class VineModel(BaseEstimator):
"""!
@brief Implements the fit, fit_transform interface of the sklearn
pipeline workflow for vine copula.
"""
def __init__(self,
vine_type='c',
trial_copula={},
copula_fit_method='mle',
vine_fit_method='ktau',
rank_transform=True):
self.trial_copula_dict = trial_copula
self._rank_transform = rank_transform
if vine_type == 'c':
self._vine = Cvine([])
else:
raise NotImplementedError
def fit(self, X, weights=None):
"""
@brief Fit vine copula model to data.
@param X corrolated vectors with shape (Nsamples, Ndim). Can be
unranked or ranked data
"""
if not isinstance(X, pd.DataFrame):
tstData = pd.DataFrame(X)
else:
tstData = X
if self.rank_transform:
x_r = tstData.dropna().rank() / (len(tstData) + 1)
else:
x_r = tstData
self.vine = Cvine(x_r, trial_copula=self.trial_copula_dict)
self.vine.constructVine()
def predict(self, n):
"""!
@brief Predict correlated output vectors given uncorrolated inputs.
@param n int. Number of samples to draw.
"""
return self.vine.sample(n)
@property
def rank_transform(self):
return self._rank_transform
@rank_transform.setter
def rank_transform(self, rt):
self._rank_transform = bool(rt)
def fit(self, X, weights=None):
"""
@brief Fit vine copula model to data.
@param X corrolated vectors with shape (Nsamples, Ndim). Can be
unranked or ranked data
"""
if not isinstance(X, pd.DataFrame):
tstData = pd.DataFrame(X)
else:
tstData = X
if self.rank_transform:
x_r = tstData.dropna().rank() / (len(tstData) + 1)
else:
x_r = tstData
self.vine = Cvine(x_r, trial_copula=self.trial_copula_dict)
self.vine.constructVine()
def testCvineConstruct(self):
stocks = np.loadtxt(dataDir + 'stocks.csv', delimiter=',')
x = stocks[:, 0]
y = stocks[:, 1]
z = stocks[:, 4]
p = stocks[:, 5]
e = stocks[:, 6]
# Create pandas data table
tstData = pd.DataFrame()
tstData['1a'] = x
tstData['2b'] = y
tstData['3c'] = z
tstData['4d'] = p
tstData['5e'] = e
# Visualize multivar data
matrixPairPlot(tstData, savefig="quad_varaite_ex.png")
# Visualize multivar ranked data
ranked_data = tstData.dropna().rank() / (len(tstData) + 1)
# ranked_data['1a'] = ranked_data['1a']
matrixPairPlot(ranked_data, savefig="quad_varaite_ranked_ex.png")
# Init Cvine
tstVine = Cvine(ranked_data)
# construct the vine
tstVine.constructVine()
# plot vine
tstVine.plotVine(savefig="c_vine_graph_ex.png")
# sample from vine
samples = tstVine.sample(n=8000)
matrixPairPlot(samples, savefig="quad_varaite_resampled_ex.png")
def __init__(self,
vine_type='c',
trial_copula={},
copula_fit_method='mle',
vine_fit_method='ktau',
rank_transform=True):
self.trial_copula_dict = trial_copula
self._rank_transform = rank_transform
if vine_type == 'c':
self._vine = Cvine([])
else:
raise NotImplementedError
def main():
# read data from external h5 file
h5file = 'Cicada_cfd_180x_cht.h5.post.binned.h5'
# store = pd.HDFStore(h5file)
store = pt.open_file(h5file)
bounds = h5Load(store, "Water/UO2 [Interface 1]/Temperature_bounds")
temperature = h5Load(store, "Water/UO2 [Interface 1]/Temperature")
