def joint_gauss_model(self, n=1, no=3):
"""
This function models the functional data using a joint Gaussian model
extracted from the principal components of the srsfs
:param n: number of random samples
:param no: number of principal components (default = 3)
:type n: integer
:type no: integer
"""
# Parameters
fn = self.fn
time = self.time
qn = self.qn
gam = self.gam
M = time.size
# Perform PCA
jfpca = fpca.fdajpca(self)
jfpca.calc_fpca(no=no)
s = jfpca.latent
U = jfpca.U
C = jfpca.C
mu_psi = jfpca.mu_psi
# compute mean and covariance
mq_new = qn.mean(axis=1)
mididx = jfpca.id
m_new = np.sign(fn[mididx, :]) * np.sqrt(np.abs(fn[mididx, :]))
mqn = np.append(mq_new, m_new.mean())
# generate random samples
vals = np.random.multivariate_normal(np.zeros(s.shape), np.diag(s), n)
tmp = np.matmul(U, np.transpose(vals))
qhat = np.tile(mqn.T, (n, 1)).T + tmp[0:M + 1, :]
tmp = np.matmul(U, np.transpose(vals) / C)
vechat = tmp[(M + 1):, :]
psihat = np.zeros((M, n))
gamhat = np.zeros((M, n))
for ii in range(n):
psihat[:, ii] = geo.exp_map(mu_psi, vechat[:, ii])
gam_tmp = cumtrapz(psihat[:, ii]**2,
np.linspace(0, 1, M),
initial=0.0)
gamhat[:, ii] = (gam_tmp - gam_tmp.min()) / (gam_tmp.max() -
gam_tmp.min())
ft = np.zeros((M, n))
fhat = np.zeros((M, n))
for ii in range(n):
fhat[:, ii] = uf.cumtrapzmid(
time, qhat[0:M, ii] * np.fabs(qhat[0:M, ii]),
np.sign(qhat[M, ii]) * (qhat[M, ii] * qhat[M, ii]), mididx)
ft[:, ii] = uf.warp_f_gamma(np.linspace(0, 1, M), fhat[:, ii],
gamhat[:, ii])
self.rsamps = True
self.fs = fhat
self.gams = gamhat
self.ft = ft
self.qs = qhat[0:M, :]
return
def align_fPCA(f, time, num_comp=3, showplot=True, smoothdata=False, cores=-1):
"""
aligns a collection of functions while extracting principal components.
The functions are aligned to the principal components
:param f: numpy ndarray of shape (M,N) of N functions with M samples
:param time: vector of size M describing the sample points
:param num_comp: number of fPCA components
:param showplot: Shows plots of results using matplotlib (default = T)
:param smooth_data: Smooth the data using a box filter (default = F)
:param cores: number of cores for parallel (default = -1 (all))
:type sparam: double
:type smooth_data: bool
:type f: np.ndarray
:type time: np.ndarray
:rtype: tuple of numpy array
:return fn: aligned functions - numpy ndarray of shape (M,N) of N
functions with M samples
:return qn: aligned srvfs - similar structure to fn
:return q0: original srvf - similar structure to fn
:return mqn: srvf mean or median - vector of length M
:return gam: warping functions - similar structure to fn
:return q_pca: srsf principal directions
:return f_pca: functional principal directions
:return latent: latent values
:return coef: coefficients
:return U: eigenvectors
:return orig_var: Original Variance of Functions
:return amp_var: Amplitude Variance
:return phase_var: Phase Variance
"""
lam = 0.0
MaxItr = 50
coef = np.arange(-2., 3.)
Nstd = coef.shape[0]
M = f.shape[0]
N = f.shape[1]
if M > 500:
parallel = True
elif N > 100:
parallel = True
else:
parallel = False
eps = np.finfo(np.double).eps
f0 = f
if showplot:
plot.f_plot(time, f, title="Original Data")
# Compute SRSF function from data
f, g, g2 = uf.gradient_spline(time, f, smoothdata)
q = g / np.sqrt(abs(g) + eps)
print("Initializing...")
mnq = q.mean(axis=1)
a = mnq.repeat(N)
d1 = a.reshape(M, N)
d = (q - d1)**2
dqq = np.sqrt(d.sum(axis=0))
min_ind = dqq.argmin()
print("Aligning %d functions in SRVF space to %d fPCA components..." %
(N, num_comp))
itr = 0
mq = np.zeros((M, MaxItr + 1))
mq[:, itr] = q[:, min_ind]
fi = np.zeros((M, N, MaxItr + 1))
fi[:, :, 0] = f
qi = np.zeros((M, N, MaxItr + 1))
qi[:, :, 0] = q
gam = np.zeros((M, N, MaxItr + 1))
cost = np.zeros(MaxItr + 1)
while itr < MaxItr:
print("updating step: r=%d" % (itr + 1))
if itr == MaxItr:
print("maximal number of iterations is reached")
# PCA Step
a = mq[:, itr].repeat(N)
d1 = a.reshape(M, N)
qhat_cent = qi[:, :, itr] - d1
K = np.cov(qi[:, :, itr])
U, s, V = svd(K)
alpha_i = np.zeros((num_comp, N))
for ii in range(0, num_comp):
for jj in range(0, N):
alpha_i[ii, jj] = trapz(qhat_cent[:, jj] * U[:, ii], time)
U1 = U[:, 0:num_comp]
tmp = U1.dot(alpha_i)
qhat = d1 + tmp
# Matching Step
if parallel:
out = Parallel(n_jobs=cores)(
delayed(uf.optimum_reparam)(qhat[:,
n], time, qi[:, n,
itr], "DP", lam)
for n in range(N))
gam_t = np.array(out)
gam[:, :, itr] = gam_t.transpose()
else:
gam[:, :, itr] = uf.optimum_reparam(qhat, time, qi[:, :, itr],
"DP", lam)
