github-starred/awesome-python
2
0
Fork 0
mirror of https://github.com/vinta/awesome-python.git synced 2026-11-08 02:15:12 -06:00
Code Issues 461 Packages Projects Releases Wiki Activity

docs: explain how to prune Optuna trials

Browse Source 
Calling report() and should_prune() alone did not stop an unpromising trial because should_prune() only returns a boolean.

Co-Authored-By: Codex <noreply@openai.com>
This commit is contained in:
Vinta Chen
2026-10-16 19:16:15 +08:00
co-authored by Codex
parent 7f5fee1997
commit 65e23805a1
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
website/data/category_intros/machine-learning.md
+1 -1
View File
@@ -35,6 +35,6 @@ sktime gives forecasting, classification, clustering, and anomaly detection [one
TimesFM is [a pretrained foundation model from Google Research](https://github.com/google-research/timesfm) for time-series forecasting. It forecasts [zero-shot](https://research.google/blog/a-decoder-only-foundation-model-for-time-series-forecasting/), with no training on your data: load a checkpoint and call `predict` with a horizon. Check the license of the weights you download: some are [for non-commercial, non-production use only](https://github.com/google-research/timesfm#license-notice-for-pretrained-weights).
Optuna is [an automatic hyperparameter optimization framework, particularly designed for machine learning](https://optuna.readthedocs.io/en/latest/). Write an `objective` function that takes a `trial`, picks each hyperparameter with methods like `suggest_float`, trains the model, and returns its score. Then [create a study and call `optimize`](https://optuna.readthedocs.io/en/latest/tutorial/10_key_features/001_first.html) with the number of trials. The search space is [plain Python, with conditionals and loops](https://optuna.readthedocs.io/en/latest/tutorial/10_key_features/002_configurations.html), so you can tune an SVM's `C` only in trials that picked an SVM. To stop unpromising trials early, [call `report` and `should_prune`](https://optuna.readthedocs.io/en/latest/tutorial/10_key_features/003_efficient_optimization_algorithms.html#activating-pruners) after each training step.
Optuna is [an automatic hyperparameter optimization framework, particularly designed for machine learning](https://optuna.readthedocs.io/en/latest/). Write an `objective` function that takes a `trial`, picks each hyperparameter with methods like `suggest_float`, trains the model, and returns its score. Then [create a study and call `optimize`](https://optuna.readthedocs.io/en/latest/tutorial/10_key_features/001_first.html) with the number of trials. The search space is [plain Python, with conditionals and loops](https://optuna.readthedocs.io/en/latest/tutorial/10_key_features/002_configurations.html), so you can tune an SVM's `C` only in trials that picked an SVM. To stop unpromising trials early, [call `report` after each training step and raise `optuna.TrialPruned()` when `should_prune()` returns true](https://optuna.readthedocs.io/en/latest/tutorial/10_key_features/003_efficient_optimization_algorithms.html#activating-pruners).
To evaluate a model on time-series data, test it on observations from after its training data. scikit-learn's [TimeSeriesSplit](https://scikit-learn.org/stable/modules/cross_validation.html#time-series-split) does that in cross-validation. For more, see [awesome-machine-learning](https://github.com/josephmisiti/awesome-machine-learning#python).