🎉 🎉 RAPIDMINER 9.10 IS OUT!!! 🎉🎉

Download the latest version helping analytics teams accelerate time-to-value for streaming and IIOT use cases.


X-Validation and Performance operators - % of accuracy from each feature

drvdrv Member Posts: 1 Contributor I
edited July 2019 in Help

I have a feature set of 100 features for 200 input samples. I am using Rapid miner as follows:
Main Process: Feature Vector-> X-Validation.
X-Validation Process:
Training: Logistic Regression operator / Decision tree
Testing : Apply model --> Performance

Features are Entropy, edgedensity, etc of 200 image samples. Labels are Class 1 and Class 2 in Text. Feature values are decimal numbers.

I would like to know how I can find the accuracy of individual feature (100 features) towards the performance accuracy of classifying Class 1 and Class 2 (E.g:  How much accuracy does entropy gives in classification, how much accuracy does edge density gives in classification etc.). Also how I can find which all features contribute the most maximum towards the overall accuracy result.

Sign In or Register to comment.