults,
"samples_%i_%i_l%i_positive.alpha.arff" % (iteration, n, level))
fd = open(gridFileNew, "w")
fd.write(Grid.serialize(grid))
fd.close()
writeAlphaARFF(alphaFileNew, alpha)
# -----------------------------------------------------------
# collect statistics
accGridSizes = np.append(accGridSizes, grid.getSize())
accLevels = np.append(accLevels, level)
l2error = np.NAN
kldivergence = np.NAN
crossEntropy = sgdeDist.crossEntropy(testSamplesUnit)
if dist is not None:
l2error = dist.l2error(sgdeDist, testSamplesUnit, testSamplesProb)
kldivergence = dist.klDivergence(sgdeDist, testSamplesUnit, testSamplesProb)
accL2error = np.append(accL2error, l2error)
accCrossEntropy = np.append(accCrossEntropy, crossEntropy)
accKLDivergence = np.append(accKLDivergence, kldivergence)
if dim == 2:
# -----------------------------------------------------------
# do some plotting
fig = plt.figure()
plotSG2d(grid, alpha)
plt.title("N=%i: vol=%g, kl=%g, log=%g, l2error=%g" % (grid.getSize(),
doQuadrature(grid, alpha),
kldivergence,
crossEntropy,
l2error))
fig.savefig(sgdePositiveJpegFile)
plt.close(fig)
# -----------------------------------------------------------
# select the best density available based on the given criterion
if optimization == 'crossEntropy':
measure = crossEntropy
elif optimization == 'kldivergence':
measure = kldivergence
elif optimization == 'l2':
measure = l2error
else:
raise AttributeError('optimization "%s" is not known for density estimation' % optimization)
isBest = measure < bestMeasure
if isBest:
bestMeasure = measure
if ans is None or isBest:
ans = sgdeDist
bestSetting = {'level': level,
'gridSize': grid.getSize(),
'l2error': l2error,
'KLDivergence': kldivergence,
'crossEntropy': crossEntropy}
# -----------------------------------------------------------
# copy grid and coefficients
gridFileNew = os.path.join(pathResults,
"samples_%i_%i.grid" % (iteration, n))
alphaFileNew = os.path.join(pathResults,
"samples_%i_%i.alpha.arff" % (iteration, n))
sampleFileNew = os.path.join(pathResults,
"samples_%i_%i.csv" % (iteration, n))
copy2(gridFile, gridFileNew)
copy2(alphaFile, alphaFileNew)
copy2(sampleFile, sampleFileNew)
gridFileNew = os.path.join(pathResults,
"samples_%i_%i_positive.grid" % (iteration, n))
alphaFileNew = os.path.join(pathResults,
"samples_%i_%i_positive.alpha.arff" % (iteration, n))
fd = open(gridFileNew, "w")
fd.write(Grid.serialize(ans.grid))
fd.close()
writeAlphaARFF(alphaFileNew, ans.alpha)
# -----------------------------------------------------------
print ": %s = %g <= %g" % (optimization, measure, bestMeasure)
print
# -----------------------------------------------------------
# write results to file
statsfilename = os.path.join(pathResults,
"sg_sgde_%i_%i_all.stats.arff" % (iteration, n))
writeDataARFF({'filename': statsfilename,
'data': DataMatrix(np.vstack(([n] * len(accGridSizes),
accGridSizes,
accLevels,
accL2error,
accKLDivergence,
accCrossEntropy)).transpose()),
'names': ['sampleSize',
'gridSize',
'level',
'l2error',
'KLDivergence',
'crossEntropy']})
# -----------------------------------------------------------
statsfilename = os.path.join(pathResults,
