def matthews_correlation_coefficient(y_true, y_pred):
'''
Matthews Correlation Coefficient
Parameters
----------
y_true: numpy.ndarray
Targets
y_pred: numpy.ndarray
Class predictions (0 or 1 values only)
Returns
------
score: float
Matthews Correlation Coefficient score
References
----------
.. [1] https://lettier.github.io/posts/2016-08-05-matthews-correlation-coefficient.html
.. [2] https://en.wikipedia.org/wiki/Matthews_correlation_coefficient
'''
# Check shapes
check_shapes(y_true, y_pred)
y_true, y_pred = align_shape(y_true, y_pred)
# Confusion matrix values
tn, fp, fn, tp = confusion_binary(y_true, y_pred)
numerator = tp * tn - fp * fn
denominator = np.sqrt((tp + fp) * (fn + tn) * (fp + tn) * (tp + fn))
return numerator / denominator
def log_loss(y_true, y_pred):
'''
Logarithmic loss
Parameters
----------
y_true: numpy.ndarray
Targets
y_pred: numpy.ndarray
Class probability
Returns
-------
score: float
Logarithmic loss score
References
----------
.. [1] https://www.kaggle.com/wiki/LogLoss
.. [2] http://www.exegetic.biz/blog/2015/12/making-sense-logarithmic-loss/
.. [3] http://wiki.fast.ai/index.php/Log_Loss
'''
# Check shapes
check_shapes(y_true, y_pred)
y_true, y_pred = align_shape(y_true, y_pred)
# Checking values
if not (y_pred > 0).all():
raise ValueError("Prediction array contains zeroes!")
return -(y_true * np.log(y_pred)).sum(axis=1).mean()
def root_mean_squared_logarithmic_error(y_true, y_pred):
'''
Root mean squared logarithmic error.
Parameters
----------
y_true: ndarray
Ground truth
y_pred: ndarray
Array of predictions
Returns
-------
rmsle: float
Root mean squared logarithmic error
References
----------
.. [1] https://www.kaggle.com/wiki/RootMeanSquaredLogarithmicError
.. [2] https://www.slideshare.net/KhorSoonHin/rmsle-cost-function
'''
# Check shapes
y_true, y_pred = align_shape(y_true, y_pred)
check_shapes(y_true, y_pred)
return np.sqrt(((np.log(y_pred + 1) - np.log(y_true + 1))**2).mean())
def mean_absolute_error(y_true, y_pred):
'''
Mean absolute error.
Parameters
----------
y_true: ndarray
Ground truth
y_pred: ndarray
Array of predictions
Returns
-------
rmsle: float
Mean absolute error
References
----------
.. [1] https://www.kaggle.com/wiki/MeanAbsoluteError
'''
# Check shapes
y_true, y_pred = align_shape(y_true, y_pred)
check_shapes(y_true, y_pred)
return np.abs(y_true - y_pred).mean()
def root_mean_squared_error(y_true, y_pred):
'''
Root mean squared error.
Parameters
----------
y_true: ndarray
Ground truth
y_pred: ndarray
Array of predictions
Returns
-------
rmsle: float
Root mean squared error
References
----------
.. [1] https://www.kaggle.com/wiki/RootMeanSquaredError
'''
# Check shapes
y_true, y_pred = align_shape(y_true, y_pred)
check_shapes(y_true, y_pred)
return np.sqrt(((y_true - y_pred)**2).mean())
def mean_utility(y_true, y_pred, weights):
'''
Mean utility
Parameters
----------
y_true: numpy.ndarray
Targets
y_pred: numpy.ndarray
Class predictions (0 or 1 values only)
Returns
------
score: float
Mean utility score
References
----------
.. [1] https://www.kaggle.com/wiki/MeanUtility
.. [2] https://en.wikipedia.org/wiki/Multi-label_classification
Notes
-----
The higher the better.
'''
# Check shapes
check_shapes(y_true, y_pred)
y_true, y_pred = align_shape(y_true, y_pred)
# Weights assignment
w_tp, w_tn, w_fp, w_fn = weights
tn, fp, fn, tp = confusion_binary(y_true, y_pred)
return w_tp * tp + w_tn * tn + w_fp * fp + w_fn * fn
def hamming_loss(y_true, y_pred):
'''
Hamming loss
Parameters
----------
y_true: numpy.ndarray
Targets
y_pred: numpy.ndarray
Class predictions (0 or 1 values only)
Returns
------
score: float
Hamming loss score
References
----------
.. [1] https://www.kaggle.com/wiki/HammingLoss
.. [2] https://en.wikipedia.org/wiki/Multi-label_classification
Notes
-----
The smaller the better.
'''
# Check shapes
check_shapes(y_true, y_pred)
y_true, y_pred = align_shape(y_true, y_pred)
# Logical values only!
check_binary(y_true, y_pred)
return np.logical_xor(y_pred, y_true).mean(axis=1).mean()
def mean_consequential_error(y_true, y_pred):
'''
Mean consequential error
Parameters
----------
y_true: numpy.ndarray
Targets
y_pred: numpy.ndarray
Class predictions (0 or 1 values only)
Returns
-------
score: float
Mean consequential error score
References
----------
.. [1] https://www.kaggle.com/wiki/MeanConsequentialError
.. [2] http://www.machinelearning.ru/wiki/images/5/59/PZAD2016_04_errors.pdf (RU)
Notes
-----
The higher the better.
'''
# Check shapes
check_shapes(y_true, y_pred)
y_true, y_pred = align_shape(y_true, y_pred)
# Checking binarity
check_binary(y_true, y_pred)
return (y_true.astype(bool) == y_pred.astype(bool)).mean()
