Krige CV

Searching for optimal kriging parameters with cross validation

Fitting 5 folds for each of 8 candidates, totalling 40 fits
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
best_score R² = -0.045
best_params =  {'method': 'universal', 'variogram_model': 'spherical'}

CV results::
 - mean_test_score : [-0.16726998 -0.16726998 -0.17326498 -0.15665013 -0.05679591 -0.05679591
 -0.05369984 -0.04486488]
 - mean_train_score : [1. 1. 1. 1. 1. 1. 1. 1.]
 - param_method : ['ordinary' 'ordinary' 'ordinary' 'ordinary' 'universal' 'universal'
 'universal' 'universal']
 - param_variogram_model : ['linear' 'power' 'gaussian' 'spherical' 'linear' 'power' 'gaussian'
 'spherical']
Fitting 5 folds for each of 8 candidates, totalling 40 fits
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
n_closest_points will be ignored for UniversalKriging
best_score R² = -0.097
best_params =  {'method': 'universal3d', 'variogram_model': 'power'}

CV results::
 - mean_test_score : [-0.25558625 -0.25299609 -0.27330461 -0.26203314 -0.11692599 -0.09740768
 -0.15082744 -0.12514965]
 - mean_train_score : [1. 1. 1. 1. 1. 1. 1. 1.]
 - param_method : ['ordinary3d' 'ordinary3d' 'ordinary3d' 'ordinary3d' 'universal3d'
 'universal3d' 'universal3d' 'universal3d']
 - param_variogram_model : ['linear' 'power' 'gaussian' 'spherical' 'linear' 'power' 'gaussian'
 'spherical']

import numpy as np
from sklearn.model_selection import GridSearchCV

from pykrige.rk import Krige

# 2D Kring param opt

param_dict = {
    "method": ["ordinary", "universal"],
    "variogram_model": ["linear", "power", "gaussian", "spherical"],
    # "nlags": [4, 6, 8],
    # "weight": [True, False]
}

estimator = GridSearchCV(Krige(), param_dict, verbose=True, return_train_score=True)

# dummy data
X = np.random.randint(0, 400, size=(100, 2)).astype(float)
y = 5 * np.random.rand(100)

# run the gridsearch
estimator.fit(X=X, y=y)


if hasattr(estimator, "best_score_"):
    print("best_score R² = {:.3f}".format(estimator.best_score_))
    print("best_params = ", estimator.best_params_)

print("\nCV results::")
if hasattr(estimator, "cv_results_"):
    for key in [
        "mean_test_score",
        "mean_train_score",
        "param_method",
        "param_variogram_model",
    ]:
        print(" - {} : {}".format(key, estimator.cv_results_[key]))

# 3D Kring param opt

param_dict3d = {
    "method": ["ordinary3d", "universal3d"],
    "variogram_model": ["linear", "power", "gaussian", "spherical"],
    # "nlags": [4, 6, 8],
    # "weight": [True, False]
}

estimator = GridSearchCV(Krige(), param_dict3d, verbose=True, return_train_score=True)

# dummy data
X3 = np.random.randint(0, 400, size=(100, 3)).astype(float)
y = 5 * np.random.rand(100)

# run the gridsearch
estimator.fit(X=X3, y=y)


if hasattr(estimator, "best_score_"):
    print("best_score R² = {:.3f}".format(estimator.best_score_))
    print("best_params = ", estimator.best_params_)

print("\nCV results::")
if hasattr(estimator, "cv_results_"):
    for key in [
        "mean_test_score",
        "mean_train_score",
        "param_method",
        "param_variogram_model",
    ]:
        print(" - {} : {}".format(key, estimator.cv_results_[key]))