def precision_recall_curve(y_true, y_pred_proba):
"""
Given labels and binary classifier predicted probabilities, compute and return the data representing a precision-recall curve.
Arguments:
y_true (ww.DataColumn, pd.Series or np.ndarray): True binary labels.
y_pred_proba (ww.DataColumn, pd.Series or np.ndarray): Predictions from a binary classifier, before thresholding has been applied. Note this should be the predicted probability for the "true" label.
Returns:
list: Dictionary containing metrics used to generate a precision-recall plot, with the following keys:
* `precision`: Precision values.
* `recall`: Recall values.
* `thresholds`: Threshold values used to produce the precision and recall.
* `auc_score`: The area under the ROC curve.
"""
y_true = _convert_to_woodwork_structure(y_true)
y_pred_proba = _convert_to_woodwork_structure(y_pred_proba)
y_true = _convert_woodwork_types_wrapper(y_true.to_series())
y_pred_proba = _convert_woodwork_types_wrapper(y_pred_proba.to_series())
precision, recall, thresholds = sklearn_precision_recall_curve(
y_true, y_pred_proba)
auc_score = sklearn_auc(recall, precision)
return {
'precision': precision,
'recall': recall,
'thresholds': thresholds,
'auc_score': auc_score
}
def test_precision_recall_curve():
y_true = np.array([0, 0, 1, 1])
y_score = np.array([0.1, 0.4, 0.35, 0.8])
precision_using_sk, recall_using_sk, thresholds_using_sk = \
sklearn_precision_recall_curve(
y_true, y_score)
precision, recall, thresholds = precision_recall_curve(y_true, y_score)
assert array_equal(precision, precision_using_sk)
assert array_equal(recall, recall_using_sk)
assert array_equal(thresholds, thresholds_using_sk)
def test_precision_recall_curve_random(n_samples, dtype):
y_true, _, _, _ = generate_random_labels(
lambda rng: rng.randint(0, 2, n_samples).astype(dtype))
y_score, _, _, _ = generate_random_labels(
lambda rng: rng.randint(0, 1000, n_samples).astype(dtype))
precision_using_sk, recall_using_sk, thresholds_using_sk = \
sklearn_precision_recall_curve(
y_true, y_score)
precision, recall, thresholds = precision_recall_curve(y_true, y_score)
assert array_equal(precision, precision_using_sk)
assert array_equal(recall, recall_using_sk)
assert array_equal(thresholds, thresholds_using_sk)
