def load_globals(config):
import mapreduce as GLOBAL # access to global variables
GLOBAL.DATA = GLOBAL.load_data(config["data"])
STRUCTURE = nibabel.load(config["structure"])
A = tv_helper.linear_operator_from_mask(STRUCTURE.get_data())
N_COMP = config["N_COMP"]
GLOBAL.A, GLOBAL.STRUCTURE, GLOBAL.N_COMP = A, STRUCTURE, N_COMP
def mapper(key, output_collector):
import mapreduce as GLOBAL # access to global variables:
#raise ImportError("could not import ")
# GLOBAL.DATA, GLOBAL.STRUCTURE, GLOBAL.A
# GLOBAL.DATA ::= {"X":[Xtrain, ytrain], "y":[Xtest, ytest]}
# key: list of parameters
Xtr = GLOBAL.DATA_RESAMPLED["X"][0]
Xte = GLOBAL.DATA_RESAMPLED["X"][1]
ytr = GLOBAL.DATA_RESAMPLED["y"][0]
yte = GLOBAL.DATA_RESAMPLED["y"][1]
print key, "Data shape:", Xtr.shape, Xte.shape, ytr.shape, yte.shape
STRUCTURE = GLOBAL.STRUCTURE
#alpha, ratio_l1, ratio_l2, ratio_tv, k = key
#key = np.array(key)
penalty_start = GLOBAL.CONFIG["penalty_start"]
class_weight = "auto" # unbiased
alpha = float(key[0])
l1, l2, tv, k = alpha * float(key[1]), alpha * float(
key[2]), alpha * float(key[3]), key[4]
print "l1:%f, l2:%f, tv:%f, k:%i" % (l1, l2, tv, k)
if k != -1:
k = int(k)
aov = SelectKBest(k=k)
aov.fit(Xtr[..., penalty_start:], ytr.ravel())
mask = STRUCTURE.get_data() != 0
mask[mask] = aov.get_support()
#print mask.sum()
A = tv_helper.linear_operator_from_mask(mask)
Xtr_r = np.hstack([
Xtr[:, :penalty_start], Xtr[:, penalty_start:][:,
aov.get_support()]
])
Xte_r = np.hstack([
Xte[:, :penalty_start], Xte[:, penalty_start:][:,
aov.get_support()]
])
else:
mask = np.ones(Xtr.shape[0], dtype=bool)
Xtr_r = Xtr
Xte_r = Xte
A = GLOBAL.A
mod = LogisticRegressionL1L2TV(l1,
l2,
tv,
A,
penalty_start=penalty_start,
class_weight=class_weight)
mod.fit(Xtr_r, ytr)
y_pred = mod.predict(Xte_r)
proba_pred = mod.predict_probability(Xte_r)
ret = dict(y_pred=y_pred,
proba_pred=proba_pred,
y_true=yte,
beta=mod.beta,
mask=mask)
if output_collector:
output_collector.collect(key, ret)
else:
return ret
def load_globals(config):
import mapreduce as GLOBAL # access to global variables
GLOBAL.DATA = GLOBAL.load_data(config["data"])
STRUCTURE = nibabel.load(config["mask_filename"])
try:
A = tv_helper.linear_operator_from_mask(STRUCTURE.get_data())
except:
A, _ = tv_helper.A_from_mask(STRUCTURE.get_data())
GLOBAL.A, GLOBAL.STRUCTURE, GLOBAL.CONFIG = A, STRUCTURE, config
def init():
INPUT_DATA_X = os.path.join(WD_ORIGINAL, 'X.npy')
INPUT_DATA_y = os.path.join(WD_ORIGINAL, 'y.npy')
INPUT_MASK_PATH = os.path.join(WD_ORIGINAL, 'mask.nii')
#INPUT_LINEAR_OPE_PATH = '/neurospin/brainomics/2016_schizConnect/analysis/NUSDAST/Freesurfer/data/30yo/Atv.npz'
# INPUT_CSV = '/neurospin/brainomics/2016_schizConnect/analysis/NUSDAST/Freesurfer/population_30yo.csv'
os.makedirs(WD, exist_ok=True)
