def _residuals(self, params) -> np.ndarray:
"""
Compute the residuals between objective and experimental data
Handle nan values in observedTS. This internal-only method
is implemented to maximize efficieency.
Parameters
----------
kwargs: dict
arguments for simulation
Instance Variables Updated
--------------------------
self.residualsTS
Returns
-------
1-d ndarray of residuals
"""
block = Logger.join(self._loggerPrefix, "fitModel._residuals")
guid = self.logger.startBlock(block)
##V
self.roadrunnerModel.reset()
self._setupModel(params)
#
roadrunnerBlock = Logger.join(block, "roadrunner")
roadrunnerGuid = self.logger.startBlock(roadrunnerBlock)
## V
#
data = self.roadrunnerModel.simulate(self.observedTS.start,
self.observedTS.end,
len(self.observedTS),
self.selectedColumns)
## ^
self.logger.endBlock(roadrunnerGuid)
#
tailBlock = Logger.join(block, "tail")
tailGuid = self.logger.startBlock(tailBlock)
## V
residualsArr = self._observedArr - data.flatten()
residualsArr = np.nan_to_num(residualsArr)
## ^
self.logger.endBlock(tailGuid)
##^
self.logger.endBlock(guid)
#
# Used for detailed debugging
if False:
self.logger.details("_residuals/std(residuals): %f" %
np.std(residualsArr))
self.logger.details("_residuals/params: %s" % str(params))
return residualsArr
def testJoin(self):
if IGNORE_TEST:
return
NAMES = ["aa", "bbb", "z"]
result = Logger.join(*NAMES)
for name in NAMES:
self.assertGreaterEqual(result.index(name), 0)
def fitModel(self, params: lmfit.Parameters = None, max_nfev: int = 100):
"""
Fits the model by adjusting values of parameters based on
differences between simulated and provided values of
floating species.
Parameters
----------
params: starting values of parameters
max_nfev: maximum number of function evaluations
Example
-------
f.fitModel()
"""
ParameterDescriptor = collections.namedtuple(
"ParameterDescriptor",
"params method std minimizer minimizerResult")
block = Logger.join(self._loggerPrefix, "fitModel")
guid = self.logger.startBlock(block)
self._initializeRoadrunnerModel()
if self.parametersToFit is None:
# Compute fit and residuals for base model
self.params = None
else:
if params is None:
params = self.mkParams()
# Fit the model to the data using one or more methods.
# Choose the result with the lowest residual standard deviation
paramDct = {}
for method in self._fitterMethods:
for _ in range(self._numFitRepeat):
minimizer = lmfit.Minimizer(self._residuals,
params,
max_nfev=max_nfev)
try:
minimizerResult = minimizer.minimize(method=method,
max_nfev=max_nfev)
except Exception as excp:
msg = "Error minimizing for method: %s" % method
self.logger.error(msg, excp)
continue
params = minimizerResult.params
std = np.std(self._residuals(params))
if method in paramDct.keys():
if std >= paramDct[method].std:
continue
paramDct[method] = ParameterDescriptor(
params=params.copy(),
method=method,
std=std,
minimizer=minimizer,
minimizerResult=minimizerResult,
)
if len(paramDct) == 0:
msg = "*** Minimizer failed for this model and data."
raise ValueError(msg)
# Select the result that has the smallest residuals
sortedMethods = sorted(paramDct.keys(),
key=lambda m: paramDct[m].std)
bestMethod = sortedMethods[0]
self.params = paramDct[bestMethod].params
self.minimizer = paramDct[bestMethod].minimizer
self.minimizerResult = paramDct[bestMethod].minimizerResult
# Ensure that residualsTS and fittedTS match the parameters
self.updateFittedAndResiduals(params=self.params)
self.logger.endBlock(guid)
def simulate(self,
params=None,
startTime=None,
endTime=None,
numPoint=None):
"""
Runs a simulation. Defaults to parameter values in the simulation.