"sg_sgde_%i_%i.stats.arff" % (iteration, n))
writeDataARFF({'filename': statsfilename,
'data': DataMatrix(np.vstack(([n],
bestSetting['gridSize'],
bestSetting['level'],
bestSetting['l2error'],
bestSetting['KLDivergence'],
bestSetting['crossEntropy'])).transpose()),
'names': ['sampleSize',
'gridSize',
'level',
'l2error',
'KLDivergence',
'crossEntropy']})
# -----------------------------------------------------------
return ans
def test_sgdeLaplace():
l2_samples = 10000
# sample_range = np.arange(10, 500, 50)
sample_range = [10, 20, 50, 100, 200, 500]
points = {}
grids = ["linear",
"modlinear", # keine OperationQuadrature
"poly",
"modpoly",
"polyBoundary",
"polyClenshawCurtis",
"modPolyClenshawCurtis",
"polyClenshawCurtisBoundary",
"bsplineClenshawCurtis",
"modBsplineClenshawCurtis" # keine OperationMultipleEval
]
U = dists.J([dists.Lognormal.by_alpha(0.5, 0.1, 0.001),
dists.Lognormal.by_alpha(0.5, 0.1, 0.001)])
l2_errors = {}
for grid in grids:
l2_errors[grid] = []
points[grid] = []
l2_errors["kde"] = []
samples = 1000
for samples in sample_range:
# for lvl in range(5, 6):
trainSamples = U.rvs(samples)
# testSamples = U.rvs(l2_samples)
for grid_name in grids:
# build parameter set
print("--------------------Samples: {} Grid: {}--------------------".format(samples, grid_name))
dist_sgde = SGDEdist.byLearnerSGDEConfig(trainSamples,
bounds=U.getBounds(),
unitIntegrand=True,
config={"grid_level": 1,
"grid_type": grid_name,
"grid_maxDegree": 6,
"refinement_numSteps": 0,
"refinement_numPoints": 10,
"solver_threshold": 1e-10,
"solver_verbose": False,
"regularization_type": "Laplace",
"crossValidation_lambda": 1e-6,
"crossValidation_enable": True,
"crossValidation_kfold": 4,
"crossValidation_lambdaSteps": 10,
"crossValidation_silent": False})
points[grid_name].append(dist_sgde.grid.getSize())
# l2_errors[grid_name].append(dist_sgde.l2error(U, testSamplesUnit=testSamples))
l2_errors[grid_name].append(dist_sgde.l2error(U, n=l2_samples))
# plt.figure()
# plotDensity2d(U, levels=(10, 20, 40, 50, 60))
# plt.figure()
# plotDensity2d(dist_sgde, levels=(10, 20, 40, 50, 60))
# plt.show()
dist_kde = dists.KDEDist(trainSamples,
kernelType=KernelType_GAUSSIAN,
bandwidthOptimizationType=BandwidthOptimizationType_SILVERMANSRULE)
l2_errors["kde"].append(dist_kde.l2error(U, testSamplesUnit=testSamples))
for grid_name in grids:
plt.plot(sample_range, l2_errors[grid_name], label=grid_name)
# plt.plot(points[grid], l2_errors[grid_name],".-", label=grid_name)
plt.plot(sample_range, l2_errors["kde"], label="KDE")
# plt.plot([x for x in range(1,300, 100)], [l2_errors["kde"][0] for i in range(1,4)], label="KDE")
plt.xlabel("# Gitterpunkte")
plt.ylabel("L2-Fehler")
plt.yscale("log")
plt.legend()
plt.show()
def estimateDensitySGDE(trainSamplesUnit,
testSamplesUnit=None,
testSamplesProb=None,
pathResults="/tmp",
dist=None,
optimization='l2',
iteration=0,
levels=[1, 2, 3, 4, 5],
refNr=0,
refPoints=0,
nSamples=1000):
"""
Estimates a sparse grid density for different levels and refinements by
optimizing over a given quantity.
