Metrics

corrai.base.metrics.nmbe(y_pred, y_true)

Normalized Mean Bias Error (NMBE).

Parameters:

• y_pred (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Estimated target values.

• y_true (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Ground truth (correct) target values.

Returns:

Normalized mean bias error, expressed as a percentage.

Return type:

float

Examples

>>> import numpy as np
>>> y_true = np.array([100, 200, 300])
>>> y_pred = np.array([110, 190, 310])
>>> nmbe(y_pred, y_true)
1.6666666666666667

>>> import pandas as pd
>>> y_true = pd.Series([10, 20, 30])
>>> y_pred = pd.Series([12, 18, 29])
>>> nmbe(y_pred, y_true)
-1.6666666666666667

corrai.base.metrics.cv_rmse(y_pred, y_true)

Coefficient of Variation of the Root Mean Squared Error (CV(RMSE)).

Parameters:

• y_pred (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Estimated target values.

• y_true (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Ground truth (correct) target values.

Returns:

CV(RMSE), expressed as a percentage.

Return type:

float

Examples

>>> import numpy as np
>>> y_true = np.array([100, 200, 300])
>>> y_pred = np.array([110, 190, 310])
>>> cv_rmse(y_pred, y_true)
 6.123724356957945

>>> import pandas as pd
>>> y_true = pd.Series([10, 20, 30])
>>> y_pred = pd.Series([12, 18, 29])
>>> cv_rmse(y_pred, y_true)
10.606601717798213