Parameters
----------
params: lmfit.Parameters
startTime: float
endTime: float
numPoint: int
Return
------
NamedTimeseries
"""
def set(default, parameter):
# Sets to default if parameter unspecified
if parameter is None:
return default
else:
return parameter
##V
block = Logger.join(self._loggerPrefix, "fitModel.simulate")
guid = self.logger.startBlock(block)
## V
sub1Block = Logger.join(block, "sub1")
sub1Guid = self.logger.startBlock(sub1Block)
startTime = set(self.observedTS.start, startTime)
endTime = set(self.observedTS.end, endTime)
numPoint = set(len(self.observedTS), numPoint)
## V
sub1aBlock = Logger.join(sub1Block, "sub1a")
sub1aGuid = self.logger.startBlock(sub1aBlock)
if self.roadrunnerModel is None:
self._initializeRoadrunnerModel()
self.roadrunnerModel.reset()
## ^
self.logger.endBlock(sub1aGuid)
## V
sub1bBlock = Logger.join(sub1Block, "sub1b")
sub1bGuid = self.logger.startBlock(sub1bBlock)
if params is not None:
# Parameters have been specified
self._setupModel(params)
## ^
self.logger.endBlock(sub1bGuid)
# Do the simulation
selectedColumns = list(self.selectedColumns)
if not TIME in selectedColumns:
selectedColumns.insert(0, TIME)
## ^
self.logger.endBlock(sub1Guid)
## V
roadrunnerBlock = Logger.join(block, "roadrunner")
roadrunnerGuid = self.logger.startBlock(roadrunnerBlock)
data = self.roadrunnerModel.simulate(startTime, endTime, numPoint,
selectedColumns)
self.logger.endBlock(roadrunnerGuid)
## ^
# Select the required columns
## V
sub2Block = Logger.join(block, "sub2")
sub2Guid = self.logger.startBlock(sub2Block)
fittedTS = NamedTimeseries(namedArray=data)
self.logger.endBlock(sub2Guid)
## ^
self.logger.endBlock(guid)
##^
return fittedTS
def _runBootstrap(arguments: _Arguments, queue=None) -> BootstrapResult:
"""
Executes bootstrapping.
Parameters
----------
arguments: inputs to bootstrap
queue: multiprocessing.Queue
Notes
-----
1. Only the first process generates progress reports.
2. Uses METHOD_LEASTSQ for fitModel iterations.
"""
fitter = arguments.fitter
logger = fitter.logger
mainBlock = Logger.join(arguments._loggerPrefix, "_runBootstrap")
mainGuid = logger.startBlock(mainBlock)
# Unapack arguments
isSuccess = False
lastErr = ""
# Do an initial fit
for _ in range(MAX_TRIES):
try:
fitter.fitModel() # Initialize model
isSuccess = True
break
except Exception as err:
lastErr = err
# Set up logging for this process
fd = logger.getFileDescriptor()
processIdx = arguments.processIdx
if fd is not None:
sys.stderr = logger.getFileDescriptor()
sys.stdout = logger.getFileDescriptor()
iterationGuid = None
if not isSuccess:
msg = "Process %d/modelFitterBootstrip/_runBootstrap" % processIdx
logger.error(msg, lastErr)
fittedStatistic = TimeseriesStatistic(fitter.observedTS,
percentiles=[])
bootstrapResult = BootstrapResult(fitter, 0, {}, fittedStatistic)
else:
numIteration = arguments.numIteration
reportInterval = arguments.reportInterval
processingRate = min(arguments.numProcess, multiprocessing.cpu_count())
cols = fitter.selectedColumns
synthesizer = arguments.synthesizerClass(
observedTS=fitter.observedTS.subsetColumns(cols),
fittedTS=fitter.fittedTS.subsetColumns(cols),
**arguments.kwargs)
# Initialize
parameterDct = {p: [] for p in fitter.parametersToFit}
numSuccessIteration = 0
lastReport = 0
if fitter.minimizerResult is None:
fitter.fitModel()
baseChisq = fitter.minimizerResult.redchi
# Do the bootstrap iterations
bootstrapError = 0
iterationBlock = Logger.join(mainBlock, "Iteration")
for iteration in range(numIteration * ITERATION_MULTIPLIER):
if iterationGuid is not None:
logger.endBlock(iterationGuid)
iterationGuid = logger.startBlock(iterationBlock)
newObservedTS = synthesizer.calculate()
fittingSetupBlock = Logger.join(iterationBlock, "fittingSetup")
fittingSetupGuid = logger.startBlock(fittingSetupBlock)
newFitter = ModelFitterBootstrap(
fitter.roadrunnerModel,
newObservedTS,
fitter.parametersToFit,
selectedColumns=fitter.selectedColumns,
# Use bootstrap methods for fitting
fitterMethods=fitter._bootstrapMethods,
parameterLowerBound=fitter.lowerBound,
parameterUpperBound=fitter.upperBound,
fittedDataTransformDct=fitter.fittedDataTransformDct,
logger=logger,
_loggerPrefix=iterationBlock,
isPlot=fitter._isPlot)
fittedStatistic = TimeseriesStatistic(newFitter.observedTS,
percentiles=[])
logger.endBlock(fittingSetupGuid)
try:
if (iteration > 0) and (iteration != lastReport) \
and (processIdx == 0):
totalSuccessIteration = numSuccessIteration * processingRate
totalIteration = iteration * processingRate
if totalIteration % reportInterval == 0:
msg = "Bootstrap completed %d total iterations "
msg += "with %d successes."
