1 # -*- coding: utf-8 -*-
3 # Copyright (C) 2008-2018 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
27 # ==============================================================================
28 class ElementaryAlgorithm(BasicObjects.Algorithm):
30 BasicObjects.Algorithm.__init__(self, "PARTICLESWARMOPTIMIZATION")
31 self.defineRequiredParameter(
32 name = "MaximumNumberOfSteps",
35 message = "Nombre maximal de pas d'optimisation",
38 self.defineRequiredParameter(
39 name = "MaximumNumberOfFunctionEvaluations",
42 message = "Nombre maximal d'évaluations de la fonction",
45 self.defineRequiredParameter(
47 typecast = numpy.random.seed,
48 message = "Graine fixée pour le générateur aléatoire",
50 self.defineRequiredParameter(
51 name = "NumberOfInsects",
54 message = "Nombre d'insectes dans l'essaim",
57 self.defineRequiredParameter(
58 name = "SwarmVelocity",
61 message = "Vitesse de groupe imposée par l'essaim",
64 self.defineRequiredParameter(
65 name = "GroupRecallRate",
68 message = "Taux de rappel au meilleur insecte du groupe (entre 0 et 1)",
72 self.defineRequiredParameter(
73 name = "QualityCriterion",
74 default = "AugmentedWeightedLeastSquares",
76 message = "Critère de qualité utilisé",
77 listval = ["AugmentedWeightedLeastSquares","AWLS","AugmentedPonderatedLeastSquares","APLS","DA",
78 "WeightedLeastSquares","WLS","PonderatedLeastSquares","PLS",
79 "LeastSquares","LS","L2",
83 self.defineRequiredParameter(
84 name = "StoreInternalVariables",
87 message = "Stockage des variables internes ou intermédiaires du calcul",
89 self.defineRequiredParameter(
90 name = "StoreSupplementaryCalculations",
93 message = "Liste de calculs supplémentaires à stocker et/ou effectuer",
103 "SimulatedObservationAtBackground",
104 "SimulatedObservationAtCurrentState",
105 "SimulatedObservationAtOptimum",
108 self.defineRequiredParameter( # Pas de type
110 message = "Liste des valeurs de bornes d'incréments de paramètres",
112 self.requireInputArguments(
113 mandatory= ("Xb", "Y", "HO", "R", "B"),
116 def run(self, Xb=None, Y=None, U=None, HO=None, EM=None, CM=None, R=None, B=None, Q=None, Parameters=None):
117 self._pre_run(Parameters, Xb, Y, R, B, Q)
119 if ("BoxBounds" in self._parameters) and isinstance(self._parameters["BoxBounds"], (list, tuple)) and (len(self._parameters["BoxBounds"]) > 0):
120 BoxBounds = self._parameters["BoxBounds"]
121 logging.debug("%s Prise en compte des bornes d'incréments de paramètres effectuee"%(self._name,))
123 raise ValueError("Particle Swarm Optimization requires bounds on all variables to be given.")
124 BoxBounds = numpy.array(BoxBounds)
125 if numpy.isnan(BoxBounds).any():
126 raise ValueError("Particle Swarm Optimization requires bounds on all variables increments to be truly given, \"None\" is not allowed. The actual increments bounds are:\n%s"%BoxBounds)
128 Phig = float( self._parameters["GroupRecallRate"] )
130 logging.debug("%s Taux de rappel au meilleur insecte du groupe (entre 0 et 1) = %s et à la meilleure position précédente (son complémentaire à 1) = %s"%(self._name, str(Phig), str(Phip)))
132 # Opérateur d'observation
133 # -----------------------
134 Hm = HO["Direct"].appliedTo
136 # Précalcul des inversions de B et R
137 # ----------------------------------
141 # Définition de la fonction-coût
142 # ------------------------------
143 def CostFunction(x, QualityMeasure="AugmentedWeightedLeastSquares"):
144 _X = numpy.asmatrix(numpy.ravel( x )).T
146 _HX = numpy.asmatrix(numpy.ravel( _HX )).T
148 if QualityMeasure in ["AugmentedWeightedLeastSquares","AWLS","AugmentedPonderatedLeastSquares","APLS","DA"]:
149 if BI is None or RI is None:
150 raise ValueError("Background and Observation error covariance matrix has to be properly defined!")