shutil.copy(INPUT_DATA_X, WD)
shutil.copy(INPUT_DATA_y, WD)
shutil.copy(INPUT_MASK_PATH, WD)
#shutil.copy(INPUT_LINEAR_OPE_PATH, WD)
## Create config file
os.chdir(WD)
X = np.load("X.npy")
y = np.load("y.npy")
if not os.path.exists(os.path.join(WD, "Atv.npz")):
import nibabel
import parsimony.functions.nesterov.tv as nesterov_tv
from parsimony.utils.linalgs import LinearOperatorNesterov
img = nibabel.load(os.path.join(WD, "mask.nii"))
Atv = nesterov_tv.linear_operator_from_mask(img.get_data(),
calc_lambda_max=True)
Atv.save(os.path.join(WD, "Atv.npz"))
Atv_ = LinearOperatorNesterov(filename=os.path.join(WD, "Atv.npz"))
assert Atv.get_singular_values(0) == Atv_.get_singular_values(0)
assert np.allclose(Atv_.get_singular_values(0),
11.942045760666732,
rtol=1e-03,
atol=1e-03)
assert np.all([
a.shape == (X.shape[1] - penalty_start, X.shape[1] - penalty_start)
for a in Atv
])
if False and not os.path.exists(os.path.join(WD, "beta_start.npz")):
betas = dict()
import time
alphas = [.01, 0.1, 1.0, 10]
for alpha in alphas:
mod = estimators.RidgeLogisticRegression(
l=alpha, class_weight="auto", penalty_start=penalty_start)
t_ = time.time()
mod.fit(X, y.ravel())
print(time.time() - t_) # 11564
betas["lambda_%.2f" % alpha] = mod.beta
np.savez(os.path.join(WD, "beta_start.npz"), **betas)
beta_start = np.load(os.path.join(WD, "beta_start.npz"))
assert np.all(
[np.all(beta_start[a] == betas[a]) for a in beta_start.keys()])
## Create config file
# ########################################################################
# Setting 1: 5cv + large range of parameters: cv_largerange
# with sub-sample training set with size 50, 100
# 5cv/cv0*[_sub50]/refit/*
# sub_sizes = [50, 100]
sub_sizes = []
cv_outer = [[
tr, te
] for tr, te in StratifiedKFold(n_splits=NFOLDS_OUTER, random_state=42).
split(np.zeros(y.shape[0]), y.ravel())]
# check we got the same CV than previoulsy
cv_old = json.load(
open(os.path.join(WD_ORIGINAL, "config_modselectcv.json")))["resample"]
cv_outer_old = [
cv_old[k] for k in ['cv%02d/refit' % i for i in range(NFOLDS_OUTER)]
]
assert np.all([
np.all(np.array(cv_outer_old[i][0]) == cv_outer[i][0])
for i in range(NFOLDS_OUTER)
])
assert np.all([
np.all(np.array(cv_outer_old[i][1]) == cv_outer[i][1])
for i in range(NFOLDS_OUTER)
])
# check END
import collections
cv = collections.OrderedDict()
cv["refit/refit"] = [np.arange(len(y)), np.arange(len(y))]
for cv_outer_i, (tr_val, te) in enumerate(cv_outer):
# Simple CV
cv["cv%02d/refit" % (cv_outer_i)] = [tr_val, te]
# Nested CV
# cv_inner = StratifiedKFold(y[tr_val].ravel(), n_folds=NFOLDS_INNER, random_state=42)
# for cv_inner_i, (tr, val) in enumerate(cv_inner):
# cv["cv%02d/cvnested%02d" % ((cv_outer_i), cv_inner_i)] = [tr_val[tr], tr_val[val]]
# Sub-sample training set with size 50, 100
# => cv*_sub[50|100]/refit
grps = np.unique(y[tr_val]).astype(int)
