def _process_integration(self, a):
i, rnd, noise = a
num_exploding = 0
repeats = 20
xx = {}
x = {}
for l in self.fit_mat.keys():
xx[l] = np.zeros((repeats, self.input_pcs.shape[0]))
if self.delay_model:
xx[l][:self.delay, :] = rnd[l].T
else:
xx[l][0, :] = rnd[l]
x[l] = np.zeros((self.int_length, self.input_pcs.shape[0]))
if self.delay_model:
x[l][:self.delay, :] = xx[l][:self.delay, :]
else:
x[l][0, :] = xx[l][0, :]
step0 = 0
if self.delay_model:
step = self.delay
else:
step = 1
blow_counter = 0
zz = {}
for n in range(repeats*int(np.ceil(self.int_length/repeats))):
for k in range(1, repeats):
if (self.delay_model and k < self.delay) and step == self.delay:
continue
if blow_counter >= 10:
raise Exception("Model blowed up 10 times.")
if step >= self.int_length:
break
# prepare predictors
for l in self.fit_mat.keys():
zz[l] = xx[0][k-1, :]
for lr in range(l):
zz[l] = np.r_[zz[l], xx[lr+1][k-1, :]]
for l in self.fit_mat.keys():
if l == 0:
if self.quad:
q = np.tril(np.outer(zz[l].T, zz[l]), -1)
quad_pred = q[np.nonzero(q)]
if self.delay_model:
zz[l] = np.tanh(self.kappa * x[l][step - self.delay, :])
if self.harmonic_pred in ['all', 'first']:
if self.quad:
zz[l] = np.r_[quad_pred, zz[l], zz[l]*self.xsin[step], zz[l]*self.xcos[step],
self.xsin[step], self.xcos[step], 1]
else:
zz[l] = np.r_[zz[l], zz[l]*self.xsin[step], zz[l]*self.xcos[step],
self.xsin[step], self.xcos[step], 1]
else:
if self.quad:
zz[l] = np.r_[quad_pred, zz[l], 1]
else:
zz[l] = np.r_[zz[l], 1]
else:
if self.harmonic_pred == 'all':
zz[l] = np.r_[zz[l], zz[l]*self.xsin[step], zz[l]*self.xcos[step],
self.xsin[step], self.xcos[step], 1]
else:
zz[l] = np.r_[zz[l], 1]
if 'cond' in self.noise_type:
n_PCs = 1
n_samples = 100
if not self.combined:
ndx = np.argsort(np.sum(np.power(self.pcs[:, :n_PCs] - xx[k-1, :n_PCs], 2), axis = 1))
Q = np.cov(self.last_level_res[ndx[:n_samples], :], rowvar = 0)
self.rr = np.linalg.cholesky(Q).T
elif self.combined:
ndx1 = np.argsort(np.sum(np.power(self.pcs[:, :n_PCs] - xx[k-1, :n_PCs], 2), axis = 1))
ndx2 = np.argsort(np.sum(np.power(self.pcs[:, self.no_input_ts:self.no_input_ts+n_PCs] - xx[k-1, self.no_input_ts:self.no_input_ts+n_PCs], 2), axis = 1))
res1 = self.last_level_res[ndx1[:n_samples], :]
res2 = self.last_level_res[ndx2[:n_samples], :]
Q = np.cov(np.concatenate((res1, res2), axis = 0), rowvar = 0)
self.rr = np.linalg.cholesky(Q).T
# integration step
for l in sorted(self.fit_mat, reverse = True):
if (l == self.no_levels-1):
forcing = np.dot(self.rr, np.random.normal(0,self.sigma,(self.rr.shape[0],)).T)
if 'seasonal' in self.noise_type:
forcing *= self.rr_last_std_ts[step%self.rr_last_std_ts.shape[0], :]
else:
forcing = xx[l+1][k, :]
xx[l][k, :] = xx[l][k-1, :] + np.dot(zz[l], self.fit_mat[l]) + forcing
# xx[l][k, :] = xx[l][k-1, :] + self.regressor.predict(zz[l]) + forcing
step += 1
# check if integration blows
if np.amax(np.abs(xx[0])) <= 2*self.maxpc and not np.any(np.isnan(xx[0])):
for l in self.fit_mat.keys():
x[l][step-repeats + 1 : step, :] = xx[l][1:, :]
# set first to last
xx[l][0, :] = xx[l][-1, :]
else:
for l in self.fit_mat.keys():
if l == 0:
xx[l][0, :] = np.dot(np.random.normal(0, self.sigma, (self.input_pcs.shape[0],)), self.diagpc)
else:
xx[l][0, :] = np.dot(np.random.normal(0, self.sigma, (self.input_pcs.shape[0],)), self.diagres[l-1])
if step != step0:
num_exploding += 1
step0 = step
step -= repeats + 1
blow_counter += 1
x = x[0].copy()
# center
x -= np.mean(x, axis = 0)
# preserve total energy level
x *= np.sqrt(np.sum(self.varpc)/np.sum(np.var(x, axis = 0, ddof = 1)))
if self.diagnostics:
xm = np.mean(x, axis = 0)
xv = np.var(x, axis = 0, ddof = 1)
xs = sts.skew(x, axis = 0)
xk = sts.kurtosis(x, axis = 0)
lc = np.zeros((2*self.max_lag + 1, self.input_pcs.shape[0]))
kden = np.zeros((100, self.input_pcs.shape[0], 2))
for k in range(self.input_pcs.shape[0]):
lc[:, k] = cross_correlation(x[:, k], x[:, k], max_lag = self.max_lag)
kden[:, k, 0], kden[:, k, 1] = kdensity_estimate(x[:, k], kernel = 'epanechnikov')
ict = np.sum(np.abs(lc), axis = 0)
return i, x, num_exploding, xm, xv, xs, xk, lc, kden, ict
else:
return i, x, num_exploding
def _process_integration(self, a):
i, rnd, noise = a
num_exploding = 0
repeats = 20
xx = {}
x = {}
for l in self.fit_mat.keys():
xx[l] = np.zeros((repeats, self.input_pcs.shape[0]))
if self.delay_model:
xx[l][:self.delay, :] = rnd[l].T
else:
xx[l][0, :] = rnd[l]
x[l] = np.zeros((self.int_length, self.input_pcs.shape[0]))
if self.delay_model:
x[l][:self.delay, :] = xx[l][:self.delay, :]
else:
x[l][0, :] = xx[l][0, :]
step0 = 0
if self.delay_model:
step = self.delay
else:
step = 1
blow_counter = 0
zz = {}
for n in range(repeats * int(np.ceil(self.int_length / repeats))):
for k in range(1, repeats):
if (self.delay_model
and k < self.delay) and step == self.delay:
continue
if blow_counter >= 10:
raise Exception("Model blowed up 10 times.")
if step >= self.int_length:
break
# prepare predictors
for l in self.fit_mat.keys():
zz[l] = xx[0][k - 1, :]
for lr in range(l):
zz[l] = np.r_[zz[l], xx[lr + 1][k - 1, :]]
for l in self.fit_mat.keys():
if l == 0:
if self.quad:
q = np.tril(np.outer(zz[l].T, zz[l]), -1)
quad_pred = q[np.nonzero(q)]
if self.delay_model:
zz[l] = np.tanh(self.kappa *
x[l][step - self.delay, :])
if self.harmonic_pred in ['all', 'first']:
if self.quad:
zz[l] = np.r_[quad_pred, zz[l],
zz[l] * self.xsin[step],
zz[l] * self.xcos[step],
self.xsin[step], self.xcos[step],
1]
else:
zz[l] = np.r_[zz[l], zz[l] * self.xsin[step],
zz[l] * self.xcos[step],
self.xsin[step], self.xcos[step],
1]
else:
if self.quad:
zz[l] = np.r_[quad_pred, zz[l], 1]
else:
zz[l] = np.r_[zz[l], 1]
else:
if self.harmonic_pred == 'all':
zz[l] = np.r_[zz[l], zz[l] * self.xsin[step],
zz[l] * self.xcos[step],
self.xsin[step], self.xcos[step], 1]
else:
zz[l] = np.r_[zz[l], 1]
if 'cond' in self.noise_type:
n_PCs = 1
n_samples = 100
if not self.combined:
ndx = np.argsort(
np.sum(np.power(
self.pcs[:, :n_PCs] - xx[k - 1, :n_PCs], 2),
axis=1))
Q = np.cov(self.last_level_res[ndx[:n_samples], :],
rowvar=0)
self.rr = np.linalg.cholesky(Q).T
elif self.combined:
ndx1 = np.argsort(
np.sum(np.power(
self.pcs[:, :n_PCs] - xx[k - 1, :n_PCs], 2),
axis=1))
ndx2 = np.argsort(
np.sum(np.power(
self.pcs[:, self.no_input_ts:self.no_input_ts +
n_PCs] -