151 Jb = 0.5 * (_X - Xb).T * BI * (_X - Xb)
152 Jo = 0.5 * (Y - _HX).T * RI * (Y - _HX)
153 elif QualityMeasure in ["WeightedLeastSquares","WLS","PonderatedLeastSquares","PLS"]:
155 raise ValueError("Observation error covariance matrix has to be properly defined!")
157 Jo = 0.5 * (Y - _HX).T * RI * (Y - _HX)
158 elif QualityMeasure in ["LeastSquares","LS","L2"]:
160 Jo = 0.5 * (Y - _HX).T * (Y - _HX)
161 elif QualityMeasure in ["AbsoluteValue","L1"]:
163 Jo = numpy.sum( numpy.abs(Y - _HX) )
164 elif QualityMeasure in ["MaximumError","ME"]:
166 Jo = numpy.max( numpy.abs(Y - _HX) )
168 J = float( Jb ) + float( Jo )
172 # Point de démarrage de l'optimisation : Xini = Xb
173 # ------------------------------------
174 if isinstance(Xb, type(numpy.matrix([]))):
175 Xini = Xb.A1.tolist()
179 Xini = numpy.zeros(len(BoxBounds[:,0]))
181 # Initialisation des bornes
182 # -------------------------
183 SpaceUp = BoxBounds[:,1] + Xini
184 SpaceLow = BoxBounds[:,0] + Xini
185 nbparam = len(SpaceUp)
187 # Initialisation de l'essaim
188 # --------------------------
189 NumberOfFunctionEvaluations = 0
190 LimitVelocity = numpy.abs(SpaceUp-SpaceLow)
194 for i in range(nbparam) :
195 PosInsect.append(numpy.random.uniform(low=SpaceLow[i], high=SpaceUp[i], size=self._parameters["NumberOfInsects"]))
196 VelocityInsect.append(numpy.random.uniform(low=-LimitVelocity[i], high=LimitVelocity[i], size=self._parameters["NumberOfInsects"]))
197 VelocityInsect = numpy.matrix(VelocityInsect)
198 PosInsect = numpy.matrix(PosInsect)
200 BestPosInsect = numpy.array(PosInsect)
202 Best = copy.copy(SpaceLow)
203 qBest = CostFunction(Best,self._parameters["QualityCriterion"])
204 NumberOfFunctionEvaluations += 1
206 for i in range(self._parameters["NumberOfInsects"]):
207 insect = numpy.ravel(PosInsect[:,i])
208 quality = CostFunction(insect,self._parameters["QualityCriterion"])
209 NumberOfFunctionEvaluations += 1
210 qBestPosInsect.append(quality)
212 Best = copy.copy( insect )
213 qBest = copy.copy( quality )
214 logging.debug("%s Initialisation, Insecte = %s, Qualité = %s"%(self._name, str(Best), str(qBest)))
216 if self._parameters["StoreInternalVariables"] or "CurrentState" in self._parameters["StoreSupplementaryCalculations"]:
217 self.StoredVariables["CurrentState"].store( Best )
218 self.StoredVariables["CostFunctionJb"].store( 0. )
219 self.StoredVariables["CostFunctionJo"].store( 0. )
220 self.StoredVariables["CostFunctionJ" ].store( qBest )
222 # Minimisation de la fonctionnelle
223 # --------------------------------
224 for n in range(self._parameters["MaximumNumberOfSteps"]):
225 for i in range(self._parameters["NumberOfInsects"]) :
226 insect = numpy.ravel(PosInsect[:,i])
227 rp = numpy.random.uniform(size=nbparam)
228 rg = numpy.random.uniform(size=nbparam)
229 for j in range(nbparam) :
230 VelocityInsect[j,i] = self._parameters["SwarmVelocity"]*VelocityInsect[j,i] + Phip*rp[j]*(BestPosInsect[j,i]-PosInsect[j,i]) + Phig*rg[j]*(Best[j]-PosInsect[j,i])
231 PosInsect[j,i] = PosInsect[j,i]+VelocityInsect[j,i]
