egttools.numerical.numerical_.calculate_expected_indicators

calculate_expected_indicators()

Calculate E[f_k] for multiple indicator functions in a single pass.

Equivalent to calling calculate_expected_indicator once per indicator, but the multivariate hypergeometric PDF is computed only once per (state, group_config) pair and shared across all indicators. Cost is O(states × groups + K) rather than O(K × states × groups).

Parameters:

  • pop_size (int) – Total number of individuals in the population.

  • group_size (int) – Number of individuals sampled per group interaction.

  • nb_strategies (int) – Number of strategies available in the population.

  • stationary_distribution (scipy.sparse.csr_matrix) – Sparse matrix representing the stationary distribution over population states.

  • indicators (list[callable]) – List of functions, each with signature f(group_config: list[int]) -> float.

Returns:

One-dimensional array of length len(indicators); element k is the expected value of indicators[k].

Return type:

numpy.ndarray

Examples

>>> # Compute cooperation level and group success simultaneously
>>> results = calculate_expected_indicators(
...     pop_size, group_size, nb_strategies, sd,
...     [
...         lambda g: g[0] / group_size,       # cooperation level
...         lambda g: float(g[0] >= threshold), # group success
...     ]
... )
>>> cooperation_level, eta_G = results