def __init__(self, pop1, pop2, objFunc, areLargeValuesMoreDifferent, minAge=0.0, maxAge=4500.0, dt=1.0, nIters=5000):
'''
:param pop1: an instance of detrital population
:param pop2: a different instance of detrital population to compare to pop1
:param objFunc: one of the comparison function defined in populationMetrics.py (or a user defined function).
objFunc needs to be a function of two variables (e.g. objFunc(pop1,pop2) that returns a single value comparing the
two.
:param areLargeValuesMoreDifferent: boolean, are large or small values 'good matches' between datasets?
:param minAge: the minimum age axis to recompute pdfs/cdfs on for objFuncs that require those values
:param maxAge: the maximum age axis to recompute pdfs/cdfs on for objFuncs that require those values
:param dt: the age axis spacing to recompute pdfs/cdfs on for objFuncs that require those values
:param nIters: the number of permutations to perform
'''
# Store the nunmber of iterations
self.nIters = nIters
# Store the directionalite of the objective function
self.areLargeValuesMoreDifferent = areLargeValuesMoreDifferent
# Concatenate ages and errors
allAges = np.hstack((pop1.ages, pop2.ages))
allErrors = np.hstack((pop1.errors, pop2.errors))
# Create indexing variable for ages and errors
indices = np.hstack((np.zeros_like(pop1.ages), np.ones_like(pop2.ages)))
# Preallocate space for permutation results
self._permVals = np.zeros(nIters)
#What is the value of the true labelling?
self._thisVal = objFunc(pop1, pop2)
# Iterate through the requested number of permutations
for i in range(nIters):
# Shuffle the indices
permIndices = np.random.permutation(len(indices))
shuffledIndices = indices[permIndices]
# Create new populations
pop1_i = population(ages=allAges[shuffledIndices == 0], errors=allErrors[shuffledIndices == 0],tmin=minAge, tmax=maxAge, delt=dt)
pop2_i = population(ages=allAges[shuffledIndices == 1], errors=allErrors[shuffledIndices == 1],tmin=minAge, tmax=maxAge, delt=dt)
# Calculate this objectiveFunctionValue
self._permVals[i] = objFunc(pop1_i, pop2_i)
# Calculate the probability of this value
self.pVal = self.getPforVal(self._thisVal)
def mixture_Dmax(daughterPop, parentPops, mixingCoefficients):
'''Determine the Dmax value, the maximum difference between CDFs
:param daughterPop: an instance of the population class describing a daughter population
:param parentPops: a list of instances of the population class describing the parents
:param mixingCoefficients: a list, or array, of fractional mixing coefficients that must sum to one
'''
mixedPop = population(parentPopulations=parentPops,
mixingCoefficients=mixingCoefficients)
return Dmax(daughterPop, mixedPop)
def mixture_Vmax(daughterPop, parentPops, mixingCoefficients):
'''Calculate the V max value of the kuiper statistic as summarized.
by Saylor and Sundell, 2016, Geosphere
:param daughterPop: an instance of the population class describing a daughter population
:param parentPops: a list of instances of the population class describing the parents
:param mixingCoefficients: a list, or array, of fractional mixing coefficients that must sum to one
'''
mixedPop = population(parentPopulations=parentPops,
mixingCoefficients=mixingCoefficients)
return Vmax(daughterPop, mixedPop)
def mixture_correlationCoeff(daughterPop, parentPops, mixingCoefficients):
'''Calculate the correlation coefficient (e.g. r^2) b/w the two pdfs.
This method was proposed by Saylor and Sundell, 2016, Geosphere
:param daughterPop: an instance of the population class describing a daughter population
:param parentPops: a list of instances of the population class describing the parents
:param mixingCoefficients: a list, or array, of fractional mixing coefficients that must sum to one
'''
mixedPop = population(parentPopulations=parentPops,
mixingCoefficients=mixingCoefficients)
return correlationCoeff(daughterPop, mixedPop)
def mixture_Likeness(daughterPop, parentPops, mixingCoefficients):
'''Determine the \'likeness\' of the daughter and mixed parent populations.