232 quality = CostFunction(insect,self._parameters["QualityCriterion"])
233 NumberOfFunctionEvaluations += 1
234 if quality < qBestPosInsect[i]:
235 BestPosInsect[:,i] = copy.copy( insect )
236 qBestPosInsect[i] = copy.copy( quality )
238 Best = copy.copy( insect )
239 qBest = copy.copy( quality )
240 logging.debug("%s Etape %i, Insecte = %s, Qualité = %s"%(self._name, n, str(Best), str(qBest)))
242 if self._parameters["StoreInternalVariables"] or "CurrentState" in self._parameters["StoreSupplementaryCalculations"]:
243 self.StoredVariables["CurrentState"].store( Best )
244 if "SimulatedObservationAtCurrentState" in self._parameters["StoreSupplementaryCalculations"]:
245 _HmX = Hm( numpy.asmatrix(numpy.ravel( Best )).T )
246 _HmX = numpy.asmatrix(numpy.ravel( _HmX )).T
247 self.StoredVariables["SimulatedObservationAtCurrentState"].store( _HmX )
248 self.StoredVariables["CostFunctionJb"].store( 0. )
249 self.StoredVariables["CostFunctionJo"].store( 0. )
250 self.StoredVariables["CostFunctionJ" ].store( qBest )
251 if NumberOfFunctionEvaluations > self._parameters["MaximumNumberOfFunctionEvaluations"]:
252 logging.debug("%s Stopping search because the number %i of function evaluations is exceeding the maximum %i."%(self._name, NumberOfFunctionEvaluations, self._parameters["MaximumNumberOfFunctionEvaluations"]))
255 # Obtention de l'analyse
256 # ----------------------
257 Xa = numpy.asmatrix(numpy.ravel( Best )).T
259 self.StoredVariables["Analysis"].store( Xa.A1 )
261 if "Innovation" in self._parameters["StoreSupplementaryCalculations"] or \
262 "OMB" in self._parameters["StoreSupplementaryCalculations"] or \
263 "SimulatedObservationAtBackground" in self._parameters["StoreSupplementaryCalculations"]:
266 if "OMA" in self._parameters["StoreSupplementaryCalculations"] or \
267 "SimulatedObservationAtOptimum" in self._parameters["StoreSupplementaryCalculations"]:
270 # Calculs et/ou stockages supplémentaires
271 # ---------------------------------------
272 if "Innovation" in self._parameters["StoreSupplementaryCalculations"]:
273 self.StoredVariables["Innovation"].store( numpy.ravel(d) )
274 if "BMA" in self._parameters["StoreSupplementaryCalculations"]:
275 self.StoredVariables["BMA"].store( numpy.ravel(Xb) - numpy.ravel(Xa) )
276 if "OMA" in self._parameters["StoreSupplementaryCalculations"]:
277 self.StoredVariables["OMA"].store( numpy.ravel(Y) - numpy.ravel(HXa) )
278 if "OMB" in self._parameters["StoreSupplementaryCalculations"]:
279 self.StoredVariables["OMB"].store( numpy.ravel(d) )
280 if "SimulatedObservationAtBackground" in self._parameters["StoreSupplementaryCalculations"]:
281 self.StoredVariables["SimulatedObservationAtBackground"].store( numpy.ravel(HXb) )
282 if "SimulatedObservationAtOptimum" in self._parameters["StoreSupplementaryCalculations"]:
283 self.StoredVariables["SimulatedObservationAtOptimum"].store( numpy.ravel(HXa) )
288 # ==============================================================================
289 if __name__ == "__main__":
290 print('\n AUTODIAGNOSTIC \n')