Skip to content

feat: update xgboost integration #1053

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 7, 2025
Merged

feat: update xgboost integration #1053

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5b53077
update
Zeyi-Lin Jun 7, 2025
85a083b
update
Zeyi-Lin Jun 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 23 additions & 1 deletion swanlab/integration/xgboost.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,13 @@


class SwanLabCallback(xgb.callback.TrainingCallback):
def __init__(self):
def __init__(
self,
log_feature_importance: bool = True,
importance_type: str = "gain",
):
self.log_feature_importance = log_feature_importance
self.importance_type = importance_type
# 如果没有注册过实验
swanlab.config["FRAMEWORK"] = "xgboost"
if swanlab.get_run() is None:
Expand All @@ -30,6 +36,9 @@ def before_training(self, model: Booster) -> Booster:
def after_training(self, model: Booster) -> Booster:
"""Run after training is finished."""

if self.log_feature_importance:
self._log_feature_importance(model)

# Log the best score and best iteration
if model.attr("best_score") is not None:
swanlab.log(
Expand All @@ -52,3 +61,16 @@ def after_iteration(self, model: Booster, epoch: int, evals_log: dict) -> bool:

return False

def _log_feature_importance(self, model: Booster) -> None:
fi = model.get_score(importance_type=self.importance_type)
x = list(fi.keys())
y = list(fi.values())
y = [round(i, 2) for i in y] # 保留两位小数
bar = swanlab.echarts.Bar()
bar.add_xaxis(x)
bar.add_yaxis("Importance", y)
swanlab.log(
{
"Feature Importance": bar
}
)
Loading