for k in range(0, N):
time0 = (time[-1] - time[0]) * gam[:, k, itr] + time[0]
fi[:, k, itr + 1] = np.interp(time0, time, fi[:, k, itr])
qi[:, k, itr + 1] = uf.f_to_srsf(fi[:, k, itr + 1], time)
qtemp = qi[:, :, itr + 1]
mq[:, itr + 1] = qtemp.mean(axis=1)
cost_temp = np.zeros(N)
for ii in range(0, N):
cost_temp[ii] = norm(qtemp[:, ii] - qhat[:, ii])**2
cost[itr + 1] = cost_temp.mean()
if abs(cost[itr + 1] - cost[itr]) < 1e-06:
break
itr += 1
if itr >= MaxItr:
itrf = MaxItr
else:
itrf = itr + 1
cost = cost[1:(itrf + 1)]
# Aligned data & stats
fn = fi[:, :, itrf]
qn = qi[:, :, itrf]
q0 = qi[:, :, 0]
mean_f0 = f0.mean(axis=1)
std_f0 = f0.std(axis=1)
mqn = mq[:, itrf]
gamf = gam[:, :, 0]
for k in range(1, itr):
gam_k = gam[:, :, k]
for l in range(0, N):
time0 = (time[-1] - time[0]) * gam_k[:, l] + time[0]
gamf[:, l] = np.interp(time0, time, gamf[:, l])
# Center Mean
gamI = uf.SqrtMeanInverse(gamf)
gamI_dev = np.gradient(gamI, 1 / float(M - 1))
time0 = (time[-1] - time[0]) * gamI + time[0]
mqn = np.interp(time0, time, mqn) * np.sqrt(gamI_dev)
for k in range(0, N):
qn[:, k] = np.interp(time0, time, qn[:, k]) * np.sqrt(gamI_dev)
fn[:, k] = np.interp(time0, time, fn[:, k])
gamf[:, k] = np.interp(time0, time, gamf[:, k])
mean_fn = fn.mean(axis=1)
std_fn = fn.std(axis=1)
# Get Final PCA
mididx = int(np.round(time.shape[0] / 2))
m_new = np.sign(fn[mididx, :]) * np.sqrt(np.abs(fn[mididx, :]))
mqn2 = np.append(mqn, m_new.mean())
qn2 = np.vstack((qn, m_new))
K = np.cov(qn2)
U, s, V = svd(K)
stdS = np.sqrt(s)
# compute the PCA in the q domain
q_pca = np.ndarray(shape=(M + 1, Nstd, num_comp), dtype=float)
for k in range(0, num_comp):
for l in range(0, Nstd):
q_pca[:, l, k] = mqn2 + coef[l] * stdS[k] * U[:, k]
# compute the correspondence in the f domain
f_pca = np.ndarray(shape=(M, Nstd, num_comp), dtype=float)
for k in range(0, num_comp):
for l in range(0, Nstd):
q_pca_tmp = q_pca[0:M, l, k] * np.abs(q_pca[0:M, l, k])
q_pca_tmp2 = np.sign(q_pca[M, l, k]) * (q_pca[M, l, k]**2)
f_pca[:, l, k] = uf.cumtrapzmid(time, q_pca_tmp, q_pca_tmp2,
np.floor(time.shape[0] / 2),
mididx)
N2 = qn.shape[1]
c = np.zeros((N2, num_comp))
for k in range(0, num_comp):
for l in range(0, N2):
c[l, k] = sum((np.append(qn[:, l], m_new[l]) - mqn2) * U[:, k])
if showplot:
CBcdict = {
'Bl': (0, 0, 0),
'Or': (.9, .6, 0),
'SB': (.35, .7, .9),
'bG': (0, .6, .5),
'Ye': (.95, .9, .25),
'Bu': (0, .45, .7),
'Ve': (.8, .4, 0),
'rP': (.8, .6, .7),
}
cl = sorted(CBcdict.keys())
# Align Plots
fig, ax = plot.f_plot(np.arange(0, M) / float(M - 1),
gamf,
title="Warping Functions")
ax.set_aspect('equal')
plot.f_plot(time, fn, title="Warped Data")
tmp = np.array([mean_f0, mean_f0 + std_f0, mean_f0 - std_f0])
tmp = tmp.transpose()
plot.f_plot(time, tmp, title=r"Original Data: Mean $\pm$ STD")
tmp = np.array([mean_fn, mean_fn + std_fn, mean_fn - std_fn])
tmp = tmp.transpose()
plot.f_plot(time, tmp, title=r"Warped Data: Mean $\pm$ STD")
# PCA Plots
fig, ax = plt.subplots(2, num_comp)
for k in range(0, num_comp):
axt = ax[0, k]
for l in range(0, Nstd):
axt.plot(time, q_pca[0:M, l, k], color=CBcdict[cl[l]])
axt.hold(True)
axt.set_title('q domain: PD %d' % (k + 1))
plot.rstyle(axt)
axt = ax[1, k]
for l in range(0, Nstd):
axt.plot(time, f_pca[:, l, k], color=CBcdict[cl[l]])
axt.hold(True)
axt.set_title('f domain: PD %d' % (k + 1))
plot.rstyle(axt)
fig.set_tight_layout(True)
cumm_coef = 100 * np.cumsum(s) / sum(s)
idx = np.arange(0, M + 1) + 1
plot.f_plot(idx, cumm_coef, "Coefficient Cumulative Percentage")
plt.xlabel("Percentage")
plt.ylabel("Index")
plt.show()
mean_f0 = f0.mean(axis=1)
std_f0 = f0.std(axis=1)
mean_fn = fn.mean(axis=1)
std_fn = fn.std(axis=1)
tmp = np.zeros(M)
tmp[1:] = cumtrapz(mqn * np.abs(mqn), time)
fmean = np.mean(f0[1, :]) + tmp
fgam = np.zeros((M, N))
for k in range(0, N):
time0 = (time[-1] - time[0]) * gamf[:, k] + time[0]
fgam[:, k] = np.interp(time0, time, fmean)
var_fgam = fgam.var(axis=1)
orig_var = trapz(std_f0**2, time)
amp_var = trapz(std_fn**2, time)
phase_var = trapz(var_fgam, time)
K = np.cov(fn)
U, s, V = svd(K)
align_fPCAresults = collections.namedtuple('align_fPCA', [
'fn', 'qn', 'q0', 'mqn', 'gam', 'q_pca', 'f_pca', 'latent', 'coef',
'U', 'orig_var', 'amp_var', 'phase_var', 'cost'
])
out = align_fPCAresults(fn, qn, q0, mqn, gamf, q_pca, f_pca, s, c, U,
orig_var, amp_var, phase_var, cost)
return out
def align_fPCA(f, time, num_comp=3, showplot=True, smoothdata=False):
"""
aligns a collection of functions while extracting principal components.
