ضبط المعاملات الفائقة

from sklearn.model_selection import (GridSearchCV, RandomizedSearchCV,
                                       cross_val_score, train_test_split)
from sklearn.experimental import enable_halving_search_cv  class="tok-comment"># noqa
from sklearn.model_selection import HalvingRandomSearchCV
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.datasets import make_classification
from scipy.stats import uniform, randint
import optuna  class="tok-comment"># for Bayesian

class="tok-comment"># ── Sample data ────────────────────────────────────────────────────────
X, y = make_classification(n_samples=class="tok-num">600, n_features=class="tok-num">10, random_state=class="tok-num">42)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=class="tok-num">0.2, random_state=class="tok-num">42)

class="tok-comment"># ── Parameter space ────────────────────────────────────────────────
param_grid = {
    class="tok-str">'n_estimators':     [class="tok-num">100, class="tok-num">200, class="tok-num">400],
    class="tok-str">'max_depth':        [class="tok-num">3, class="tok-num">5, class="tok-num">7, class="tok-num">9],
    class="tok-str">'learning_rate':    [class="tok-num">0.01, class="tok-num">0.05, class="tok-num">0.1, class="tok-num">0.2],
    class="tok-str">'subsample':        [class="tok-num">0.7, class="tok-num">0.8, class="tok-num">1.0],
    class="tok-str">'min_samples_leaf': [class="tok-num">1, class="tok-num">3, class="tok-num">5],
}

class="tok-comment"># ── class="tok-num">1. Grid Search (exhaustive, expensive) ─────────────────────────
gs = GridSearchCV(GradientBoostingClassifier(), param_grid,
                  cv=class="tok-num">5, scoring=class="tok-str">'roc_auc', n_jobs=-class="tok-num">1)
gs.fit(X_train, y_train)
print(fclass="tok-str">"Grid best: {gs.best_score_:.4f}  {gs.best_params_}")

class="tok-comment"># ── class="tok-num">2. Random Search (fast, almost-as-good) ────────────────────────
param_dist = {
    class="tok-str">'n_estimators':     randint(class="tok-num">50, class="tok-num">500),
    class="tok-str">'max_depth':        randint(class="tok-num">2, class="tok-num">12),
    class="tok-str">'learning_rate':    uniform(class="tok-num">0.005, class="tok-num">0.3),
    class="tok-str">'subsample':        uniform(class="tok-num">0.6, class="tok-num">0.4),
}
rs = RandomizedSearchCV(GradientBoostingClassifier(), param_dist,
                        n_iter=class="tok-num">60, cv=class="tok-num">5, scoring=class="tok-str">'roc_auc',
                        n_jobs=-class="tok-num">1, random_state=class="tok-num">42)
rs.fit(X_train, y_train)
print(fclass="tok-str">"Random best: {rs.best_score_:.4f}  {rs.best_params_}")

class="tok-comment"># ── class="tok-num">3. Optuna (Bayesian, best quality) ─────────────────────────────
def objective(trial):
    params = {
        class="tok-str">'n_estimators':   trial.suggest_int(class="tok-str">'n_estimators', class="tok-num">50, class="tok-num">500),
        class="tok-str">'max_depth':      trial.suggest_int(class="tok-str">'max_depth', class="tok-num">2, class="tok-num">12),
        class="tok-str">'learning_rate':  trial.suggest_float(class="tok-str">'learning_rate', class="tok-num">1e-3, class="tok-num">0.3, log=True),
        class="tok-str">'subsample':      trial.suggest_float(class="tok-str">'subsample', class="tok-num">0.5, class="tok-num">1.0),
    }
    model = GradientBoostingClassifier(**params)
    return cross_val_score(model, X_train, y_train, cv=class="tok-num">3, scoring=class="tok-str">'roc_auc').mean()

study = optuna.create_study(direction=class="tok-str">'maximize')
study.optimize(objective, n_trials=class="tok-num">100, n_jobs=class="tok-num">4)
print(fclass="tok-str">"Optuna best: {study.best_value:.4f}  {study.best_params}")