Machine Learning
Tuning & Cross‑Validation
Tune carefully without leaking test data.
Cross-Validation
CV estimates performance more reliably than a single split, especially on small datasets.
Grid Search Example
from sklearn.model_selection import GridSearchCV
from sklearn.ensemble import RandomForestClassifier
grid = GridSearchCV(
RandomForestClassifier(random_state=42),
param_grid={"n_estimators":[200,500], "max_depth":[None, 5, 10]},
cv=5,
n_jobs=-1
)
grid.fit(X_train, y_train)
print("best:", grid.best_params_)