The functions are aligned to the principal components
:param f: numpy ndarray of shape (M,N) of N functions with M samples
:param time: vector of size M describing the sample points
:param num_comp: number of fPCA components
:param showplot: Shows plots of results using matplotlib (default = T)
:param smooth_data: Smooth the data using a box filter (default = F)
:param sparam: Number of times to run box filter (default = 25)
:type sparam: double
:type smooth_data: bool
:type f: np.ndarray
:type time: np.ndarray
:rtype: tuple of numpy array
:return fn: aligned functions - numpy ndarray of shape (M,N) of N
functions with M samples
:return qn: aligned srvfs - similar structure to fn
:return q0: original srvf - similar structure to fn
:return mqn: srvf mean or median - vector of length M
:return gam: warping functions - similar structure to fn
:return q_pca: srsf principal directions
:return f_pca: functional principal directions
:return latent: latent values
:return coef: coefficients
:return U: eigenvectors
:return orig_var: Original Variance of Functions
:return amp_var: Amplitude Variance
:return phase_var: Phase Variance
"""
lam = 0.0
MaxItr = 50
coef = np.arange(-2., 3.)
Nstd = coef.shape[0]
M = f.shape[0]
N = f.shape[1]
if M > 500:
parallel = True
elif N > 100:
parallel = True
else:
parallel = False
eps = np.finfo(np.double).eps
f0 = f
if showplot:
plot.f_plot(time, f, title="Original Data")
# Compute SRSF function from data
f, g, g2 = uf.gradient_spline(time, f, smoothdata)
q = g / np.sqrt(abs(g) + eps)
print ("Initializing...")
mnq = q.mean(axis=1)
a = mnq.repeat(N)
d1 = a.reshape(M, N)
d = (q - d1) ** 2
dqq = np.sqrt(d.sum(axis=0))
min_ind = dqq.argmin()
print("Aligning %d functions in SRVF space to %d fPCA components..."
% (N, num_comp))
itr = 0
mq = np.zeros((M, MaxItr + 1))
mq[:, itr] = q[:, min_ind]
fi = np.zeros((M, N, MaxItr + 1))
fi[:, :, 0] = f
qi = np.zeros((M, N, MaxItr + 1))
qi[:, :, 0] = q
gam = np.zeros((M, N, MaxItr + 1))
cost = np.zeros(MaxItr + 1)
while itr < MaxItr:
print("updating step: r=%d" % (itr + 1))
if itr == MaxItr:
print("maximal number of iterations is reached")
# PCA Step
a = mq[:, itr].repeat(N)
d1 = a.reshape(M, N)
qhat_cent = qi[:, :, itr] - d1
K = np.cov(qi[:, :, itr])
U, s, V = svd(K)
alpha_i = np.zeros((num_comp, N))
for ii in range(0, num_comp):
for jj in range(0, N):
alpha_i[ii, jj] = trapz(qhat_cent[:, jj] * U[:, ii], time)
U1 = U[:, 0:num_comp]
tmp = U1.dot(alpha_i)
qhat = d1 + tmp
# Matching Step
if parallel:
out = Parallel(n_jobs=-1)(
delayed(uf.optimum_reparam)(qhat[:, n], time, qi[:, n, itr],
lam) for n in range(N))
gam_t = np.array(out)
gam[:, :, itr] = gam_t.transpose()
else:
gam[:, :, itr] = uf.optimum_reparam(qhat, time, qi[:, :, itr], lam)
for k in range(0, N):
time0 = (time[-1] - time[0]) * gam[:, k, itr] + time[0]
fi[:, k, itr + 1] = np.interp(time0, time, fi[:, k, itr])
qi[:, k, itr + 1] = uf.f_to_srsf(fi[:, k, itr + 1], time)
qtemp = qi[:, :, itr + 1]
mq[:, itr + 1] = qtemp.mean(axis=1)
cost_temp = np.zeros(N)
for ii in range(0, N):
cost_temp[ii] = norm(qtemp[:, ii] - qhat[:, ii]) ** 2
cost[itr + 1] = cost_temp.mean()
if abs(cost[itr + 1] - cost[itr]) < 1e-06:
break
itr += 1
if itr >= MaxItr:
itrf = MaxItr
else:
itrf = itr+1
cost = cost[1:(itrf+1)]
# Aligned data & stats
fn = fi[:, :, itrf]
qn = qi[:, :, itrf]
q0 = qi[:, :, 0]
mean_f0 = f0.mean(axis=1)
std_f0 = f0.std(axis=1)
mqn = mq[:, itrf]
gamf = gam[:, :, 0]
for k in range(1, itr):
gam_k = gam[:, :, k]
for l in range(0, N):
time0 = (time[-1] - time[0]) * gam_k[:, l] + time[0]
gamf[:, l] = np.interp(time0, time, gamf[:, l])
# Center Mean
gamI = uf.SqrtMeanInverse(gamf)
gamI_dev = np.gradient(gamI, 1 / float(M - 1))
time0 = (time[-1] - time[0]) * gamI + time[0]
mqn = np.interp(time0, time, mqn) * np.sqrt(gamI_dev)
for k in range(0, N):
qn[:, k] = np.interp(time0, time, qn[:, k]) * np.sqrt(gamI_dev)
fn[:, k] = np.interp(time0, time, fn[:, k])
gamf[:, k] = np.interp(time0, time, gamf[:, k])
mean_fn = fn.mean(axis=1)
std_fn = fn.std(axis=1)
# Get Final PCA
mididx = np.round(time.shape[0] / 2)
m_new = np.sign(fn[mididx, :]) * np.sqrt(np.abs(fn[mididx, :]))
mqn2 = np.append(mqn, m_new.mean())
qn2 = np.vstack((qn, m_new))
K = np.cov(qn2)
U, s, V = svd(K)
stdS = np.sqrt(s)
# compute the PCA in the q domain
q_pca = np.ndarray(shape=(M + 1, Nstd, num_comp), dtype=float)
for k in range(0, num_comp):
for l in range(0, Nstd):
q_pca[:, l, k] = mqn2 + coef[l] * stdS[k] * U[:, k]
# compute the correspondence in the f domain
f_pca = np.ndarray(shape=(M, Nstd, num_comp), dtype=float)
for k in range(0, num_comp):
for l in range(0, Nstd):
q_pca_tmp = q_pca[0:M, l, k] * np.abs(q_pca[0:M, l, k])
q_pca_tmp2 = np.sign(q_pca[M, l, k]) * (q_pca[M, l, k] ** 2)
f_pca[:, l, k] = uf.cumtrapzmid(time, q_pca_tmp, q_pca_tmp2)
N2 = qn.shape[1]
c = np.zeros((N2, num_comp))
for k in range(0, num_comp):
for l in range(0, N2):
c[l, k] = sum((np.append(qn[:, l], m_new[l]) - mqn2) * U[:, k])
if showplot:
CBcdict = {
'Bl': (0, 0, 0),
'Or': (.9, .6, 0),
'SB': (.35, .7, .9),
'bG': (0, .6, .5),
'Ye': (.95, .9, .25),
