'Weka - Local Outlier Factor not activated in the classifer option
I'm trying to detect outliers using a no code platform called Weka. I've installed the packages maintained by Weka within it's package manager. However, I've imported the KD-CUP 1999 dataset into Weka and I'm trying to use the classifer option (The Classify tab is for training and evaluating the performance of different machine learning algorithms) The issue is that the Local Outlier Factor algorithm is not activated or simply isn't allowing me to use it depsite me installing via Weka package manager, an image is provided for better insight: https://i.stack.imgur.com/9FLTr.png
Solution 1:[1]
When an algorithm is grayed out in Weka, that means that there is a discrepancy between the type of data (i.e., attributes types) that you loaded and what the algorithm, e.g., classifier or clusterer, can handle.
Check the Capabilities of the classifier in the user interface (choose the classifier, then left-click on the field listing the name/options and then click the Capabilities button).
It is possible that you may have to convert some attributes in your dataset with filters (e.g., StringToNominal or NumericToNominal) before you can use that particular classifier.
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 | fracpete |