Description Usage Arguments Value
The differences are determined by weighted means. The number of examples in which a particular feature is defined is used to estimate the means in both classes.
1 2 | select.top.features(features, labels, feature.count = 10000,
min.example.fraction = 0.01)
|
features |
Feature matrix |
labels |
Feature labels (Should be +1/-1) |
feature.count |
Number of features to select. Default is 10000. |
min.example.fraction |
Minimal fraction of examples that a feature should defined in. Default is 1%. |
Vector of selected feature indexes.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.