'Bu': (0, .45, .7),
'Ve': (.8, .4, 0),
'rP': (.8, .6, .7),
}
cl = sorted(CBcdict.keys())
# Align Plots
fig, ax = plot.f_plot(np.arange(0, M) / float(M - 1), gamf,
title="Warping Functions")
ax.set_aspect('equal')
plot.f_plot(time, fn, title="Warped Data")
tmp = np.array([mean_f0, mean_f0 + std_f0, mean_f0 - std_f0])
tmp = tmp.transpose()
plot.f_plot(time, tmp, title="Original Data: Mean $\pm$ STD")
tmp = np.array([mean_fn, mean_fn + std_fn, mean_fn - std_fn])
tmp = tmp.transpose()
plot.f_plot(time, tmp, title="Warped Data: Mean $\pm$ STD")
# PCA Plots
fig, ax = plt.subplots(2, num_comp)
for k in range(0, num_comp):
axt = ax[0, k]
for l in range(0, Nstd):
axt.plot(time, q_pca[0:M, l, k], color=CBcdict[cl[l]])
axt.hold(True)
axt.set_title('q domain: PD %d' % (k + 1))
plot.rstyle(axt)
axt = ax[1, k]
for l in range(0, Nstd):
axt.plot(time, f_pca[:, l, k], color=CBcdict[cl[l]])
axt.hold(True)
axt.set_title('f domain: PD %d' % (k + 1))
plot.rstyle(axt)
fig.set_tight_layout(True)
cumm_coef = 100 * np.cumsum(s) / sum(s)
idx = np.arange(0, M + 1) + 1
plot.f_plot(idx, cumm_coef, "Coefficient Cumulative Percentage")
plt.xlabel("Percentage")
plt.ylabel("Index")
plt.show()
mean_f0 = f0.mean(axis=1)
std_f0 = f0.std(axis=1)
mean_fn = fn.mean(axis=1)
std_fn = fn.std(axis=1)
tmp = np.zeros(M)
tmp[1:] = cumtrapz(mqn * np.abs(mqn), time)
fmean = np.mean(f0[1, :]) + tmp
fgam = np.zeros((M, N))
for k in range(0, N):
time0 = (time[-1] - time[0]) * gamf[:, k] + time[0]
fgam[:, k] = np.interp(time0, time, fmean)
var_fgam = fgam.var(axis=1)
orig_var = trapz(std_f0 ** 2, time)
amp_var = trapz(std_fn ** 2, time)
phase_var = trapz(var_fgam, time)
K = np.cov(fn)
U, s, V = svd(K)
align_fPCAresults = collections.namedtuple('align_fPCA', ['fn', 'qn',
'q0', 'mqn', 'gam', 'q_pca',
'f_pca', 'latent', 'coef',
'U', 'orig_var', 'amp_var',
'phase_var', 'cost'])
out = align_fPCAresults(fn, qn, q0, mqn, gamf, q_pca, f_pca, s, c,
U, orig_var, amp_var, phase_var, cost)
return out
def gauss_model(self, n=1, sort_samples=False):
"""
This function models the functional data using a Gaussian model
extracted from the principal components of the srvfs
:param n: number of random samples
:param sort_samples: sort samples (default = T)
:type n: integer
:type sort_samples: bool
"""
fn = self.fn
time = self.time
qn = self.qn
gam = self.gam
# Parameters
eps = np.finfo(np.double).eps
binsize = np.diff(time)
binsize = binsize.mean()
M = time.size
# compute mean and covariance in q-domain
mq_new = qn.mean(axis=1)
mididx = np.round(time.shape[0] / 2)
m_new = np.sign(fn[mididx, :]) * np.sqrt(np.abs(fn[mididx, :]))
mqn = np.append(mq_new, m_new.mean())
qn2 = np.vstack((qn, m_new))
C = np.cov(qn2)
q_s = np.random.multivariate_normal(mqn, C, n)
q_s = q_s.transpose()
# compute the correspondence to the original function domain
fs = np.zeros((M, n))
for k in range(0, n):
fs[:, k] = uf.cumtrapzmid(time, q_s[0:M, k] * np.abs(q_s[0:M, k]),
np.sign(q_s[M, k]) * (q_s[M, k]**2),
mididx)
fbar = fn.mean(axis=1)
fsbar = fs.mean(axis=1)
err = np.transpose(np.tile(fbar - fsbar, (n, 1)))
fs += err
# random warping generation
rgam = uf.randomGamma(gam, n)
gams = np.zeros((M, n))
for k in range(0, n):
gams[:, k] = uf.invertGamma(rgam[:, k])
# sort functions and warping
if sort_samples:
mx = fs.max(axis=0)
seq1 = mx.argsort()
# compute the psi-function
fy = np.gradient(rgam, binsize)
psi = fy / np.sqrt(abs(fy) + eps)
ip = np.zeros(n)
len = np.zeros(n)
for i in range(0, n):
tmp = np.ones(M)
ip[i] = tmp.dot(psi[:, i] / M)
len[i] = np.arccos(tmp.dot(psi[:, i] / M))
seq2 = len.argsort()
# combine x-variability and y-variability
ft = np.zeros((M, n))
for k in range(0, n):
ft[:, k] = np.interp(gams[:, seq2[k]],
np.arange(0, M) / np.double(M - 1),
fs[:, seq1[k]])
tmp = np.isnan(ft[:, k])
while tmp.any():
rgam2 = uf.randomGamma(gam, 1)
ft[:, k] = np.interp(gams[:, seq2[k]],
np.arange(0, M) / np.double(M - 1),
uf.invertGamma(rgam2))
else:
# combine x-variability and y-variability
ft = np.zeros((M, n))
for k in range(0, n):
ft[:, k] = np.interp(gams[:, k],
np.arange(0, M) / np.double(M - 1), fs[:,
k])
tmp = np.isnan(ft[:, k])
while tmp.any():
rgam2 = uf.randomGamma(gam, 1)
ft[:, k] = np.interp(gams[:, k],
np.arange(0, M) / np.double(M - 1),
uf.invertGamma(rgam2))
self.rsamps = True
self.fs = fs
self.gams = rgam
self.ft = ft
self.qs = q_s[0:M, :]
return
def jointfPCA(fn, time, qn, q0, gam, no=2, showplot=True):
"""
This function calculates joint functional principal component analysis
on aligned data
:param fn: numpy ndarray of shape (M,N) of N aligned functions with M
samples
:param time: vector of size N describing the sample points
:param qn: numpy ndarray of shape (M,N) of N aligned SRSF with M samples
:param no: number of components to extract (default = 2)
:param showplot: Shows plots of results using matplotlib (default = T)
:type showplot: bool
:type no: int
:rtype: tuple of numpy ndarray
:return q_pca: srsf principal directions
:return f_pca: functional principal directions
:return latent: latent values
:return coef: coefficients
:return U: eigenvectors
"""
coef = np.arange(-1., 2.)
