iam-git / WellMet (public) (License: MIT) (since 2021-08-31) (hash sha1)
WellMet is pure Python framework for spatial structural reliability analysis. Or, more specifically, for "failure probability estimation and detection of failure surfaces by adaptive sequential decomposition of the design domain".
List of commits:
Subject Hash Author Date (UTC)
whitebox: add rude approximation for sumexp. (Je teda opravdu hodně nepřesná) 281f66ac70e21756415c8efecfdee50873b34b58 I am 2022-01-18 22:25:51
whitebox: add four betas class 57a25000259e74f1ac28bb1bac6b0cc01dd5201c I am 2022-01-18 21:43:00
whitebox: introduce Gaussian_Z_prod_2D class with respective exact solution 13e592f107918d4cc3daaeec1f08e38779a943aa I am 2022-01-18 18:51:23
mplot: polish maxes and mfigs dfb9193da5fcb633fbe58fb39ff7b4432de4a5c5 I am 2022-01-18 00:44:56
testcases: add gaussian_2D module c5e279c08bba39bdd82c79d15d00241c786c795d I am 2022-01-18 00:06:36
qt_gui.qt_testcases: simplify code for the unparametrized testcases 60b7678186738107b3346beae7fb0744570d60fc I am 2022-01-18 00:05:34
mplot.mart: move setup_labels to mart module 9d7783a3a9905a72c51b4fec76e367dffdbc4563 I am 2022-01-17 17:33:16
mplot.__init__: set up small non zero padding (0.01) f0d23235b109c4224599eb0426ad0d9ee8b2a9b8 I am 2022-01-17 17:31:44
mplot: raster candidates, polishing 63d6d00dfe7affc8ed3d05161fd4a5b50db62207 I am 2022-01-17 16:34:05
mplot: more figures 3a7f54e09cd78a2fc2ff50d7cf5c142f04ffdc28 I am 2022-01-09 00:42:33
testcases: add proxy_prod 2D testcase edb11ab54bcf677757974f133d2d66816b701ade I am 2022-01-09 00:41:27
stm_df: fix proxy, pandas nějak nám šťourá v našich boolean maticích 1d9f360edfc03932a08dff8aad97f189b155e708 I am 2022-01-09 00:39:24
mplot.maxes: a little bit more to labels d989a2d1b69b116a14f7ff81776f5f75d80cfea0 I am 2022-01-06 17:48:57
mplot.figs: add double and triple triangulations plots 091361cc326239b552078c489f9f164ccda4f54b I am 2022-01-06 16:17:50
mplot.maxes: aspoň nějak nastavit popísky os 50e8e467c24d73d9522166183275deab547243f8 I am 2022-01-06 16:16:36
mplot.maxes: add labels to candidates plot f8aa0f271a8d30cb7d79206290409f862c406a51 I am 2022-01-06 12:14:48
mplot.maxes: add candidates sampling (rejection-like) plot 5a15e10a9a462dd409e0627528bcb8910df77c7e I am 2022-01-06 09:40:38
mplot.maxes: add candidates plot 11e156edc351ca84fde742edf7ea1d85c3b0bc38 I am 2022-01-06 08:15:43
mplot.maxes: polish tri plots a little bit 9a4e0a18061e2d9f48c0c32c200bd1a408ceb77f I am 2022-01-05 13:15:00
mplot.mart: add plot_points() function 2c799e22d9f45b825a7f8a795ce6b9fe5fbd9c76 I am 2022-01-05 13:14:12
Commit 281f66ac70e21756415c8efecfdee50873b34b58 - whitebox: add rude approximation for sumexp. (Je teda opravdu hodně nepřesná)
Author: I am
Author date (UTC): 2022-01-18 22:25
Committer name: I am
Committer date (UTC): 2022-01-18 22:25
Parent(s): 57a25000259e74f1ac28bb1bac6b0cc01dd5201c
Signer:
Signing key:
Signing status: N
Tree: 4af996f395807fbdb78deb11fa889d8f705fbbbb
File Lines added Lines deleted
testcases/gaussian_2D.py 7 2
whitebox.py 22 3
File testcases/gaussian_2D.py changed (mode: 100644) (index 16490c9..f7da17c)
... ... import numpy as np
10 10 from .. import g_models as gm from .. import g_models as gm
11 11 from .. import f_models from .. import f_models
12 12 from .. import samplebox #č pro proxy_prod from .. import samplebox #č pro proxy_prod
13 from ..whitebox import WhiteBox, Gaussian_Z_prod_2D, Gaussian_ProdFourBetas_2D
13 from ..whitebox import WhiteBox, Gaussian_Z_prod_2D
14 from ..whitebox import Gaussian_ProdFourBetas_2D
15 from ..whitebox import Gaussian_Z_sumexp_2D
14 16
15 17 __all__ = [] __all__ = []
16 18
 
... ... def cos_exp():
235 237 return WhiteBox(f, gm.CosExp2D(s=5)) return WhiteBox(f, gm.CosExp2D(s=5))
236 238
237 239
238
240 # g = np.sum(np.exp(-(sample**2)), axis=1) + self._const
241 add('sumexp')
242 def sumexp():
243 return Gaussian_Z_sumexp_2D(-0.003)
239 244
240 245
File whitebox.py changed (mode: 100644) (index 05cfad7..9b916e4)
... ... class Weibull_Z_min(WhiteBox):
491 491
492 492
493 493
494 #č masturbace
495 class Gaussian_Z_sumexp_2D(WhiteBox):
496 def __init__(self, const):
497 self.const = const
498 self.f = f_models.SNorm(2)
499 self.beta = np.sqrt(-np.log(-self.const/2)*2)
500 self.pf_exact_method = 'rude (product) asymptotic approximation'
501 self.pf_exact = stats.norm.cdf(-self.beta) * 2 * np.sqrt(2)
502
503 self.gm = g_models.Z_sumexp(self.const)
504 # na začatku nemáme vzorky - pouze rozdělení a podpís
505 self.sample_box = SampleBox(self.f(), gm_signature=self.gm_signature)
506
507 def __str__(self):
508 return 'Gaussian_Z_sumexp_2D'
509
510 def __repr__(self):
511 return 'Gaussian_Z_sumexp_2D(%s)' % repr(self.const)
494 512
495 # já teda tridu zababachnu, ale že to teoreticky platí jsem neodvozoval
496 # UPD: testy neprochází, logicky hodnoty nesedí
497 # vůbec netuším jak by se to mohlo odvozovat
513 #č masturbace pro příště
514 #č tady jsou nekorektní hračky s momenty rozdělení
515 #č není známo, jestli se někdy do tohoto kódu dorazí
516 #č korektní výpočet pf
498 517 #class Gaussian_Z_sumexp(WhiteBox): #class Gaussian_Z_sumexp(WhiteBox):
499 518 # def __init__(self, nvar=2, **kwargs): # def __init__(self, nvar=2, **kwargs):
500 519 # """ # """
Hints:
Before first commit, do not forget to setup your git environment:
git config --global user.name "your_name_here"
git config --global user.email "your@email_here"

Clone this repository using HTTP(S):
git clone https://rocketgit.com/user/iam-git/WellMet

Clone this repository using ssh (do not forget to upload a key first):
git clone ssh://rocketgit@ssh.rocketgit.com/user/iam-git/WellMet

Clone this repository using git:
git clone git://git.rocketgit.com/user/iam-git/WellMet

You are allowed to anonymously push to this repository.
This means that your pushed commits will automatically be transformed into a merge request:
... clone the repository ...
... make some changes and some commits ...
git push origin main