tke = h5Load(store, "Water/UO2 [Interface 1]/TurbulentKineticEnergy")
crud_thick = h5Load(store, "Water/UO2 [Interface 1]/CrudThickness")
b10 = h5Load(store, "Water/UO2 [Interface 1]/CrudBoronDensity")
weight = h5Load(store, "Water/UO2 [Interface 1]/Temperature_weights")
bhf = h5Load(store, "Water/UO2 [Interface 1]/BoundaryHeatFlux")
"""
# create multi-variate dataset for span 1
# for zone in range(69, 81):
for zone in range(69, 78):
lower_b = bounds.read()[:, zone][0]
print("Generating plot for zone: " + str(zone))
temps = temperature.read()[:, zone][~np.isnan(temperature.read()[:, zone])]
tkes = tke.read()[:, zone][~np.isnan(tke.read()[:, zone])]
cruds = crud_thick.read()[:, zone][~np.isnan(crud_thick.read()[:, zone])]
b10s = b10.read()[:, zone][~np.isnan(b10.read()[:, zone])]
bhfs = bhf.read()[:, zone][~np.isnan(bhf.read()[:, zone])]
weights = weight.read()[:, zone][~np.isnan(weight.read()[:, zone])]
span_1_dataDict = {"Residual Temperature [K]": temps,
"Residual TKE [J/kg]": tkes,
"Residual BHF [W/m^2]": bhfs,
}
span_1_mvd = mvd.Mvd()
span_1_mvd.setData(span_1_dataDict, weights)
span_1_mvd.plot(savefig="mvd_" + str(round(lower_b, 3)) + ".png", kde=False)
"""
# upper span plot
tsat = -618.5
zones = range(72, 74)
temps = temperature.read()[:,
zones][~np.isnan(temperature.read()[:, zones])]
tkes = tke.read()[:, zones][~np.isnan(tke.read()[:, zones])]
cruds = crud_thick.read()[:, zones][~np.isnan(crud_thick.read()[:, zones])]
b10s = b10.read()[:, zones][~np.isnan(b10.read()[:, zones])]
bhfs = bhf.read()[:, zones][~np.isnan(bhf.read()[:, zones])]
weights = weight.read()[:, zones][~np.isnan(weight.read()[:, zones])]
span_1_dataDict = {
"Residual Temperature [K]": temps,
"Residual TKE [J/kg]": tkes,
"Residual BHF [W/m^2]": bhfs,
}
span_1_mvd = mvd.Mvd()
span_1_mvd.setData(span_1_dataDict, weights)
span_1_mvd.plot(savefig="upper_span.png", kde=False)
# fit bivariate copula to span plot; T vs TKE:
# copula = bvc.PairCopula(temps, tkes)
# copula.copulaTournament()
# init Cvine
print("================= Construct Upper Vine =================")
upperData = pd.DataFrame({"t": temps, "tke": tkes, "q": bhfs})
upperVine = Cvine(pd.DataFrame({"t": temps, "tke": tkes, "q": bhfs}))
upperVine.constructVine()
upperVine.plotVine(savefig="upper_vine.png")
print("========================================================")
upperVineSamples = upperVine.sample(n=500)
plt.figure(22)
matrixPairPlot(upperVineSamples, savefig="upper_vine_samples.png")
upper_ranked_data = upperData.dropna().rank() / (len(upperData) + 1)
matrixPairPlot(upper_ranked_data, savefig="upper_ranked_samples.png")
t_hat_vine, tke_hat_vine, q_hat_vine = upperVineSamples[
't'], upperVineSamples['tke'], upperVineSamples['q']
