Description Usage Arguments Details Value References
SBC
under-samples the input data using the Under-Sampling Based on
Clustering algorithm.
1 2 |
data |
A data frame containing the predictors and the outcome. The
predictors must be numeric and the outcome must be both a binary valued
factor and the last column of |
perc_maj |
The desired % size of the majority class relative to the
whole data set. For instance, if |
perc_under |
% of examples to select from the majority class. If
specified |
k |
Number of clusters for the |
max_iter |
Maximum number of iterations of the k-Means algorithm. |
nstart |
Number of random restarts of the k-Means algorithm. |
classes |
A named vector identifying the majority and the minority classes. The names must be "Majority" and "Minority". This argument is only useful if the function is called inside another sampling function. |
Under-Sampling Based on Clustering clusters the input data into k clusters and randomly selects a number of majority examples from each cluster based on the imbalance ratio of the cluster.
The authors did not specify if sampling of majority examples should be performed with or without replacement, however, in many occasions the algorithm tries to sample more examples than what is available in the cluster, therefore, we always perform sampling with replacement here.
A data frame containing a more balanced version of the input data after under-sampling with the Under-Sampling Based on Clustering algorithm.
Yen, S. J., & Lee, Y. S. (2009). Cluster-based under-sampling approaches for imbalanced data distributions. Expert Systems with Applications, 36(3), 5718-5727.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.