dp_activate: Activate DP nodes
In nicolaroberts/hdp: Hierarchical Dirichlet Process for categorical count data

Description Usage Arguments Details Value See Also Examples

Specifiy the number of starting clusters, and activate the DP nodes to be included in the posterior sampling process (hdp_posterior). When initialised, the DP nodes are 'heldout' (not available for posterior sampling).

1	dp_activate(hdp, dpindex, initcc, seed = sample(1:10^7, 1))

`hdp`	A hdpState object
`dpindex`	Indices of the DPs to activate (include all parent DPs)
`initcc`	Number of data clusters to start with (every data item is randomly assigned to a cluster to start with)
`seed`	The (integer) seed that can be set to reproduce output. Default is a random seed from 1 – 10^7, reported in the output.

Note that this step can be slow and memory-intensive for very large datasets.

A hdpState object with activated DPs and an initial random cluster allocation for each data item. See hdpState-class

hdp_init, hdp_addconparam, hdp_adddp, hdp_setdata, hdp_posterior

my_hdp <- hdp_init(ppindex=0, cpindex=1, hh=rep(1, 6), alphaa=rep(1, 3), alphab=rep(2, 3))
my_hdp <- hdp_adddp(my_hdp, 2, 1, 2)
my_hdp <- hdp_adddp(my_hdp, 10, c(rep(2, 5), rep(3, 5)), 3)
my_hdp <- hdp_setdata(my_hdp, 4:13, example_data_hdp)
# active all DPs and start with two data clusters
my_hdp <- dp_activate(my_hdp, 1:13, 2)