msg = msg % (totalIteration, totalSuccessIteration)
fitter.logger.status(msg)
lastReport = numSuccessIteration
if numSuccessIteration >= numIteration:
# Performed the iterations
break
tryBlock = Logger.join(iterationBlock, "try")
tryGuid = logger.startBlock(tryBlock)
try:
tryFitterBlock = Logger.join(tryBlock, "Fitter")
tryFitterGuid = logger.startBlock(tryFitterBlock)
newFitter.fitModel(params=fitter.params)
logger.endBlock(tryFitterGuid)
except Exception as err:
# Problem with the fit. Don't numSuccessIteration it.
msg = "Process %d/modelFitterBootstrap" % processIdx
msg += " Fit failed on iteration %d." % iteration
fitter.logger.error(msg, err)
logger.endBlock(tryGuid)
continue
if newFitter.minimizerResult.redchi > MAX_CHISQ_MULT * baseChisq:
if IS_REPORT:
msg = "Process %d: Fit has high chisq: %2.2f on iteration %d."
fitter.logger.exception(
msg %
(processIdx, newFitter.minimizerResult.redchi,
iteration))
logger.endBlock(tryGuid)
continue
if newFitter.params is None:
continue
numSuccessIteration += 1
dct = newFitter.params.valuesdict()
[
parameterDct[p].append(dct[p])
for p in fitter.parametersToFit
]
cols = newFitter.fittedTS.colnames
fittedStatistic.accumulate(newFitter.fittedTS)
newFitter.observedTS = synthesizer.calculate()
logger.endBlock(tryGuid)
except Exception as err:
msg = "Process %d/modelFitterBootstrap" % processIdx
msg += " Error on iteration %d." % iteration
fitter.logger.error(msg, err)
bootstrapError += 1
fitter.logger.status("Process %d: completed bootstrap." %
(processIdx + 1))
bootstrapResult = BootstrapResult(fitter,
numSuccessIteration,
parameterDct,
fittedStatistic,
bootstrapError=bootstrapError)
if iterationGuid is not None:
logger.endBlock(iterationGuid)
logger.endBlock(mainGuid)
if fd is not None:
if not fd.closed:
fd.close()
if queue is None:
return bootstrapResult
else:
queue.put(bootstrapResult)
def fitModel(self, params: lmfit.Parameters = None, max_nfev=100):
"""
Fits the model by adjusting values of parameters based on
differences between simulated and provided values of
floating species.
Parameters
----------
params: starting values of parameters
Example
-------
f.fitModel()
"""
ParameterDescriptor = collections.namedtuple(
"ParameterDescriptor",
"params method rssq kwargs minimizer minimizerResult")
MAX_NFEV = "max_nfev"
block = Logger.join(self._loggerPrefix, "fitModel")
guid = self.logger.startBlock(block)
self.initializeRoadRunnerModel()
self.params = None
if self.parametersToFit is not None:
if params is None:
params = self.mkParams()
# Fit the model to the data using one or more methods.
# Choose the result with the lowest residual standard deviation
paramResults = []
lastExcp = None
for idx, optimizerMethod in enumerate(self._fitterMethods):
method = optimizerMethod.method
kwargs = optimizerMethod.kwargs
if MAX_NFEV not in kwargs:
kwargs[MAX_NFEV] = max_nfev
for _ in range(self._numFitRepeat):
self._bestParameters = _BestParameters(params=None,
rssq=None)
minimizer = lmfit.Minimizer(self._residuals, params)
try:
minimizerResult = minimizer.minimize(method=method,
**kwargs)
except Exception as excp:
lastExcp = excp
msg = "Error minimizing for method: %s" % method
self.logger.error(msg, excp)
continue
params = self._bestParameters.params.copy()
rssq = np.sum(self._residuals(params)**2)
if len(paramResults) > idx:
if rssq >= paramResults[idx].rssq:
continue
parameterDescriptor = ParameterDescriptor(
params=params,
method=method,
rssq=rssq,
kwargs=dict(kwargs),
minimizer=minimizer,
minimizerResult=minimizerResult,
)
paramResults.append(parameterDescriptor)
if len(paramResults) == 0:
msg = "*** Minimizer failed for this model and data."
self.logger.error(msg, lastExcp)
else:
# Select the result that has the smallest residuals
sortedMethods = sorted(paramResults, key=lambda r: r.rssq)
bestMethod = sortedMethods[0]
self.params = bestMethod.params
self.minimizer = bestMethod.minimizer
self.minimizerResult = bestMethod.minimizerResult
# Ensure that residualsTS and fittedTS match the parameters
self.updateFittedAndResiduals(params=self.params)
self.logger.endBlock(guid)
