# DensityDist error after sampling

**URL:** <https://discourse.pymc.io/t/densitydist-error-after-sampling/6212>\
**Category:** Questions\
**Created:** [November 4, 2020, 5:52pm UTC](https://discourse.pymc.io/t/densitydist-error-after-sampling/6212 "2020-11-04T17:52:17Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![sperezconesa](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.pymc.io/sperezconesa/32/3093_2.png) [@sperezconesa](https://discourse.pymc.io/u/sperezconesa)\
**Post date:** [November 4, 2020, 5:52pm UTC](https://discourse.pymc.io/t/densitydist-error-after-sampling/6212/1 "2020-11-04T17:52:17Z")

</div>

Hello everyone!  
I am trying to work with the following likelyhood:  
 ![image](https://canada1.discourse-cdn.com/flex036/uploads/pymc3/original/2X/6/680a113a9eaa23a42d66cc1e6f53aa1cb5522fee.png)  
I think it has a technical name but I don’t remember it, would love if anyone could tell me 🙂

I have set it up in the following way:

```python
def logp_exp_lag(t, tau_0, tau):
    return T.log(T.switch(t < tau_0, 1E-20,T.exp( - (t - tau_0) / tau)/ tau ))
with pm.Model() as my_model:
    tau = pm.Uniform('tau', 0.1, 10, shape=1)
    tau_0 = pm.Uniform('tau_0', 0.1, 5, shape=1)
    like = DensityDist('like', logp_exp_lag, observed= { 't': df['tp (ns)'].to_numpy(),
                                                                             'tau' : tau,
                                                                             'tau_0' : tau_0
                                                                            }
                       , shape=1
                      )
with my_model:
    my_model_trace = pm.sample(1000, random_seed=RANDOM_SEED, cores=1)

