我希望在笔记本中使用最佳模型来预测不同的测试批次。
可重现的示例(取自Optuna Github):
import lightgbm as lgb
import numpy as np
import sklearn.datasets
import sklearn.metrics
from sklearn.model_selection import train_test_split
import optuna
# FYI: Objective functions can take additional arguments
# (https://optuna.readthedocs.io/en/stable/faq.html#objective-func-additional-args).
def objective(trial):
data, target = sklearn.datasets.load_breast_cancer(return_X_y=True)
train_x, valid_x, train_y, valid_y = train_test_split(data, target, test_size=0.25)
dtrain = lgb.Dataset(train_x, label=train_y)
dvalid = lgb.Dataset(valid_x, label=valid_y)
param = {
"objective": "binary",
"metric": "auc",
"verbosity": -1,
"boosting_type": "gbdt",
"lambda_l1": trial.suggest_loguniform("lambda_l1", 1e-8, 10.0),
"lambda_l2": trial.suggest_loguniform("lambda_l2", 1e-8, 10.0),
"num_leaves": trial.suggest_int("num_leaves", 2, 256),
"feature_fraction": trial.suggest_uniform("feature_fraction", 0.4, 1.0),
"bagging_fraction": trial.suggest_uniform("bagging_fraction", 0.4, 1.0),
"bagging_freq": trial.suggest_int("bagging_freq", 1, 7),
"min_child_samples": trial.suggest_int("min_child_samples", 5, 100),
}
# Add a callback for pruning.
pruning_callback = optuna.integration.LightGBMPruningCallback(trial, "auc")
gbm = lgb.train(
param, dtrain, valid_sets=[dvalid], verbose_eval=False, callbacks=[pruning_callback]
)
preds = gbm.predict(valid_x)
pred_labels = np.rint(preds)
accuracy = sklearn.metrics.accuracy_score(valid_y, pred_labels)
return accuracy
我理解下面的研究将调整准确性。我想以某种方式检索出研究中最佳的模型(而不仅仅是参数),而不必将其保存为pickle文件,我只想在笔记本的其他地方使用该模型。
if __name__ == "__main__":
study = optuna.create_study(
pruner=optuna.pruners.MedianPruner(n_warmup_steps=10), direction="maximize"
)
study.optimize(objective, n_trials=100)
print("Best trial:")
trial = study.best_trial
print(" Params: ")
for key, value in trial.params.items():
print(" {}: {}".format(key, value))
期望的输出将是
best_model = ~model from above~
new_target_pred = best_model.predict(new_data_test)
metrics.accuracy_score(new_target_test, new__target_pred)