@param trainSamplesUnit:
@param testSamplesUnit:
@param testSamplesProb:
@param pathResults:
@param dist:
@param optimization:
@param iteration:
@param levels:
@param refNr:
@param refPoints:
"""
config = """
[general]
method = dmest
[files]
inFileTrain = %s
usingTrain = %s
inFileTest = %s
outFileTest = %s
usingTest = %s
[dmest]
gridFile = %s
lambda = -1 # 0.01
regType=Laplace
refNr = %i
refPoints = %i
writeGridFile = %s
writeAlphaFile = %s
samp_rejectionTrialMax = 5000
samp_numSamples = %i
samp_outFile = %s
printSurfaceFile = %s
"""
# write the samples to file
if len(trainSamplesUnit.shape) == 1:
n, dim = trainSamplesUnit.shape[0], 1
usingTrainTag = "%i" % dim
else:
n, dim = trainSamplesUnit.shape
usingTrainTag = "1:%i" % dim
trainSamplesUnitFile = os.path.join(
pathResults, "samples_%i_%i_train.csv" % (iteration, n))
np.savetxt(trainSamplesUnitFile, trainSamplesUnit)
testSamplesUnitFile = ""
usingTestTag = ""
if testSamplesUnit is not None:
testSamplesUnitFile = os.path.join(
pathResults, "samples_%i_%i_test.csv" % (iteration, n))
if dim == 1:
usingTestTag = "%i" % dim
else:
usingTestTag = "1:%i" % dim
np.savetxt(testSamplesUnitFile, testSamplesUnit)
# collector arrays
accGridSizes = np.array([])
accLevels = np.array([])
accL2error = np.array([])
accCrossEntropy = np.array([])
accKLDivergence = np.array([])
# best estimation
ans = None
bestMeasure = 1e20
bestSetting = None
for level in levels:
# define output files
gridFile = os.path.join(
pathResults, "samples_%i_%i_l%i.grid" % (iteration, n, level))
alphaFile = os.path.join(
pathResults,
"samples_%i_%i_l%i.alpha.arff" % (iteration, n, level))
sampleFile = os.path.join(
pathResults, "samples_%i_%i_l%i.csv" % (iteration, n, level))
likelihoodFile = ""
if testSamplesUnit is not None:
likelihoodFile = os.path.join(
pathResults,
"samples_%i_%i_l%i_likelihood.csv" % (iteration, n, level))
surfaceFile = ""
if dim == 2:
surfaceFile = os.path.join(
pathResults, "samples_%i_%i_l%i.xyz" % (iteration, n, level))
gnuplotJpegFile = os.path.join(
pathResults,
"samples_%i_%i_l%i_gnuplot.jpg" % (iteration, n, level))
sgdeJpegFile = os.path.join(
pathResults, "samples_%i_%i_l%i_sgde.jpg" % (iteration, n, level))
sgdePositiveJpegFile = os.path.join(
pathResults,
"samples_%i_%i_l%i_sgdePositive.jpg" % (iteration, n, level))
configFile = os.path.join(pathResults,
"sgde_%i_%i_l%i.cfg" % (iteration, n, level))
gnuplotConfig = os.path.join(
pathResults, "sgde_%i_%i_l%i.gnuplot" % (iteration, n, level))
# generate the grid
grid = Grid.createLinearBoundaryGrid(dim)
grid.createGridGenerator().regular(level)
if grid.getSize() <= n:
print " l=%i" % level,
fd = open(gridFile, "w")
fd.write(grid.serialize())
fd.close()
# write config to file
fd = open(configFile, "w")
fd.write(config %
(trainSamplesUnitFile, usingTrainTag, testSamplesUnitFile,
likelihoodFile, usingTestTag, gridFile, refNr, refPoints,
gridFile, alphaFile, nSamples, sampleFile, surfaceFile))
fd.close()
sgdeDist = SGDEdist.byConfig(configFile)
grid, alpha = sgdeDist.grid, sgdeDist.alpha
# -----------------------------------------------------------
# do some plotting
if dim == 2:
# gnuplot
sgdeDist.gnuplot(gnuplotJpegFile, gnuplotConfig=gnuplotConfig)
# -----------------------------------------------------------
# matplotlib
l2error = np.NAN
kldivergence = np.NAN
crossEntropy = sgdeDist.crossEntropy(testSamplesUnit)
if dist is not None:
l2error = dist.l2error(sgdeDist, testSamplesUnit,
testSamplesProb)
kldivergence = dist.klDivergence(sgdeDist, testSamplesUnit,
testSamplesProb)
fig = plt.figure()
plotSG2d(grid, alpha)
plt.title("N=%i: vol=%g, kl=%g, log=%g, l2error=%g" %
(grid.getSize(), doQuadrature(grid, alpha),
kldivergence, crossEntropy, l2error))
fig.savefig(sgdeJpegFile)
plt.close(fig)
# -----------------------------------------------------------
# copy grid and coefficients
gridFileNew = os.path.join(
pathResults, "samples_%i_%i_sgde.grid" % (iteration, n))
alphaFileNew = os.path.join(
pathResults, "samples_%i_%i_sgde.alpha.arff" % (iteration, n))
sampleFileNew = os.path.join(
pathResults, "samples_%i_%i_sgde.csv" % (iteration, n))
copy2(gridFile, gridFileNew)
copy2(alphaFile, alphaFileNew)
copy2(sampleFile, sampleFileNew)
