Computes the hard clustering through the Maximum A Posteriori rule from the matrix of a posteriori probabilities (soft clustering).

1 |

`tau` |
matrix with posterior probabilities of each class for each observation (classes in columns, observations in rows). |

`n` |
number of observations. |

`K` |
number of classes. |

a matrix of same dimensions as *tau*. For each observation (row), only zeros except for the column corresponding to the cluster to which the observation is assigned, which value is one.

J.-P. Baudry and G. Celeux

J.-P. Baudry, A. E. Raftery, G. Celeux, K. Lo and R. Gottardo (2010). Combining mixture components for clustering. *Journal of Computational and Graphical Statistics, 19(2):332-353.*

1 2 3 4 5 6 7 8 9 10 | ```
set.seed(1)
data(Baudry_etal_2010_JCGS_examples)
res <- mixmodCombi(ex4.1, nbCluster = 1:8)
res@hierarchy[[3]]@proba[1:10,] # Is the matrix of posterior probabilities of each of the combined
# classes in the 3-class solution, for the 10 first observations
mixmodMap(res@hierarchy[[3]]@proba[1:10,]) # Is the matrix of corresponding class assignments for
# the 10 first observations (available as a labels vector: res@hierarchy[[3]]@partition[1:10])
``` |

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.