AdaBoost Optimization

Hyperparameter optimization for AdaBoost ensemble algorithm.

from sklearn.datasets import load_breast_cancer
from sklearn.ensemble import AdaBoostClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, f1_score
import numpy as np
import plotly
from mloptimizer.interfaces import HyperparameterSpaceBuilder, GeneticSearch
from mloptimizer.application.reporting.plots import plotly_search_space, plotly_logbook

Load and prepare the dataset

print("Loading Breast Cancer dataset...")
data = load_breast_cancer()
X, y = data.data, data.target

print(f"Dataset shape: {X.shape}")

Loading Breast Cancer dataset...
Dataset shape: (569, 30)

Split the data

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)

Define the hyperparameter space

hyperparam_space = HyperparameterSpaceBuilder.get_default_space(
    estimator_class=AdaBoostClassifier
)

Configure and run the genetic optimization

genetic_params = {
    'generations': 5,
    'population_size': 8,
    'n_elites': 2,
    'seed': 42,
    'use_mlflow': False,
    'use_parallel': False
}

opt = GeneticSearch(
    estimator_class=AdaBoostClassifier,
    hyperparam_space=hyperparam_space,
    cv=3,
    scoring='accuracy',
    **genetic_params
)

print("Starting AdaBoostClassifier optimization...")
opt.fit(X_train, y_train)

/home/docs/checkouts/readthedocs.org/user_builds/mloptimizer/checkouts/master/examples/plot_adaboost.py:47: UserWarning: Expected mutations per offspring is very low (0.32). With mutpb=0.8, indpb=0.2, and 2 hyperparameters, the population will converge prematurely. Recommended: mutpb >= 0.8, indpb >= 0.2 (gives ~0.3 mutations/offspring).
  opt = GeneticSearch(
Starting AdaBoostClassifier optimization...

Genetic execution:   0%|          | 0/6 [00:00<?, ?it/s, best fitness=?]
Genetic execution:  17%|█▋        | 1/6 [00:00<00:01,  4.05it/s, best fitness=0.967]
Genetic execution:  17%|█▋        | 1/6 [00:01<00:05,  1.09s/it, best fitness=0.967]
Genetic execution:  17%|█▋        | 1/6 [00:01<00:07,  1.56s/it, best fitness=0.967]
Genetic execution:  17%|█▋        | 1/6 [00:01<00:09,  1.89s/it, best fitness=0.969]
Genetic execution:  33%|███▎      | 2/6 [00:04<00:08,  2.24s/it, best fitness=0.969]
Genetic execution:  33%|███▎      | 2/6 [00:04<00:08,  2.24s/it, best fitness=0.974]
Genetic execution:  50%|█████     | 3/6 [00:06<00:06,  2.28s/it, best fitness=0.974]
Genetic execution:  67%|██████▋   | 4/6 [00:09<00:04,  2.33s/it, best fitness=0.974]
Genetic execution:  83%|████████▎ | 5/6 [00:10<00:02,  2.09s/it, best fitness=0.974]
Genetic execution: 100%|██████████| 6/6 [00:12<00:00,  1.94s/it, best fitness=0.974]
Genetic execution: 100%|██████████| 6/6 [00:14<00:00,  2.36s/it, best fitness=0.974]

GeneticSearch(cv=StratifiedKFold(n_splits=3, random_state=42, shuffle=True),
              estimator_class=<class 'sklearn.ensemble._weight_boosting.AdaBoostClassifier'>,
              generations=5,
              hyperparam_space=HyperparameterSpace(fixed_hyperparams={'algorithm': 'SAMME'}, evolvable_hyperparams={'n_estimators': Hyperparam('n_estimators', 10, 200, 'int'), 'learning_rate': Hyperparam('learning_rate', 1, 200, 'float', 100)}),
              n_elites=2, population_size=8, scoring='accuracy', seed=42,
              use_parallel=False)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Evaluate the optimized model

best_clf = opt.best_estimator_
y_pred = best_clf.predict(X_test)
test_accuracy = accuracy_score(y_test, y_pred)
test_f1 = f1_score(y_test, y_pred, average='binary')

print(f"\nOptimization completed!")
print(f"Best parameters: {opt.best_params_}")
print(f"Test accuracy: {test_accuracy:.4f}")
print(f"Test F1: {test_f1:.4f}")

Optimization completed!
Best parameters: {'algorithm': 'SAMME', 'estimator': None, 'learning_rate': 0.63, 'n_estimators': 67, 'random_state': 42}
Test accuracy: 0.9561
Test F1: 0.9660

Visualize the search space

population_df = opt.populations_
top_params = ['n_estimators', 'learning_rate', 'fitness']
df_filtered = population_df[top_params]
g_search_space = plotly_search_space(df_filtered, top_params)
g_search_space.update_layout(
    title="AdaBoostClassifier Hyperparameter Search Space",
    autosize=True,
    width=None,
    height=650
)
plotly.io.show(g_search_space, config={'responsive': True})

Visualize the optimization evolution

g_logbook = plotly_logbook(opt.logbook_, population_df)
g_logbook.update_layout(
    title="AdaBoostClassifier Optimization Evolution",
    autosize=True,
    width=None,
    height=500
)
plotly.io.show(g_logbook, config={'responsive': True})

Analyze optimization performance

print("\n=== Optimization Performance ===")
print(f"Unique evaluations performed: {opt.n_trials_}")
print(f"Total individuals in population history: {len(opt.populations_)}")
print(f"Optimization time: {opt.optimization_time_:.4f} seconds")
print(f"Time per evaluation: {opt.optimization_time_ / opt.n_trials_:.4f} seconds")

=== Optimization Performance ===
Unique evaluations performed: 33
Total individuals in population history: 48
Optimization time: 14.1626 seconds
Time per evaluation: 0.4292 seconds