# -----------------------------------------------------------
# # make it positive and do all over again
# opPositive = OperationMakePositive(sgdeDist.grid)
# alg = EstimateDensityAlgorithm(configFile)
# opPositive.setInterpolationAlgorithm(alg)
# grid, alpha = opPositive.makePositive(sgdeDist.alpha)
# scale to unit integrand
alpha.mult(1. /
createOperationQuadrature(grid).doQuadrature(alpha))
sgdeDist.grid = grid
sgdeDist.alpha = alpha
gridFileNew = os.path.join(
pathResults,
"samples_%i_%i_l%i_positive.grid" % (iteration, n, level))
alphaFileNew = os.path.join(
pathResults, "samples_%i_%i_l%i_positive.alpha.arff" %
(iteration, n, level))
fd = open(gridFileNew, "w")
fd.write(Grid.serialize(grid))
fd.close()
writeAlphaARFF(alphaFileNew, alpha)
# -----------------------------------------------------------
# collect statistics
accGridSizes = np.append(accGridSizes, grid.getSize())
accLevels = np.append(accLevels, level)
l2error = np.NAN
kldivergence = np.NAN
crossEntropy = sgdeDist.crossEntropy(testSamplesUnit)
if dist is not None:
l2error = dist.l2error(sgdeDist, testSamplesUnit,
testSamplesProb)
kldivergence = dist.klDivergence(sgdeDist, testSamplesUnit,
testSamplesProb)
accL2error = np.append(accL2error, l2error)
accCrossEntropy = np.append(accCrossEntropy, crossEntropy)
accKLDivergence = np.append(accKLDivergence, kldivergence)
if dim == 2:
# -----------------------------------------------------------
# do some plotting
fig = plt.figure()
plotSG2d(grid, alpha)
plt.title("N=%i: vol=%g, kl=%g, log=%g, l2error=%g" %
(grid.getSize(), doQuadrature(grid, alpha),
kldivergence, crossEntropy, l2error))
fig.savefig(sgdePositiveJpegFile)
plt.close(fig)
# -----------------------------------------------------------
# select the best density available based on the given criterion
if optimization == 'crossEntropy':
measure = crossEntropy
elif optimization == 'kldivergence':
measure = kldivergence
elif optimization == 'l2':
measure = l2error
else:
raise AttributeError(
'optimization "%s" is not known for density estimation' %
optimization)
isBest = measure < bestMeasure
if isBest:
bestMeasure = measure
if ans is None or isBest:
ans = sgdeDist
bestSetting = {
'level': level,
'gridSize': grid.getSize(),
'l2error': l2error,
'KLDivergence': kldivergence,
'crossEntropy': crossEntropy
}
# -----------------------------------------------------------
# copy grid and coefficients
gridFileNew = os.path.join(
pathResults, "samples_%i_%i.grid" % (iteration, n))
alphaFileNew = os.path.join(
pathResults, "samples_%i_%i.alpha.arff" % (iteration, n))
sampleFileNew = os.path.join(
pathResults, "samples_%i_%i.csv" % (iteration, n))
copy2(gridFile, gridFileNew)
copy2(alphaFile, alphaFileNew)
copy2(sampleFile, sampleFileNew)
gridFileNew = os.path.join(
pathResults,
"samples_%i_%i_positive.grid" % (iteration, n))
alphaFileNew = os.path.join(
pathResults,
"samples_%i_%i_positive.alpha.arff" % (iteration, n))
fd = open(gridFileNew, "w")
fd.write(Grid.serialize(ans.grid))
fd.close()
writeAlphaARFF(alphaFileNew, ans.alpha)
# -----------------------------------------------------------
print ": %s = %g <= %g" % (optimization, measure, bestMeasure)
print
# -----------------------------------------------------------
# write results to file
statsfilename = os.path.join(
pathResults, "sg_sgde_%i_%i_all.stats.arff" % (iteration, n))
writeDataARFF({
'filename':
statsfilename,
'data':
DataMatrix(
np.vstack(
([n] * len(accGridSizes), accGridSizes, accLevels, accL2error,
accKLDivergence, accCrossEntropy)).transpose()),
'names': [
'sampleSize', 'gridSize', 'level', 'l2error', 'KLDivergence',
'crossEntropy'
]
})
# -----------------------------------------------------------
statsfilename = os.path.join(pathResults,
"sg_sgde_%i_%i.stats.arff" % (iteration, n))
writeDataARFF({
'filename':
statsfilename,
'data':
DataMatrix(
np.vstack(([n], bestSetting['gridSize'], bestSetting['level'],
bestSetting['l2error'], bestSetting['KLDivergence'],
bestSetting['crossEntropy'])).transpose()),
'names': [
'sampleSize', 'gridSize', 'level', 'l2error', 'KLDivergence',
'crossEntropy'
]
})
# -----------------------------------------------------------
return ans
# -------------------- prepare data
C = np.array([[0.1, 0.08],
[0.08, 0.1]]) / 10.
