Silhouette Score
Compute a silhouette width from within- and between-cluster distances.
Description
A silhouette width compares within-cluster distance with distance to the nearest other cluster.
A silhouette width compares within-cluster distance with distance to the nearest other cluster. A positive value indicates the supplied within distance is smaller.1
Compute a silhouette width from within- and between-cluster distances.
When to use Silhouette Score
Use this tool to compute a silhouette width from within- and between-cluster distances.
Prepare the upstream counts, expression values, sequences or record lists requested by this tool. Keep corresponding features in the same order and confirm count units, transformations and caller-selected criteria.
How to use Silhouette Score and understand its results
- Prepare the upstream counts, expression values, sequences or record lists requested by this tool. Keep corresponding features in the same order and confirm count units, transformations and caller-selected criteria.
- Enter withinClusterDistance, nearestOtherClusterDistance using the field table and calculation rules, then run the tool.
- Read silhouette, separated. The explanation below defines the units, signs, ordering and any flags or placeholder values.
- If the tool reports an input issue, correct the values and run it again. Apply the stated assumptions when interpreting a successfully returned result.
| Input field | Meaning | Value type; see rules below | Requirement |
|---|---|---|---|
| withinClusterDistance | Within cluster distance | number | Required |
| nearestOtherClusterDistance | Nearest other cluster distance | number | Required |
Enter nonnegative within distance a and nearest-other distance b, with at least one positive. Return the width and a strict s>0 separated flag. Equal positive distances give zero and false; a=0,b>0 gives one.
s=(b−a)/max(a,b) Units, indexing, boundary conditions and exceptional cases are defined in the calculation rules above.
| Output field | Meaning | Value type |
|---|---|---|
| silhouette | Silhouette | number |
| separated | Separated | boolean |
{
"input": {
"withinClusterDistance": 2,
"nearestOtherClusterDistance": 6
},
"output": {
"silhouette": 0.6666666666666666,
"separated": true
}
}Limitations and assumptions
The tool consumes already summarized distances rather than computing pairwise distances or a dataset mean. It does not validate cluster assignments or supply special singleton-cluster handling.
Numeric inputs must be finite. Follow the calculation-specific rules for overflow, underflow and exceptional cases. Missing required fields, extra fields, wrong value types and violations of the calculation rules are input errors. A successfully returned false flag is an evaluated outcome; its meaning is explained above.
Alternative or Complementary methods
Use Correlation Distance Matrix: Build a Pearson correlation-distance matrix for hierarchical clustering. For a complementary task, use Community Resolution Selector: Select a tested community resolution closest to the target cluster count.
References
-
Silhouette Score — tool.io
Similar or alternative tools
- Correlation Distance Matrix
Build a Pearson correlation-distance matrix for hierarchical clustering.
- Community Resolution Selector
Select a tested community resolution closest to the target cluster count.