Error with pystan

[gabriel-fontinele]

Hello, when I run the program the error message described below appears, and I apparently installed Pystan correctly, but when I go to import I can't, so if I just use import stan, then it works. Should I install the previous version of this module?

gabriel@gabriel-Aspire-A515-51G:/astrosoft/pyproffit-master/validation$ python test_script.py
WARNING: FITSFixedWarning: RADECSYS= 'FK5 ' / Equatorial system reference
the RADECSYS keyword is deprecated, use RADESYSa. [astropy.wcs.wcs]
File reading test passed
Excluded 2 sources
Region file test passed
Applying high-pass filter
/home/gabriel/miniconda3/lib/python3.10/site-packages/pyproffit/data.py:259: RuntimeWarning: invalid value encountered in divide
img_smoothed = np.nan_to_num(np.divide(gsb, gsexp))
Interpolating in the masked regions
Filling holes
Dmfilth test passed
Computing centroid and ellipse parameters using principal component analysis
Will search for the centroid within a region of 20 arcmin centered on RA=55.5399, DEC=-53.5573
Denoising image...
Running PCA...
Centroid position: 276.6758121528362 282.19710486450094
Corresponding FK5 coordinates: 55.688756583569834 -53.62322183974974
Ellipse axis ratio and position angle: 1.167875137382187 -170.89745485625753
Centroid calculation test failed, difference RA=0.00359309 , difference DEC=0.00077744
Determining X-ray peak
Coordinates of surface-brightness peak: 272.0 281.0
Corresponding FK5 coordinates: 55.72147733144434 -53.628226297404545
SB peak test passed
Corresponding pixels coordinates: 277.18944608325205 282.3833169452636
Surface brightness profile test passed
/home/gabriel/miniconda3/lib/python3.10/site-packages/pyproffit/fitting.py:58: VisibleDeprecationWarning: make_func_code is deprecated: Use of func_code attribute to declare parameters is deprecated. Use _parameters instead, which is a dict of parameter names to limits.
self.func_code = iminuit.util.make_func_code(iminuit.util.describe(self.model)[1:])
┌─────────────────────────────────────────────────────────────────────────┐
│ Migrad │
├──────────────────────────────────┬──────────────────────────────────────┤
│ FCN = 120.7 │ Nfcn = 263 │
│ EDM = 4.05e-05 (Goal: 0.0002) │ │
├──────────────────────────────────┼──────────────────────────────────────┤
│ Valid Minimum │ Below EDM threshold (goal x 10) │
├──────────────────────────────────┼──────────────────────────────────────┤
│ No parameters at limit │ Below call limit │
├──────────────────────────────────┼──────────────────────────────────────┤
│ Hesse ok │ Covariance accurate │
└──────────────────────────────────┴──────────────────────────────────────┘
┌───┬──────┬───────────┬───────────┬────────────┬────────────┬─────────┬─────────┬───────┐
│ │ Name │ Value │ Hesse Err │ Minos Err- │ Minos Err+ │ Limit- │ Limit+ │ Fixed │
├───┼──────┼───────────┼───────────┼────────────┼────────────┼─────────┼─────────┼───────┤
│ 0 │ beta │ 0.750 │ 0.022 │ │ │ │ │ │
│ 1 │ rc │ 4.23 │ 0.20 │ │ │ │ │ │
│ 2 │ norm │ -1.471 │ 0.015 │ │ │ │ │ │
│ 3 │ bkg │ -3.688 │ 0.015 │ │ │ │ │ │
└───┴──────┴───────────┴───────────┴────────────┴────────────┴─────────┴─────────┴───────┘
┌──────┬─────────────────────────────────────┐
│ │ beta rc norm bkg │
├──────┼─────────────────────────────────────┤
│ beta │ 0.000504 4.3e-3 -0.19e-3 0.21e-3 │
│ rc │ 4.3e-3 0.0404 -2.37e-3 1.55e-3 │
│ norm │ -0.19e-3 -2.37e-3 0.000239 -0.06e-3 │
│ bkg │ 0.21e-3 1.55e-3 -0.06e-3 0.000234 │
└──────┴─────────────────────────────────────┘
Best fit chi-squared: 120.679 for 100 bins and 96 d.o.f
Reduced chi-squared: 1.25707
Fitting test passed, output written to file test_plot_fit.pdf
Saving model image test passed, test image written to test_outmod.fits
PSF calculation test passed
WARNING: VerifyWarning: Keyword name 'ROT_ANGLE' is greater than 8 characters or contains characters not allowed by the FITS standard; a HIERARCH card will be created. [astropy.io.fits.card]
WARNING: VerifyWarning: Keyword name 'ELL_RATIO' is greater than 8 characters or contains characters not allowed by the FITS standard; a HIERARCH card will be created. [astropy.io.fits.card]
Output profile saving test passed, file written to test_sb.fits