m = np.array([0.5, 0.5])
U = MultivariateNormal(m, C, 0, 1)
np.random.seed(12345)
samples = U.rvs(1000)
testSamples = U.rvs(1000)
# ---------- using SGDE from SG++ ------------------------
dist = SGDEdist.byLearnerSGDEConfig(samples,
config={"grid_level": 6,
"grid_type": "Linear",
"refinement_numSteps": 0,
"refinement_numPoints": 3,
"regularization_type": "Laplace",
"crossValidation_lambda": 0.000562341,
"crossValidation_enable": False,
"crossValidation_kfold": 5,
"crossValidation_silent": False},
bounds=U.getBounds())
fig, ax = plotDensity3d(U)
ax.set_title("true density")
fig.show()
fig, ax, _ = plotSG3d(dist.grid, dist.alpha)
ax.set_title("estimated density")
fig.show()
print("mean = %g ~ %g" % (m.prod(), dist.mean()))
print("var = %g ~ %g" % (np.var(testSamples), dist.var()))
def test2DNormalMoments(self):
mean = 0
var = 0.5
U = dists.J(
[dists.Normal(mean, var, -2, 2),
dists.Normal(mean, var, -2, 2)])
np.random.seed(1234567)
trainSamples = U.rvs(1000)
dist = SGDEdist.byLearnerSGDEConfig(trainSamples,
config={
"grid_level": 5,
"grid_type": "linear",
"refinement_numSteps": 0,
"refinement_numPoints": 10,
"regularization_type":
"Laplace",
"crossValidation_lambda":
0.000562341,
"crossValidation_enable":
False,
"crossValidation_kfold": 5,
"crossValidation_silent": True,
"sgde_makePositive": True
},
bounds=U.getBounds())
samples_dist = dist.rvs(1000, shuffle=True)
kde = KDEDist(trainSamples)
samples_kde = kde.rvs(1000, shuffle=True)
# -----------------------------------------------
self.assertTrue(
np.abs(U.mean() - dist.mean()) < 1e-2, "SGDE mean wrong")
self.assertTrue(
np.abs(U.var() - dist.var()) < 4e-2, "SGDE variance wrong")
# -----------------------------------------------
# print the results
print("E(x) ~ %g ~ %g" % (kde.mean(), dist.mean()))
print("V(x) ~ %g ~ %g" % (kde.var(), dist.var()))
print(
"log ~ %g ~ %g" %
(kde.crossEntropy(trainSamples), dist.crossEntropy(trainSamples)))
print("-" * 60)
print(dist.cov())
print(kde.cov())
sgde_x1 = dist.marginalizeToDimX(0)
kde_x1 = kde.marginalizeToDimX(0)
plt.figure()
plotDensity1d(U.getDistributions()[0], label="analytic")
plotDensity1d(sgde_x1, label="sgde")
plotDensity1d(kde_x1, label="kde")
plt.title("mean: sgde=%g, kde=%g; var: sgde=%g, kde=%g" %
(sgde_x1.mean(), kde_x1.mean(), sgde_x1.var(), kde_x1.var()))
plt.legend()
fig = plt.figure()
plotDensity2d(U, addContour=True)
plt.title("analytic")
fig = plt.figure()
plotDensity2d(kde, addContour=True)
plt.scatter(samples_kde[:, 0], samples_kde[:, 1])
plt.title("kde")
fig = plt.figure()
plotDensity2d(dist, addContour=True)
plt.scatter(samples_dist[:, 0], samples_dist[:, 1])
plt.title(
"sgde (I(f) = %g)" %
(np.prod(U.getBounds()) * doQuadrature(dist.grid, dist.alpha), ))
plt.show()
def estimateSGDEDensity(functionName,
trainSamples,
testSamples=None,
bounds=None,
iteration=0,
plot=False,
out=True,
label="sgde_zero",
candidates="intersections",
interpolation="setToZero"):
print("train: %i x %i (mean=%g, var=%g)" %
(trainSamples.shape[0], trainSamples.shape[1], np.mean(trainSamples),
np.var(trainSamples)))
if testSamples is not None:
print("test : %i x %i (mean=%g, var=%g)" %
(testSamples.shape[0], testSamples.shape[1],
np.mean(testSamples), np.var(testSamples)))