Nstd = coef.shape[0]
# set up for fPCA in q-space
mq_new = qn.mean(axis=1)
M = time.shape[0]
mididx = int(np.round(M / 2))
m_new = np.sign(fn[mididx, :]) * np.sqrt(np.abs(fn[mididx, :]))
mqn = np.append(mq_new, m_new.mean())
qn2 = np.vstack((qn, m_new))
# calculate vector space of warping functions
mu_psi, gam_mu, psi, vec = uf.SqrtMean(gam)
# joint fPCA
C = fminbound(find_C,0,1e4,(qn2,vec,q0,no,mu_psi))
qhat, gamhat, a, U, s, mu_g = jointfPCAd(qn2, vec, C, no, mu_psi)
# geodesic paths
q_pca = np.ndarray(shape=(M, Nstd, no), dtype=float)
f_pca = np.ndarray(shape=(M, Nstd, no), dtype=float)
for k in range(0, no):
for l in range(0, Nstd):
qhat = mqn + dot(U[0:(M+1),k],coef[l]*np.sqrt(s[k]))
vechat = dot(U[(M+1):,k],(coef[l]*np.sqrt(s[k]))/C)
psihat = geo.exp_map(mu_psi,vechat)
gamhat = cumtrapz(psihat*psihat,np.linspace(0,1,M),initial=0)
gamhat = (gamhat - gamhat.min()) / (gamhat.max() - gamhat.min())
if (sum(vechat)==0):
gamhat = np.linspace(0,1,M)
fhat = uf.cumtrapzmid(time, qhat[0:M]*np.fabs(qhat[0:M]), np.sign(qhat[M])*(qhat[M]*qhat[M]), mididx)
f_pca[:,l,k] = uf.warp_f_gamma(np.linspace(0,1,M), fhat, gamhat)
q_pca[:,l,k] = uf.warp_q_gamma(np.linspace(0,1,M), qhat[0:M], gamhat)
jfpca_results = collections.namedtuple('jfpca', ['q_pca', 'f_pca', 'latent', 'coef', 'U'])
jfpca = jfpca_results(q_pca, f_pca, s, a, U)
if showplot:
CBcdict = {
'Bl': (0, 0, 0),
'Or': (.9, .6, 0),
'SB': (.35, .7, .9),
'bG': (0, .6, .5),
'Ye': (.95, .9, .25),
'Bu': (0, .45, .7),
'Ve': (.8, .4, 0),
'rP': (.8, .6, .7),
}
cl = sorted(CBcdict.keys())
fig, ax = plt.subplots(2, no)
for k in range(0, no):
axt = ax[0, k]
for l in range(0, Nstd):
axt.plot(time, q_pca[0:M, l, k], color=CBcdict[cl[l]])
axt.set_title('q domain: PD %d' % (k + 1))
axt = ax[1, k]
for l in range(0, Nstd):
axt.plot(time, f_pca[:, l, k], color=CBcdict[cl[l]])
axt.set_title('f domain: PD %d' % (k + 1))
fig.set_tight_layout(True)
cumm_coef = 100 * np.cumsum(s) / sum(s)
idx = np.arange(0, s.shape[0]) + 1
plot.f_plot(idx, cumm_coef, "Coefficient Cumulative Percentage")
plt.xlabel("Percentage")
plt.ylabel("Index")
plt.show()
return jfpca
def gauss_model(fn, time, qn, gam, n=1, sort_samples=False):
"""
This function models the functional data using a Gaussian model
extracted from the principal components of the srvfs
:param fn: numpy ndarray of shape (M,N) of N aligned functions with
M samples
:param time: vector of size M describing the sample points
:param qn: numpy ndarray of shape (M,N) of N aligned srvfs with M samples
:param gam: warping functions
:param n: number of random samples
:param sort_samples: sort samples (default = T)
:type n: integer
:type sort_samples: bool
:type fn: np.ndarray
:type qn: np.ndarray
:type gam: np.ndarray
:type time: np.ndarray
:rtype: tuple of numpy array
:return fs: random aligned samples
:return gams: random warping functions
:return ft: random samples
"""
# Parameters
eps = np.finfo(np.double).eps
binsize = np.diff(time)
binsize = binsize.mean()
M = time.size
# compute mean and covariance in q-domain
mq_new = qn.mean(axis=1)
mididx = np.round(time.shape[0] / 2)
m_new = np.sign(fn[mididx, :]) * np.sqrt(np.abs(fn[mididx, :]))
mqn = np.append(mq_new, m_new.mean())
qn2 = np.vstack((qn, m_new))
C = np.cov(qn2)
q_s = np.random.multivariate_normal(mqn, C, n)
q_s = q_s.transpose()
# compute the correspondence to the original function domain
fs = np.zeros((M, n))
for k in range(0, n):
fs[:, k] = uf.cumtrapzmid(time, q_s[0:M, k] * np.abs(q_s[0:M, k]),
np.sign(q_s[M, k]) * (q_s[M, k]**2), mididx)
fbar = fn.mean(axis=1)
fsbar = fs.mean(axis=1)
err = np.transpose(np.tile(fbar - fsbar, (n, 1)))
fs += err
# random warping generation
rgam = uf.randomGamma(gam, n)
gams = np.zeros((M, n))
for k in range(0, n):
gams[:, k] = uf.invertGamma(rgam[:, k])
# sort functions and warping
if sort_samples:
mx = fs.max(axis=0)
seq1 = mx.argsort()
# compute the psi-function
fy = np.gradient(rgam, binsize)
psi = fy / np.sqrt(abs(fy) + eps)
ip = np.zeros(n)
len = np.zeros(n)
for i in range(0, n):
tmp = np.ones(M)
ip[i] = tmp.dot(psi[:, i] / M)
len[i] = np.acos(tmp.dot(psi[:, i] / M))
seq2 = len.argsort()
# combine x-variability and y-variability
ft = np.zeros((M, n))
