update.theta: Samples theta and v parameters
In drvalle1/EcoCluster: Bayesian Clustering using Truncated Stick-Breaking priors

This function samples the v parameters, which are then used to calculate the theta parameters

1 2	## S3 method for class 'theta' update(z, ngroup, gamma1, burnin, gibbs.step, theta, phi)

`z`	vector of size L with cluster assignment of each location
`ngroup`	maximum number of location groups (K)
`gamma1`	this is the truncated stick-breaking prior parameter for the number of location groups. This value should be between 0 and 1, and small values enforce more parsimonius results (i.e., fewer groups)
`burnin`	number of iterations to drop as part of burn-in phase
`gibbs.step`	current iteration of the gibbs sampler
`theta`	vector of length K with the probability of each location group
`phi`	K x S matrix with the probability of observing each species in each group