```

And I get the following error:

```auto
MissingInputError Traceback (most recent call last)
<ipython-input-42-5fde18f3ad5a> in <module>
      1 with my_model:
----> 2 my_model_trace = pm.sample(1000, random_seed=RANDOM_SEED, cores=1)
      3 #ppc = pm.sample_posterior_predictive(my_model_trace, var_names=["like"], random_seed=RANDOM_SEED, cores=1 )

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/pymc3/sampling.py in sample(draws, step, init, n_init, start, trace, chain_idx, chains, cores, tune, progressbar, model, random_seed, discard_tuned_samples, compute_convergence_checks, **kwargs)
    496 warnings.warn("The number of samples is too small to check convergence reliably.")
    497 else:
--> 498 trace.report._run_convergence_checks(trace, model)
    499 
    500 trace.report._log_summary()

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/pymc3/backends/report.py in _run_convergence_checks(self, trace, model)
     82 varnames.append(rv_name)
     83 
---> 84 self._ess = ess = ess(trace, var_names=varnames)
     85 self._rhat = rhat = rhat(trace, var_names=varnames)
     86 

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/pymc3/stats/ __init__.py in wrapped(*args, **kwargs)
     22 )
     23 kwargs[new] = kwargs.pop(old)
---> 24 return func(*args, **kwargs)
     25 
     26 return wrapped

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/arviz/stats/diagnostics.py in ess(data, var_names, method, relative, prob)
    186 raise TypeError(msg)
    187 
--> 188 dataset = convert_to_dataset(data, group="posterior")
    189 var_names = _var_names(var_names, dataset)
    190 

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/arviz/data/converters.py in convert_to_dataset(obj, group, coords, dims)
    175 xarray.Dataset
    176 """
--> 177 inference_data = convert_to_inference_data(obj, group=group, coords=coords, dims=dims)
    178 dataset = getattr(inference_data, group, None)
    179 if dataset is None:

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/arviz/data/converters.py in convert_to_inference_data(obj, group, coords, dims, **kwargs)
     89 return from_pystan(**kwargs)
     90 elif obj. __class__. __name__ == "MultiTrace": # ugly, but doesn't make PyMC3 a requirement
---> 91 return from_pymc3(trace=kwargs.pop(group), **kwargs)
     92 elif obj. __class__. __name__ == "EnsembleSampler": # ugly, but doesn't make emcee a requirement
     93 return from_emcee(sampler=kwargs.pop(group), **kwargs)

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/arviz/data/io_pymc3.py in from_pymc3(trace, prior, posterior_predictive, log_likelihood, coords, dims, model, save_warmup)
    538 dims=dims,
    539 model=model,
--> 540 save_warmup=save_warmup,
    541 ).to_inference_data()
    542 

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/arviz/data/io_pymc3.py in __init__ (self, trace, prior, posterior_predictive, log_likelihood, predictions, coords, dims, model, save_warmup)
    159 self.dims = { **model_dims,** self.dims}
    160 
--> 161 self.observations, self.multi_observations = self.find_observations()
    162 
    163 def find_observations(self) -> Tuple[Optional[Dict[str, Var]], Optional[Dict[str, Var]]]:

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/arviz/data/io_pymc3.py in find_observations(self)
    172 elif hasattr(obs, "data"):
    173 for key, val in obs.data.items():
--> 174 multi_observations[key] = val.eval() if hasattr(val, "eval") else val
    175 return observations, multi_observations
    176 

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/theano/gof/graph.py in eval(self, inputs_to_values)
    520 inputs = tuple(sorted(inputs_to_values.keys(), key=id))
    521 if inputs not in self._fn_cache:
--> 522 self._fn_cache[inputs] = theano.function(inputs, self)
    523 args = [inputs_to_values[param] for param in inputs]
    524 

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/theano/compile/function.py in function(inputs, outputs, mode, updates, givens, no_default_updates, accept_inplace, name, rebuild_strict, allow_input_downcast, profile, on_unused_input)
    315 on_unused_input=on_unused_input,
    316 profile=profile,
--> 317 output_keys=output_keys)
    318 return fn

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/theano/compile/pfunc.py in pfunc(params, outputs, mode, updates, givens, no_default_updates, accept_inplace, name, rebuild_strict, allow_input_downcast, profile, on_unused_input, output_keys)
    484 accept_inplace=accept_inplace, name=name,
    485 profile=profile, on_unused_input=on_unused_input,
--> 486 output_keys=output_keys)
    487 
    488 

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/theano/compile/function_module.py in orig_function(inputs, outputs, mode, accept_inplace, name, profile, on_unused_input, output_keys)
   1837 on_unused_input=on_unused_input,
   1838 output_keys=output_keys,
-> 1839 name=name)
   1840 with theano.change_flags(compute_test_value="off"):
   1841 fn = m.create(defaults)

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/theano/compile/function_module.py in __init__ (self, inputs, outputs, mode, accept_inplace, function_builder, profile, on_unused_input, fgraph, output_keys, name)
   1485 # OUTPUT VARIABLES)
   1486 fgraph, additional_outputs = std_fgraph(inputs, outputs,
-> 1487 accept_inplace)
   1488 fgraph.profile = profile
   1489 else:

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/theano/compile/function_module.py in std_fgraph(input_specs, output_specs, accept_inplace)
    179 
    180 fgraph = gof.fg.FunctionGraph(orig_inputs, orig_outputs,
--> 181 update_mapping=update_mapping)
    182 
    183 for node in fgraph.apply_nodes:

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/theano/gof/fg.py in __init__ (self, inputs, outputs, features, clone, update_mapping)
    173 
    174 for output in outputs:
--> 175 self. __import_r__ (output, reason="init")
    176 for i, output in enumerate(outputs):
    177 output.clients.append(('output', i))

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/theano/gof/fg.py in __import_r__ (self, variable, reason)
    344 # Imports the owners of the variables
    345 if variable.owner and variable.owner not in self.apply_nodes:
--> 346 self. __import__ (variable.owner, reason=reason)
    347 elif (variable.owner is None and
    348 not isinstance(variable, graph.Constant) and

~/data_partition/bin2/anaconda3/envs/electroporation_modeling/lib/python3.7/site-packages/theano/gof/fg.py in __import__ (self, apply_node, check, reason)
    389 "for more information on this error."
    390 % (node.inputs.index(r), str(node)))
--> 391 raise MissingInputError(error_msg, variable=r)
    392 
    393 for node in new_nodes:

MissingInputError: Input 0 of the graph (indices start from 0), used to compute sigmoid(tau_interval__), was not provided and not given a value. Use the Theano flag exception_verbosity='high', for more information on this error.

```

This happens after the sampling. Does anyone have suggestions?

By the way, is there a way to add a 0 instead of a 1E-20 it is very hacky.

Thanks a lot!  
Best,  
Sergio

---

<div class="post-metadata">

**Author:** ![sperezconesa](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.pymc.io/sperezconesa/32/3093_2.png) [@sperezconesa](https://discourse.pymc.io/u/sperezconesa)\
**Post date:** [November 5, 2020, 7:07pm UTC](https://discourse.pymc.io/t/densitydist-error-after-sampling/6212/2 "2020-11-05T19:07:12Z")

</div>

Found the solution here:

> [@Issue with custom likelihood](https://discourse.pymc.io/t/issue-with-custom-likelihood/5885/4):
>
> Hi, Thanks for the suggestion. However, for the scale of the data that prior is reasonably informative (data values range from 1e2 to 1e6). I found that the divergences actually came about because, while trying out different things to get the likelihood working, I’d switched the prior on the amplitude to a Normal (as opposed to the half Normal). So ruling out non-physical values probably stopped the leap-frog steps wandering in to a region the lead to divergences. I am now encountering some o…