fix: Correct out of bounds initialization parameter for impact notebook

[matthewfeickert]

Description

Fix in docs/examples/notebooks/ImpactPlot.ipynb

E           ValueError                                Traceback (most recent call last)
E           <ipython-input-7-8b96e1f272ad> in <module>
E           ----> 1 impacts, labels = get_impact_data()
E           
E           <ipython-input-6-0d59a87fecbf> in get_impact_data()
E                33         if i % 5 == 0:
E                34             print(i)
E           ---> 35         impct = calc_impact(i, b[i], e[i], width, initv[i], model.config.poi_index)
E                36         impacts.append(impct - poi_free)
E                37     return np.asarray(impacts), labels
E           
E           <ipython-input-5-541db5dc867d> in calc_impact(idx, b, e, i, width, poi_index)
E                 6     poi_dn_post = bb[poi_index]
E                 7 
E           ----> 8     _, _, bb, ee = fitresults([(idx, b + width)])
E                 9     poi_up_pre = bb[poi_index]
E                10 
E           
E           <ipython-input-4-b266f6140696> in fitresults(constraints)
E                12         fixed_params[idx] = True
E                13 
E           ---> 14     result = pyhf.infer.mle.fit(
E                15         data, model, init_pars=init_pars, fixed_params=fixed_params, return_uncertainties=True
E                16     )
E           
E           ~/work/pyhf/pyhf/src/pyhf/infer/mle.py in fit(data, pdf, init_pars, par_bounds, fixed_params, **kwargs)
E               111     fixed_params = fixed_params or pdf.config.suggested_fixed()
E               112 
E           --> 113     _validate_fit_inputs(init_pars, par_bounds, fixed_params)
E               114 
E               115     # get fixed vals from the model
E           
E           ~/work/pyhf/pyhf/src/pyhf/infer/mle.py in _validate_fit_inputs(init_pars, par_bounds, fixed_params)
E                51     for par_idx, (value, bound) in enumerate(zip(init_pars, par_bounds)):
E                52         if not (bound[0] <= value <= bound[1]):
E           ---> 53             raise ValueError(
E                54                 f"fit initialization parameter (index: {par_idx}, value: {value}) lies outside of its bounds: {bound}"
E                55                 + "\nTo correct this adjust the initialization parameter values in the model spec or those given"
E           
E           ValueError: fit initialization parameter (index: 0, value: 1.9999586270208174) lies outside of its bounds: [0.915, 1.085]
E           To correct this adjust the initialization parameter values in the model spec or those given
E           as arguments to pyhf.infer.fit. If this value is intended, adjust the range of the parameter
E           bounds.

Checklist Before Requesting Reviewer

• Tests are passing
• Verified notebook workflow tests are passing
• "WIP" removed from the title of the pull request
• Selected an Assignee for the PR to be responsible for the log summary

Before Merging

For the PR Assignees:

• Summarize commit messages into a comprehensive review of the PR

* TBD
* Move 'non-asymptotic calculators' to Implemented list in README

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[codecov]

Codecov Report

Merging #1149 (4c79e25) into master (d83771e) will not change coverage.
The diff coverage is n/a.

@@           Coverage Diff           @@
##           master    #1149   +/-   ##
=======================================
  Coverage   97.43%   97.43%           
=======================================
  Files          63       63           
  Lines        3665     3665           
  Branches      522      522           
=======================================
  Hits         3571     3571           
  Misses         55       55           
  Partials       39       39           

Flag	Coverage Δ
unittests	97.43% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update d83771e...4c79e25. Read the comment docs.