df_penguins=pd.read_csv(r’https://raw.githubusercontent.com/BayesianModelingandComputationInPython/BookCode_Edition1/main/data/penguins.csv’)
#df_penguins.to_csv(‘penguins.csv’)
df=df_penguins.dropna(how = ‘any’).reset_index(drop=True)
df_s=df.sample(50).reset_index()
data=df_s[‘body_mass_g’]
species = pd.Categorical(df_s[“species”]) #with pm.Model(coords={“species”: [‘Adelie’, ‘Chinstrap’, ‘Gentoo’]})
with pm.Model(coords={‘species’:species.categories}) as model_penguin_mass_all_species:
μ = pm.Normal(“μ”, 4000, 3000, dims=‘species’)
σ = pm.HalfStudentT(“σ”, 100, 2000, dims=‘species’)
y = pm.Normal(“y”,mu=μ[species.codes],sigma=σ[species.codes],observed=data)
difference_10=pm.Deterministic('μ[1]-μ[0]',μ[1]-μ[0])
idata_all = pm.sample(chains=2)
idata_all.extend(pm.sample_prior_predictive())
idata_all.extend(pm.sample_posterior_predictive(idata_all))
display(az.summary(idata_all))
az.plot_posterior(idata_all)
In az.summary(idata_all) it would be very nice if μ[1]-μ[0] was displayed as μ[Chinstrap]-μ[Adelie] ie with the name of the group, or category which is the penguin species in this case. all the other entries in az.summary are labelled with the species names except the deterministic variable; is there an easy way to fix this? Thanking you, declan