candidateSearchAlgorithm = strToCandidateSearchAlgorithm(candidates)
interpolationAlgorithm = strToInterpolationAlgorithm(interpolation)
results = {}
crossEntropies = {}
config = {
"grid_level": 1,
"grid_type": "linear",
"grid_maxDegree": 1,
"refinement_numSteps": 0,
"refinement_numPoints": 3,
"solver_threshold": 1e-10,
"solver_verbose": False,
"regularization_type": "Laplace",
"crossValidation_enable": True,
"crossValidation_kfold": 5,
"crossValidation_silent": True,
"sgde_makePositive": False
}
pathResults = os.path.join("data", label)
key = 1
bestCV = float("Inf")
bestDist = None
# stats
stats = {
'config': {
'functionName': functionName,
'numDims': 2,
'adaptive': True,
'refnums': 0,
'consistentGrid': True,
'candidateSearchAlgorithm': candidates,
'interpolationAlgorithm': interpolation,
'maxNumGridPoints': 0,
'iteration': iteration
},
'trainSamples': trainSamples,
'testSamples': testSamples
}
for level in range(2, 7):
print("-" * 60)
print("l=%i" % level)
for refinementSteps in range(0, 5):
config["grid_level"] = level
config["refinement_numSteps"] = refinementSteps
sgdeDist = SGDEdist.byLearnerSGDEConfig(trainSamples,
config=config,
bounds=bounds)
# -----------------------------------------------------------
grid, alpha = sgdeDist.grid, sgdeDist.alpha
cvSgde = sgdeDist.crossEntropy(testSamples)
maxLevel = grid.getStorage().getMaxLevel()
numDims = grid.getStorage().getDimension()
print(" " + "-" * 30)
print(" #ref = %i: gs=%i -> CV test = %g" %
(refinementSteps, sgdeDist.grid.getSize(), cvSgde))
# -----------------------------------------------------------
# make it positive
positiveGrid = grid.clone()
positiveAlpha_vec = DataVector(alpha)
opPositive = createOperationMakePositive(candidateSearchAlgorithm,
interpolationAlgorithm,
True, False)
opPositive.makePositive(positiveGrid, positiveAlpha_vec, True)
# scale to unit integrand
positiveAlpha = positiveAlpha_vec.array()
positiveSgdeDist = SGDEdist(positiveGrid,
positiveAlpha,
trainSamples,
bounds=bounds)
# -----------------------------------------------------------
cvPositiveSgde = positiveSgdeDist.crossEntropy(testSamples)
if plot and numDims == 2:
fig = plt.figure()
plotSG2d(grid,
alpha,
show_negative=True,
show_grid_points=True)
plt.title("pos: N=%i: vol=%g, log=%g" %
(positiveGrid.getSize(),
doQuadrature(positiveGrid,
positiveAlpha), cvPositiveSgde))
plt.tight_layout()
if out:
plt.savefig(
os.path.join(
pathResults, "%s_density_pos_i%i_l%i_r%i.jpg" %
(label, iteration, level, refinementSteps)))
plt.savefig(
os.path.join(
pathResults, "%s_density_pos_i%i_l%i_r%i.pdf" %
(label, iteration, level, refinementSteps)))
else:
plt.close(fig)
# -----------------------------------------------------------
print(" positive: gs=%i -> CV test = %g" %
(positiveGrid.getSize(), cvPositiveSgde))
# -----------------------------------------------------------
# select the best density available based on the given criterion
results[key] = {'config': config, 'dist': positiveSgdeDist}
crossEntropies[key] = cvPositiveSgde
key += 1
candidateSearch = opPositive.getCandidateSetAlgorithm()
if cvPositiveSgde < bestCV:
bestCV = cvPositiveSgde
bestDist = positiveSgdeDist
numComparisons = candidateSearch.costsComputingCandidates()
