cov_block

pyoptex.doe.cost_optimal.cov.cov_block(cost=1, ratios=1.0, cost_index=0)

Covariance function to add a blocking factor to the system every cost in the cumulative cost. This is mostly used when cost is time related.

For example, if cost = 2 and the cumulative cost is [0, 1, 2, 3, 4, 5], the added blocking groups are [0, 0, 1, 1, 2, 2].

Parameters

costfloat

Every cost in cumulative cost, a new block is started.

ratiofloat or np.array(1d)

The ratios for each of the Vinv (in a Bayesian approach). In case the ratio is a float, it is broadcasted accordingly.

cost_indexint

The index in the multi-cost objective to look at.

Returns

covfunc(Y, X, Zs, Vinv, costs)

The covariance function.