Search space graph

mloptimizer provides a function to plot the search space of the optimization.

from sklearn.tree import DecisionTreeClassifier
from mloptimizer.domain.evaluation import kfold_stratified_score
from mloptimizer.application.reporting.plots import plotly_search_space
import plotly
import os
from sklearn.datasets import load_iris
from mloptimizer.interfaces import HyperparameterSpaceBuilder, GeneticSearch
from sklearn.model_selection import StratifiedKFold

Load the iris dataset to obtain a vector of features X and a vector of labels y. Another dataset or a custom one can be used

X, y = load_iris(return_X_y=True)

Define the HyperparameterSpace, you can use the default hyperparameters for the machine learning model that you want to optimize. In this case we use the default hyperparameters for a DecisionTreeClassifier. Another dataset or a custom one can be used

hyperparam_space = HyperparameterSpaceBuilder.get_default_space(estimator_class=DecisionTreeClassifier)

The GeneticSearch class is used to optimize the hyperparameters of a machine learning model.

cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
opt = GeneticSearch(
        estimator_class=DecisionTreeClassifier,
        hyperparam_space=hyperparam_space,
        **{"generations": 30, "population_size": 100},
        cv=cv
        )

To optimizer the classifier we need to call the fit method.

opt.fit(X, y)
clf = opt.best_estimator_

Genetic execution:   0%|          | 0/31 [00:00<?, ?it/s, best fitness=?]
Genetic execution:   3%|▎         | 1/31 [00:00<00:00, 77.34it/s, best fitness=0.94]
Genetic execution:   3%|▎         | 1/31 [00:00<00:13,  2.29it/s, best fitness=0.96]
Genetic execution:   6%|▋         | 2/31 [00:00<00:11,  2.55it/s, best fitness=0.96]
Genetic execution:  10%|▉         | 3/31 [00:01<00:13,  2.04it/s, best fitness=0.96]
Genetic execution:  13%|█▎        | 4/31 [00:02<00:14,  1.84it/s, best fitness=0.96]
Genetic execution:  16%|█▌        | 5/31 [00:02<00:14,  1.74it/s, best fitness=0.96]
Genetic execution:  19%|█▉        | 6/31 [00:03<00:14,  1.68it/s, best fitness=0.96]
Genetic execution:  23%|██▎       | 7/31 [00:03<00:14,  1.65it/s, best fitness=0.96]
Genetic execution:  26%|██▌       | 8/31 [00:04<00:14,  1.62it/s, best fitness=0.96]
Genetic execution:  29%|██▉       | 9/31 [00:05<00:13,  1.60it/s, best fitness=0.96]
Genetic execution:  32%|███▏      | 10/31 [00:05<00:13,  1.59it/s, best fitness=0.96]
Genetic execution:  35%|███▌      | 11/31 [00:06<00:12,  1.58it/s, best fitness=0.96]
Genetic execution:  39%|███▊      | 12/31 [00:07<00:12,  1.57it/s, best fitness=0.96]
Genetic execution:  42%|████▏     | 13/31 [00:07<00:11,  1.57it/s, best fitness=0.96]
Genetic execution:  45%|████▌     | 14/31 [00:08<00:10,  1.56it/s, best fitness=0.96]
Genetic execution:  48%|████▊     | 15/31 [00:09<00:10,  1.56it/s, best fitness=0.96]
Genetic execution:  52%|█████▏    | 16/31 [00:09<00:09,  1.55it/s, best fitness=0.96]
Genetic execution:  55%|█████▍    | 17/31 [00:10<00:09,  1.55it/s, best fitness=0.96]
Genetic execution:  58%|█████▊    | 18/31 [00:11<00:08,  1.55it/s, best fitness=0.96]
Genetic execution:  61%|██████▏   | 19/31 [00:11<00:07,  1.54it/s, best fitness=0.96]
Genetic execution:  65%|██████▍   | 20/31 [00:12<00:07,  1.54it/s, best fitness=0.96]
Genetic execution:  68%|██████▊   | 21/31 [00:12<00:06,  1.54it/s, best fitness=0.96]
Genetic execution:  71%|███████   | 22/31 [00:13<00:05,  1.53it/s, best fitness=0.96]
Genetic execution:  74%|███████▍  | 23/31 [00:14<00:05,  1.53it/s, best fitness=0.96]
Genetic execution:  77%|███████▋  | 24/31 [00:14<00:04,  1.53it/s, best fitness=0.96]
Genetic execution:  81%|████████  | 25/31 [00:15<00:03,  1.53it/s, best fitness=0.96]
Genetic execution:  84%|████████▍ | 26/31 [00:16<00:03,  1.52it/s, best fitness=0.96]
Genetic execution:  87%|████████▋ | 27/31 [00:16<00:02,  1.52it/s, best fitness=0.96]
Genetic execution:  90%|█████████ | 28/31 [00:17<00:01,  1.52it/s, best fitness=0.96]
Genetic execution:  94%|█████████▎| 29/31 [00:18<00:01,  1.51it/s, best fitness=0.96]
Genetic execution:  97%|█████████▋| 30/31 [00:18<00:00,  1.51it/s, best fitness=0.96]
Genetic execution: 100%|██████████| 31/31 [00:19<00:00,  1.51it/s, best fitness=0.96]
Genetic execution: 100%|██████████| 31/31 [00:20<00:00,  1.53it/s, best fitness=0.96]

Following we can generate the plot of the search space

population_df = opt.populations_
param_names = list(opt.get_evolvable_hyperparams().keys())
param_names.append("fitness")
df = population_df[param_names]
g_search_space = plotly_search_space(df, param_names)
plotly.io.show(g_search_space)

At the end of the evolution the graph is saved as an html at the path:

print(opt._optimizer_service.optimizer.tracker.graphics_path)
print(os.listdir(opt._optimizer_service.optimizer.tracker.graphics_path))

./20250807_114202_DecisionTreeClassifier/graphics
['search_space.html', 'logbook.html']

The data to generate the graph is available at the path:

print(opt._optimizer_service.optimizer.tracker.results_path)
print(os.listdir(opt._optimizer_service.optimizer.tracker.results_path))

del opt

./20250807_114202_DecisionTreeClassifier/results
['populations.csv', 'logbook.csv']