def test_get_points_in_roc_curve(self):
"""Ensures correct output from get_points_in_roc_curve."""
these_pofd, these_pod = model_eval.get_points_in_roc_curve(
forecast_probabilities=FORECAST_PROBABILITIES,
observed_labels=OBSERVED_LABELS,
threshold_arg=model_eval.THRESHOLD_ARG_FOR_UNIQUE_FORECASTS,
forecast_precision=FORECAST_PRECISION)
self.assertTrue(
numpy.allclose(these_pofd, POFD_BY_THRESHOLD, atol=TOLERANCE))
self.assertTrue(
numpy.allclose(these_pod, POD_BY_THRESHOLD, atol=TOLERANCE))
def _create_roc_curve(forecast_probabilities, observed_labels, output_dir_name):
"""Creates ROC (receiver operating characteristic) curve.
N = number of forecast-observation pairs
:param forecast_probabilities: See doc for `run_evaluation`.
:param observed_labels: Same.
:param output_dir_name: Same.
:return: auc: Area under ROC curve, calculated by GewitterGefahr.
:return: scikit_learn_auc: Area under ROC curve, calculated by scikit-learn.
"""
pofd_by_threshold, pod_by_threshold = model_eval.get_points_in_roc_curve(
forecast_probabilities=forecast_probabilities,
observed_labels=observed_labels,
threshold_arg=model_eval.THRESHOLD_ARG_FOR_UNIQUE_FORECASTS,
unique_forecast_precision=FORECAST_PRECISION_FOR_THRESHOLDS)
auc = model_eval.get_area_under_roc_curve(
pofd_by_threshold=pofd_by_threshold,
pod_by_threshold=pod_by_threshold)
scikit_learn_auc = roc_auc_score(
y_true=observed_labels, y_score=forecast_probabilities)
title_string = 'AUC = {0:.4f} ... scikit-learn AUC = {1:.4f}'.format(
auc, scikit_learn_auc)
print title_string
figure_file_name = '{0:s}/roc_curve.jpg'.format(output_dir_name)
print 'Saving ROC curve to: "{0:s}"...\n'.format(figure_file_name)
_, axes_object = pyplot.subplots(
1, 1, figsize=(FIGURE_WIDTH_INCHES, FIGURE_HEIGHT_INCHES))
model_eval_plotting.plot_roc_curve(
axes_object=axes_object, pod_by_threshold=pod_by_threshold,
pofd_by_threshold=pofd_by_threshold)
pyplot.title(title_string)
pyplot.savefig(figure_file_name, dpi=DOTS_PER_INCH)
pyplot.close()
return auc, scikit_learn_auc
def _plot_roc_curves(class_probability_matrix, observed_labels,
output_dir_name):
"""Plots one-versus-all ROC curve for each class.
K = number of classes
:param class_probability_matrix: See doc for `run_evaluation`.
:param observed_labels: Same.
:param output_dir_name: Same.
:return: auc_by_class: length-K numpy array of AUC (area under ROC curve)
values computed by GewitterGefahr.
:return: sklearn_auc_by_class: length-K numpy array of AUC values computed
by scikit-learn.
"""
num_classes = class_probability_matrix.shape[1]
auc_by_class = numpy.full(num_classes, numpy.nan)
sklearn_auc_by_class = numpy.full(num_classes, numpy.nan)
for k in range(num_classes):
print 'Creating ROC curve for class {0:d}...'.format(k)
this_pofd_by_threshold, this_pod_by_threshold = (
model_eval.get_points_in_roc_curve(
forecast_probabilities=class_probability_matrix[:, k],
observed_labels=(observed_labels == k).astype(int),
threshold_arg=model_eval.THRESHOLD_ARG_FOR_UNIQUE_FORECASTS,
unique_forecast_precision=FORECAST_PRECISION_FOR_THRESHOLDS))
auc_by_class[k] = model_eval.get_area_under_roc_curve(
pofd_by_threshold=this_pofd_by_threshold,
pod_by_threshold=this_pod_by_threshold)
sklearn_auc_by_class[k] = roc_auc_score(
y_true=(observed_labels == k).astype(int),
y_score=class_probability_matrix[:, k])
_, this_axes_object = pyplot.subplots(1,
1,
figsize=(FIGURE_WIDTH_INCHES,
FIGURE_HEIGHT_INCHES))
model_eval_plotting.plot_roc_curve(
axes_object=this_axes_object,
pod_by_threshold=this_pod_by_threshold,
pofd_by_threshold=this_pofd_by_threshold)
this_title_string = (
'AUC = {0:.4f} ... scikit-learn AUC = {1:.4f}').format(
auc_by_class[k], sklearn_auc_by_class[k])
print this_title_string
pyplot.title(this_title_string)
this_figure_file_name = '{0:s}/roc_curve_class{1:d}.jpg'.format(
output_dir_name, k)
print 'Saving figure to: "{0:s}"...\n'.format(this_figure_file_name)
pyplot.savefig(this_figure_file_name, dpi=FIGURE_RESOLUTION_DPI)
pyplot.close()
return auc_by_class, sklearn_auc_by_class