def test_label_binarizer_errors():
# Check that invalid arguments yield ValueError
one_class = np.array([0, 0, 0, 0])
lb = LabelBinarizer().fit(one_class)
multi_label = [(2, 3), (0, ), (0, 2)]
err_msg = "You appear to be using a legacy multi-label data representation."
with pytest.raises(ValueError, match=err_msg):
lb.transform(multi_label)
lb = LabelBinarizer()
err_msg = "This LabelBinarizer instance is not fitted yet"
with pytest.raises(ValueError, match=err_msg):
lb.transform([])
with pytest.raises(ValueError, match=err_msg):
lb.inverse_transform([])
input_labels = [0, 1, 0, 1]
err_msg = "neg_label=2 must be strictly less than pos_label=1."
lb = LabelBinarizer(neg_label=2, pos_label=1)
with pytest.raises(ValueError, match=err_msg):
lb.fit(input_labels)
err_msg = "neg_label=2 must be strictly less than pos_label=2."
lb = LabelBinarizer(neg_label=2, pos_label=2)
with pytest.raises(ValueError, match=err_msg):
lb.fit(input_labels)
err_msg = (
"Sparse binarization is only supported with non zero pos_label and zero "
"neg_label, got pos_label=2 and neg_label=1")
lb = LabelBinarizer(neg_label=1, pos_label=2, sparse_output=True)
with pytest.raises(ValueError, match=err_msg):
lb.fit(input_labels)
# Fail on y_type
err_msg = "foo format is not supported"
with pytest.raises(ValueError, match=err_msg):
_inverse_binarize_thresholding(
y=csr_matrix([[1, 2], [2, 1]]),
output_type="foo",
classes=[1, 2],
threshold=0,
)
# Sequence of seq type should raise ValueError
y_seq_of_seqs = [[], [1, 2], [3], [0, 1, 3], [2]]
err_msg = "You appear to be using a legacy multi-label data representation"
with pytest.raises(ValueError, match=err_msg):
LabelBinarizer().fit_transform(y_seq_of_seqs)
# Fail on the number of classes
err_msg = "The number of class is not equal to the number of dimension of y."
with pytest.raises(ValueError, match=err_msg):
_inverse_binarize_thresholding(
y=csr_matrix([[1, 2], [2, 1]]),
output_type="foo",
classes=[1, 2, 3],
threshold=0,
)
# Fail on the dimension of 'binary'
err_msg = "output_type='binary', but y.shape"
with pytest.raises(ValueError, match=err_msg):
_inverse_binarize_thresholding(
y=np.array([[1, 2, 3], [2, 1, 3]]),
output_type="binary",
classes=[1, 2, 3],
threshold=0,
)
# Fail on multioutput data
err_msg = "Multioutput target data is not supported with label binarization"
with pytest.raises(ValueError, match=err_msg):
LabelBinarizer().fit(np.array([[1, 3], [2, 1]]))
with pytest.raises(ValueError, match=err_msg):
label_binarize(np.array([[1, 3], [2, 1]]), classes=[1, 2, 3])
def class_report(y_true, y_pred, y_score=None, average='micro'):
if y_true.shape != y_pred.shape:
print("Error! y_true %s is not the same shape as y_pred %s" %
(y_true.shape, y_pred.shape))
return
lb = LabelBinarizer()
if len(y_true.shape) == 1:
lb.fit(y_true)
#Value counts of predictions
labels, cnt = np.unique(y_pred, return_counts=True)
n_classes = len(labels)
pred_cnt = pd.Series(cnt, index=labels)
metrics_summary = precision_recall_fscore_support(y_true=y_true,
y_pred=y_pred,
labels=labels)
avg = list(
precision_recall_fscore_support(y_true=y_true,
y_pred=y_pred,
average='weighted'))
metrics_sum_index = ['precision', 'recall', 'f1-score', 'support']
class_report_df = pd.DataFrame(list(metrics_summary),
index=metrics_sum_index,
columns=labels)
support = class_report_df.loc['support']
total = support.sum()
class_report_df['avg / total'] = avg[:-1] + [total]
class_report_df = class_report_df.T
class_report_df['pred'] = pred_cnt
class_report_df['pred'].iloc[-1] = total
if not (y_score is None):
fpr = dict()
tpr = dict()
roc_auc = dict()
for label_it, label in enumerate(labels):
fpr[label], tpr[label], _ = roc_curve(
(y_true == label).astype(int), y_score[:, label_it])
roc_auc[label] = auc(fpr[label], tpr[label])
if average == 'micro':
if n_classes <= 2:
fpr["avg / total"], tpr["avg / total"], _ = roc_curve(
lb.transform(y_true).ravel(), y_score[:, 1].ravel())
else:
fpr["avg / total"], tpr["avg / total"], _ = roc_curve(
lb.transform(y_true).ravel(), y_score.ravel())
roc_auc["avg / total"] = auc(fpr["avg / total"],
tpr["avg / total"])
elif average == 'macro':
# First aggregate all false positive rates
all_fpr = np.unique(np.concatenate([fpr[i] for i in labels]))
# Then interpolate all ROC curves at this points
mean_tpr = np.zeros_like(all_fpr)
for i in labels:
mean_tpr += interp(all_fpr, fpr[i], tpr[i])
# Finally average it and compute AUC
mean_tpr /= n_classes
fpr["macro"] = all_fpr
tpr["macro"] = mean_tpr
roc_auc["avg / total"] = auc(fpr["macro"], tpr["macro"])
class_report_df['AUC'] = pd.Series(roc_auc)
return class_report_df