1 # -*- coding: utf-8 -*-
3 # Copyright (C) 2008-2019 EDF R&D
5 # This library is free software; you can redistribute it and/or
6 # modify it under the terms of the GNU Lesser General Public
7 # License as published by the Free Software Foundation; either
8 # version 2.1 of the License.
10 # This library is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 # Lesser General Public License for more details.
15 # You should have received a copy of the GNU Lesser General Public
16 # License along with this library; if not, write to the Free Software
17 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
19 # See http://www.salome-platform.org/ or email : webmaster.salome@opencascade.com
21 # Author: Jean-Philippe Argaud, jean-philippe.argaud@edf.fr, EDF R&D
24 from daCore import BasicObjects
25 import numpy, copy, itertools
27 # ==============================================================================
28 class ElementaryAlgorithm(BasicObjects.Algorithm):
30 BasicObjects.Algorithm.__init__(self, "SAMPLINGTEST")
31 self.defineRequiredParameter(
32 name = "SampleAsnUplet",
35 message = "Points de calcul définis par une liste de n-uplet",
37 self.defineRequiredParameter(
38 name = "SampleAsExplicitHyperCube",
41 message = "Points de calcul définis par un hyper-cube dont on donne la liste des échantillonages de chaque variable comme une liste",
43 self.defineRequiredParameter(
44 name = "SampleAsMinMaxStepHyperCube",
47 message = "Points de calcul définis par un hyper-cube dont on donne la liste des échantillonages de chaque variable par un triplet [min,max,step]",
49 self.defineRequiredParameter(
50 name = "SampleAsIndependantRandomVariables",
53 message = "Points de calcul définis par un hyper-cube dont les points sur chaque axe proviennent de l'échantillonage indépendant de la variable selon la spécification ['distribution',[parametres],nombre]",
55 self.defineRequiredParameter(
56 name = "QualityCriterion",
57 default = "AugmentedWeightedLeastSquares",
59 message = "Critère de qualité utilisé",
60 listval = ["AugmentedWeightedLeastSquares","AWLS","AugmentedPonderatedLeastSquares","APLS","DA",
61 "WeightedLeastSquares","WLS","PonderatedLeastSquares","PLS",
62 "LeastSquares","LS","L2",
66 self.defineRequiredParameter(
70 message = "Activation du mode debug lors de l'exécution",
72 self.defineRequiredParameter(
73 name = "StoreSupplementaryCalculations",
76 message = "Liste de calculs supplémentaires à stocker et/ou effectuer",
82 "InnovationAtCurrentState",
83 "SimulatedObservationAtCurrentState",
86 self.defineRequiredParameter(
88 typecast = numpy.random.seed,
89 message = "Graine fixée pour le générateur aléatoire",
91 self.requireInputArguments(
92 mandatory= ("Xb", "HO"),
95 def run(self, Xb=None, Y=None, U=None, HO=None, EM=None, CM=None, R=None, B=None, Q=None, Parameters=None):
96 self._pre_run(Parameters, Xb, Y, R, B, Q)
98 Hm = HO["Direct"].appliedTo
102 # ---------------------------
103 if len(self._parameters["SampleAsnUplet"]) > 0:
104 sampleList = self._parameters["SampleAsnUplet"]
105 for i,Xx in enumerate(sampleList):
106 if numpy.ravel(Xx).size != Xn.size:
107 raise ValueError("The size %i of the %ith state X in the sample and %i of the checking point Xb are different, they have to be identical."%(numpy.ravel(Xx).size,i+1,Xn.size))
108 elif len(self._parameters["SampleAsExplicitHyperCube"]) > 0:
109 sampleList = itertools.product(*list(self._parameters["SampleAsExplicitHyperCube"]))
110 elif len(self._parameters["SampleAsMinMaxStepHyperCube"]) > 0:
112 for i,dim in enumerate(self._parameters["SampleAsMinMaxStepHyperCube"]):