Here likeness is defined following Satkoski et al., 2013 as summarized in
Saylor and Sundell, 2016
:param daughterPop: an instance of the population class describing a daughter population
:param parentPops: a list of instances of the population class describing the parents
:param mixingCoefficients: a list, or array, of fractional mixing coefficients that must sum to one
'''
mixedPop = population(parentPopulations=parentPops,
mixingCoefficients=mixingCoefficients)
return likeness(daughterPop, mixedPop)
def mixture_Similarity(daughterPop, parentPops, mixingCoefficients):
'''Determine the \'similarity\' of the the mixed and daughtter DZ populations using the Gehrels, 2000 method
This function is a wrapper to call calcSimilarity on the PDFs defined by
two population objects
:param daughterPop: an instance of the population class describing a daughter population
:param parentPops: a list of instances of the population class describing the parents
:param mixingCoefficients: a list, or array, of fractional mixing coefficients that must sum to one
'''
mixedPop = population(parentPopulations=parentPops,
mixingCoefficients=mixingCoefficients)
return similarity(daughterPop, mixedPop)
def getMixedPopulation(self,mixtureNumber,parentPops,**kwargs):
'''Return a population produced from the mixture definined by the ith mixture coefficients
'''
return population(parentPopulations = parentPops,mixingCoefficients = self.mixingCoeffs[mixtureNumber],**kwargs)
#The name of the sheets where data is stored in that file
#Name of the rows in the exceel sheet that contain information
ageHeader = 'BestAge' #For ages
errorHeader = 'BestAge_err_1s_Ma' #For 1-sigma errors
sampleID = 'Sample_ID' #For sample names
#How do we want to scale the PDFs?
minAge = 0.0
maxAge = 300.0
dt = 1.0
#Read in a few different samples, 'DR584'
DR584 = detPop.population(excelFileName=pathToExcelFile,
excelSheetName=excelSheet,
ageHeader=ageHeader,
errorHeader=errorHeader,
sampleIDfield=sampleID,
sampleID='DR584')
#Sample T693, which mixture modelling of Sharman and Johnstone, 2017 suggests is pretty similar to DR584
T693 = detPop.population(excelFileName=pathToExcelFile,
excelSheetName=excelSheet,
ageHeader=ageHeader,
errorHeader=errorHeader,
sampleIDfield=sampleID,
sampleID='T693')
#Sample T978, which mixture modelling of Sharman and Johnstone, 2017 suggests is pretty different to DR584
T978 = detPop.population(excelFileName=pathToExcelFile,
excelSheetName=excelSheet,
ageHeader=ageHeader,
#mixOrder = 'reverse' #high values correspond to good mixtures (e.g. cross correlation)
#At what resolution to we want to create mixtures
mixSpacing = 0.01 #Keep coarse for testing (e.g. 0.1 (10%) ) to improve efficiency
# %%
#==============================================================================
# Load in the parents and daughters
#==============================================================================
parentSet = []
for parent in ParentList:
parentSet.append(
dp.population(excelFileName=filePath,
excelSheetName=excelSheet,
ageHeader=ageHeader,
errorHeader=errorHeader,
sampleIDfield=sampleID,
sampleID=parent))
daughterSet = []
for daughter in DaughterList:
daughterSet.append(
dp.population(excelFileName=filePath,
excelSheetName=excelSheet,
ageHeader=ageHeader,
errorHeader=errorHeader,
sampleIDfield=sampleID,
sampleID=daughter))
# %%
#==============================================================================
minAge = 0.0
maxAge = 3501.0
tSpacing = 2.0
#Samples to export
sampleList = [
'MAN', 'MLB', 'DR585', 'DR591', 'DR584', 'T755', 'MDP', 'T1135', 'GSB',
'T693', 'T978', 'T958'
]
with open(outfile, 'w') as f:
#Iterate through all the samples
for i, sample in enumerate(sampleList):
print(sample)
pop = dp.population(excelFileName=filePath,
excelSheetName=excelSheet,
ageHeader=ageHeader,
errorHeader=errorHeader,
sampleIDfield=sampleID,
sampleID=sample)
pop.calcDF(forceCalc=True,
tmin=minAge,
tmax=maxAge,
delt=tSpacing,
method=densityFunctionMethod,
bandwidth=kdeBandwidth)
#Before first sample, write the header
if i == 0:
ts = pop._tAxisDF_
tStrList = [' ' + ageFmt % t for t in ts]
header = 'Age' + outDelimiter + outDelimiter.join(tStrList) + '\n'
f.write(header)
def genRandomAges(n, mean, spread):
''' A function to return a selection of n random ages drawn from the population
described by mean and spread
'''
return np.random.randn(int(n)) * spread + mean
#Create a random population of ages with two components
#by concatenating two random arrays
n = 100 #number of ages
randAges = np.hstack((genRandomAges(n, 30.0,
5.0), genRandomAges(n, 200.0, 3.0)))
randErrors = randAges * 0.10 #assign a constant relative error
#Create a population based on these ages and errors
popArray = population(ages=randAges, errors=randErrors)
#Next we will load in a population from a file
#This file must be a delimeted text file, must have headers titled 'age' and 'error'
# or header must be specified.
ageHdrName = 'ages'
errorHdrName = 'errors'
pathToFile = 'testData.csv'
#We will just create a text file to load in, or feel free to provide your own by commenting out the next few lines, and
#updating the above path to something of your own.
##### Starting file creation - comment out if providing your own.
#Again, we will just create some random distributions
n = 100 #number of ages
