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_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_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_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(QuadraticDiscriminantAnalysis())
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()
print "Downloaded magic04.data"
data = pandas.read_csv('toy_datasets/magic04.data', names=columns)
labels = numpy.array(data['g'] == 'g', dtype=int)
data = data.drop('g', axis=1)
import numpy
import numexpr
import pandas
from rep import utils
from sklearn.ensemble import GradientBoostingClassifier
from rep.report.metrics import RocAuc
from rep.metaml import GridOptimalSearchCV, FoldingScorer, RandomParameterOptimizer
from rep.estimators import SklearnClassifier, TMVAClassifier, XGBoostRegressor
# define grid parameters
grid_param = {}
grid_param['learning_rate'] = [0.2, 0.1, 0.05, 0.02, 0.01]
grid_param['max_depth'] = [2, 3, 4, 5]
# use random hyperparameter optimization algorithm
generator = RandomParameterOptimizer(grid_param)
# define folding scorer
scorer = FoldingScorer(RocAuc(), folds=3, fold_checks=3)
estimator = SklearnClassifier(GradientBoostingClassifier(n_estimators=30))
#grid_finder = GridOptimalSearchCV(estimator, generator, scorer)
#% time grid_finder.fit(data, labels)
grid_finder = GridOptimalSearchCV(estimator, generator, scorer, parallel_profile="default")
print "start grid search"
grid_finder.fit(data, labels)
grid_finder.params_generator.print_results()
assert 10 == grid_finder.params_generator.n_evaluations, "oops"
data = data.drop('g', axis=1)
import numpy
import numexpr
import pandas
from rep import utils
from sklearn.ensemble import GradientBoostingClassifier
from rep.report.metrics import RocAuc
from rep.metaml import GridOptimalSearchCV, FoldingScorer, RandomParameterOptimizer
from rep.estimators import SklearnClassifier, TMVAClassifier, XGBoostRegressor
# define grid parameters
grid_param = {}
grid_param['learning_rate'] = [0.2, 0.1, 0.05, 0.02, 0.01]
grid_param['max_depth'] = [2, 3, 4, 5]
# use random hyperparameter optimization algorithm
generator = RandomParameterOptimizer(grid_param)
# define folding scorer
scorer = FoldingScorer(RocAuc(), folds=3, fold_checks=3)
estimator = SklearnClassifier(GradientBoostingClassifier(n_estimators=30))
#grid_finder = GridOptimalSearchCV(estimator, generator, scorer)
#% time grid_finder.fit(data, labels)
grid_finder = GridOptimalSearchCV(estimator,
generator,
scorer,
parallel_profile="default")
print "start grid search"
grid_finder.fit(data, labels)
grid_finder.params_generator.print_results()
assert 10 == grid_finder.params_generator.n_evaluations, "oops"