xx[k - 1,
self.no_input_ts:self.no_input_ts + n_PCs],
2),
axis=1))
res1 = self.last_level_res[ndx1[:n_samples], :]
res2 = self.last_level_res[ndx2[:n_samples], :]
Q = np.cov(np.concatenate((res1, res2), axis=0),
rowvar=0)
self.rr = np.linalg.cholesky(Q).T
# integration step
for l in sorted(self.fit_mat, reverse=True):
if (l == self.no_levels - 1):
forcing = np.dot(
self.rr,
np.random.normal(0, self.sigma,
(self.rr.shape[0], )).T)
if 'seasonal' in self.noise_type:
forcing *= self.rr_last_std_ts[
step % self.rr_last_std_ts.shape[0], :]
else:
forcing = xx[l + 1][k, :]
xx[l][k, :] = xx[l][k - 1, :] + np.dot(
zz[l], self.fit_mat[l]) + forcing
# xx[l][k, :] = xx[l][k-1, :] + self.regressor.predict(zz[l]) + forcing
step += 1
# check if integration blows
if np.amax(np.abs(xx[0])) <= 2 * self.maxpc and not np.any(
np.isnan(xx[0])):
for l in self.fit_mat.keys():
x[l][step - repeats + 1:step, :] = xx[l][1:, :]
# set first to last
xx[l][0, :] = xx[l][-1, :]
else:
for l in self.fit_mat.keys():
if l == 0:
xx[l][0, :] = np.dot(
np.random.normal(0, self.sigma,
(self.input_pcs.shape[0], )),
self.diagpc)
else:
xx[l][0, :] = np.dot(
np.random.normal(0, self.sigma,
(self.input_pcs.shape[0], )),
self.diagres[l - 1])
if step != step0:
num_exploding += 1
step0 = step
step -= repeats + 1
blow_counter += 1
x = x[0].copy()
# center
x -= np.mean(x, axis=0)
# preserve total energy level
x *= np.sqrt(np.sum(self.varpc) / np.sum(np.var(x, axis=0, ddof=1)))
if self.diagnostics:
xm = np.mean(x, axis=0)
xv = np.var(x, axis=0, ddof=1)
xs = sts.skew(x, axis=0)
xk = sts.kurtosis(x, axis=0)
lc = np.zeros((2 * self.max_lag + 1, self.input_pcs.shape[0]))
kden = np.zeros((100, self.input_pcs.shape[0], 2))
for k in range(self.input_pcs.shape[0]):
lc[:, k] = cross_correlation(x[:, k],
x[:, k],
max_lag=self.max_lag)
kden[:, k,
0], kden[:, k,
1] = kdensity_estimate(x[:, k],
kernel='epanechnikov')
ict = np.sum(np.abs(lc), axis=0)
return i, x, num_exploding, xm, xv, xs, xk, lc, kden, ict
else:
return i, x, num_exploding
def integrate_model(self, n_realizations, int_length = None, noise_type = 'white', sigma = 1., n_workers = 3, diagnostics = True):
"""
Integrate trained model.
noise_type:
-- white - classic white noise, spatial correlation by cov. matrix of last level residuals
-- cond - find n_samples closest to the current space in subset of n_pcs and use their cov. matrix
-- seasonal - seasonal dependence of the residuals, fit n_harm harmonics of annual cycle, could also be used with cond.
except 'white', one can choose more settings like ['seasonal', 'cond']
"""
if self.verbose:
print("preparing to integrate model...")
pcs = self.input_pcs.copy()
pcs = pcs.T # time x dim
pcmax = np.amax(pcs, axis = 0)
pcmin = np.amin(pcs, axis = 0)
self.varpc = np.var(pcs, axis = 0, ddof = 1)
self.int_length = pcs.shape[0] if int_length is None else int_length
self.diagnostics = diagnostics
if self.harmonic_pred in ['all', 'first']:
if self.verbose:
print("...using harmonic predictors (with annual frequency)...")
self.xsin = np.sin(2*np.pi*np.arange(self.int_length) / 12.)
self.xcos = np.cos(2*np.pi*np.arange(self.int_length) / 12.)