Determining X-ray peak
Coordinates of surface-brightness peak: 272.0 281.0
Corresponding FK5 coordinates: 55.72147733144434 -53.628226297404545
Running PyMC3 reconstruction
JAX not found, using default sampler
Running MCMC...
|█████████████| 100.00% [360/360 00:00<00:00 logp = -637.88, ||grad|| = 1.5661]
Only 100 samples in chain.
Auto-assigning NUTS sampler...
Initializing NUTS using jitter+adapt_diag...
Multiprocess sampling (4 chains in 4 jobs)
NUTS: [coefs, bkg]
Sampling 4 chains for 500 tune and 100 draw iterations (2_000 + 400 draws total) took 135 seconds.
The rhat statistic is larger than 1.01 for some parameters. This indicates problems during sampling. See https://arxiv.org/abs/1903.08008 for details
The effective sample size per chain is smaller than 100 for some parameters. A higher number is needed for reliable rhat and ess computation. See https://arxiv.org/abs/1903.08008 for details
There were 40 divergences after tuning. Increase target_accept or reparameterize.
Chain 0 reached the maximum tree depth. Increase max_treedepth, increase target_accept or reparameterize.
Chain 1 reached the maximum tree depth. Increase max_treedepth, increase target_accept or reparameterize.
Chain 2 reached the maximum tree depth. Increase max_treedepth, increase target_accept or reparameterize.
Chain 3 reached the maximum tree depth. Increase max_treedepth, increase target_accept or reparameterize.
Done.
Total computing time is: 2.420164668560028 minutes
/home/gabriel/astrosoft/pyproffit-master/validation/test_script.py:147: RuntimeWarning: invalid value encountered in divide
check_pymc3_sb=np.nan_to_num(ref_pymc3[:,0]/depr.sb)
Possible issue with PyMC3 reconstruction, check plots
Possible issue with gas density calculation, check plots
Possible issue with Mgas calculation, check plots
Density profile outputted to test_density.pdf
Mgas profile outputted to test_mgas.pdf
Reconstruction test passed, results written to file test_save_all.fits
Running Onion Peeling test
Running Stan reconstruction
Traceback (most recent call last):
File "/home/gabriel/astrosoft/pyproffit-master/validation/test_script.py", line 261, in
run()
File "/home/gabriel/astrosoft/pyproffit-master/validation/test_script.py", line 231, in run
depr_stan.Multiscale(backend='stan', nmcmc=1000, bkglim=25.)
File "/home/gabriel/miniconda3/lib/python3.10/site-packages/pyproffit/deproject.py", line 948, in Multiscale
Deproject_Multiscale_Stan(self,bkglim=bkglim,back=back,nmcmc=nmcmc,samplefile=samplefile,nrc=nrc,nbetas=nbetas,depth=depth,min_beta=min_beta)
File "/home/gabriel/miniconda3/lib/python3.10/site-packages/pyproffit/deproject.py", line 477, in Deproject_Multiscale_Stan
import stan_utility as su
File "/home/gabriel/miniconda3/lib/python3.10/site-packages/stan_utility/init.py", line 1, in
from stan_utility.utils import compile_model, check_all_diagnostics
File "/home/gabriel/miniconda3/lib/python3.10/site-packages/stan_utility/utils.py", line 1, in
import pystan
ModuleNotFoundError: No module named 'pystan'
gabriel@gabriel-Aspire-A515-51G:/astrosoft/pyproffit-master/validation$ python
Python 3.10.11 (main, May 16 2023, 00:28:57) [GCC 11.2.0] on linux
Type "help", "copyright", "credits" or "license" for more information.

import stan
import pystan
Traceback (most recent call last):
File "", line 1, in
ModuleNotFoundError: No module named 'pystan'
exit()

[domeckert]

Seems like a duplicate from this issue:

#21

Try the following:

pip install pystan<3.0

[gabriel-fontinele]

the command doesn't work, it said nonexistent file or directory

[domeckert]

Add quotes

pip install "pystan<3.0"

[ktrehaeven]

Hi. I'm getting a similar error. Any work-arounds @gabriel-fontinele ?

[botteon]

@domeckert : this is a long-standing issue and it is not clear if stan_utilis will be ever updated to be compatible with pystan>3.0

pystan is used only by Deproject_Multiscale_Stan, shouldn't pyproffit just rely on Deproject_Multiscale_PyMC3 (thus on pymc) at this point?

[domeckert]

Hi @botteon

Yes you are right, I am never using the stan version anyway and given the progress of PyMC, it is not necessary to fix this. The functionality will simply be removed.