# plot original
# bvc.bvJointPlot(temps, tkes, savefig="upper_t_tke_original.png")
# sample from copula
# print("Copula Params: " + str(copula.copulaParams))
# t_hat, tke_hat = copula.copulaModel.sample(500)
# bvc.bvJointPlot(t_hat_vine, tke_hat_vine, savefig="upper_t_tke_copula_sample.png")
# rand_u = np.linspace(0.05, 0.95, 40)
# rand_v = np.linspace(0.05, 0.95, 40)
# u, v = np.meshgrid(rand_u, rand_v)
# copula_pdf = copula.copulaModel.pdf(u.flatten(), v.flatten())
# bvc.bvContourf(u.flatten(), v.flatten(), copula_pdf, savefig="upper_t_tke_copula_pdf.png")
# Resample original data
def icdf_uv_bisect(ux, X, marginalCDFModel):
icdf = np.zeros(np.array(X).size)
for i, xx in enumerate(X):
kde_cdf_err = lambda m: xx - marginalCDFModel(-np.inf, m)
try:
icdf[i] = bisect(kde_cdf_err,
min(ux) - np.abs(0.5 * min(ux)),
max(ux) + np.abs(0.5 * max(ux)),
xtol=1e-3,
maxiter=15)
icdf[i] = newton(kde_cdf_err, icdf[i], tol=1e-6, maxiter=20)
except:
icdf[i] = np.nan
return icdf
kde_cdf = gaussian_kde(temps).integrate_box
resampled_t = icdf_uv_bisect(temps, t_hat_vine, kde_cdf)
kde_cdf = gaussian_kde(tkes).integrate_box
resampled_tke = icdf_uv_bisect(tkes, tke_hat_vine, kde_cdf)
bvc.bvJointPlot(resampled_t,
resampled_tke,
vs=[temps, tkes],
savefig="upper_t_tke_resampled.png")
# LOWER SPAN
tsat = -618.5
zones = range(70, 71)
temps = temperature.read()[:,
zones][~np.isnan(temperature.read()[:, zones])]
tkes = tke.read()[:, zones][~np.isnan(tke.read()[:, zones])]
cruds = crud_thick.read()[:, zones][~np.isnan(crud_thick.read()[:, zones])]
b10s = b10.read()[:, zones][~np.isnan(b10.read()[:, zones])]
bhfs = bhf.read()[:, zones][~np.isnan(bhf.read()[:, zones])]
weights = weight.read()[:, zones][~np.isnan(weight.read()[:, zones])]
span_1_dataDict = {
"Residual Temperature [K]": temps,
"Residual TKE [J/kg]": tkes,
"Residual BHF [W/m^2]": bhfs,
}
span_1_mvd = mvd.Mvd()
span_1_mvd.setData(span_1_dataDict, weights)
span_1_mvd.plot(savefig="lower_span.png", kde=False)
# fit bivariate copula to span plot; T vs TKE:
# copula = bvc.PairCopula(temps, tkes)
# copula.copulaTournament()
# init Cvine
print("================= Construct Lower Vine =================")
lowerData = pd.DataFrame({"t": temps, "tke": tkes, "q": bhfs})
lowerVine = Cvine(pd.DataFrame({"tke": tkes, "t": temps, "q": bhfs}))
lowerVine.constructVine()
plt.figure(20)
lowerVine.plotVine(savefig="lower_vine.png")
print("========================================================")
lowerVineSamples = lowerVine.sample(n=500)
matrixPairPlot(lowerVineSamples, savefig="lower_vine_samples.png")
lower_ranked_data = lowerData.dropna().rank() / (len(lowerData) + 1)
matrixPairPlot(lower_ranked_data, savefig="lower_ranked_samples.png")
t_hat_vine, tke_hat_vine, q_hat_vine = lowerVineSamples[
't'], lowerVineSamples['tke'], lowerVineSamples['q']
# plot original
# bvc.bvJointPlot(temps, tkes, savefig="lower_t_tke_original.png")
# sample from copula
# print("Copula Params: " + str(copula.copulaParams))
# t_hat, tke_hat = copula.copulaModel.sample(500)
# bvc.bvJointPlot(t_hat_vine, tke_hat_vine, savefig="lower_t_tke_copula_sample.png")
# rand_u = np.linspace(0.05, 0.95, 40)
# rand_v = np.linspace(0.05, 0.95, 40)
# u, v = np.meshgrid(rand_u, rand_v)
# copula_pdf = copula.copulaModel.pdf(u.flatten(), v.flatten())
# bvc.bvContourf(u.flatten(), v.flatten(), copula_pdf, savefig="lower_t_tke_copula_pdf.png")
# Resample original data
def icdf_uv_bisect(ux, X, marginalCDFModel):