if self.verbose:
print("...preparing noise forcing...")
self.sigma = sigma
if isinstance(noise_type, basestring):
if noise_type not in ['white', 'cond', 'seasonal']:
raise Exception("Unknown noise type to be used as forcing. Use 'white', 'cond', or 'seasonal'.")
elif isinstance(noise_type, list):
noise_type = frozenset(noise_type)
if not noise_type.issubset(set(['white', 'cond', 'seasonal'])):
raise Exception("Unknown noise type to be used as forcing. Use 'white', 'cond', or 'seasonal'.")
self.last_level_res = self.residuals[max(self.residuals.keys())]
self.noise_type = noise_type
if noise_type == 'white':
if self.verbose:
print("...using spatially correlated white noise...")
Q = np.cov(self.last_level_res, rowvar = 0)
self.rr = np.linalg.cholesky(Q).T
if 'seasonal' in noise_type:
n_harmonics = 5
if self.verbose:
print("...fitting %d harmonics to estimate seasonal modulation of last level's residual..." % n_harmonics)
if self.delay_model:
resid_delayed = self.last_level_res[-(self.last_level_res.shape[0]//12)*12:].copy()
rr_last = np.reshape(resid_delayed, (12, self.last_level_res.shape[0]//12, self.last_level_res.shape[1]), order = 'F')
else:
rr_last = np.reshape(self.last_level_res, (12, self.last_level_res.shape[0]//12, self.last_level_res.shape[1]), order = 'F')
rr_last_std = np.nanstd(rr_last, axis = 1, ddof = 1)
predictors = np.zeros((12, 2*n_harmonics + 1))
for nh in range(n_harmonics):
predictors[:, 2*nh] = np.cos(2*np.pi*(nh+1)*np.arange(12) / 12)
predictors[:, 2*nh+1] = np.sin(2*np.pi*(nh+1)*np.arange(12) / 12)
predictors[:, -1] = np.ones((12,))
bamp = np.zeros((predictors.shape[1], pcs.shape[1]))
for k in range(bamp.shape[1]):
bamp[:, k] = np.linalg.lstsq(predictors, rr_last_std[:, k])[0]
rr_last_std_ts = np.dot(predictors, bamp)
self.rr_last_std_ts = np.repeat(rr_last_std_ts, repeats = self.last_level_res.shape[0]//12, axis = 0)
if self.delay_model:
resid_delayed /= self.rr_last_std_ts
Q = np.cov(resid_delayed, rowvar = 0)
else:
self.last_level_res /= self.rr_last_std_ts
Q = np.cov(self.last_level_res, rowvar = 0)
self.rr = np.linalg.cholesky(Q).T
if diagnostics:
if self.verbose:
print("...running diagnostics for the data...")
# ACF, kernel density, integral corr. timescale for data
self.max_lag = 50
lag_cors = np.zeros((2*self.max_lag + 1, pcs.shape[1]))
kernel_densities = np.zeros((100, pcs.shape[1], 2))
for k in range(pcs.shape[1]):
lag_cors[:, k] = cross_correlation(pcs[:, k], pcs[:, k], max_lag = self.max_lag)
kernel_densities[:, k, 0], kernel_densities[:, k, 1] = kdensity_estimate(pcs[:, k], kernel = 'epanechnikov')
integral_corr_timescale = np.sum(np.abs(lag_cors), axis = 0)
# init for integrations
lag_cors_int = np.zeros([n_realizations] + list(lag_cors.shape))
kernel_densities_int = np.zeros([n_realizations] + list(kernel_densities.shape))
stat_moments_int = np.zeros((4, n_realizations, pcs.shape[1])) # mean, variance, skewness, kurtosis
int_corr_scale_int = np.zeros((n_realizations, pcs.shape[1]))
self.diagpc = np.diag(np.std(pcs, axis = 0, ddof = 1))
self.maxpc = np.amax(np.abs(pcs))
self.diagres = {}
self.maxres = {}
for l in self.residuals.keys():
self.diagres[l] = np.diag(np.std(self.residuals[l], axis = 0, ddof = 1))
self.maxres[l] = np.amax(np.abs(self.residuals[l]))
self.pcs = pcs