ytr = y.copy()
ytr[te] = np.nan
g_idx = [np.where(ytr == g)[0] for g in grps]
assert np.all([np.all(ytr[g_idx[g]] == g) for g in grps])
g_size = np.array([len(g) for g in g_idx])
g_prop = g_size / g_size.sum()
for sub_size in sub_sizes:
# sub_size = sub_sizes[0]
sub_g_size = np.round(g_prop * sub_size).astype(int)
g_sub_idx = [
np.random.choice(g_idx[g], sub_g_size[g], replace=False)
for g in grps
]
assert np.all([np.all(y[g_sub_idx[g]] == g) for g in grps])
tr_val_sub = np.concatenate(g_sub_idx)
assert len(tr_val_sub) == sub_size
assert np.all([idx in tr_val for idx in tr_val_sub])
assert np.all(np.logical_not([idx in te for idx in tr_val_sub]))
cv["cv%02d_sub%i/refit" %
(cv_outer_i, sub_size)] = [tr_val_sub, te]
cv = {k: [cv[k][0].tolist(), cv[k][1].tolist()] for k in cv}
# Nested CV
# assert len(cv_largerange) == NFOLDS_OUTER * NFOLDS_INNER + NFOLDS_OUTER + 1
# Simple CV
# assert len(cv) == NFOLDS_OUTER + 1
# Simple CV + sub-sample training set with size 50, 100:
assert len(cv) == NFOLDS_OUTER * (1 + len(sub_sizes)) + 1
print(list(cv.keys()))
# Large grid of parameters
alphas = [0.001, 0.01, 0.1, 1.0]
# alphas = [.01, 0.1, 1.0] # first ran with this grid
tv_ratio = [0.01, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
l1l2_ratio = [0.1, 0.5, 0.9]
#l1l2_ratio = [0, 0.1, 0.5, 0.9, 1.0] # first ran with this grid
algos = ["enettv", "enetgn"]
params_enet_tvgn = [
list(param)
for param in itertools.product(algos, alphas, l1l2_ratio, tv_ratio)
]
assert len(params_enet_tvgn) == 240 # old 300
params_enet = [
list(param)
for param in itertools.product(["enet"], alphas, l1l2_ratio, [0])
]
assert len(params_enet) == 12 # old 15
params = params_enet_tvgn + params_enet
assert len(params) == 252 # 315
# Simple CV
# assert len(params) * len(cv) == 1890
# Simple CV + sub-sample training set with size 50, 100:
assert len(params) * len(cv) == 1512 # 1890
config = dict(data=dict(X="X.npy", y="y.npy"),
params=params,
resample=cv,
structure_linear_operator_tv="Atv.npz",
beta_start="beta_start.npz",
map_output="5cv",
user_func=user_func_filename)
json.dump(config, open(os.path.join(WD, "config_cv_largerange.json"), "w"))
# Build utils files: sync (push/pull) and PBS
import brainomics.cluster_gabriel as clust_utils
cmd = "mapreduce.py --map %s/config_cv_largerange.json" % WD_CLUSTER
clust_utils.gabriel_make_qsub_job_files(WD,
cmd,
walltime="250:00:00",
suffix="_cv_largerange",
freecores=2)
# ########################################################################
# Setting 2: dcv + reduced range of parameters: dcv_reducedrange
# 5cv/cv0*/cvnested0*/*
cv_outer = [[
tr, te
] for tr, te in StratifiedKFold(n_splits=NFOLDS_OUTER, random_state=42).
