def all_tasks(self, skip_aborted=True):
all_tasks = []
all_tasks += getattr(self, 'tasks', [])
task_groups = getattr(self, 'task_groups', [])
all_tasks += [t for task_group in task_groups for t in task_group]
if skip_aborted:
all_tasks = [t for t in all_tasks if not is_aborted(t)]
return all_tasks
def all_tasks(self, skip_aborted=True):
all_tasks = []
all_tasks += getattr(self, 'tasks', [])
task_groups = getattr(self, 'task_groups', [])
all_tasks += [t for task_group in task_groups
for t in task_group]
if skip_aborted:
all_tasks = [t for t in all_tasks if not is_aborted(t)]
return all_tasks
def find_bests(self, n_top=5):
"""Compute the mean score of the completed tasks"""
mean_scores = []
for params, task_group in zip(self.all_parameters, self.task_groups):
evaluations = [Evaluation(*t.get())
for t in task_group
if t.ready() and not is_aborted(t)]
if len(evaluations) == 0:
continue
val_scores = [e.validation_score for e in evaluations]
train_scores = [e.train_score for e in evaluations]
mean_scores.append((np.mean(val_scores), sem(val_scores),
np.mean(train_scores), sem(train_scores),
params))
return sorted(mean_scores, reverse=True)[:n_top]
def boxplot_parameters(self, display_train=False):
"""Plot boxplot for each parameters independently"""
import pylab as pl
results = [
Evaluation(*task.get()) for task_group in self.task_groups
for task in task_group if task.ready() and not is_aborted(task)
]
n_rows = len(self.parameter_grid)
pl.figure()
grid_items = self.parameter_grid.items()
for i, (param_name, param_values) in enumerate(grid_items):
pl.subplot(n_rows, 1, i + 1)
val_scores_per_value = []
train_scores_per_value = []
for param_value in param_values:
train_scores = [
r.train_score for r in results
if r.parameters[param_name] == param_value
]
train_scores_per_value.append(train_scores)
val_scores = [
r.validation_score for r in results
if r.parameters[param_name] == param_value
]
val_scores_per_value.append(val_scores)
widths = 0.25
positions = np.arange(len(param_values)) + 1
offset = 0
if display_train:
offset = 0.175
pl.boxplot(train_scores_per_value,
widths=widths,
positions=positions - offset)
pl.boxplot(val_scores_per_value,
widths=widths,
positions=positions + offset)
pl.xticks(np.arange(len(param_values)) + 1, param_values)
pl.xlabel(param_name)
pl.ylabel("Val. Score")
def find_bests(self, n_top=5):
"""Compute the mean score of the completed tasks"""
mean_scores = []
for params, task_group in zip(self.all_parameters, self.task_groups):
evaluations = [
Evaluation(*t.get()) for t in task_group
if t.ready() and not is_aborted(t)
]
if len(evaluations) == 0:
continue
val_scores = [e.validation_score for e in evaluations]
train_scores = [e.train_score for e in evaluations]
mean_scores.append(
(np.mean(val_scores), sem(val_scores), np.mean(train_scores),
sem(train_scores), params))
return sorted(mean_scores, reverse=True)[:n_top]
def boxplot_parameters(self, display_train=False):
"""Plot boxplot for each parameters independently"""
import pylab as pl
results = [Evaluation(*task.get())
for task_group in self.task_groups
for task in task_group
if task.ready() and not is_aborted(task)]
n_rows = len(self.parameter_grid)
pl.figure()
grid_items = self.parameter_grid.items()
for i, (param_name, param_values) in enumerate(grid_items):
pl.subplot(n_rows, 1, i + 1)
val_scores_per_value = []
train_scores_per_value = []
for param_value in param_values:
train_scores = [r.train_score for r in results
if r.parameters[param_name] == param_value]
train_scores_per_value.append(train_scores)
val_scores = [r.validation_score for r in results
if r.parameters[param_name] == param_value]
val_scores_per_value.append(val_scores)
widths = 0.25
positions = np.arange(len(param_values)) + 1
offset = 0
if display_train:
offset = 0.175
pl.boxplot(
train_scores_per_value, widths=widths,
positions=positions - offset)
pl.boxplot(
val_scores_per_value, widths=widths,
positions=positions + offset)
pl.xticks(np.arange(len(param_values)) + 1, param_values)
pl.xlabel(param_name)
pl.ylabel("Val. Score")