for k in range(0, n):
ft[:, k] = np.interp(gams[:, seq2[k]],
np.arange(0, M) / np.double(M - 1),
fs[:, seq1[k]])
tmp = np.isnan(ft[:, k])
while tmp.any():
rgam2 = uf.randomGamma(gam, 1)
ft[:, k] = np.interp(gams[:, seq2[k]],
np.arange(0, M) / np.double(M - 1),
uf.invertGamma(rgam2))
else:
# combine x-variability and y-variability
ft = np.zeros((M, n))
for k in range(0, n):
ft[:, k] = np.interp(gams[:, k],
np.arange(0, M) / np.double(M - 1), fs[:, k])
tmp = np.isnan(ft[:, k])
while tmp.any():
rgam2 = uf.randomGamma(gam, 1)
ft[:, k] = np.interp(gams[:, k],
np.arange(0, M) / np.double(M - 1),
uf.invertGamma(rgam2))
samples = collections.namedtuple('samples', ['fs', 'gams', 'ft'])
out = samples(fs, rgam, ft)
return out
def vertfPCA(fn, time, qn, no=2, showplot=True):
"""
This function calculates vertical functional principal component analysis
on aligned data
:param fn: numpy ndarray of shape (M,N) of N aligned functions with M
samples
:param time: vector of size N describing the sample points
:param qn: numpy ndarray of shape (M,N) of N aligned SRSF with M samples
:param no: number of components to extract (default = 2)
:param showplot: Shows plots of results using matplotlib (default = T)
:type showplot: bool
:type no: int
:rtype: tuple of numpy ndarray
:return q_pca: srsf principal directions
:return f_pca: functional principal directions
:return latent: latent values
:return coef: coefficients
:return U: eigenvectors
"""
coef = np.arange(-2., 3.)
Nstd = coef.shape[0]
# FPCA
mq_new = qn.mean(axis=1)
N = mq_new.shape[0]
mididx = int(np.round(time.shape[0] / 2))
m_new = np.sign(fn[mididx, :]) * np.sqrt(np.abs(fn[mididx, :]))
mqn = np.append(mq_new, m_new.mean())
qn2 = np.vstack((qn, m_new))
K = np.cov(qn2)
U, s, V = svd(K)
stdS = np.sqrt(s)
# compute the PCA in the q domain
q_pca = np.ndarray(shape=(N + 1, Nstd, no), dtype=float)
for k in range(0, no):
for l in range(0, Nstd):
q_pca[:, l, k] = mqn + coef[l] * stdS[k] * U[:, k]
# compute the correspondence in the f domain
f_pca = np.ndarray(shape=(N, Nstd, no), dtype=float)
for k in range(0, no):
for l in range(0, Nstd):
f_pca[:, l, k] = uf.cumtrapzmid(time, q_pca[0:N, l, k] * np.abs(q_pca[0:N, l, k]),
np.sign(q_pca[N, l, k]) * (q_pca[N, l, k] ** 2),
mididx)
fbar = fn.mean(axis=1)
fsbar = f_pca[:, :, k].mean(axis=1)
err = np.transpose(np.tile(fbar-fsbar, (Nstd,1)))
f_pca[:, :, k] += err
N2 = qn.shape[1]
c = np.zeros((N2, no))
for k in range(0, no):
for l in range(0, N2):
c[l, k] = sum((np.append(qn[:, l], m_new[l]) - mqn) * U[:, k])
vfpca_results = collections.namedtuple('vfpca', ['q_pca', 'f_pca', 'latent', 'coef', 'U'])
vfpca = vfpca_results(q_pca, f_pca, s, c, U)
if showplot:
CBcdict = {
'Bl': (0, 0, 0),
'Or': (.9, .6, 0),
'SB': (.35, .7, .9),
'bG': (0, .6, .5),
'Ye': (.95, .9, .25),
'Bu': (0, .45, .7),
'Ve': (.8, .4, 0),
'rP': (.8, .6, .7),
}
cl = sorted(CBcdict.keys())
fig, ax = plt.subplots(2, no)
for k in range(0, no):
axt = ax[0, k]
for l in range(0, Nstd):
axt.plot(time, q_pca[0:N, l, k], color=CBcdict[cl[l]])
axt.set_title('q domain: PD %d' % (k + 1))
axt = ax[1, k]
for l in range(0, Nstd):
axt.plot(time, f_pca[:, l, k], color=CBcdict[cl[l]])
axt.set_title('f domain: PD %d' % (k + 1))
fig.set_tight_layout(True)
cumm_coef = 100 * np.cumsum(s) / sum(s)
idx = np.arange(0, N + 1) + 1
plot.f_plot(idx, cumm_coef, "Coefficient Cumulative Percentage")
plt.xlabel("Percentage")
plt.ylabel("Index")
plt.show()
return vfpca
def vertfPCA(fn, time, qn, no=1, showplot=True):
"""
This function calculates vertical functional principal component analysis
on aligned data
:param fn: numpy ndarray of shape (M,N) of N aligned functions with M
samples
:param time: vector of size N describing the sample points
:param qn: numpy ndarray of shape (M,N) of N aligned SRSF with M samples
:param no: number of components to extract (default = 1)
:param showplot: Shows plots of results using matplotlib (default = T)
:type showplot: bool
:type no: int
:rtype: tuple of numpy ndarray
:return q_pca: srsf principal directions
:return f_pca: functional principal directions
:return latent: latent values
:return coef: coefficients
:return U: eigenvectors
"""
coef = np.arange(-2., 3.)
