Branch: master
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
64 lines (50 sloc) 2.57 KB
Optuna example that demonstrates a pruner for XGBoost.
In this example, we optimize the validation accuracy of cancer detection using XGBoost.
We optimize both the choice of booster model and their hyperparameters. Throughout
training of models, a pruner observes intermediate results and stop unpromising trials.
You can run this example as follows:
$ python
from __future__ import division
import numpy as np
import sklearn.datasets
import sklearn.metrics
from sklearn.model_selection import train_test_split
import xgboost as xgb
import optuna
# FYI: Objective functions can take additional arguments
# (
def objective(trial):
data, target = sklearn.datasets.load_breast_cancer(return_X_y=True)
train_x, test_x, train_y, test_y = train_test_split(data, target, test_size=0.25)
dtrain = xgb.DMatrix(train_x, label=train_y)
dtest = xgb.DMatrix(test_x, label=test_y)
param = {
'silent': 1,
'objective': 'binary:logistic',
'booster': trial.suggest_categorical('booster', ['gbtree', 'gblinear', 'dart']),
'lambda': trial.suggest_loguniform('lambda', 1e-8, 1.0),
'alpha': trial.suggest_loguniform('alpha', 1e-8, 1.0)
if param['booster'] == 'gbtree' or param['booster'] == 'dart':
param['max_depth'] = trial.suggest_int('max_depth', 1, 9)
param['eta'] = trial.suggest_loguniform('eta', 1e-8, 1.0)
param['gamma'] = trial.suggest_loguniform('gamma', 1e-8, 1.0)
param['grow_policy'] = trial.suggest_categorical('grow_policy', ['depthwise', 'lossguide'])
if param['booster'] == 'dart':
param['sample_type'] = trial.suggest_categorical('sample_type', ['uniform', 'weighted'])
param['normalize_type'] = trial.suggest_categorical('normalize_type', ['tree', 'forest'])
param['rate_drop'] = trial.suggest_loguniform('rate_drop', 1e-8, 1.0)
param['skip_drop'] = trial.suggest_loguniform('skip_drop', 1e-8, 1.0)
# Add a callback for pruning.
pruning_callback = optuna.integration.XGBoostPruningCallback(trial, 'validation-error')
bst = xgb.train(param, dtrain, evals=[(dtest, 'validation')], callbacks=[pruning_callback])
preds = bst.predict(dtest)
pred_labels = np.rint(preds)
accuracy = sklearn.metrics.accuracy_score(test_y, pred_labels)
return 1.0 - accuracy
if __name__ == '__main__':
study = optuna.create_study(pruner=optuna.pruners.MedianPruner(n_warmup_steps=5))
study.optimize(objective, n_trials=100)