def bootstrapMCMCprobabilityOfDeath(EmpFrame, AICFrame, N=10, MCMConPartitions = [], Delta=2, Punishment='Death'):
"""Return the high and low confidence intervals for probabiity of death base on MCMC run on partitions.
"""
#NOTE: Unfinished WIP
#Generate our own dummy data
"""
EmpFrame = oboM.changePeriod( oboM.loadCatEmp( 'Data/Raw/OBOextractNoGender1yr.csv'), Delta=2).iloc[ [30, 31, 116, 117]]
AICFrame = oboM.loadMod('Data/Partitions/AICtableSortedValuesProperly2yr.csv').iloc[[30,31,116,117],0:4]
"""
puns = 7
offs = 9
PunIndex = c2n.puncatFullUp.index(Punishment)
DFlon,DFlen = EmpFrame.shape
OffenceEstimate = oboM.generateDependentModelLaplace(oboM.combineOnOffence(EmpFrame),Delta=Delta)
#Generate MCMC data if it does not exist.
if type(MCMConPartitions) is list:
print('Generating MCMC on {} partitions'.format(N))
MCMConPartitions = mcmcOnPartitions(AICFrame, N = N, Verbose=True, Sort=False)
MCMClon,MCMClen = MCMConPartitions.shape
#Convert the partition numbers to partitions:
#print('Converting the MCMC frame of partition numbers to partitions')
#MCMCofPartitions = MCMCofPartitions.applymap(lambda x: oboP.partitioN[x])
for row in range(DFlon):
print('Calculating probabilites for row {} of {}'.format(row,DFlon))
print('Looping through every MCMC partitioning')
#Find the groupings for the counts per partition as a series
Row = MCMCofPartitions.iloc[row]
RowGrouping = Row.apply(lambda partId: [ x for x in oboP.partitioN.unrank_rgf(partId)[1:] for y in range(puns) ])
#Find the punishment groupings, with 1 for the punishment and 0 else, discarding 0:
PunishmentGrouping = Row.apply(lambda partId: [ x if y is PunIndex else 0 for x in oboP.partitioN.unrank_rgf(partId)[1:] for y in list(range(puns)) ])
#Find the percentage probability estimates for the punishment, per block:
RowCountsPerBlock = RowGrouping.apply(lambda group: EmpRow.groupby(group).sum())
PunishmentCountPerBlock = RowDeathOffGrouping.apply(lambda blah: EmpRow.groupby(blah).sum()[1:])
PunishmentEstimatesPerBlock = (PunishmentCountPerBlock/ RowGroupingCounts)*100
#Get rid of the pesky il defined infinities
PunishmentEstimatesPerBlock[np.isinf(PunishmentEstimatesPerBlock)] = 0
#for MCMC in range(MCMClen):
#print('Finding estimates for {} for row {}, partition {}'.format(Punishment, row, MCMC))
#RowDeathOffGrouping = EmpFrame.iloc[row].apply(lambda partId: [ x if y is PunIndex else 0 for x in partitioN.unrank_rgf( MCMConPartitions.iloc[row,MCMC] )[1:] for y in list(range(puns)) ])
#print(RowDeathOffGrouping)
return OffenceEstimate, MCMConPartitions
def validateAICModelSelection(DummyEmp):
"""Create a DataFrame containing AIC scores of all standard models. Only NoGender at this stage.
Parameters
----------
DumyEmp : pandas DataFrame, Dummy emperical data frame as generated by generateDummyDataFrame()
Returns:
pandas DataFrame, Sorted AIC scores for different Delta's and model types
"""
AICFrame = pd.DataFrame(columns = ['Delta','k','ll','AIC'])
CatEmp = DummyEmp.mul(1)
Deltas = [1,2,3,4,5,10]
#Generate all the refactorings:
CatEmps = [ oboM.changePeriod(CatEmp,Delta) for Delta in Deltas]*2 #*2 as one for Dep and one for Indep
CatModsDep = [ oboM.generateDependentModelLaplace(CatEmp, Delta=Delta) for Delta in Deltas ]
CatModsIndep = [ oboM.generateIndependentModel(CatEmp, Delta=Delta) for Delta in Deltas ]
CatMods = CatModsDep + CatModsIndep
#For all generated model types on all deltas
for c,CatMod in enumerate(CatMods):
ModType = 'Dependent' if (c < len(CatMods)/2) else 'Independent'
if 'Dependent' in ModType:
k = (9-1)*(7-1)*CatMod.shape[0]
elif 'Independent' in ModType:
k = (9+7-2)*CatMod.shape[0]
else:
print('Oh deary me')
return
ll = oboM.loglikilyhood(CatEmps[c], CatMod)
AIC = 2*k - 2*ll
AICFrame.loc[c] = [ ModType + ' Delta = ' + str(Deltas[int(c%(len(CatMods)/2))]), k, ll, AIC]
##print('{}, years: {}, model index {}, k {}, log-likelihood {}, AIC {}'.format(file,fileYearDelta,DeltasIndex,k,ll, AIC))
##print('{} loaded'.format(file))
#except:
#print('{} failed to load'.format(file))
##Return the frame
return AICFrame.sort('AIC')
