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_gridsearch_sklearn_regression():
scorer = RegressionFoldingScorer(mean_squared_error)
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)
grid = GridOptimalSearchCV(SklearnRegressor(clf=AdaBoostRegressor()),
generator, scorer)
# parallel_profile='threads-3')
_ = check_grid(grid,
False,
False,
False,
use_weights=True,
classification=False)
regressor = check_grid(grid,
False,
False,
False,
use_weights=False,
classification=False)
# Check parameters of best fitted classifier
assert 2 <= len(regressor.features) <= 3, 'Features were not set'
params = regressor.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_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 grid_sklearn(score_function):
grid_param = OrderedDict({
"n_estimators": [10, 20],
"learning_rate": [0.1, 0.05],
'features': [['column0', 'column1'], ['column0', 'column1', 'column2']]
})
generator = RegressionParameterOptimizer(grid_param)
scorer = FoldingScorer(score_function)
grid = GridOptimalSearchCV(SklearnClassifier(clf=AdaBoostClassifier()),
generator, scorer)
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]