Tuning DataOps with Optuna#

This example shows how to use Optuna to tune the hyperparameters of a skrub DataOp. As seen in the previous example, skrub DataOps can contain “choices”, objects created with choose_from(), choose_int(), choose_float(), etc. and we can use hyperparameter search techniques to pick the best outcome for each choice. Performing this search with Optuna allows us to benefit from its many features, such as state-of-the-art search strategies, monitoring and visualization, stopping and resuming searches, and parallel or distributed computation.

In order to use Optuna with skrub, the package must be installed first. This can be done with pip:

pip install optuna

A simple regressor and example data.#

We will fit a regressor containing a few choices on a toy dataset. We try 2 regressors: extra trees and ridge. They both have hyperparameters that we want to tune.

from sklearn.ensemble import ExtraTreesRegressor
from sklearn.linear_model import Ridge

import skrub

extra_tree = ExtraTreesRegressor(
    min_samples_leaf=skrub.choose_int(1, 32, log=True, name="min_samples_leaf"),
)
ridge = Ridge(alpha=skrub.choose_float(0.01, 10.0, log=True, name="α"))

regressor = skrub.choose_from(
    {"extra_tree": extra_tree, "ridge": ridge}, name="regressor"
)
data = skrub.var("data")
X = data.drop(columns="MedHouseVal", errors="ignore").skb.mark_as_X()
y = data["MedHouseVal"].skb.mark_as_y()
pred = X.skb.apply(regressor, y=y)
print(pred.skb.describe_param_grid())
- regressor: 'extra_tree'
  min_samples_leaf: choose_int(1, 32, log=True, name='min_samples_leaf')
- regressor: 'ridge'
  α: choose_float(0.01, 10.0, log=True, name='α')

Load data for the example

import pandas as pd
from sklearn.model_selection import KFold

# (We subsample the dataset by half to make the example run faster)
file_path = skrub.datasets.fetch_california_housing().path
df = pd.read_csv(file_path).sample(10_000, random_state=0)

# The environment we will use to fit the learners created by our DataOp.
env = {"data": df}
cv = KFold(n_splits=4, shuffle=True, random_state=0)

Selecting the best hyperparameters with Optuna.#

The simplest way to use Optuna is to pass backend='optuna' to DataOp.skb.make_randomized_search(). It is used very similarly as with the default backend (sklearn.model_selection.RandomizedSearchCV). Additional parameters are available to control the Optuna sampler, storage and study name, and timeout. Note that in order to persist the study and resume it later, the storage parameter must be set to a valid database URL (e.g., a SQLite file). Refer to the User Guide for an example.

search = pred.skb.make_randomized_search(
    backend="optuna", cv=cv, n_iter=10, random_state=10
)
search.fit(env)
search.results_
Running optuna search for study skrub_randomized_search_b7379792-d518-4584-8cc4-202640550fc5 in storage /tmp/tmpdw1h_hmz_skrub_optuna_search_storage/optuna_storage
[I 2026-10-08 13:21:15,982] A new study created in Journal with name: skrub_randomized_search_b7379792-d518-4584-8cc4-202640550fc5
[I 2026-10-08 13:21:16,301] Trial 0 finished with value: 0.5998958893326463 and parameters: {'2:regressor': '1:ridge', '1:α': 0.08737056333717456}. Best is trial 0 with value: 0.5998958893326463.
[I 2026-10-08 13:21:16,608] Trial 1 finished with value: 0.5998965729709886 and parameters: {'2:regressor': '1:ridge', '1:α': 0.17777676175509427}. Best is trial 1 with value: 0.5998965729709886.
[I 2026-10-08 13:21:16,916] Trial 2 finished with value: 0.5998956300607201 and parameters: {'2:regressor': '1:ridge', '1:α': 0.05323908243249831}. Best is trial 1 with value: 0.5998965729709886.
[I 2026-10-08 13:21:17,224] Trial 3 finished with value: 0.5998953213503151 and parameters: {'2:regressor': '1:ridge', '1:α': 0.012709575518456051}. Best is trial 1 with value: 0.5998965729709886.
[I 2026-10-08 13:21:23,452] Trial 4 finished with value: 0.7908631218996123 and parameters: {'2:regressor': '0:extra_tree', '0:min_samples_leaf': 2}. Best is trial 4 with value: 0.7908631218996123.
[I 2026-10-08 13:21:32,040] Trial 5 finished with value: 0.792110790768255 and parameters: {'2:regressor': '0:extra_tree', '0:min_samples_leaf': 1}. Best is trial 5 with value: 0.792110790768255.
[I 2026-10-08 13:21:32,352] Trial 6 finished with value: 0.5998987110257883 and parameters: {'2:regressor': '1:ridge', '1:α': 0.464456825115831}. Best is trial 5 with value: 0.792110790768255.
[I 2026-10-08 13:21:36,316] Trial 7 finished with value: 0.7577499694028037 and parameters: {'2:regressor': '0:extra_tree', '0:min_samples_leaf': 7}. Best is trial 5 with value: 0.792110790768255.
[I 2026-10-08 13:21:41,137] Trial 8 finished with value: 0.7753297869826369 and parameters: {'2:regressor': '0:extra_tree', '0:min_samples_leaf': 4}. Best is trial 5 with value: 0.792110790768255.
[I 2026-10-08 13:21:47,237] Trial 9 finished with value: 0.7903329131373835 and parameters: {'2:regressor': '0:extra_tree', '0:min_samples_leaf': 2}. Best is trial 5 with value: 0.792110790768255.
[I 2026-10-08 13:21:47,238] A new study created in memory with name: skrub_randomized_search_b7379792-d518-4584-8cc4-202640550fc5

Please enable javascript

The skrub table reports need javascript to display correctly. If you are displaying a report in a Jupyter notebook and you see this message, you may need to re-execute the cell or to trust the notebook (button on the top right or "File > Trust notebook").



