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 grid_tmva(score_function):
grid_param = OrderedDict({"MaxDepth": [4, 5], "NTrees": [10, 20]})
generator = SubgridParameterOptimizer(grid_param)
scorer = FoldingScorer(score_function)
from rep.estimators import TMVAClassifier
grid = GridOptimalSearchCV(TMVAClassifier(features=['column0', 'column1']),
generator, scorer)
cl = check_grid(grid, False, False, False)
assert 1 <= len(cl.features) <= 3
params = cl.get_params()
for key in grid_param:
assert params[key] == grid.generator.best_params_[key]
def grid_custom(custom):
grid_param = OrderedDict({
"n_estimators": [10, 20],
"learning_rate": [0.1, 0.05],
'features': [['column0', 'column1'], ['column0', 'column1', 'column2']]
})
generator = SubgridParameterOptimizer(grid_param)
grid = GridOptimalSearchCV(
SklearnClassifier(clf=AdaBoostClassifier(),
features=['column0', 'column1']), generator, custom)
cl = check_grid(grid, False, False, False)
assert 1 <= len(cl.features) <= 3
params = cl.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_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_grid_with_custom_scorer():
"""
Introducing here special scorer which always uses all data passed to gridsearch.fit as training
and tests on another fixed dataset (which was passed to scorer) bu computing roc_auc_score from sklearn.
"""
class CustomScorer(object):
def __init__(self, testX, testY):
self.testY = testY
self.testX = testX
def __call__(self, base_estimator, params, X, y, sample_weight=None):
cl = clone(base_estimator)
cl.set_params(**params)
if sample_weight is not None:
cl.fit(X, y, sample_weight)
else:
cl.fit(X, y)
return roc_auc_score(self.testY,
cl.predict_proba(self.testX)[:, 1])
X, y, _ = generate_classification_data()
custom_scorer = CustomScorer(X, y)
grid_param = OrderedDict({
"n_estimators": [10, 20],
"learning_rate": [0.1, 0.05],
'features': [['column0', 'column1'], ['column0', 'column1', 'column2']]
})
generator = SubgridParameterOptimizer(grid_param)
base_estimator = SklearnClassifier(clf=AdaBoostClassifier())
grid = GridOptimalSearchCV(base_estimator, generator, custom_scorer)
cl = check_grid(grid, False, False, False)
assert len(cl.features) <= 3
params = cl.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_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