if n_workers > 1:
# from multiprocessing import Pool
from pathos.multiprocessing import ProcessingPool
pool = ProcessingPool(n_workers)
map_func = pool.amap
if self.verbose:
print("...running integration of %d realizations using %d workers..." % (n_realizations, n_workers))
else:
map_func = map
if self.verbose:
print("...running integration of %d realizations single threaded..." % n_realizations)
rnds = []
for n in range(n_realizations):
r = {}
for l in self.fit_mat.keys():
if l == 0:
if self.delay_model:
r[l] = np.dot(self.diagpc, np.random.normal(0, sigma, (pcs.shape[1], self.delay)))
else:
r[l] = np.dot(np.random.normal(0, sigma, (pcs.shape[1],)), self.diagpc)
else:
if self.delay_model:
r[l] = np.dot(self.diagres[l-1], np.random.normal(0, sigma, (pcs.shape[1], self.delay)))
else:
r[l] = np.dot(np.random.normal(0, sigma, (pcs.shape[1],)), self.diagres[l-1])
rnds.append(r)
args = [[i, rnd, noise_type] for i, rnd in zip(range(n_realizations), rnds)]
results = map_func(self._process_integration, args)
del args
if n_workers > 1:
pool.close()
self.integration_results = np.zeros((n_realizations, pcs.shape[1], self.int_length))
self.num_exploding = np.zeros((n_realizations,))
if n_workers > 1:
results = results.get()
if self.diagnostics:
# x, num_exploding, xm, xv, xs, xk, lc, kden, ict
for i, x, num_expl, xm, xv, xs, xk, lc, kden, ict in results:
self.integration_results[i, ...] = x.T
self.num_exploding[i] = num_expl
stat_moments_int[0, i, :] = xm
stat_moments_int[1, i, :] = xv
stat_moments_int[2, i, :] = xs
stat_moments_int[3, i, :] = xk
lag_cors_int[i, ...] = lc
kernel_densities_int[i, ...] = kden
int_corr_scale_int[i, ...] = ict
else:
for i, x, num_expl in results:
self.integration_results[i, ...] = x.T
self.num_exploding[i] = num_expl
if self.verbose:
print("...integration done, now saving results...")
if self.verbose:
print("...results saved to structure.")
print("there was %d expolding integration chunks in %d realizations." % (np.sum(self.num_exploding), n_realizations))
if self.diagnostics:
if self.verbose:
print("plotting diagnostics...")
import matplotlib.pyplot as plt
# plot all diagnostic stuff
## mean, variance, skewness, kurtosis, integral corr. time scale
t**s = ['MEAN', 'VARIANCE', 'SKEWNESS', 'KURTOSIS', 'INTEGRAL CORRELATION TIME SCALE']
plot = [np.mean(pcs, axis = 0), np.var(pcs, axis = 0, ddof = 1), sts.skew(pcs, axis = 0), sts.kurtosis(pcs, axis = 0), integral_corr_timescale]
xplot = np.arange(1, pcs.shape[1]+1)
for i, tit, p in zip(range(5), t**s, plot):
plt.figure()
plt.title(tit, size = 20)
plt.plot(xplot, p, linewidth = 3, color = '#3E3436')
if i < 4:
plt.plot(xplot, np.percentile(stat_moments_int[i, :, :], q = 2.5, axis = 0), '--', linewidth = 2.5, color = '#EA3E36')
plt.plot(xplot, np.percentile(stat_moments_int[i, :, :], q = 97.5, axis = 0), '--', linewidth = 2.5, color = '#EA3E36')
else:
plt.plot(xplot, np.percentile(int_corr_scale_int, q = 2.5, axis = 0), '--', linewidth = 2.5, color = '#EA3E36')
plt.plot(xplot, np.percentile(int_corr_scale_int, q = 97.5, axis = 0), '--', linewidth = 2.5, color = '#EA3E36')
plt.xlabel("# PC", size = 15)
plt.xlim([xplot[0], xplot[-1]])
plt.show()
plt.close()
## lagged correlations, PDF - plot first 9 PCs (or less if input number of pcs is < 9)
t**s = ['AUTOCORRELATION', 'PDF']