# update the stats -> just for the current best one
# write the stats of the current best results to the stats dict
C = np.ndarray(numDims - 1, dtype="int")
M = np.sum([1 for i in range(len(alpha)) if alpha[i] < 0])
for d in range(2, numDims + 1):
C[d - 2] = binom(M, d)
stats['config']['refnums'] = refinementSteps
stats['config']['adaptive'] = refinementSteps > 0
stats['negSGDE_json'] = sgdeDist.toJson()
stats['posSGDE_json'] = positiveSgdeDist.toJson()
stats['level'] = level
stats['maxLevel'] = maxLevel
stats['fullGridSize'] = (2**maxLevel - 1)**numDims
stats['sparseGridSize'] = grid.getSize()
stats['discretizedGridSize'] = positiveGrid.getSize()
stats['crossEntropyTrainZeroSGDE'] = sgdeDist.crossEntropy(
trainSamples)
stats[
'crossEntropyTrainDiscretizedSGDE'] = positiveSgdeDist.crossEntropy(
trainSamples)
stats['crossEntropyTestZeroSGDE'] = cvSgde
stats['crossEntropyTestDiscretizedSGDE'] = cvPositiveSgde
stats['numCandidates'] = int(candidateSearch.numCandidates())
stats['numCandidatesPerLevel'] = np.array(
candidateSearch.numCandidatesPerLevel().array(),
dtype="int")
stats['numCandidatesPerIteration'] = np.array(
candidateSearch.numCandidatesPerIteration().array(),
dtype="int")
stats[
'costsCandidateSearch'] = candidateSearch.costsComputingCandidates(
)
stats['costsCandidateSearchBinomial'] = int(C.sum())
stats['costsCandidateSearchPerIteration'] = np.array(
candidateSearch.costsComputingCandidatesPerIteration(
).array(),
dtype="int")
stats['costsCandidateSearchPerIterationBinomial'] = C
if plot and numDims == 2:
fig = plt.figure()
plotSG2d(
positiveGrid,
positiveAlpha,
show_negative=True,
show_grid_points=False,
colorbarLabel=
r"$f_{\mathcal{I}^\text{SG} \cup \mathcal{I}^\text{ext}}$"
)
plt.title(r"positive: $N=%i/%i$; \# comparisons$=%i$" %
(positiveGrid.getSize(),
(2**maxLevel - 1)**numDims, numComparisons))
plt.xlabel(r"$\xi_1$")
plt.ylabel(r"$\xi_2$")
# plt.title(r"N=%i $\rightarrow$ %i: log=%g $\rightarrow$ %g" % (sgdeDist.grid.getSize(),
# positiveSgdeDist.grid.getSize(),
# cvSgde,
# cvPositiveSgde))
plt.tight_layout()
plt.savefig(
os.path.join(
pathResults, "%s_pos_i%i_l%i_r%i.jpg" %
(label, iteration, level, refinementSteps)))
plt.savefig(
os.path.join(
pathResults, "%s_pos_i%i_l%i_r%i.pdf" %
(label, iteration, level, refinementSteps)))
if out:
plt.close(fig)
fig, ax, _ = plotSG3d(positiveGrid, positiveAlpha)
ax.set_zlabel(
r"$f_{\mathcal{I}^{\text{SG}} \cup \mathcal{I}^\text{ext}}(\xi_1, \xi_2)$",
fontsize=20)
ax.set_xlabel(r"$\xi_1$", fontsize=20)
ax.set_ylabel(r"$\xi_2$", fontsize=20)
plt.tight_layout()
plt.savefig(
os.path.join(
pathResults, "%s_pos_i%i_l%i_r%i_3d.jpg" %
(label, iteration, level, refinementSteps)))
plt.savefig(
os.path.join(
pathResults, "%s_pos_i%i_l%i_r%i_3d.pdf" %
(label, iteration, level, refinementSteps)))
if out:
plt.close(fig)
if plot and numDims == 2 and not out:
plt.show()
if out:
# save stats
filename = os.path.join(
"data", label, "stats_d%i_a%i_r%i_i%i_%s_%s.pkl" %
(numDims, 1, refinementSteps, iteration, candidates,
interpolation))
fd = open(filename, "w")
pkl.dump(stats, fd)
fd.close()
print("stats saved to -> '%s'" % filename)
# dictionary that stores the information on the estimated densities
myjson = {
"Grid": {
"dimNames": ["phi", "log(K_A)"],
