Grid Search

snippet.py

# https://scikit-learn.org/stable/auto_examples/model_selection/plot_multi_metric_evaluation.html#sphx-glr-auto-examples-model-selection-plot-multi-metric-evaluation-py
# https://machinelearningmastery.com/nested-cross-validation-for-machine-learning-with-python/

from numpy import mean
from numpy import std
from sklearn.datasets import make_classification
from sklearn.metrics import make_scorer, accuracy_score
from sklearn.model_selection import cross_val_score, KFold, RandomizedSearchCV, GridSearchCV, train_test_split
from sklearn.ensemble import RandomForestClassifier

# Data
X, y = make_classification(n_samples=1000, n_features=20, random_state=1, n_informative=10, n_redundant=10)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=123)

# Model
model = RandomForestClassifier(random_state=1)
grid = {
    'n_estimators' : [10, 100, 500],
    'max_features': [2, 4, 6]
}
scoring = {"AUC": "roc_auc", "Accuracy": make_scorer(accuracy_score)}
cv = KFold(n_splits=10, shuffle=True)
gs = GridSearchCV(model, param_grid=space, scoring=scoring, refit="Accuracy", n_jobs=-1, cv=cv, return_train_score=True)
gs.fit(X_train, y_train)
print(gs.score(X_test,y_test))
print(gs.best_score_)
print(gs.best_estimator_)
print(gs.best_params_)
print(gs.best_index_)
print(gs.cv_results_["mean_test_Accuracy"])
# ... or only score
print(cross_val_score(gs, X=X_test, y=y_test, cv=5).mean())