Methods of computing initial clusters for the K-Means algorithm.
More...
Constructs the initialization method object using the provided value
- Parameters
-
value | Value corresponding to the initialization method object |
Returns the value corresponding to the initialization method object
- Returns
- Value corresponding to the initialization method object
Default: uses first nClusters points as initial clusters
Uses first nClusters points as initial clusters for data in a CSR numeric table
Synonym of deterministicDense
Kmeans|| algorithm: scalable Kmeans++ by Bahmani et al. (2012)
Kmeans|| algorithm: scalable Kmeans++ by Bahmani et al. (2012)
Kmeans++ algorithm by Arthur and Vassilvitskii (2007)
Kmeans++ algorithm by Arthur and Vassilvitskii (2007)
Uses random nClusters points as initial clusters for data in a CSR numeric table
Uses random nClusters points as initial clusters
The documentation for this class was generated from the following file:
- kmeans/init/InitMethod.java