plot = [[lag_cors, lag_cors_int], [kernel_densities, kernel_densities_int]]
xlabs = ['LAG', '']
for i, tit, p, xlab in zip(range(2), t**s, plot, xlabs):
plt.figure()
plt.suptitle(tit, size = 25)
no_plts = 9 if self.no_input_ts > 9 else self.no_input_ts
for sub in range(0,no_plts):
plt.subplot(3, 3, sub+1)
if i == 0:
xplt = np.arange(0, self.max_lag+1)
plt.plot(xplt, p[0][p[0].shape[0]//2:, sub], linewidth = 3, color = '#3E3436')
plt.plot(xplt, np.percentile(p[1][:, p[0].shape[0]//2:, sub], q = 2.5, axis = 0), '--', linewidth = 2.5, color = '#EA3E36')
plt.plot(xplt, np.percentile(p[1][:, p[0].shape[0]//2:, sub], q = 97.5, axis = 0), '--', linewidth = 2.5, color = '#EA3E36')
plt.xlim([xplt[0], xplt[-1]])
else:
plt.plot(p[0][:, sub, 0], p[0][:, sub, 1], linewidth = 3, color = '#3E3436')
plt.plot(p[1][0, :, sub, 0], np.percentile(p[1][:, :, sub, 1], q = 2.5, axis = 0), '--', linewidth = 2.5, color = '#EA3E36')
plt.plot(p[1][0, :, sub, 0], np.percentile(p[1][:, :, sub, 1], q = 97.5, axis = 0), '--', linewidth = 2.5, color = '#EA3E36')
plt.xlim([p[0][0, sub, 0], p[0][-1, sub, 0]])
plt.xlabel(xlab, size = 15)
plt.title("PC %d" % (int(sub)+1), size = 20)
# plt.tight_layout()
plt.show()
plt.close()
def integrate_model(self,
n_realizations,
int_length=None,
noise_type='white',
sigma=1.,
n_workers=3,
diagnostics=True):
"""
Integrate trained model.
noise_type:
-- white - classic white noise, spatial correlation by cov. matrix of last level residuals
-- cond - find n_samples closest to the current space in subset of n_pcs and use their cov. matrix
-- seasonal - seasonal dependence of the residuals, fit n_harm harmonics of annual cycle, could also be used with cond.
except 'white', one can choose more settings like ['seasonal', 'cond']
"""
if self.verbose:
print("preparing to integrate model...")
pcs = self.input_pcs.copy()
pcs = pcs.T # time x dim
pcmax = np.amax(pcs, axis=0)
pcmin = np.amin(pcs, axis=0)
self.varpc = np.var(pcs, axis=0, ddof=1)
self.int_length = pcs.shape[0] if int_length is None else int_length
self.diagnostics = diagnostics
if self.harmonic_pred in ['all', 'first']:
if self.verbose:
print(
"...using harmonic predictors (with annual frequency)...")
self.xsin = np.sin(2 * np.pi * np.arange(self.int_length) / 12.)
self.xcos = np.cos(2 * np.pi * np.arange(self.int_length) / 12.)
if self.verbose:
print("...preparing noise forcing...")
self.sigma = sigma
if isinstance(noise_type, basestring):
if noise_type not in ['white', 'cond', 'seasonal']:
raise Exception(
"Unknown noise type to be used as forcing. Use 'white', 'cond', or 'seasonal'."
)
elif isinstance(noise_type, list):
noise_type = frozenset(noise_type)
if not noise_type.issubset(set(['white', 'cond', 'seasonal'])):
raise Exception(
"Unknown noise type to be used as forcing. Use 'white', 'cond', or 'seasonal'."
)
self.last_level_res = self.residuals[max(self.residuals.keys())]
self.noise_type = noise_type
if noise_type == 'white':
if self.verbose:
print("...using spatially correlated white noise...")
Q = np.cov(self.last_level_res, rowvar=0)
self.rr = np.linalg.cholesky(Q).T
if 'seasonal' in noise_type:
n_harmonics = 5
if self.verbose:
print(
"...fitting %d harmonics to estimate seasonal modulation of last level's residual..."
