how to plot a graph

3 次查看（过去 30 天）
nkumar
nkumar 2014-11-15
评论： Star Strider 2014-11-15
I want to plot ROC sensitivity vs specitivity,I have calcuated all these parameters for 3 class problem,now kindly tell how to plot roc crve
results are
Actual Classes
-------------1--------2--------3-----
TP | 38.00 | 50.00 | 50.00
FP | 12.00 | 0.00 | 0.00
FN | 0.00 | 12.00 | 0.00
TN | 100.00 | 88.00 | 100.00
Preci. | 0.76 | 1.00 | 1.00
Sensi. | 1.00 | 0.81 | 1.00
Speci. | 0.89 | 1.00 | 1.00
------------------------------------------
Model Accuracy is 0.92

请先登录，再回答此问题。

采纳的回答

Star Strider
Star Strider 2014-11-15
Use the perfcurve function.
  2 个评论
nkumar
nkumar 2014-11-15
i tried this but could not plot it ,[x,y]=perfcurve();here i get x,y as only four values,where mu input to this function is 44 values
Star Strider
Star Strider 2014-11-15
You have to give it the raw results of your classification, not the confusion matrix summary results you posted. I assume you have the classification results it requires. See the documentation on Performance Curves for a detailed discussion.
From that documentation:
  • perfcurve is intended for use with classifiers that return scores, not those that return only predicted classes. As a counter-example, consider a decision tree that returns only hard classification labels, 0 or 1, for data with two classes. In this case, the performance curve reduces to a single point because classified instances can be split into positive and negative categories in one way only.

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 ROC - AUC 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by