The usual results_, detailed_results_ and plot_results() are still available.



The Optuna Study that was used to run the hyperparameter search is available in the attribute study_:

<optuna.study.study.Study object at 0x7d129e2cdfa0>
{'2:regressor': '0:extra_tree', '0:min_samples_leaf': 1}

This allows us to use Optuna’s reporting capabilities provided in optuna.visualization or optuna-dashboard.

import optuna

optuna.visualization.plot_slice(search.study_, params=["0:min_samples_leaf"])


Using Optuna directly for more advanced use cases#

Often we may want more control over the use of Optuna, or to access functionality not available through DataOp.skb.make_randomized_search() such as the ask-and-tell interface, trial pruning, callbacks, multi-objective optimization, etc. .

Directly using Optuna ourselves is also easy, as we will show now. What makes this possible is that we can pass an Optuna Trial to DataOp.skb.make_learner() in which case the parameters suggested by the trial are used to create the learner.

We revisit the example above, following the typical Optuna workflow.

The optuna.Study runs the hyperparameter search.

Its method optimize is given an objective function. The objective must accept a Trial object (which is produced by the study and picks the parameters for a given evaluation of the objective) and return the value to maximize (or minimize).

To use Optuna with a DataOp, we just need to pass the Trial object to DataOp.skb.make_learner(). This creates a SkrubLearner initialized with the parameters picked by the optuna Trial.

We can then cross-validate the SkrubLearner, or score it however we prefer, and return the score so that the optuna Study can take it into account.

Here we return a single score (R²), but multi-objective optimization is also possible. Please refer to the Optuna documentation for more information.

def objective(trial):
    learner = pred.skb.make_learner(choose=trial)
    cv_results = skrub.cross_validate(learner, environment=env, cv=cv)
    return cv_results["test_score"].mean()


study = optuna.create_study(direction="maximize")
study.optimize(objective, n_trials=10)
study.best_params
[I 2026-10-08 13:21:54,343] A new study created in memory with name: no-name-90088fa2-7ec2-480d-a1a5-3f29fc743321
[I 2026-10-08 13:21:54,647] Trial 0 finished with value: 0.5998983348186715 and parameters: {'2:regressor': '1:ridge', '1:α': 0.4135712636368853}. Best is trial 0 with value: 0.5998983348186715.
[I 2026-10-08 13:21:58,031] Trial 1 finished with value: 0.7326726766368489 and parameters: {'2:regressor': '0:extra_tree', '0:min_samples_leaf': 14}. Best is trial 1 with value: 0.7326726766368489.
[I 2026-10-08 13:21:58,300] Trial 2 finished with value: 0.5998956721102164 and parameters: {'2:regressor': '1:ridge', '1:α': 0.058768868596943635}. Best is trial 1 with value: 0.7326726766368489.
[I 2026-10-08 13:22:07,006] Trial 3 finished with value: 0.7937163330264896 and parameters: {'2:regressor': '0:extra_tree', '0:min_samples_leaf': 1}. Best is trial 3 with value: 0.7937163330264896.
[I 2026-10-08 13:22:07,275] Trial 4 finished with value: 0.599896750528651 and parameters: {'2:regressor': '1:ridge', '1:α': 0.20135557837409876}. Best is trial 3 with value: 0.7937163330264896.
[I 2026-10-08 13:22:07,543] Trial 5 finished with value: 0.5998957743369033 and parameters: {'2:regressor': '1:ridge', '1:α': 0.07222164306087846}. Best is trial 3 with value: 0.7937163330264896.
[I 2026-10-08 13:22:07,815] Trial 6 finished with value: 0.5998965004388972 and parameters: {'2:regressor': '1:ridge', '1:α': 0.16815654321270762}. Best is trial 3 with value: 0.7937163330264896.
[I 2026-10-08 13:22:12,128] Trial 7 finished with value: 0.7683714119270719 and parameters: {'2:regressor': '0:extra_tree', '0:min_samples_leaf': 5}. Best is trial 3 with value: 0.7937163330264896.
[I 2026-10-08 13:22:15,280] Trial 8 finished with value: 0.7249743279656428 and parameters: {'2:regressor': '0:extra_tree', '0:min_samples_leaf': 17}. Best is trial 3 with value: 0.7937163330264896.
[I 2026-10-08 13:22:15,551] Trial 9 finished with value: 0.5998980731286335 and parameters: {'2:regressor': '1:ridge', '1:α': 0.3782880194545392}. Best is trial 3 with value: 0.7937163330264896.

{'2:regressor': '0:extra_tree', '0:min_samples_leaf': 1}

We can also use Optuna’s visualization capabilities to inspect the study:



Now we build a learner with the best hyperparameters and fit it on the full dataset:

best_learner = pred.skb.make_learner(choose=study.best_trial)

# This would achieve the same result:
# best_learner = pred.skb.make_learner()
# best_learner.set_params(**study.best_params)

best_learner.fit(env)
print(best_learner.describe_params())
{'min_samples_leaf': 1, 'regressor': 'extra_tree'}

Total running time of the script: (1 minutes 5.783 seconds)

Estimated memory usage: 728 MB

Gallery generated by Sphinx-Gallery