% n_harmonics)
if self.delay_model:
resid_delayed = self.last_level_res[-(
self.last_level_res.shape[0] // 12) * 12:].copy()
rr_last = np.reshape(resid_delayed,
(12, self.last_level_res.shape[0] // 12,
self.last_level_res.shape[1]),
order='F')
else:
rr_last = np.reshape(self.last_level_res,
(12, self.last_level_res.shape[0] // 12,
self.last_level_res.shape[1]),
order='F')
rr_last_std = np.nanstd(rr_last, axis=1, ddof=1)
predictors = np.zeros((12, 2 * n_harmonics + 1))
for nh in range(n_harmonics):
predictors[:, 2 * nh] = np.cos(2 * np.pi * (nh + 1) *
np.arange(12) / 12)
predictors[:, 2 * nh + 1] = np.sin(2 * np.pi * (nh + 1) *
np.arange(12) / 12)
predictors[:, -1] = np.ones((12, ))
bamp = np.zeros((predictors.shape[1], pcs.shape[1]))
for k in range(bamp.shape[1]):
bamp[:, k] = np.linalg.lstsq(predictors, rr_last_std[:, k])[0]
rr_last_std_ts = np.dot(predictors, bamp)
self.rr_last_std_ts = np.repeat(
rr_last_std_ts,
repeats=self.last_level_res.shape[0] // 12,
axis=0)
if self.delay_model:
resid_delayed /= self.rr_last_std_ts
Q = np.cov(resid_delayed, rowvar=0)
else:
self.last_level_res /= self.rr_last_std_ts
Q = np.cov(self.last_level_res, rowvar=0)
self.rr = np.linalg.cholesky(Q).T
if diagnostics:
if self.verbose:
print("...running diagnostics for the data...")
# ACF, kernel density, integral corr. timescale for data
self.max_lag = 50
lag_cors = np.zeros((2 * self.max_lag + 1, pcs.shape[1]))
kernel_densities = np.zeros((100, pcs.shape[1], 2))
for k in range(pcs.shape[1]):
lag_cors[:, k] = cross_correlation(pcs[:, k],
pcs[:, k],
max_lag=self.max_lag)
kernel_densities[:, k,
0], kernel_densities[:, k,
1] = kdensity_estimate(
pcs[:, k],
kernel='epanechnikov'
)
integral_corr_timescale = np.sum(np.abs(lag_cors), axis=0)
# init for integrations
lag_cors_int = np.zeros([n_realizations] + list(lag_cors.shape))
kernel_densities_int = np.zeros([n_realizations] +
list(kernel_densities.shape))
stat_moments_int = np.zeros(
(4, n_realizations,
pcs.shape[1])) # mean, variance, skewness, kurtosis
int_corr_scale_int = np.zeros((n_realizations, pcs.shape[1]))
self.diagpc = np.diag(np.std(pcs, axis=0, ddof=1))
self.maxpc = np.amax(np.abs(pcs))
self.diagres = {}
self.maxres = {}
for l in self.residuals.keys():
self.diagres[l] = np.diag(np.std(self.residuals[l], axis=0,
ddof=1))
self.maxres[l] = np.amax(np.abs(self.residuals[l]))
self.pcs = pcs
if n_workers > 1:
# from multiprocessing import Pool
from pathos.multiprocessing import ProcessingPool
pool = ProcessingPool(n_workers)
map_func = pool.amap
if self.verbose:
print(
"...running integration of %d realizations using %d workers..."
% (n_realizations, n_workers))
else:
map_func = map
if self.verbose:
print(
"...running integration of %d realizations single threaded..."
% n_realizations)
rnds = []
for n in range(n_realizations):
r = {}
for l in self.fit_mat.keys():
if l == 0:
if self.delay_model:
r[l] = np.dot(
self.diagpc,
np.random.normal(0, sigma,
(pcs.shape[1], self.delay)))
else:
r[l] = np.dot(
np.random.normal(0, sigma, (pcs.shape[1], )),
self.diagpc)
else:
if self.delay_model:
r[l] = np.dot(
self.diagres[l - 1],
np.random.normal(0, sigma,
(pcs.shape[1], self.delay)))
else:
r[l] = np.dot(
np.random.normal(0, sigma, (pcs.shape[1], )),
self.diagres[l - 1])
rnds.append(r)
args = [[i, rnd, noise_type]
for i, rnd in zip(range(n_realizations), rnds)]
results = map_func(self._process_integration, args)
del args
if n_workers > 1:
pool.close()
self.integration_results = np.zeros(
(n_realizations, pcs.shape[1], self.int_length))
self.num_exploding = np.zeros((n_realizations, ))
if n_workers > 1:
results = results.get()
if self.diagnostics:
# x, num_exploding, xm, xv, xs, xk, lc, kden, ict
for i, x, num_expl, xm, xv, xs, xk, lc, kden, ict in results:
self.integration_results[i, ...] = x.T
self.num_exploding[i] = num_expl
stat_moments_int[0, i, :] = xm
stat_moments_int[1, i, :] = xv
stat_moments_int[2, i, :] = xs
stat_moments_int[3, i, :] = xk
lag_cors_int[i, ...] = lc
kernel_densities_int[i, ...] = kden
int_corr_scale_int[i, ...] = ict
else:
for i, x, num_expl in results:
self.integration_results[i, ...] = x.T
self.num_exploding[i] = num_expl
if self.verbose:
print("...integration done, now saving results...")
if self.verbose:
print("...results saved to structure.")
print(
"there was %d expolding integration chunks in %d realizations."