Nstd = coef.shape[0]
# FPCA
mq_new = qn.mean(axis=1)
N = mq_new.shape[0]
mididx = np.round(time.shape[0] / 2)
m_new = np.sign(fn[mididx, :]) * np.sqrt(np.abs(fn[mididx, :]))
mqn = np.append(mq_new, m_new.mean())
qn2 = np.vstack((qn, m_new))
K = np.cov(qn2)
U, s, V = svd(K)
stdS = np.sqrt(s)
# compute the PCA in the q domain
q_pca = np.ndarray(shape=(N + 1, Nstd, no), dtype=float)
for k in range(0, no):
for l in range(0, Nstd):
q_pca[:, l, k] = mqn + coef[l] * stdS[k] * U[:, k]
# compute the correspondence in the f domain
f_pca = np.ndarray(shape=(N, Nstd, no), dtype=float)
for k in range(0, no):
for l in range(0, Nstd):
f_pca[:, l, k] = uf.cumtrapzmid(time, q_pca[0:N, l, k] * np.abs(q_pca[0:N, l, k]),
np.sign(q_pca[N, l, k]) * (q_pca[N, l, k] ** 2))
N2 = qn.shape[1]
c = np.zeros((N2, no))
for k in range(0, no):
for l in range(0, N2):
c[l, k] = sum((np.append(qn[:, l], m_new[l]) - mqn) * U[:, k])
vfpca_results = collections.namedtuple('vfpca', ['q_pca', 'f_pca', 'latent', 'coef', 'U'])
vfpca = vfpca_results(q_pca, f_pca, s, c, U)
if showplot:
CBcdict = {
'Bl': (0, 0, 0),
'Or': (.9, .6, 0),
'SB': (.35, .7, .9),
'bG': (0, .6, .5),
'Ye': (.95, .9, .25),
'Bu': (0, .45, .7),
'Ve': (.8, .4, 0),
'rP': (.8, .6, .7),
}
cl = sorted(CBcdict.keys())
fig, ax = plt.subplots(2, no)
for k in range(0, no):
axt = ax[0, k]
for l in range(0, Nstd):
axt.plot(time, q_pca[0:N, l, k], color=CBcdict[cl[l]])
axt.hold(True)
axt.set_title('q domain: PD %d' % (k + 1))
plot.rstyle(axt)
axt = ax[1, k]
for l in range(0, Nstd):
axt.plot(time, f_pca[:, l, k], color=CBcdict[cl[l]])
axt.hold(True)
axt.set_title('f domain: PD %d' % (k + 1))
plot.rstyle(axt)
fig.set_tight_layout(True)
cumm_coef = 100 * np.cumsum(s) / sum(s)
idx = np.arange(0, N + 1) + 1
plot.f_plot(idx, cumm_coef, "Coefficient Cumulative Percentage")
plt.xlabel("Percentage")
plt.ylabel("Index")
plt.show()
return vfpca
def calc_fpca(self, no=3, id=None, stds=np.arange(-1, 2)):
"""
This function calculates vertical functional principal component analysis
on aligned data
:param no: number of components to extract (default = 3)
:param id: point to use for f(0) (default = midpoint)
:param stds: number of standard deviations along gedoesic to compute (default = -1,0,1)
:type no: int
:type id: int
:rtype: fdavpca object containing
:return q_pca: srsf principal directions
:return f_pca: functional principal directions
:return latent: latent values
:return coef: coefficients
:return U: eigenvectors
"""
fn = self.warp_data.fn
time = self.warp_data.time
qn = self.warp_data.qn
M = time.shape[0]
if id is None:
mididx = int(np.round(M / 2))
else:
mididx = id
Nstd = stds.shape[0]
# FPCA
mq_new = qn.mean(axis=1)
N = mq_new.shape[0]
m_new = np.sign(fn[mididx, :]) * np.sqrt(np.abs(fn[mididx, :]))
mqn = np.append(mq_new, m_new.mean())
qn2 = np.vstack((qn, m_new))
K = np.cov(qn2)
U, s, V = svd(K)
stdS = np.sqrt(s)
# compute the PCA in the q domain
q_pca = np.ndarray(shape=(N + 1, Nstd, no), dtype=float)
for k in range(0, no):
for l in range(0, Nstd):
q_pca[:, l, k] = mqn + stds[l] * stdS[k] * U[:, k]
# compute the correspondence in the f domain
f_pca = np.ndarray(shape=(N, Nstd, no), dtype=float)
for k in range(0, no):
for l in range(0, Nstd):
f_pca[:, l, k] = uf.cumtrapzmid(
time, q_pca[0:N, l, k] * np.abs(q_pca[0:N, l, k]),
np.sign(q_pca[N, l, k]) * (q_pca[N, l, k]**2), mididx)
fbar = fn.mean(axis=1)
fsbar = f_pca[:, :, k].mean(axis=1)
err = np.transpose(np.tile(fbar - fsbar, (Nstd, 1)))
f_pca[:, :, k] += err
N2 = qn.shape[1]
c = np.zeros((N2, no))
for k in range(0, no):
for l in range(0, N2):
c[l, k] = sum((np.append(qn[:, l], m_new[l]) - mqn) * U[:, k])
self.q_pca = q_pca
self.f_pca = f_pca
self.latent = s[0:no]
self.coef = c
self.U = U[:, 0:no]
self.id = mididx
self.mqn = mqn
self.time = time
self.stds = stds
self.no = no
return
def calc_fpca(self,
no=3,
stds=np.arange(-1., 2.),
id=None,
parallel=False,
cores=-1):
"""
This function calculates joint functional principal component analysis
on aligned data
:param no: number of components to extract (default = 3)
:param id: point to use for f(0) (default = midpoint)
:param stds: number of standard deviations along gedoesic to compute (default = -1,0,1)
:param parallel: run in parallel (default = F)
:param cores: number of cores for parallel (default = -1 (all))
:type no: int
:type id: int
:type parallel: bool
:type cores: int
:rtype: fdajpca object of numpy ndarray
:return q_pca: srsf principal directions
:return f_pca: functional principal directions
:return latent: latent values
:return coef: coefficients
