Up: Component summary
Up: Component summary
Component
ClusterReorderRe-orders cluster ID numbers based on a given data vector. The function is used to re-order cluster IDs of K-means results, where the cluster IDs are returned randomly.
The new order is decided by taking the mean of values, but other methods can be used aswell.
| Version | 1.0 |
|---|---|
| Bundle | tools |
| Categories | Clustering |
| Authors | Ville Rantanen (ville.rantanen@helsinki.fi) |
| Issue tracker | View/Report issues |
| Requires | R |
| Source files | component.xml ClusterReorder.r |
| Usage | Example with default values |
Inputs| Name | Type | Mandatory | Description |
|---|---|---|---|
| in | CSV | Mandatory | Data to sort with sorting column, and cluster id. |
Outputs| Name | Type | Description |
|---|---|---|
| out | CSV | Re-ordered cluster IDs and input data |
Parameters| Name | Type | Default | Description |
|---|---|---|---|
| clusterCol | string | "clusterId" | Cluster ID column name |
| sortCol | string | (no default) | Sorting column to use. |
| summaryFunction | string | "mean" | Function to summarize a cluster. min,max,mean,median or sd, or any R function |
Test cases| Test case | Parameters▼ | IN in |
OUT out |
|||
|---|---|---|---|---|---|---|
| case1 | properties | in | out | |||
|
sortCol=Mean |
||||||
| case2 | properties | in | out | |||
|
sortCol=Mean, |
||||||