# construct a test system
S = np.zeros(shape = (20, 50), dtype = np.int32)
S[10:18, 25:45] = 1
S[0:3, 6:12] = 2
S[8:15, 2:12] = 3
v, Sr = constructVAR(S, [0.0, 0.4, 0.8, 0.7], [-0.5, 0.5], [0.0, 0.0])
# v, Sr = constructVAR(S, [0.0, 0.001, 0.01], [-0.1, 0.1], [0.00, 0.00], [0.01, 0.01])
ts = v.simulate(200)
gf = make_model_geofield(S, ts)
# initialize a parallel pool
pool = Pool(POOL_SIZE)
# replace field with surrogate field
sgf = SurrGeoFieldAR()
sgf.copy_field(gf)
sgf.prepare_surrogates(pool)
sgf.construct_surrogate_with_noise()
gf = sgf
gf.d = gf.surr_data().copy()
# # construct "components" from the structural matrix
Uopt = np.zeros((len(Sr), np.amax(Sr)))
for i in range(Uopt.shape[1]):
Uopt[:,i] = np.where(Sr == (i+1), 1.0, 0.0)
# remove the first element (it's the driver which is not included in the optimal component)
Uopt[np.nonzero(Uopt[:,i])[0][0],i] = 0.0
Uopt[:,i] /= np.sum(Uopt[:,i]**2) ** 0.5
print("Analyzing data ...")
from datetime import datetime, date
from surr_geo_field_ar import SurrGeoFieldAR
from geo_field import GeoField
from multiprocessing import Pool
# load netCDF SLP field
d = GeoField()
d.load("/home/martin/Work/Geo/data/netcdf/pres.mon.mean.nc", 'pres')
d.slice_date_range(date(1948, 1, 1), date(2012, 1, 1))
#d.slice_months([12, 1, 2])
d.slice_spatial(None, [-89, 89])
# copy into surrogate field
sd = SurrGeoFieldAR()
sd.copy_field(d)
# create the Pool
pool = Pool(4)
t1 = datetime.now()
sd.prepare_surrogates(pool)
print("Prep: elapsed time %s" % str(datetime.now() - t1))
t1 = datetime.now()
sd.construct_surrogate()
print("Gen: elapsed time %s" % str(datetime.now() - t1))
t1 = datetime.now()
sd.construct_surrogate()
print("Gen: elapsed time %s" % str(datetime.now() - t1))
# construct the testing model from a spec
S = np.zeros(shape=(20, 50), dtype=np.int32)
S[10:18, 25:45] = 1
S[0:3, 6:12] = 2
v, Sr = constructVAR(S, [0.0, 0.8, 0.8], [-0.1, 0.1], [0.0, 0.0])
#v, Sr = constructVAR2(S, [-0.2, 0.2], [0.0, 0.9, 0.9], 0.8)
#S = np.zeros(shape = (5, 10), dtype = np.int32)
#S[1:4, 0:2] = 1
#S[0:3, 6:9] = 2v, Sr = constructVAR(S, [0.0, 0.191, 0.120], [-0.1, 0.1], [0.00, 0.00], [0.01, 0.01])
ts = v.simulate(768)
gf = make_model_geofield(S, ts)
sgf = SurrGeoFieldAR()
sgf.copy_field(gf)
sgf.prepare_surrogates()
sgf.construct_surrogate_with_noise()
ts2 = sgf.surr_data()
plt.figure(figsize=(8, 8))
plt.imshow(S, interpolation='nearest')
plt.title('Structural matrix')
plt.figure()
plt.imshow(v.A, interpolation='nearest')
plt.colorbar()
plt.title('AR structural')
plt.figure()
plt.plot(ts)
S[8:15, 2:12] = 3
v, Sr = constructVAR(S, [0.0, 0.6, 0.9, 0.7], [0.3, 0.5], [0.0, 0.0])
ts = v.simulate(200)
gf = make_model_geofield(S, ts)
# initialize a parallel pool
pool = Pool(POOL_SIZE)
# compute the eigenvalues/eigenvectos of the covariance matrix of
Ud, dlam, _ = pca_components_gf(gf.data())
drdims = np.zeros((NUM_EIGS, ))
for i in range(NUM_EIGS):
drdims[i] = dlam[i] / np.sum(dlam[i:]**2)**0.5
sd = SurrGeoFieldAR([0, 30], 'sbc')
sd.copy_field(gf)
sd.prepare_surrogates(pool)
srdims = np.zeros((NUM_SURR, NUM_EIGS))
# generate and compute eigenvalues for 20000 surrogates
t1 = datetime.now()
# construct the surrogates in parallel
# we can duplicate the list here without worry as it will be copied into new python processes
# thus creating separate copies of sd
print("Running parallel generation of surrogates and SVD")
slam_list = pool.map(compute_surrogate_cov_eigvals, [Ud] * NUM_SURR)
# rearrange into numpy array (can I use vstack for this?)
for i in range(len(slam_list)):
srdims[i, :] = slam_list[i]
from datetime import datetime, date
from surr_geo_field_ar import SurrGeoFieldAR
from geo_field import GeoField
from multiprocessing import Pool
# load netCDF SLP field
d = GeoField()
d.load("/home/martin/Work/Geo/data/netcdf/pres.mon.mean.nc", 'pres')
d.slice_date_range(date(1948, 1, 1), date(2012, 1, 1))
#d.slice_months([12, 1, 2])
d.slice_spatial(None, [-89, 89])
# copy into surrogate field
sd = SurrGeoFieldAR()
sd.copy_field(d)
# create the Pool
pool = Pool(4)
t1 = datetime.now()
sd.prepare_surrogates(pool)
print("Prep: elapsed time %s" % str(datetime.now() - t1))
t1 = datetime.now()
sd.construct_surrogate()
print("Gen: elapsed time %s" % str(datetime.now() - t1))
t1 = datetime.now()
sd.construct_surrogate()
print("Gen: elapsed time %s" % str(datetime.now() - t1))
S[8:15, 2:12] = 3
v, Sr = constructVAR(S, [0.0, 0.6, 0.9, 0.7], [0.3, 0.5], [0.0, 0.0])
ts = v.simulate(200)
gf = make_model_geofield(S, ts)
# initialize a parallel pool
pool = Pool(POOL_SIZE)
# compute the eigenvalues/eigenvectos of the covariance matrix of
Ud, dlam, _ = pca_components_gf(gf.data())
drdims = np.zeros((NUM_EIGS,))
for i in range(NUM_EIGS):
drdims[i] = dlam[i] / np.sum(dlam[i:]**2)**0.5
sd = SurrGeoFieldAR([0, 30], 'sbc')
sd.copy_field(gf)
sd.prepare_surrogates(pool)
srdims = np.zeros((NUM_SURR, NUM_EIGS))
# generate and compute eigenvalues for 20000 surrogates
t1 = datetime.now()
# construct the surrogates in parallel
# we can duplicate the list here without worry as it will be copied into new python processes
# thus creating separate copies of sd
print("Running parallel generation of surrogates and SVD")
slam_list = pool.map(compute_surrogate_cov_eigvals, [Ud] * NUM_SURR)
# rearrange into numpy array (can I use vstack for this?)
for i in range(len(slam_list)):
srdims[i, :] = slam_list[i]
