def test_gridsearch_sklearn():
metric = numpy.random.choice([OptimalAMS(), RocAuc(), LogLoss()])
scorer = ClassificationFoldingScorer(metric)
maximization = True
if isinstance(metric, LogLoss):
maximization = False
grid_param = OrderedDict({
"n_estimators": [10, 20],
"learning_rate": [0.1, 0.05],
'features': [['column0', 'column1'], ['column0', 'column1', 'column2']]
})
generator = RegressionParameterOptimizer(grid_param,
n_evaluations=4,
maximize=maximization)
grid = GridOptimalSearchCV(SklearnClassifier(clf=AdaBoostClassifier()),
generator,
scorer,
parallel_profile='threads-3')
_ = check_grid(grid, False, False, False, use_weights=True)
classifier = check_grid(grid, False, False, False, use_weights=False)
# Check parameters of best fitted classifier
assert 2 <= len(classifier.features) <= 3, 'Features were not set'
params = classifier.get_params()
for key in grid_param:
if key in params:
assert params[key] == grid.generator.best_params_[key]
else:
assert params['clf__' + key] == grid.generator.best_params_[key]
def test_gridsearch_metrics_threads(n_threads=3):
X, y, sample_weight = generate_classification_data(n_classes=2,
distance=0.7)
param_grid = OrderedDict({'reg_param': numpy.linspace(0, 1, 20)})
from itertools import cycle
optimizers = cycle([
RegressionParameterOptimizer(param_grid=param_grid,
n_evaluations=4,
start_evaluations=2),
SubgridParameterOptimizer(param_grid=param_grid, n_evaluations=4),
RandomParameterOptimizer(param_grid=param_grid, n_evaluations=4),
])
for metric in [RocAuc(), OptimalAMS(), OptimalSignificance(), log_loss]:
scorer = FoldingScorer(metric)
clf = SklearnClassifier(QDA())
grid = GridOptimalSearchCV(
estimator=clf,
params_generator=next(optimizers),
scorer=scorer,
parallel_profile='threads-{}'.format(n_threads))
grid.fit(X, y)
print(grid.params_generator.best_score_)
print(grid.params_generator.best_params_)
grid.params_generator.print_results()
def test_optimal_metric_function(size=10000):
labels = numpy.random.randint(0, 2, size=size)
predictions = numpy.random.random(size=[size, 2])
predictions /= predictions.sum(axis=1, keepdims=True)
sample_weight = numpy.random.random(size=size)
for metric, optimal_metric in [(significance, OptimalSignificance()),
(ams, OptimalAMS())]:
optimal_metric.fit(None, labels, sample_weight=sample_weight)
value = optimal_metric(labels,
predictions,
sample_weight=sample_weight)
thresholds, values = optimal_metric.compute(
labels, predictions, sample_weight=sample_weight)
assert numpy.max(values) == value, "maximal value doesn't coincide"
index = numpy.random.randint(0, len(thresholds))
threshold = thresholds[index]
passed = numpy.array(predictions[:, 1] >= threshold)
s = optimal_metric.expected_s * numpy.average(
passed, weights=sample_weight * (labels == 1))
b = optimal_metric.expected_b * numpy.average(
passed, weights=sample_weight * (labels == 0))
assert numpy.allclose(metric(s, b), values[index]), \
'no coincidence {} {} {}'.format(type(optimal_metric), metric(s, b), values[index])
def test_gridsearch_threads(n_threads=3):
scorer = FoldingScorer(numpy.random.choice([OptimalAMS(), RocAuc()]))
grid_param = OrderedDict({
"n_estimators": [10, 20],
"learning_rate": [0.1, 0.05],
'features': [['column0', 'column1'], ['column0', 'column1', 'column2']]
})
generator = RegressionParameterOptimizer(grid_param, n_evaluations=4)
base = SklearnClassifier(clf=AdaBoostClassifier())
grid = GridOptimalSearchCV(base,
generator,
scorer,
parallel_profile='threads-{}'.format(n_threads))
X, y, sample_weight = generate_classification_data()
grid.fit(X, y, sample_weight=sample_weight)
def test_gridsearch_on_tmva():
metric = numpy.random.choice([OptimalAMS(), RocAuc()])
scorer = FoldingScorer(metric)
grid_param = OrderedDict({"MaxDepth": [4, 5], "NTrees": [10, 20]})
generator = SubgridParameterOptimizer(grid_param)
try:
from rep.estimators import TMVAClassifier
grid = GridOptimalSearchCV(
TMVAClassifier(features=['column0', 'column1']), generator, scorer)
classifier = check_grid(grid, False, False, False)
# checking parameters
assert len(classifier.features) == 2
params = classifier.get_params()
for key in grid_param:
assert params[key] == grid.generator.best_params_[key]
except ImportError:
pass
def test_gridsearch_on_tmva():
metric = numpy.random.choice([OptimalAMS(), RocAuc()])
scorer = FoldingScorer(metric)
grid_param = OrderedDict({"MaxDepth": [4, 5], "NTrees": [10, 20]})
generator = SubgridParameterOptimizer(n_evaluations=5,
param_grid=grid_param)
try:
from rep.estimators import TMVAClassifier
base_tmva = TMVAClassifier(
factory_options="Silent=True:V=False:DrawProgressBar=False",
features=['column0', 'column1'],
method='kBDT')
grid = GridOptimalSearchCV(base_tmva, generator, scorer)
classifier = check_grid(grid, False, False, False)
# checking parameters
assert len(classifier.features) == 2
params = classifier.get_params()
for key in grid_param:
assert params[key] == grid.generator.best_params_[key]
except ImportError:
pass