Clustering : Parameters used in clustering

Click in graph to show relevant configuration - Click in hashtag to open in new page

# clusterAxis

Axis to use when clustering data
Type: string
Default: samples
Options: samples, variables

# clusteringDistance

Distance metric to use when clustering data
Type: string
Default: euclidianDistance
Options: euclidianDistance, manhattanDistance, maxDistance

# imputeMethod

Imputation method for missing data when clustering
Type: string
Default: mean
Options: mean, median

# kmeansSmpClusters

Number of clusters when clustering sample data with kmeans
Type: integer
Default: 3

# kmeansVarClusters

Number of clusters when clustering variable data with kmeans
Type: integer
Default: 3

# linkage

Linkage type to use when clustering data
Type: string
Default: complete
Options: single, complete, average

# maxIterations

Number of maximum iterations when clustering data with kmeans for one dimensional graphs or maximum number of iterations when calculating force direct layout networks
Type: integer
Default: 500

# samplesClustered

Configuration property to cluster samples
Type: boolean
Default: false

# samplesKmeaned

Configuration property to k-mean samples
Type: boolean
Default: false

# variablesClustered

Configuration property to cluster variables
Type: boolean
Default: false

# variablesKmeaned

Configuration property to k-mean variables
Type: boolean
Default: false