split(np.zeros(y.shape[0]), y.ravel())]
# check we got the same CV than previoulsy
cv_old = json.load(
open(os.path.join(WD_ORIGINAL, "config_modselectcv.json")))["resample"]
cv_outer_old = [
cv_old[k] for k in ['cv%02d/refit' % i for i in range(NFOLDS_OUTER)]
]
assert np.all([
np.all(np.array(cv_outer_old[i][0]) == cv_outer[i][0])
for i in range(NFOLDS_OUTER)
])
assert np.all([
np.all(np.array(cv_outer_old[i][1]) == cv_outer[i][1])
for i in range(NFOLDS_OUTER)
])
# check END
import collections
cv = collections.OrderedDict()
cv["refit/refit"] = [np.arange(len(y)), np.arange(len(y))]
for cv_outer_i, (tr_val, te) in enumerate(cv_outer):
cv["cv%02d/refit" % (cv_outer_i)] = [tr_val, te]
cv_inner = StratifiedKFold(n_splits=NFOLDS_INNER,
random_state=42).split(
np.zeros(y[tr_val].shape[0]),
y[tr_val].ravel())
for cv_inner_i, (tr, val) in enumerate(cv_inner):
cv["cv%02d/cvnested%02d" %
((cv_outer_i), cv_inner_i)] = [tr_val[tr], tr_val[val]]
cv = {k: [cv[k][0].tolist(), cv[k][1].tolist()] for k in cv}
#assert len(cv) == NFOLDS_OUTER + 1
assert len(cv) == NFOLDS_OUTER * NFOLDS_INNER + NFOLDS_OUTER + 1
print(list(cv.keys()))
# Reduced grid of parameters
alphas = [0.001, 0.01, 0.1, 1.0]
tv_ratio = [0.2, 0.8]
l1l2_ratio = [0.1, 0.9]
algos = ["enettv", "enetgn"]
params_enet_tvgn = [
list(param)
for param in itertools.product(algos, alphas, l1l2_ratio, tv_ratio)
]
assert len(params_enet_tvgn) == 32 # 16
params_enet = [
list(param)
for param in itertools.product(["enet"], alphas, l1l2_ratio, [0])
]
assert len(params_enet) == 8 # 4
params = params_enet_tvgn + params_enet
assert len(params) == 40 # 20
assert len(params) * len(cv) == 1240 # 620
config = dict(data=dict(X="X.npy", y="y.npy"),
params=params,
resample=cv,
structure_linear_operator_tv="Atv.npz",
beta_start="beta_start.npz",
map_output="5cv",
user_func=user_func_filename)
json.dump(config,
open(os.path.join(WD, "config_dcv_reducedrange.json"), "w"))
# Build utils files: sync (push/pull) and PBS
import brainomics.cluster_gabriel as clust_utils
cmd = "mapreduce.py --map %s/config_dcv_reducedrange.json" % WD_CLUSTER
clust_utils.gabriel_make_qsub_job_files(WD,
cmd,
walltime="250:00:00",
suffix="_dcv_reducedrange",
freecores=2)
X[site.ravel() ==
4, :] = X[site.ravel() == 4, :] - X[site.ravel() == 4, :].mean(axis=0)
X[site.ravel() ==
5, :] = X[site.ravel() == 5, :] - X[site.ravel() == 5, :].mean(axis=0)
X[site.ravel() ==
6, :] = X[site.ravel() == 6, :] - X[site.ravel() == 6, :].mean(axis=0)
#Stack covariates
X = np.hstack([Z, X])
n, p = X.shape
np.save(os.path.join(OUTPUT, "X.npy"), X)
np.save(os.path.join(OUTPUT, "y.npy"), y)
###############################################################################
###############################################################################
# precompute linearoperatorSS
#X = np.load("/neurospin/brainomics/2018_euaims_leap_predict_vbm/results/VBM/1.5mm/data/X.npy")
#y = np.load("/neurospin/brainomics/2018_euaims_leap_predict_vbm/results/VBM/1.5mm/data/y.npy")
mask = nibabel.load(os.path.join(OUTPUT, "mask.nii"))
import parsimony.functions.nesterov.tv as nesterov_tv
from parsimony.utils.linalgs import LinearOperatorNesterov
Atv = nesterov_tv.linear_operator_from_mask(mask.get_data(),
calc_lambda_max=True)
Atv.save(os.path.join(OUTPUT, "Atv.npz"))
Atv_ = LinearOperatorNesterov(filename=os.path.join(OUTPUT, "Atv.npz"))
assert Atv.get_singular_values(0) == Atv_.get_singular_values(0)
arxiv = np.load("ADNI_ADAS11-MCIc-CTL_N199.npz")
X = arxiv["X"]
y = arxiv["y"]
beta_start = arxiv["beta_start"]
assert X.shape == (199, 286214)
TAU = 0.2
EPS = 1e-6 # PRECISION FOR THE PAPER
###############################################################################