% (np.sum(self.num_exploding), n_realizations))
if self.diagnostics:
if self.verbose:
print("plotting diagnostics...")
import matplotlib.pyplot as plt
# plot all diagnostic stuff
## mean, variance, skewness, kurtosis, integral corr. time scale
t**s = [
'MEAN', 'VARIANCE', 'SKEWNESS', 'KURTOSIS',
'INTEGRAL CORRELATION TIME SCALE'
]
plot = [
np.mean(pcs, axis=0),
np.var(pcs, axis=0, ddof=1),
sts.skew(pcs, axis=0),
sts.kurtosis(pcs, axis=0), integral_corr_timescale
]
xplot = np.arange(1, pcs.shape[1] + 1)
for i, tit, p in zip(range(5), t**s, plot):
plt.figure()
plt.title(tit, size=20)
plt.plot(xplot, p, linewidth=3, color='#3E3436')
if i < 4:
plt.plot(xplot,
np.percentile(stat_moments_int[i, :, :],
q=2.5,
axis=0),
'--',
linewidth=2.5,
color='#EA3E36')
plt.plot(xplot,
np.percentile(stat_moments_int[i, :, :],
q=97.5,
axis=0),
'--',
linewidth=2.5,
color='#EA3E36')
else:
plt.plot(xplot,
np.percentile(int_corr_scale_int, q=2.5, axis=0),
'--',
linewidth=2.5,
color='#EA3E36')
plt.plot(xplot,
np.percentile(int_corr_scale_int, q=97.5, axis=0),
'--',
linewidth=2.5,
color='#EA3E36')
plt.xlabel("# PC", size=15)
plt.xlim([xplot[0], xplot[-1]])
plt.show()
plt.close()
## lagged correlations, PDF - plot first 9 PCs (or less if input number of pcs is < 9)
t**s = ['AUTOCORRELATION', 'PDF']
plot = [[lag_cors, lag_cors_int],
[kernel_densities, kernel_densities_int]]
xlabs = ['LAG', '']
for i, tit, p, xlab in zip(range(2), t**s, plot, xlabs):
plt.figure()
plt.suptitle(tit, size=25)
no_plts = 9 if self.no_input_ts > 9 else self.no_input_ts
for sub in range(0, no_plts):
plt.subplot(3, 3, sub + 1)
if i == 0:
xplt = np.arange(0, self.max_lag + 1)
plt.plot(xplt,
p[0][p[0].shape[0] // 2:, sub],
linewidth=3,
color='#3E3436')
plt.plot(xplt,
np.percentile(p[1][:, p[0].shape[0] // 2:,
sub],
q=2.5,
axis=0),
'--',
linewidth=2.5,
color='#EA3E36')
plt.plot(xplt,
np.percentile(p[1][:, p[0].shape[0] // 2:,
sub],
q=97.5,
axis=0),
'--',
linewidth=2.5,
color='#EA3E36')
plt.xlim([xplt[0], xplt[-1]])
else:
plt.plot(p[0][:, sub, 0],
p[0][:, sub, 1],
linewidth=3,
color='#3E3436')
plt.plot(p[1][0, :, sub, 0],
np.percentile(p[1][:, :, sub, 1],
q=2.5,
axis=0),
'--',
linewidth=2.5,
color='#EA3E36')
plt.plot(p[1][0, :, sub, 0],
np.percentile(p[1][:, :, sub, 1],
q=97.5,
axis=0),
'--',
linewidth=2.5,
color='#EA3E36')
plt.xlim([p[0][0, sub, 0], p[0][-1, sub, 0]])
plt.xlabel(xlab, size=15)
plt.title("PC %d" % (int(sub) + 1), size=20)
# plt.tight_layout()
plt.show()
plt.close()