JWRebecca
JWRebecca

Reputation: 13

Multi class AUC ROC score in python

I would like to calculate AUC ROC score for three classes 0, 1, 2. After I get the prediction probability using predict_proda, I use roc_auc_score(y_test_over, y_prob, multi_class="ovo", average="macro"). However, I get the error enter image description here

Then, I use the code from https://github.com/scikit-learn/scikit-learn/issues/3298 that

from sklearn.metrics import roc_auc_score
from sklearn.preprocessing import LabelBinarizer

def multiclass_roc_auc_score(truth, pred, average="macro"):

   lb = LabelBinarizer()
   lb.fit(truth)

   truth = lb.transform(truth)
   pred = lb.transform(pred)

   return roc_auc_score(truth, pred, average=average)

But I still get an error when I call this function, which says enter image description here

Can anyone help me solve this? Thank you!

Upvotes: 0

Views: 2914

Answers (1)

Sy Ker
Sy Ker

Reputation: 2190

For the ROC curve, you need a classifier with a decision function. Example from the documentation;

# caculate ROC for all class 

y_score = classifier.fit(X_train, y_train).decision_function(X_test)

# Compute ROC curve and ROC area for each class
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
    fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_score[:, i])
    roc_auc[i] = auc(fpr[i], tpr[i])

# Compute micro-average ROC curve and ROC area
fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_score.ravel())
roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])

Than plot what you have found, you will have to repeat for each class;

# plot of a ROC curve for a specific class

plt.figure()
lw = 2
plt.plot(fpr[2], tpr[2], color='darkorange',
         lw=lw, label='ROC curve (area = %0.2f)' % roc_auc[2])
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic example')
plt.legend(loc="lower right")
plt.show()

Upvotes: 1

Related Questions