# -*- coding: utf-8 -*-
#
-# Copyright (C) 2008-2018 EDF R&D
+# Copyright (C) 2008-2021 EDF R&D
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# Author: Jean-Philippe Argaud, jean-philippe.argaud@edf.fr, EDF R&D
import logging
-from daCore import BasicObjects
+from daCore import BasicObjects, NumericObjects
import numpy
# ==============================================================================
typecast = tuple,
message = "Liste de calculs supplémentaires à stocker et/ou effectuer",
listval = [
+ "Analysis",
"APosterioriCorrelations",
"APosterioriCovariance",
"APosterioriStandardDeviations",
"APosterioriVariances",
"BMA",
- "OMA",
- "OMB",
- "CurrentState",
"CostFunctionJ",
+ "CostFunctionJAtCurrentOptimum",
"CostFunctionJb",
+ "CostFunctionJbAtCurrentOptimum",
"CostFunctionJo",
+ "CostFunctionJoAtCurrentOptimum",
+ "CurrentOptimum",
+ "CurrentState",
"Innovation",
+ "MahalanobisConsistency",
+ "OMA",
+ "OMB",
+ "SampledStateForQuantiles",
"SigmaBck2",
"SigmaObs2",
- "MahalanobisConsistency",
- "SimulationQuantiles",
"SimulatedObservationAtBackground",
+ "SimulatedObservationAtCurrentOptimum",
"SimulatedObservationAtCurrentState",
"SimulatedObservationAtOptimum",
+ "SimulationQuantiles",
]
)
self.defineRequiredParameter(
name = "SimulationForQuantiles",
default = "Linear",
typecast = str,
- message = "Type de simulation pour l'estimation des quantiles",
+ message = "Type de simulation en estimation des quantiles",
listval = ["Linear", "NonLinear"]
)
+ self.defineRequiredParameter( # Pas de type
+ name = "StateBoundsForQuantiles",
+ message = "Liste des paires de bornes pour les états utilisés en estimation des quantiles",
+ )
self.requireInputArguments(
mandatory= ("Xb", "Y", "HO", "R", "B"),
)
+ self.setAttributes(tags=(
+ "DataAssimilation",
+ "NonLinear",
+ "Filter",
+ ))
def run(self, Xb=None, Y=None, U=None, HO=None, EM=None, CM=None, R=None, B=None, Q=None, Parameters=None):
- self._pre_run(Parameters, Xb, Y, R, B, Q)
+ self._pre_run(Parameters, Xb, Y, U, HO, EM, CM, R, B, Q)
#
Hm = HO["Tangent"].asMatrix(Xb)
Hm = Hm.reshape(Y.size,Xb.size) # ADAO & check shape
# Calcul de la matrice de gain et de l'analyse
# --------------------------------------------
if Y.size <= Xb.size:
- _A = R + Hm * B * Ha
+ _A = R + numpy.dot(Hm, B * Ha)
_u = numpy.linalg.solve( _A , d )
Xa = Xb + B * Ha * _u
else:
- _A = BI + Ha * RI * Hm
- _u = numpy.linalg.solve( _A , Ha * RI * d )
+ _A = BI + numpy.dot(Ha, RI * Hm)
+ _u = numpy.linalg.solve( _A , numpy.dot(Ha, RI * d) )
Xa = Xb + _u
self.StoredVariables["Analysis"].store( Xa.A1 )
#
# Calcul de la fonction coût
# --------------------------
if self._parameters["StoreInternalVariables"] or \
- self._toStore("CostFunctionJ") or \
+ self._toStore("CostFunctionJ") or self._toStore("CostFunctionJAtCurrentOptimum") or \
+ self._toStore("CostFunctionJb") or self._toStore("CostFunctionJbAtCurrentOptimum") or \
+ self._toStore("CostFunctionJo") or self._toStore("CostFunctionJoAtCurrentOptimum") or \
self._toStore("OMA") or \
self._toStore("SigmaObs2") or \
self._toStore("MahalanobisConsistency") or \
+ self._toStore("SimulatedObservationAtCurrentOptimum") or \
self._toStore("SimulatedObservationAtCurrentState") or \
self._toStore("SimulatedObservationAtOptimum") or \
self._toStore("SimulationQuantiles"):
HXa = numpy.matrix(numpy.ravel( H( Xa ) )).T
oma = Y - HXa
if self._parameters["StoreInternalVariables"] or \
- self._toStore("CostFunctionJ") or \
+ self._toStore("CostFunctionJ") or self._toStore("CostFunctionJAtCurrentOptimum") or \
+ self._toStore("CostFunctionJb") or self._toStore("CostFunctionJbAtCurrentOptimum") or \
