[WIP] Getting there

Author: Leguark

gempy_probability/modules/model_definition/model_examples.py

@@ -79,13 +79,17 @@ def two_wells_prob_model_I(geo_model: gempy.core.data.GeoModel, normal, y_obs_li
 # 1) Define your priors
 gravity_priors = {
         # e.g. density contrast of layer index 3
-        "mu_density": dist.Normal(2.62, 0.5)
+        # "mu_density": dist.Normal(2.62, 0.5),
+        "mu_thickness":  dist.Normal(
+            loc=torch.tensor(0.0487, dtype=torch.float64),
+            scale=torch.tensor(0.1, dtype=torch.float64)
+        )
 }
 
 # 2) Wrap your forward pass into a small fn
 def run_gempy_forward(samples, geo_model):
 
-    mu_top = samples["mu_density"]
+    mu_top = samples["mu_thickness"]
 
     interp_input = interpolation_input_from_structural_frame(geo_model)
 

tests/test_prob_model/test_prob_factory.py

@@ -101,20 +101,20 @@ def _prob_run(geo_model: gp.data.GeoModel, prob_model: callable,
         warmup_steps=50,
         disable_validation=False
     )
-    mcmc.run(geo_model, normal, y_obs_list)
+    mcmc.run(geo_model, y_obs_list)
     posterior_samples = mcmc.get_samples()
     posterior_predictive_fn = Predictive(
         model=prob_model,
         posterior_samples=posterior_samples
     )
-    posterior_predictive = posterior_predictive_fn(geo_model, normal, y_obs_list)
+    posterior_predictive = posterior_predictive_fn(geo_model, y_obs_list)
 
     data = az.from_pyro(posterior=mcmc, prior=prior, posterior_predictive=posterior_predictive)
     # endregion
 
     # print("Number of interpolations: ", geo_model.counter)
 
-    if True:  # * Save the arviz data
+    if False:  # * Save the arviz data
         data.to_netcdf("arviz_data.nc")
 
     az.plot_trace(data)