:return U: eigenvectors
"""
fn = self.warp_data.fn
time = self.warp_data.time
qn = self.warp_data.qn
q0 = self.warp_data.q0
gam = self.warp_data.gam
M = time.shape[0]
if id is None:
mididx = int(np.round(M / 2))
else:
mididx = id
Nstd = stds.shape[0]
# set up for fPCA in q-space
mq_new = qn.mean(axis=1)
m_new = np.sign(fn[mididx, :]) * np.sqrt(np.abs(fn[mididx, :]))
mqn = np.append(mq_new, m_new.mean())
qn2 = np.vstack((qn, m_new))
# calculate vector space of warping functions
mu_psi, gam_mu, psi, vec = uf.SqrtMean(gam, parallel, cores)
# joint fPCA
C = fminbound(find_C, 0, 1e4,
(qn2, vec, q0, no, mu_psi, parallel, cores))
qhat, gamhat, a, U, s, mu_g, g, cov = jointfPCAd(
qn2, vec, C, no, mu_psi, parallel, cores)
# geodesic paths
q_pca = np.ndarray(shape=(M, Nstd, no), dtype=float)
f_pca = np.ndarray(shape=(M, Nstd, no), dtype=float)
for k in range(0, no):
for l in range(0, Nstd):
qhat = mqn + np.dot(U[0:(M + 1), k], stds[l] * np.sqrt(s[k]))
vechat = np.dot(U[(M + 1):, k], (stds[l] * np.sqrt(s[k])) / C)
psihat = geo.exp_map(mu_psi, vechat)
gamhat = cumtrapz(psihat * psihat,
np.linspace(0, 1, M),
initial=0)
gamhat = (gamhat - gamhat.min()) / (gamhat.max() -
gamhat.min())
if (sum(vechat) == 0):
gamhat = np.linspace(0, 1, M)
fhat = uf.cumtrapzmid(time, qhat[0:M] * np.fabs(qhat[0:M]),
np.sign(qhat[M]) * (qhat[M] * qhat[M]),
mididx)
f_pca[:, l, k] = uf.warp_f_gamma(np.linspace(0, 1, M), fhat,
gamhat)
q_pca[:, l, k] = uf.warp_q_gamma(np.linspace(0, 1, M),
qhat[0:M], gamhat)
self.q_pca = q_pca
self.f_pca = f_pca
self.latent = s[0:no]
self.coef = a
self.U = U[:, 0:no]
self.mu_psi = mu_psi
self.mu_g = mu_g
self.id = mididx
self.C = C
self.time = time
self.g = g
self.cov = cov
self.no = no
self.stds = stds
return
def gauss_model(fn, time, qn, gam, n=1, sort_samples=False):
"""
This function models the functional data using a Gaussian model
extracted from the principal components of the srvfs
:param fn: numpy ndarray of shape (M,N) of N aligned functions with
M samples
:param time: vector of size M describing the sample points
:param qn: numpy ndarray of shape (M,N) of N aligned srvfs with M samples
:param gam: warping functions
:param n: number of random samples
:param sort_samples: sort samples (default = T)
:type n: integer
:type sort_samples: bool
:type fn: np.ndarray
:type qn: np.ndarray
:type gam: np.ndarray
:type time: np.ndarray
:rtype: tuple of numpy array
:return fs: random aligned samples
:return gams: random warping functions
:return ft: random samples
"""
# Parameters
eps = np.finfo(np.double).eps
binsize = np.diff(time)
binsize = binsize.mean()
M = time.size
# compute mean and covariance in q-domain
mq_new = qn.mean(axis=1)
mididx = np.round(time.shape[0] / 2)
m_new = np.sign(fn[mididx, :]) * np.sqrt(np.abs(fn[mididx, :]))
mqn = np.append(mq_new, m_new.mean())
qn2 = np.vstack((qn, m_new))
C = np.cov(qn2)
q_s = np.random.multivariate_normal(mqn, C, n)
q_s = q_s.transpose()
# compute the correspondence to the original function domain
fs = np.zeros((M, n))
for k in range(0, n):
fs[:, k] = uf.cumtrapzmid(time, q_s[0:M, k] * np.abs(q_s[0:M, k]),
np.sign(q_s[M, k]) * (q_s[M, k] ** 2),
mididx)
fbar = fn.mean(axis=1)
fsbar = fs.mean(axis=1)
err = np.transpose(np.tile(fbar-fsbar, (n,1)))
fs += err
# random warping generation
rgam = uf.randomGamma(gam, n)
gams = np.zeros((M, n))
for k in range(0, n):
gams[:, k] = uf.invertGamma(rgam[:, k])
# sort functions and warping
if sort_samples:
mx = fs.max(axis=0)
seq1 = mx.argsort()
# compute the psi-function
fy = np.gradient(rgam, binsize)
psi = fy / np.sqrt(abs(fy) + eps)
ip = np.zeros(n)
len = np.zeros(n)
for i in range(0, n):
tmp = np.ones(M)
ip[i] = tmp.dot(psi[:, i] / M)
len[i] = np.acos(tmp.dot(psi[:, i] / M))
seq2 = len.argsort()
# combine x-variability and y-variability
ft = np.zeros((M, n))
for k in range(0, n):
ft[:, k] = np.interp(gams[:, seq2[k]], np.arange(0, M) /
np.double(M - 1), fs[:, seq1[k]])
tmp = np.isnan(ft[:, k])
while tmp.any():
rgam2 = uf.randomGamma(gam, 1)
ft[:, k] = np.interp(gams[:, seq2[k]], np.arange(0, M) /
np.double(M - 1), uf.invertGamma(rgam2))
else:
# combine x-variability and y-variability
ft = np.zeros((M, n))
for k in range(0, n):
ft[:, k] = np.interp(gams[:, k], np.arange(0, M) /
np.double(M - 1), fs[:, k])
tmp = np.isnan(ft[:, k])
while tmp.any():
rgam2 = uf.randomGamma(gam, 1)
ft[:, k] = np.interp(gams[:, k], np.arange(0, M) /
np.double(M - 1), uf.invertGamma(rgam2))
samples = collections.namedtuple('samples', ['fs', 'gams', 'ft'])
out = samples(fs, rgam, ft)
return out