# Fit model
ALPHA = 0.01 #
l, k, g = ALPHA * np.array([0.3335, 0.3335, 0.333])
mask_ima = nibabel.load(os.path.join(WD, mask_filename))
Atv = tv.linear_operator_from_mask(mask_ima.get_data())
out = os.path.join(WD, "run", "conesta_ite_snapshots/")
snapshot = AlgorithmSnapshot(out, saving_period=1).save_conesta
info = [
Info.converged, Info.num_iter, Info.time, Info.func_val, Info.mu, Info.gap,
Info.converged, Info.fvalue
]
conesta = algorithms.proximal.CONESTA(callback_conesta=snapshot)
algorithm_params = dict(max_iter=1000000, info=info)
os.makedirs(out, exist_ok=True)
algorithm_params["callback"] = snapshot
mod = estimators.LinearRegressionL1L2TV(l,
def test_tvhelper_linear_operator_from_mask(self):
import parsimony.functions.nesterov.tv as tv
## Simple mask with offset
shape = (5, 4)
mask = np.zeros(shape)
mask[1:(shape[0] - 1), 0:(shape[1] - 1)] = 1
Ax_ = np.matrix(
[[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, -1, 0, 0, 1, 0, 0, 0, 0, 0],
[0, 0, -1, 0, 0, 1, 0, 0, 0, 0],
[0, 0, 0, -1, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 0, -1, 0, 0, 1, 0, 0],
[0, 0, 0, 0, 0, -1, 0, 0, 1, 0],
[0, 0, 0, 0, 0, 0, -1, 0, 0, 1],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]])
Ay_ = np.matrix(
[[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, -1, 1, 0, 0, 0, 0, 0, 0, 0],
[0, 0, -1, 1, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, -1, 1, 0, 0, 0, 0],
[0, 0, 0, 0, 0, -1, 1, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, -1, 1, 0],
[0, 0, 0, 0, 0, 0, 0, 0, -1, 1],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]])
A = tv.linear_operator_from_mask(mask, offset=1)
Ax, Ay, Az = A
assert np.all(Ax.todense() == Ax_)
assert np.all(Ay.todense() == Ay_)
assert np.sum(Az.todense() == 0)
#######################################################################
## GROUP TV
shape = (6, 4)
mask = np.zeros(shape, dtype=int)
mask[:3, :3] = 1
mask[3:6, 1:4] = 2
Ax_ = np.matrix(
[[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, -1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, -1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, -1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, -1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, -1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 0, 0, 1, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 0, 0, 1, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 0, 0, 1, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 0, 0, 1, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 0, 0, 1],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]])
Ay_ = np.matrix(
[[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, -1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, -1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, -1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, -1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, -1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 1, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 1, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 1, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 1, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 1, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 1],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]])
A = tv.linear_operator_from_mask(mask)
Ax, Ay, Az = A
assert np.all(Ax.todense() == Ax_)
assert np.all(Ay.todense() == Ay_)
assert np.sum(Az.todense() == 0)
#######################################################################
## test function tv on checkerboard
#######################################################################
dx = 5 # p should be odd
shape = (dx, dx, dx)
# linear_operator_from_masks
mask = np.zeros(shape)
