Up: Component summary
Up: Component summary
Component
LinearBinnerA very basic clustering-like method. Bins each column in N number of bins. Bins are based on z-scores. First bin starts from MEAN-3*SD and last bin ends at MEAN+3*SD. Bin breaks are linearly distributed.
ClusterId is a unique numerical representation of the bin in N-D space. The columns in the input data are assumed to be in most-meaningful-first order.
Non-numeric columns are skipped.
| 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 binning.r |
| Usage | Example with default values |
Inputs| Name | Type | Mandatory | Description |
|---|---|---|---|
| in | CSV | Mandatory | Matrix data. |
Outputs| Name | Type | Description |
|---|---|---|
| binned | CSV | Bin ID for each column. |
| cluster | CSV | Cluster ID for each row. |
Parameters| Name | Type | Default | Description |
|---|---|---|---|
| N | int | 2 | Number of bins. |
Test cases| Test case | Parameters▼ | IN in |
OUT binned |
OUT cluster |
||
|---|---|---|---|---|---|---|
| case1 | properties | in | binned | cluster | ||
|
N=3 |
||||||