icdf = np.zeros(np.array(X).size)
for i, xx in enumerate(X):
kde_cdf_err = lambda m: xx - marginalCDFModel(-np.inf, m)
try:
icdf[i] = bisect(kde_cdf_err,
min(ux) - np.abs(0.5 * min(ux)),
max(ux) + np.abs(0.5 * max(ux)),
xtol=1e-2,
maxiter=10)
icdf[i] = newton(kde_cdf_err, icdf[i], tol=1e-6, maxiter=20)
except:
icdf[i] = np.nan
return icdf
kde_cdf = gaussian_kde(temps).integrate_box
resampled_t = icdf_uv_bisect(temps, t_hat_vine, kde_cdf)
kde_cdf = gaussian_kde(tkes).integrate_box
resampled_tke = icdf_uv_bisect(tkes, tke_hat_vine, kde_cdf)
bvc.bvJointPlot(resampled_t,
resampled_tke,
vs=[temps, tkes],
savefig="lower_t_tke_resampled.png")
# Clean up
store.close()
def testCvineConstruct(self):
stocks = np.loadtxt(dataDir + 'stocks.csv', delimiter=',')
x = stocks[:, 0]
y = stocks[:, 1]
z = stocks[:, 4]
p = stocks[:, 5]
e = stocks[:, 6]
# Create pandas data table
tstData = pd.DataFrame()
tstData['1a'] = x
tstData['2b'] = y
tstData['3c'] = z
tstData['4d'] = p
tstData['5e'] = e
# Visualize multivar data
matrixPairPlot(tstData, savefig="quad_varaite_ex.png")
# Visualize multivar ranked data
ranked_data = tstData.dropna().rank() / (len(tstData) + 1)
# ranked_data['1a'] = ranked_data['1a']
matrixPairPlot(ranked_data, savefig="quad_varaite_ranked_ex.png")
# Init Cvine
tstVine = Cvine(ranked_data)
# construct the vine
tstVine.constructVine()
# plot vine
tstVine.plotVine(savefig="c_vine_graph_ex.png")
# sample from vine
c_vine_samples = tstVine.sample(n=8000)
matrixPairPlot(c_vine_samples, savefig="vine_resampled_ex.png")
# check that the original data has same correlation coefficients as re-sampled
# data from the fitted c-vine
tst_rho_matrix = ranked_data.corr(method='pearson')
tst_ktau_matrix = ranked_data.corr(method='kendall')
sample_rho_matrix = c_vine_samples.corr(method='pearson')
sample_ktau_matrix = c_vine_samples.corr(method='kendall')
# sort by col labels
tst_rho_matrix = tst_rho_matrix.reindex(sorted(tst_rho_matrix.columns),
axis=1)
tst_ktau_matrix = tst_ktau_matrix.reindex(sorted(
tst_ktau_matrix.columns),
axis=1)
sample_rho_matrix = sample_rho_matrix.reindex(sorted(
sample_rho_matrix.columns),
axis=1)
sample_ktau_matrix = sample_ktau_matrix.reindex(sorted(
sample_ktau_matrix.columns),
axis=1)
print("Original data corr matrix:")
print(tst_rho_matrix)
print("Vine sample corr matrix:")
print(sample_rho_matrix)
print("Diff:")
print(tst_rho_matrix - sample_rho_matrix)
self.assertTrue(
np.allclose(tst_rho_matrix - sample_rho_matrix, 0, atol=0.10))
self.assertTrue(
np.allclose(tst_ktau_matrix - sample_ktau_matrix, 0, atol=0.10))
# fit marginal distributions to original data
marginal_dict = {}
for col_name in tstData.columns:
marginal_dict[col_name] = beta(*beta.fit(tstData[col_name]))
# scale the samples
c_vine_scaled_samples_a = tstVine.scaleSamples(c_vine_samples,
marginal_dict)
matrixPairPlot(c_vine_scaled_samples_a,
savefig="vine_varaite_resampled_scaled_a.png")