mask[1:(dx - 1), 1:(dx - 1), 1:(dx - 1)] = 1
p = np.prod((dx - 2, dx - 2, dx - 2))
beta = np.zeros(p)
beta[0:p:2] = 1 # checkerboard of 0 and 1
A = tv.linear_operator_from_mask(mask)
tvfunc = tv.TotalVariation(l=1., A=A)
assert tvfunc.f(beta) == self._f_checkerboard_cube((dx - 2,
dx - 2,
dx - 2))
# linear_operator_from_masks with group
mask = np.zeros(shape)
# 4 groups
mask[0:(dx / 2), 0:(dx / 2), :] = 1
mask[0:(dx / 2), (dx / 2):dx, :] = 2
mask[(dx / 2):dx, 0:(dx / 2), :] = 3
mask[(dx / 2):dx, (dx / 2):dx, :] = 4
p = np.prod((dx, dx, dx))
beta = np.zeros(p)
beta[0:p:2] = 1 # checkerboard of 0 and 1
A = tv.linear_operator_from_mask(mask)
tvfunc = tv.TotalVariation(l=1., A=A)
assert np.allclose(tvfunc.f(beta),
self._f_checkerboard_cube((dx / 2, dx / 2, dx)) +
self._f_checkerboard_cube((dx / 2, dx / 2 + 1, dx)) +
self._f_checkerboard_cube((dx / 2 + 1, dx / 2, dx)) +
self._f_checkerboard_cube((dx / 2 + 1, dx / 2 + 1, dx)))
shape = (2, 3)
mask = np.ones(shape)
weights1D = [1.0, 2.0, 3.0, 4.0, 5.0, 6.0]
#weights2D = np.reshape(weights1D, shape)
A_shape = tv.linear_operator_from_shape(shape, weights1D)
#A_mask = tv.linear_operator_from_subset_mask(mask, weights2D)
A_true = (np.array([[-1., 1., 0., 0., 0., 0.],
[0., -2., 2., 0., 0., 0.],
[0., 0., 0., 0., 0., 0.],
[0., 0., 0., -4., 4., 0.],
[0., 0., 0., 0., -5., 5.],
[0., 0., 0., 0., 0., 0.]]),
np.array([[-1., 0., 0., 1., 0., 0.],
[0., -2., 0., 0., 2., 0.],
[0., 0., -3., 0., 0., 3.],
[0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0.]]),
np.array([[0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0., 0.]]))
assert np.array_equal(A_true[0], A_shape[0].todense())
assert np.array_equal(A_shape[0].todense(), A_shape[0].todense())
assert np.array_equal(A_true[1], A_shape[1].todense())
assert np.array_equal(A_shape[1].todense(), A_shape[1].todense())
assert np.array_equal(A_true[2], A_shape[2].todense())
assert np.array_equal(A_shape[2].todense(), A_shape[2].todense())
#############################################################################
#File to store classification scores
f = open(
os.path.join(BASE_PATH, 'results', 'Logistic_L1_L2_TV_withHC',
'parameters_sorescsv'), 'wb')
c = csv.writer(f, delimiter=',')
c.writerow([
"alpha", "l1", "l2", "tv", "accuracy", "recall_0", "recall_1",
"precision_0", "precision_1", "auc"
])
# Empirically set the global penalty, based on maximum l1 penaly
alpha = l1_max_logistic_loss(T, y)
conesta = algorithms.proximal.CONESTA(max_iter=500)
A = nesterov_tv.linear_operator_from_mask(mask_bool)
# Messages for communication between processes
FLAG_STOP_PROCESS = "STOP_WORK"
FLAG_PROCESS_FINISHED = "PROCESS_HAS_FINISHED"
nb_processes = 30
# Data structures for parallel processing
manager = Manager() # multiprocessing.Manager()
work_queue, result_queue = manager.Queue(), manager.Queue()
# Add jobs in work_queue
for p in params:
#print p
work_queue.put(p)
# Add poison pills to stop the remote workers
import pca_struct
import parsimony.functions.nesterov.tv as tv_helper
global_pen = 0.1
gn_ratio = 0.5
l1_ratio = 0.5
lgn = global_pen * gn_ratio
ll1 = l1_ratio * global_pen * (1 - gn_ratio)
ll2 = (1 - l1_ratio) * global_pen * (1 - gn_ratio)
assert(np.allclose(ll1 + ll2 + lgn, global_pen))
nib_mask = nib.load(INPUT_MASK)
Agn = sparse.vstack(tv_helper.linear_operator_from_mask(nib_mask.get_data()))
################################################################################
snapshot = AlgorithmSnapshot('/neurospin/brainomics/2014_pca_struct/fmri/fmri_time/gn_1e-8/').save_nipals
mod = pca_struct.PCAGraphNet(n_components=3,
l1=ll1, l2=ll2, lgn=lgn,
Agn=Agn,
criterion="frobenius",
eps=1e-8,
max_iter=500,
output=False,callback = snapshot)
mod.fit(X)