+ self._toStore("CostFunctionJo") or self._toStore("CostFunctionJoAtCurrentOptimum") or \
self._toStore("MahalanobisConsistency"):
Jb = float( 0.5 * (Xa - Xb).T * BI * (Xa - Xb) )
Jo = float( 0.5 * oma.T * RI * oma )
self.StoredVariables["CostFunctionJb"].store( Jb )
self.StoredVariables["CostFunctionJo"].store( Jo )
self.StoredVariables["CostFunctionJ" ].store( J )
+ self.StoredVariables["CostFunctionJbAtCurrentOptimum"].store( Jb )
+ self.StoredVariables["CostFunctionJoAtCurrentOptimum"].store( Jo )
+ self.StoredVariables["CostFunctionJAtCurrentOptimum" ].store( J )
#
# Calcul de la covariance d'analyse
# ---------------------------------
if self._toStore("APosterioriCovariance") or \
self._toStore("SimulationQuantiles"):
- if (Y.size <= Xb.size): K = B * Ha * (R + Hm * B * Ha).I
- elif (Y.size > Xb.size): K = (BI + Ha * RI * Hm).I * Ha * RI
+ if (Y.size <= Xb.size): K = B * Ha * (R + numpy.dot(Hm, B * Ha)).I
+ elif (Y.size > Xb.size): K = (BI + numpy.dot(Ha, RI * Hm)).I * Ha * RI
A = B - K * Hm * B
if min(A.shape) != max(A.shape):
raise ValueError("The %s a posteriori covariance matrix A is of shape %s, despites it has to be a squared matrix. There is an error in the observation operator, please check it."%(self._name,str(A.shape)))
# ---------------------------------------
if self._parameters["StoreInternalVariables"] or self._toStore("CurrentState"):
self.StoredVariables["CurrentState"].store( numpy.ravel(Xa) )
+ if self._toStore("CurrentOptimum"):
+ self.StoredVariables["CurrentOptimum"].store( numpy.ravel(Xa) )
if self._toStore("Innovation"):
self.StoredVariables["Innovation"].store( numpy.ravel(d) )
if self._toStore("BMA"):
if self._toStore("MahalanobisConsistency"):
self.StoredVariables["MahalanobisConsistency"].store( float( 2.*J/d.size ) )
if self._toStore("SimulationQuantiles"):
- nech = self._parameters["NumberOfSamplesForQuantiles"]
HtM = HO["Tangent"].asMatrix(ValueForMethodForm = Xa)
HtM = HtM.reshape(Y.size,Xa.size) # ADAO & check shape
- YfQ = None
- for i in range(nech):
- if self._parameters["SimulationForQuantiles"] == "Linear":
- dXr = numpy.matrix(numpy.random.multivariate_normal(Xa.A1,A) - Xa.A1).T
- dYr = numpy.matrix(numpy.ravel( HtM * dXr )).T
- Yr = HXa + dYr
- elif self._parameters["SimulationForQuantiles"] == "NonLinear":
- Xr = numpy.matrix(numpy.random.multivariate_normal(Xa.A1,A)).T
- Yr = numpy.matrix(numpy.ravel( H( Xr ) )).T
- if YfQ is None:
- YfQ = Yr
- else:
- YfQ = numpy.hstack((YfQ,Yr))
- YfQ.sort(axis=-1)
- YQ = None
- for quantile in self._parameters["Quantiles"]:
- if not (0. <= float(quantile) <= 1.): continue
- indice = int(nech * float(quantile) - 1./nech)
- if YQ is None: YQ = YfQ[:,indice]
- else: YQ = numpy.hstack((YQ,YfQ[:,indice]))
- self.StoredVariables["SimulationQuantiles"].store( YQ )
+ NumericObjects.QuantilesEstimations(self, A, Xa, HXa, H, HtM)
if self._toStore("SimulatedObservationAtBackground"):
self.StoredVariables["SimulatedObservationAtBackground"].store( numpy.ravel(HXb) )
if self._toStore("SimulatedObservationAtCurrentState"):
self.StoredVariables["SimulatedObservationAtCurrentState"].store( numpy.ravel(HXa) )
+ if self._toStore("SimulatedObservationAtCurrentOptimum"):
+ self.StoredVariables["SimulatedObservationAtCurrentOptimum"].store( numpy.ravel(HXa) )
if self._toStore("SimulatedObservationAtOptimum"):
self.StoredVariables["SimulatedObservationAtOptimum"].store( numpy.ravel(HXa) )
#
# ==============================================================================
if __name__ == "__main__":
- print('\n AUTODIAGNOSTIC \n')
+ print('\n AUTODIAGNOSTIC\n')