c_vine_scaled_samples_b = tstVine.sampleScale(8000, marginal_dict)
# compute correlation coeffs
sample_scaled_rho_matrix_a = c_vine_scaled_samples_a.corr(
method='pearson')
sample_scaled_rho_matrix_b = c_vine_scaled_samples_b.corr(
method='pearson')
# check for consistency
self.assertTrue(
np.allclose(tst_rho_matrix - sample_scaled_rho_matrix_a,
0,
atol=0.1))
self.assertTrue(
np.allclose(tst_rho_matrix - sample_scaled_rho_matrix_b,
0,
atol=0.1))
def main():
# read data from external h5 file
h5file = 'Cicada_cfd_180x_cht.h5.post.binned.h5'
# store = pd.HDFStore(h5file)
store = pt.open_file(h5file)
bounds = h5Load(store, "Water/UO2 [Interface 1]/Temperature_bounds")
temperature = h5Load(store, "Water/UO2 [Interface 1]/Temperature")
tke = h5Load(store, "Water/UO2 [Interface 1]/TurbulentKineticEnergy")
crud_thick = h5Load(store, "Water/UO2 [Interface 1]/CrudThickness")
b10 = h5Load(store, "Water/UO2 [Interface 1]/CrudBoronDensity")
weight = h5Load(store, "Water/UO2 [Interface 1]/Temperature_weights")
bhf = h5Load(store, "Water/UO2 [Interface 1]/BoundaryHeatFlux")
# SPAN
tsat = -618.5
zones = range(65, 98)
for zone in zones:
zBounds = bounds.read()[:, zone][~np.isnan(bounds.read()[:, zone])]
temps = temperature.read()[:,
zone][~np.isnan(temperature.read()[:,
zone])]
tkes = tke.read()[:, zone][~np.isnan(tke.read()[:, zone])]
cruds = crud_thick.read()[:,
zone][~np.isnan(crud_thick.read()[:, zone])]
b10s = b10.read()[:, zone][~np.isnan(b10.read()[:, zone])]
bhfs = bhf.read()[:, zone][~np.isnan(bhf.read()[:, zone])]
weights = weight.read()[:, zone][~np.isnan(weight.read()[:, zone])]
span_1_dataDict = {
"Residual Temperature [K]": temps,
"Residual TKE [J/kg]": tkes,
"Residual BHF [W/m^2]": bhfs,
}
span_1_mvd = mvd.Mvd()
span_1_mvd.setData(span_1_dataDict, weights)
upper_z, lower_z = zBounds
bounds_label = str(lower_z) + "_" + str(upper_z)
# span_1_mvd.plot(savefig=bounds_label + "_span.png", kde=False)
# Construct Cvine
lowerData = pd.DataFrame({"t": temps, "tke": tkes, "q": bhfs})
lowerVine = Cvine(pd.DataFrame({"tke": tkes, "t": temps, "q": bhfs}))
lowerVine.constructVine()
# Sample Cvine
lowerVineSamples = lowerVine.sample(n=500)
matrixPairPlot(lowerVineSamples,
savefig="singlePinPlots/" + bounds_label +
"_vine_samples.png")
ranked_data = lowerData.dropna().rank() / (len(lowerData) + 1)
# matrixPairPlot(ranked_data, savefig="singlePinPlots/" + bounds_label + "_ranked_samples.png")
t_hat_vine, tke_hat_vine, q_hat_vine = lowerVineSamples[
't'], lowerVineSamples['tke'], lowerVineSamples['q']
kde_cdf = gaussian_kde(temps).integrate_box
resampled_t = icdf_uv_bisect(temps, t_hat_vine, kde_cdf)
kde_cdf = gaussian_kde(tkes).integrate_box
resampled_tke = icdf_uv_bisect(tkes, tke_hat_vine, kde_cdf)
# bvc.bvJointPlot(resampled_t, resampled_tke, vs=[temps, tkes],
# savefig="singlePinPlots/" + bounds_label + "_t_tke_resampled.png")
# Grow crud at resampled points
#crudModel = Mamba1d(len(resampled_t))
# Compare resampled crud to original crud result
# Clean up
store.close()