114 raise ValueError("For dimension %i, the variable definition \"%s\" is incorrect, it should be [min,max,step]."%(i,dim))
116 coordinatesList.append(numpy.linspace(dim[0],dim[1],1+int((float(dim[1])-float(dim[0]))/float(dim[2]))))
117 sampleList = itertools.product(*coordinatesList)
118 elif len(self._parameters["SampleAsIndependantRandomVariables"]) > 0:
120 for i,dim in enumerate(self._parameters["SampleAsIndependantRandomVariables"]):
122 raise ValueError("For dimension %i, the variable definition \"%s\" is incorrect, it should be ('distribution',(parameters),length) with distribution in ['normal'(mean,std),'lognormal'(mean,sigma),'uniform'(low,high),'weibull'(shape)]."%(i,dim))
123 elif not( str(dim[0]) in ['normal','lognormal','uniform','weibull'] and hasattr(numpy.random,dim[0]) ):
124 raise ValueError("For dimension %i, the distribution name \"%s\" is not allowed, please choose in ['normal'(mean,std),'lognormal'(mean,sigma),'uniform'(low,high),'weibull'(shape)]"%(i,dim[0]))
126 distribution = getattr(numpy.random,str(dim[0]),'normal')
128 coordinatesList.append(distribution(*dim[1], size=max(1,int(dim[2]))))
129 sampleList = itertools.product(*coordinatesList)
131 sampleList = iter([Xn,])
135 def CostFunction(x, HmX, QualityMeasure="AugmentedWeightedLeastSquares"):
136 if numpy.any(numpy.isnan(HmX)):
139 Jb, Jo, J = numpy.nan, numpy.nan, numpy.nan
141 _X = numpy.asmatrix(numpy.ravel( x )).T
142 _HX = numpy.asmatrix(numpy.ravel( HmX )).T
143 if QualityMeasure in ["AugmentedWeightedLeastSquares","AWLS","AugmentedPonderatedLeastSquares","APLS","DA"]:
144 if BI is None or RI is None:
145 raise ValueError("Background and Observation error covariance matrix has to be properly defined!")
146 Jb = 0.5 * (_X - Xb).T * BI * (_X - Xb)
147 Jo = 0.5 * (Y - _HX).T * RI * (Y - _HX)
148 elif QualityMeasure in ["WeightedLeastSquares","WLS","PonderatedLeastSquares","PLS"]:
150 raise ValueError("Observation error covariance matrix has to be properly defined!")
152 Jo = 0.5 * (Y - _HX).T * RI * (Y - _HX)
153 elif QualityMeasure in ["LeastSquares","LS","L2"]:
155 Jo = 0.5 * (Y - _HX).T * (Y - _HX)
156 elif QualityMeasure in ["AbsoluteValue","L1"]:
158 Jo = numpy.sum( numpy.abs(Y - _HX) )
159 elif QualityMeasure in ["MaximumError","ME"]:
161 Jo = numpy.max( numpy.abs(Y - _HX) )
163 J = float( Jb ) + float( Jo )
164 if self._toStore("CurrentState"):
165 self.StoredVariables["CurrentState"].store( _X )
166 if self._toStore("InnovationAtCurrentState"):
167 self.StoredVariables["InnovationAtCurrentState"].store( Y - _HX )
168 if self._toStore("SimulatedObservationAtCurrentState"):
169 self.StoredVariables["SimulatedObservationAtCurrentState"].store( _HX )
170 self.StoredVariables["CostFunctionJb"].store( Jb )
171 self.StoredVariables["CostFunctionJo"].store( Jo )
172 self.StoredVariables["CostFunctionJ" ].store( J )
175 if self._parameters["SetDebug"]:
176 CUR_LEVEL = logging.getLogger().getEffectiveLevel()
177 logging.getLogger().setLevel(logging.DEBUG)
178 print("===> Beginning of evaluation, activating debug\n")
179 print(" %s\n"%("-"*75,))
182 for i,Xx in enumerate(sampleList):
183 if self._parameters["SetDebug"]:
184 print("===> Launching evaluation for state %i"%i)
185 __Xn = numpy.asmatrix(numpy.ravel( Xx )).T
191 J, Jb, Jo = CostFunction(__Xn,Yn,self._parameters["QualityCriterion"])
194 if self._parameters["SetDebug"]:
195 print("\n %s\n"%("-"*75,))
196 print("===> End evaluation, deactivating debug if necessary\n")
197 logging.getLogger().setLevel(CUR_LEVEL)
202 # ==============================================================================
203 if __name__ == "__main__":
204 print('\n AUTODIAGNOSTIC \n')