-
```python
>>> import pyhf
>>> pyhf.set_backend("jax")
>>> m = pyhf.simplemodels.hepdata_like([10], [15], [5])
>>> pyhf.infer.mle.fit([12.5], m)
```
crashes like so
with a possible hint?…
-
### Summary
When I try to get upper_limit, toms748 returns the error `FailedMinimization: Inequality constraints incompatible` or `ValueError: Invalid function value: f(9.500000) -> nan `.
### OS /…
-
The current implementation of the maximum likelihood fits uses gradient descent to converge to the optimal parameter values. In principle, for comparison with the [optimization implementation in pyhf]…
-
# Description
This suggestion comes from @jpivarski in an IRIS-HEP Slack thread:
> @kratsg: It's pretty easy for `pyhf` to just pipe through, e.g. `gunzip foo.zip --extract bkgonly.json | pyhf i…
-
### Summary
In a similar vein to Issue #2249, it should be possible over time to drastically reduce the code surface area that the pyhf backends need to provide themselves if [`array-api-compat`](htt…
-
# Description
In PR #596 the `codecov/patch` test failed as the relative coverage was below the total project coverage. This was confusing, as none of the code was new and just some lines were gett…
-
### Summary
In the context of #760 I was wondering what would happen in a setup that exploits the fact that `pyhf` allows customizing parameter names for `staterror` modifiers to assign multiple such…
-
It would be nice if we could solve the issue of running into negative bin counts when sampling from the Poisson distribution. I run into this issue with some examples, where I just do not have enough …
-
Hi! @matthewfeickert. Thanks for your interest in join this organization. To be added to this organization. Please respond with a comment below to the following questions. (Please note that failure t…
-
### Summary
Create a learn notebook that demonstrates the `s/sqrt(b)` approximation using the `q0` test statistic like so:
```python
>>> import pyhf
>>>
>>> model = pyhf.simplemodels.uncorre…