def f1_score(y, yhat):
"""
The F_1 score is a metric for classification which tries to balance
precision and recall, ie both true positives and true negatives.
For F_1 score higher is better.
:param y: The expected input (i.e. from dataset).
:param yhat: The given input (i.e. from phenotype).
:return: The f1 score.
"""
# if phen is a constant, eg 0.001 (doesn't refer to x), then yhat
# will be a constant. that will break f1_score. so convert to a
# constant array.
if not isinstance(yhat, np.ndarray) or len(yhat.shape) < 1:
yhat = np.ones_like(y) * yhat
# convert real values to boolean with a zero threshold
yhat = (yhat > 0)
with warnings.catch_warnings():
# if we predict the same value for all samples (trivial
# individuals will do so as described above) then f-score is
# undefined, and sklearn will give a runtime warning and
# return 0. We can ignore that warning and happily return 0.
warnings.simplefilter("ignore")
return sklearn_f1_score(y, yhat, average="weighted")
def f1_score(y, yhat):
"""
The F_1 score is a metric for classification which tries to balance
precision and recall, ie both true positives and true negatives.
For F_1 score higher is better.
:param y: The expected input (i.e. from dataset).
:param yhat: The given input (i.e. from phenotype).
:return: The f1 score.
"""
# if phen is a constant, eg 0.001 (doesn't refer to x), then yhat
# will be a constant. that will break f1_score. so convert to a
# constant array.
if not isinstance(yhat, np.ndarray) or len(yhat.shape) < 1:
yhat = np.ones_like(y) * yhat
# Deal with possibility of {-1, 1} or {0, 1} class label
# convention. FIXME: would it be better to canonicalise the
# convention elsewhere and/or create user parameter to control it?
# See https://github.com/PonyGE/PonyGE2/issues/113.
y_vals = set(y)
# convert from {-1, 1} to {0, 1}
if -1 in y_vals:
y[y == -1] = 0
# We binarize with a threshold, so this cannot be used for multiclass
assert len(y_vals) == 2
# convert real values to boolean {0, 1} with a zero threshold
yhat = (yhat > 0)
with warnings.catch_warnings():
# if we predict the same value for all samples (trivial
# individuals will do so as described above) then f-score is
# undefined, and sklearn will give a runtime warning and
# return 0. We can ignore that warning and happily return 0.
warnings.simplefilter("ignore")
return sklearn_f1_score(y, yhat, average="weighted")