How do I pull a subset of an ARVIZ array within the inference data?

Questions v5
3

I’m not sure what ‘constant_data’ is in the example…

obs_county = data.posterior["County"][data.constant_data["county_idx"]]
data = data.assign_coords(obs_id=obs_county, groups="observed_vars")
az.plot_ppc(data, coords={'obs_id': ['ANOKA', 'BELTRAMI']}, flatten=[])

Here is my inference data:

image
image783×522 22.4 KB

So I tried:
obs_item = prior_checks.prior['ITEM_NUMBER'][prior_checks.constant_data['item_idx']] but that didn’t work.

For reference, here is my model.

coords = {"ITEM_NUMBER":list(items_loc)}
with pm.Model(coords=coords, rng_seeder=RANDOM_SEED) as pooled_model:
    store_idx = pm.Data('item_idx',items, dims="obs_id", mutable=True)
    a = pm.Normal("a", 0.0, sigma=10.0, dims="ITEM_NUMBER")

    theta = a[store_idx]
    sigma = pm.HalfCauchy("error", 0.5)

    y = pm.Normal("y", theta, sigma=sigma, observed=training_data['eaches'], dims="obs_id")