def parallel_function(
dataset_name, method, tol=1e-8, n_outer=15):
# load data
X, y = fetch_libsvm(dataset_name)
# subsample the samples and the features
n_samples, n_features = dict_subsampling[dataset_name]
t_max = dict_t_max[dataset_name]
# t_max = 3600
X, y = clean_dataset(X, y, n_samples, n_features)
alpha_max, n_classes = get_alpha_max(X, y)
log_alpha_max = np.log(alpha_max) # maybe to change alpha max value
algo = ImplicitForward(None, n_iter_jac=2000)
estimator = LogisticRegression(
C=1, fit_intercept=False, warm_start=True, max_iter=30, verbose=False)
model = SparseLogreg(estimator=estimator)
idx_train, idx_val, idx_test = get_splits(X, y)
logit_multiclass = LogisticMulticlass(
idx_train, idx_val, algo, idx_test=idx_test)
monitor = Monitor()
if method == "implicit_forward":
log_alpha0 = np.ones(n_classes) * np.log(0.1 * alpha_max)
optimizer = LineSearch(n_outer=100)
grad_search(
algo, logit_multiclass, model, optimizer, X, y, log_alpha0,
monitor)
elif method.startswith(('random', 'bayesian')):
max_evals = dict_max_eval[dataset_name]
log_alpha_min = np.log(alpha_max) - 7
hyperopt_wrapper(
algo, logit_multiclass, model, X, y, log_alpha_min, log_alpha_max,
monitor, max_evals=max_evals, tol=tol, t_max=t_max, method=method,
size_space=n_classes)
elif method == 'grid_search':
n_alphas = 20
p_alphas = np.geomspace(1, 0.001, n_alphas)
p_alphas = np.tile(p_alphas, (n_classes, 1))
for i in range(n_alphas):
log_alpha_i = np.log(alpha_max * p_alphas[:, i])
logit_multiclass.get_val(
model, X, y, log_alpha_i, None, monitor, tol)
monitor.times = np.array(monitor.times).copy()
monitor.objs = np.array(monitor.objs).copy()
monitor.acc_vals = np.array(monitor.acc_vals).copy()
monitor.acc_tests = np.array(monitor.acc_tests).copy()
monitor.log_alphas = np.array(monitor.log_alphas).copy()
return (
dataset_name, method, tol, n_outer, monitor.times, monitor.objs,
monitor.acc_vals, monitor.acc_tests, monitor.log_alphas, log_alpha_max,
n_samples, n_features, n_classes)
from sparse_ho.optimizers import GradientDescent
from sparse_ho.ho import grad_search, hyperopt_wrapper
from sparse_ho.utils import Monitor
from sparse_ho.datasets.utils_datasets import (
alpha_max_multiclass, clean_dataset, get_splits)
# load data
n_samples = 1_000
n_features = 1_000
# n_samples = 1_100
# n_features = 3_200
# X, y = fetch_libsvm('sensit')
# X, y = fetch_libsvm('usps')
X, y = fetch_libsvm('rcv1_multiclass')
# X, y = fetch_libsvm('sector_scale')
# X, y = fetch_libsvm('sector')
# X, y = fetch_libsvm('smallNORB')
# X, y = fetch_libsvm('mnist')
# clean data and subsample
X, y = clean_dataset(X, y, n_samples, n_features)
idx_train, idx_val, idx_test = get_splits(X, y)
n_samples, n_features = X.shape
algo = ImplicitForward(n_iter_jac=1000)
estimator = LogisticRegression(
C=1, fit_intercept=False, warm_start=True, max_iter=2000, verbose=False)
from sparse_ho.ho import grad_search
from sparse_ho.utils import Monitor
from sparse_ho.models import SparseLogreg
from sparse_ho.criterion import HeldOutLogistic
from sparse_ho import ImplicitForward
from sparse_ho import Forward
from sparse_ho.grid_search import grid_search
print(__doc__)
dataset = 'rcv1_train'
# dataset = 'simu'
if dataset != 'simu':
X, y = fetch_libsvm(dataset)
X = X[:, :100]
else:
X, y = make_classification(n_samples=100,
n_features=1_000,
random_state=42,
flip_y=0.02)
n_samples = X.shape[0]
idx_train = np.arange(0, n_samples // 2)
idx_val = np.arange(n_samples // 2, n_samples)
print("Starting path computation...")
n_samples = len(y[idx_train])
alpha_max = np.max(np.abs(X[idx_train, :].T.dot(y[idx_train])))
from sparse_ho.criterion import HeldOutMSE
from sparse_ho import Forward
from sparse_ho import ImplicitForward
from sparse_ho.utils import Monitor
from sparse_ho.ho import grad_search
from sparse_ho.grid_search import grid_search
from libsvmdata.datasets import fetch_libsvm
print(__doc__)
dataset = 'rcv1'
# dataset = 'simu'
if dataset == 'rcv1':
X, y = fetch_libsvm('rcv1_train')
else:
X, y = make_regression(n_samples=1000, n_features=1000, noise=40)
n_samples = X.shape[0]
idx_train = np.arange(0, n_samples // 2)
idx_val = np.arange(n_samples // 2, n_samples)
print("Starting path computation...")
n_samples = len(y[idx_train])
alpha_max = np.max(np.abs(X[idx_train, :].T.dot(
y[idx_train]))) / len(idx_train)
log_alpha0 = np.log(alpha_max / 10)
n_alphas = 10
p_alphas = np.geomspace(1, 0.0001, n_alphas)
import sklearn
from sklearn.linear_model import LogisticRegression
from libsvmdata.datasets import fetch_libsvm
from sparse_ho.models import SparseLogreg
from sparse_ho.criterion import LogisticMulticlass
from sparse_ho import ImplicitForward
from sparse_ho.utils import Monitor
from sparse_ho.datasets.utils_datasets import (alpha_max_multiclass,
clean_dataset)
# load data
n_samples = 1000
n_features = 10
X, y = fetch_libsvm('mnist')
my_bool = np.logical_or(np.logical_or(y == 0, y == 1), y == 2)
X = X[my_bool, :]
y = y[my_bool]
# clean data and subsample
X, y = clean_dataset(X, y, n_samples, n_features)
idx_train = np.arange(len(y) // 2)
idx_val = np.arange(len(y) // 2, len(y))
alpha_max, n_classes = alpha_max_multiclass(X, y)
tol = 1e-8
n_classes = np.unique(y).shape[0]
max_iter = 10000
from sparse_ho.ho import grad_search
from sparse_ho.utils import Monitor
from sparse_ho.utils_plot import discrete_cmap
from sparse_ho.optimizers import GradientDescent
# dataset = "rcv1"
dataset = 'simu'
##############################################################################
# Load some data
# dataset = 'rcv1'
dataset = 'simu'
if dataset == 'rcv1':
X, y = fetch_libsvm('rcv1.binary')
y -= y.mean()
y /= np.linalg.norm(y)
else:
X, y, _ = make_correlated_data(n_samples=200,
n_features=400,
snr=5,
random_state=0)
n_samples = X.shape[0]
idx_train = np.arange(0, n_samples // 2)
idx_val = np.arange(n_samples // 2, n_samples)
print("Starting path computation...")
alpha_max = np.max(np.abs(X[idx_train, :].T @ y[idx_train])) / len(idx_train)