"matrixEntries": ["phi", "log(K_A)"]
},
"Set": {
"path": "",
"grids": [],
"alphas": [],
"paramValues": [],
"paramName": "grid_size"
}
}
for key, result in list(results.items()):
config = result['config']
dist = result['dist']
# serialize grid and coefficients
out = "sgde.i%i.k%i.N%i" % (iteration, key, dist.grid.getSize())
out_grid = os.path.join(pathResults, "%s.grid" % out)
out_alpha = os.path.join(pathResults, "%s.alpha.arff" % out)
writeGrid(out_grid, dist.grid)
writeAlphaARFF(out_alpha, dist.alpha)
# collect information for json
myjson["Set"]["grids"].append(os.path.abspath(out_grid))
myjson["Set"]["alphas"].append(os.path.abspath(out_alpha))
myjson["Set"]["paramValues"].append(crossEntropies[key])
# -----------------------------------------------------------
# serialize the config
out_config = os.path.join(pathResults,
"sgde.i%i.k%i.config" % (iteration, key))
fd = open(out_config, "w")
json.dump(config, fd, ensure_ascii=True, indent=True)
fd.close()
crossEntropies[key] = (crossEntropies[key], out_grid, out_alpha,
out_config)
# sort the results in myjson according to the cross entropy
ixs = np.argsort(myjson["Set"]["paramValues"])
myjson["Set"]["grids"] = [myjson["Set"]["grids"][ix] for ix in ixs]
myjson["Set"]["alphas"] = [myjson["Set"]["alphas"][ix] for ix in ixs]
myjson["Set"]["paramValues"] = [
myjson["Set"]["paramValues"][ix] for ix in ixs
]
# serialize myjson
out_config = os.path.join(pathResults,
"sgde_visualization.i%i.config" % iteration)
fd = open(out_config, "w")
json.dump(myjson, fd, ensure_ascii=True, indent=True)
fd.close()
# serialize cross entropies
out_crossEntropies = os.path.join(
pathResults, "sgde_cross_entropies.i%i.csv" % iteration)
fd = open(out_crossEntropies, 'wb')
file_writer = csv.writer(fd)
file_writer.writerow(["crossEntropy", "grid", "alpha", "sgdeConfig"])
for out in list(crossEntropies.values()):
file_writer.writerow(out)
fd.close()
# serialize samples
np.savetxt(
os.path.join(pathResults,
"sgde_train_samples.i%i.csv" % iteration),
trainSamples)
np.savetxt(
os.path.join(pathResults, "sgde_test_samples.i%i.csv" % iteration),
testSamples)
# serialize best configuration to json
out_bestDist = os.path.join(pathResults,
"sgde_best_config.i%i.json" % iteration)
text = bestDist.toJson()
fd = open(out_bestDist, "w")
fd.write(text)
fd.close()
return bestDist, stats
refnum + 1, gs.getSize()))
# extend alpha vector (new entries uninitialized)
alpha.resize(gs.getSize())
# set function values in alpha
for i in range(gs.getSize()):
gs.getPoint(i).getStandardCoordinates(p)
alpha[i] = dist.pdf(p.array())
# hierarchize
createOperationHierarchisation(grid).doHierarchisation(alpha)
alpha = alpha.array()
sgdeDist = SGDEdist(grid,
alpha,
trainData=trainSamples,
bounds=dist.getBounds())
print(
"l=%i: (gs=%i) -> %g (%g, %g)," %
(level, sgdeDist.grid.getSize(), dist.klDivergence(sgdeDist, testSamples),
sgdeDist.crossEntropy(testSamples), sgdeDist.vol))
print("-" * 80)
if numDims == 2 and plot:
# plot the result
fig = plt.figure()
plotGrid2d(grid, alpha, show_numbers=False)
# plt.title("neg: #gp = %i, kldivergence = %g, log = %g" % (grid.getStorage().getSize(),
# dist.klDivergence(sgdeDist, testSamples),
# dist.crossEntropy(testSamples)))
fig.show()
