Multi-hyperparameter, cross-validated grid search

multi_hyperparam_grid_search.py

from sklearn.model_selection import KFold, GridSearchCV
from sklearn.ensemble import RandomForestRegressor
from sklearn.datasets import load_boston

boston = load_boston()
X = boston.data
y = boston.target

# Create kf instance 
kf = KFold(n_splits=5, shuffle=True, random_state=42)
# Create dt instance 
rf = RandomForestRegressor()
# Create grid search instance 
gscv = GridSearchCV(
    rf, 
    {"max_depth": range(1, 20),
     "n_estimators": range(2, 20), 
     "min_samples_leaf": range(1, 6),
     "min_samples_split": range(2, 10)},
    cv=kf, 
    n_jobs=-1
)
gscv.fit(X, y)
# Get cross-validation data
cv_df = pd.DataFrame(gscv.cv_results_)
# Create a heatmap-style table
piv_df = cv_df.pivot_table(index=["param_max_depth", "param_min_samples_leaf"],
           columns=["param_n_estimators", "param_min_samples_split"],
           values="mean_test_score").round(3)
piv_df.style.background_gradient(cmap="nipy_spectral", axis=None)