clustering_from_file {subspace} | R Documentation |
Reads a Clustering Object from a File
Description
Reads a File and creates an object of class subspace_clustering from that.
Usage
clustering_from_file(file_path, index_starts_at = 0, dim = NULL)
Arguments
file_path |
The path to the File from which the clustering should be read |
index_starts_at |
The index used in the file to refer to the first object in The data matrix |
dim |
if provided, overrides any value for dim that is found in the first line of the file |
Note
Files must have the following Format: The first line contains the substring "DIM=*dim*;" where *dim* is the number of dimensions of the data set.
Each subsequent line corresponds to a cluster and contains only numbers separated by spaces. The first *dim* of these values have to be either '0' or '1' and indicate in which subspace a cluster exists. All other values in the line have to be the row numbers of the objects that the cluster contains. Row numbers in the file are assumed to be 0-indexed and are changed to 1-indexed as they are loaded into R. This can be changed with the parameter index_starts_at. E.g. a clustering for a three-dimensional dataset with one cluster that is in the first and third dimension and contains the first, second and 1337-th object has to be represented as:
DIM=3;
1 0 1 0 1 1336