def learn_model(draw, X, y, task, learner, n_estimators, n_targets):
# for lgbm or xgb return the booster or sklearn object?
use_sklearn_estimator = draw(st.booleans())
if learner == 'xgb':
assume(has_xgboost())
if task == 'regression':
objective = draw(
st.sampled_from(['reg:squarederror', 'reg:pseudohubererror']))
model = xgb.XGBRegressor(n_estimators=n_estimators,
tree_method='gpu_hist',
objective=objective,
enable_categorical=True,
verbosity=0).fit(X, y)
elif task == 'classification':
valid_objectives = [
'binary:logistic',
'binary:hinge',
'binary:logitraw',
'count:poisson',
]
if n_targets > 2:
valid_objectives += [
'rank:pairwise', 'rank:ndcg', 'rank:map', 'multi:softmax',
'multi:softprob'
]
objective = draw(st.sampled_from(valid_objectives))
model = xgb.XGBClassifier(n_estimators=n_estimators,
tree_method='gpu_hist',
objective=objective,
enable_categorical=True,
verbosity=0).fit(X, y)
pred = model.predict(X, output_margin=True)
if not use_sklearn_estimator:
model = model.get_booster()
return model, pred
elif learner == 'rf':
predict_model = 'GPU ' if y.dtype == np.float32 else 'CPU'
if task == 'regression':
model = cuml.ensemble.RandomForestRegressor(
n_estimators=n_estimators)
model.fit(X, y)
pred = model.predict(X, predict_model=predict_model)
elif task == 'classification':
model = cuml.ensemble.RandomForestClassifier(
n_estimators=n_estimators)
model.fit(X, y)
pred = model.predict_proba(X)
return model, pred
elif learner == 'skl_rf':
assume(has_sklearn())
if task == 'regression':
model = sklrfr(n_estimators=n_estimators)
model.fit(X, y)
pred = model.predict(X)
elif task == 'classification':
model = sklrfc(n_estimators=n_estimators)
model.fit(X, y)
pred = model.predict_proba(X)
return model, pred
elif learner == 'lgbm':
assume(has_lightgbm())
if task == 'regression':
model = lgb.LGBMRegressor(n_estimators=n_estimators).fit(X, y)
elif task == 'classification':
model = lgb.LGBMClassifier(n_estimators=n_estimators).fit(X, y)
pred = model.predict(X, raw_score=True)
if not use_sklearn_estimator:
model = model.booster_
return model, pred
@pytest.mark.skipif(has_xgboost() is False, reason="need to install xgboost")
def test_output_args(small_classifier_and_preds):
model_path, X, xgb_preds = small_classifier_and_preds
fm = ForestInference.load(model_path,
algo='TREE_REORG',
output_class=False,
threshold=0.50)
X = np.asarray(X)
fil_preds = fm.predict(X)
fil_preds = np.reshape(fil_preds, np.shape(xgb_preds))
assert array_equal(fil_preds, xgb_preds, 1e-3)
@pytest.mark.parametrize('num_classes', [2, 5])
@pytest.mark.skipif(has_lightgbm() is False, reason="need to install lightgbm")
def test_lightgbm(tmp_path, num_classes):
import lightgbm as lgb
X, y = simulate_data(500,
10 if num_classes == 2 else 50,
num_classes,
random_state=43210,
classification=True)
train_data = lgb.Dataset(X, label=y)
num_round = 5
model_path = str(os.path.join(tmp_path, 'lgb.model'))
if num_classes == 2:
param = {
'objective': 'binary',
'metric': 'binary_logloss',
from cuml.common.exceptions import NotFittedError
from cuml.ensemble import RandomForestRegressor as curfr
from cuml.ensemble import RandomForestClassifier as curfc
import cuml
from cuml.testing.utils import as_type
# See issue #4729
# Xgboost disabled due to CI failures
xgb = None
def has_xgboost():
return False
if has_lightgbm():
import lightgbm as lgb
if has_shap():
import shap
if has_sklearn():
from sklearn.datasets import make_regression, make_classification
from sklearn.ensemble import RandomForestRegressor as sklrfr
from sklearn.ensemble import RandomForestClassifier as sklrfc
def make_classification_with_categorical(*,
n_samples,
n_features,
n_categorical,
n_informative,
n_redundant,