def sample_parallel_proc():
from pyrallel import mmap_utils, model_selection
_ = reload(mmap_utils), reload(model_selection)
from sklearn.datasets import load_digits
from sklearn.preprocessing import MinMaxScaler
digits = load_digits()
X = MinMaxScaler().fit_transform(digits.data)
y = digits.target
digits_cv_split_filenames = mmap_utils.persist_cv_splits('digits_10', X, y, 10)
mmap_utils.warm_mmap_on_cv_splits(client, digits_cv_split_filenames)
from sklearn.svm import LinearSVC
from collections import OrderedDict
import numpy as np
linear_svc_params = OrderedDict((
('C', np.logspace(-2, 2, 5)),
))
linear_svc = LinearSVC()
linear_svc_search = model_selection.RandomizedGridSeach(lb_view)
linear_svc_search.launch_for_splits(linear_svc, linear_svc_params, digits_cv_split_filenames)
def main():
client = Client()
print 'n. clients: ', len(client)
digits = load_digits()
X = MinMaxScaler().fit_transform(digits.data)
y = digits.target
pre_processing = hp.choice('preproc_algo', [
scope.PCA(
n_components=1 + hp.qlognormal(
'pca_n_comp', np.log(10), np.log(10), 1),
whiten=hp.choice(
'pca_whiten', [False, True])),
scope.GMM(
n_components=1 + hp.qlognormal(
'gmm_n_comp', np.log(100), np.log(10), 1),
covariance_type=hp.choice(
'gmm_covtype', ['spherical', 'tied', 'diag', 'full'])),
])
classifier = hp.choice('classifier', [
scope.DecisionTreeClassifier(
criterion=hp.choice('dtree_criterion', ['gini', 'entropy']),
max_features=hp.uniform('dtree_max_features', 0, 1),
max_depth=hp.quniform('dtree_max_depth', 1, 25, 1)),
scope.SVC(
C=hp.lognormal('svc_rbf_C', 0, 3),
kernel='rbf',
gamma=hp.lognormal('svc_rbf_gamma', 0, 2),
tol=hp.lognormal('svc_rbf_tol', np.log(1e-3), 1)),
])
sklearn_space = {'pre_processing': pre_processing,
'classifier': classifier}
digits_cv_split_filenames = mmap_utils.persist_cv_splits(
X, y, name='digits_10', n_cv_iter=10)
mmap_utils.warm_mmap_on_cv_splits(client, digits_cv_split_filenames)
trials = hyperselect.IPythonTrials(client)
trials.fmin(
partial(compute_evaluation,
cv_split_filename=digits_cv_split_filenames[0],
),
sklearn_space,
algo=hyperopt.tpe.suggest,
max_evals=30,
verbose=1,
)
trials.wait()
print trials.best_trial
def launch_for_splits(self,
model,
parameter_grid,
cv_split_filenames,
pre_warm=True,
collect_files_on_reset=False):
"""Launch a Grid Search on precomputed CV splits."""
# Abort any existing processing and erase previous state
self.reset()
self.parameter_grid = parameter_grid
# Mark the files for garbage collection
if collect_files_on_reset:
self._temp_files.extend(cv_split_filenames)
# Warm the OS disk cache on each host with sequential reads instead
# of having concurrent evaluation tasks compete for the the same host
# disk resources later.
if pre_warm:
warm_mmap_on_cv_splits(self.lb_view.client, cv_split_filenames)
# Randomize the grid order
random_state = check_random_state(self.random_state)
self.all_parameters = list(ParameterGrid(parameter_grid))
random_state.shuffle(self.all_parameters)
for params in self.all_parameters:
task_group = []
for cv_split_filename in cv_split_filenames:
task = self.lb_view.apply(compute_evaluation,
model,
cv_split_filename,
params=params)
task_group.append(task)
self.task_groups.append(task_group)
# Make it possible to chain method calls
return self
def launch_for_splits(self, model, parameter_grid, cv_split_filenames,
pre_warm=True, collect_files_on_reset=False):
"""Launch a Grid Search on precomputed CV splits."""
# Abort any existing processing and erase previous state
self.reset()
self.parameter_grid = parameter_grid
# Mark the files for garbage collection
if collect_files_on_reset:
self._temp_files.extend(cv_split_filenames)
# Warm the OS disk cache on each host with sequential reads instead
# of having concurrent evaluation tasks compete for the the same host
# disk resources later.
if pre_warm:
warm_mmap_on_cv_splits(self.lb_view.client, cv_split_filenames)
# Randomize the grid order
random_state = check_random_state(self.random_state)
self.all_parameters = list(ParameterGrid(parameter_grid))
random_state.shuffle(self.all_parameters)
for params in self.all_parameters:
task_group = []
for cv_split_filename in cv_split_filenames:
task = self.lb_view.apply(
compute_evaluation,
model, cv_split_filename, gini=gini, params=params)
task_group.append(task)
self.task_groups.append(task_group)
# Make it possible to chain method calls
return self
