I found that some codes use :

pm.DensityDist(‘likelihood’, lambda v: logl(v), observed={‘v’: theta})

pm.DensityDist(‘likelihood’, my_loglike,

observed={‘theta’: (m, c), ‘x’: x, ‘data’: data, ‘sigma’: sigma})

such as :v

some like: obs = pm.Normal(‘obs’, mu=mu, sd=1, observed=np.random.randn(100))

such as :randn

some like :like = pymc.Normal(‘y_est’, mu=alpha + beta * xdata, sd=sigma, observed=ydata)

such as :ydata(python - Defining the Stochastic and Deterministic variables with pymc3 - Cross Validated)

I was confused.What’s the difference?