def testErrors(self):
crpss_dict = self.crpssDict()
crpss_dict['variable'] = 'pr'
crpss = Crpss(**crpss_dict)
self.assertRaises(NoFilesFoundError, crpss.prepareInput)
crpss_dict['variable'] = 'tas'
crpss_dict['observation'] = 'merra'
crpss = Crpss(**crpss_dict)
self.assertRaises(NotEnoughYearsInFile, crpss.prepareInput)
crpss_dict['observation'] = 'HadCrut'
crpss_dict['project'] = 'cmip5'
crpss_dict['experiment'] = 'hist*'
crpss_dict['product1'] = 'output1'
crpss = Crpss(**crpss_dict)
self.assertRaises(NoFilesFoundError, crpss.prepareInput)
crpss_dict = self.crpssDict()
crpss_dict['ensemblemembers'] = 'r1i1p1'
crpss = Crpss(**crpss_dict)
crpss.prepareInput()
self.assertRaises(NotEnoughEnsemblemembersFound, crpss.analyze)
def testBootstrap(self):
crpss_dict = self.crpssDict()
crpss_dict['bootstrapSwitch'] = True
crpss_dict['bootstrap_number'] = 5
crpss = Crpss(**crpss_dict)
crpss.prepareInput()
crpss.analyze()
def testCrpss(self):
crpss_dict = self.crpssDict()
crpss = Crpss(**crpss_dict)
crpss.prepareInput()
crpss.analyze()
#test file names
res_files = [f for r,_,files in os.walk(self.tmp_dir+'/output') for f in files]
test_files = [f for r,_,files in os.walk(self.test_path+'/output') for f in files]
self.assertEqual(sorted(res_files),sorted(test_files))
res_files = [f for r,_,files in os.walk(self.tmp_dir+'/plots') for f in files]
test_files = [f for r,_,files in os.walk(self.test_path+'/plots') for f in files]
self.assertEqual(sorted(res_files),sorted(test_files))
#test values of all .nc files
res_files = sorted([os.path.join(r,f) for r,_,files in os.walk(self.tmp_dir+'/output') for f in files])
test_files = sorted([os.path.join(r,f) for r,_,files in os.walk(self.test_path+'/output') for f in files])
for i,f in enumerate(res_files):
t1 = FileHandler.openNetCDFFile(res_files[i])
t2 = FileHandler.openNetCDFFile(test_files[i])
np.testing.assert_array_almost_equal(t1['variable'], t2['variable'], 3)
#elf.assertTrue((t1['variable']==t2['variable']).all())
self.assertTrue((t1['lon']==t2['lon']).all())
self.assertTrue((t1['lat']==t2['lat']).all())
def testMaxLeadYearHistorical(self):
crpss_dict = self.crpssDict()
crpss_dict['decadals'] = range(1990,2000,5)
crpss_dict['project'] = 'cmip5'
crpss_dict['product1'] = 'output1'
crpss_dict['leadtimes'] = '1,2'
crpss_dict['experiment'] = 'historical'
crpss = Crpss(**crpss_dict)
crpss.prepareInput()
crpss.analyze()
def testEnsemblemembers(self):
crpss_dict = self.crpssDict()
crpss_dict['ensemblemembers'] = 'r2i1p1,r3i1p1'
crpss = Crpss(**crpss_dict)
crpss.prepareInput()
crpss.analyze()
for year in crpss_dict['decadals']:
self.assertTrue(len(crpss.inputDict[year]) == 2, 'Too many ensemblemembers found!')
def testErrors(self):
crpss_dict = self.crpssDict()
crpss_dict['variable'] = 'pr'
crpss = Crpss(**crpss_dict)
self.assertRaises(NoFilesFoundError, crpss.prepareInput)
crpss_dict['variable'] = 'tas'
crpss_dict['observation'] = 'merra'
crpss = Crpss(**crpss_dict)
self.assertRaises(NotEnoughYearsInFile, crpss.prepareInput)
crpss_dict['observation'] = 'HadCrut'
crpss_dict['project'] = 'cmip5'
crpss_dict['experiment'] = 'hist*'
crpss_dict['product1'] = 'output1'
crpss = Crpss(**crpss_dict)
self.assertRaises(NoFilesFoundError, crpss.prepareInput)
crpss_dict = self.crpssDict()
crpss_dict['ensemblemembers'] = 'r1i1p1'
crpss = Crpss(**crpss_dict)
crpss.prepareInput()
self.assertRaises(NotEnoughEnsemblemembersFound, crpss.analyze)
def testTestfiles(self):
def crps(var,H,O):
x = (H-O)/var
crps = -var * (1./np.sqrt(np.pi) - 2. * stats.norm.pdf(x) - x * (2. * stats.norm.cdf(x) - 1.))
return crps
def condBias(H,O):
H_ensmean = np.mean(H, axis=1)
r = np.corrcoef(H_ensmean, O)[0,1]
std_H = np.std(H_ensmean)
std_O = np.std(O)
cond_bias = r * std_O/std_H
return cond_bias
from create_testfiles import createCrpssInput, getCrpssTimeseries
mse_goal = 4
ensspread_goal = 3
ensemble_size = 10
length = 20
#create timeseries
(t,hind,obs) = getCrpssTimeseries(mse_goal, ensspread_goal, ensemble_size, length)
(hindcasts,observations) = createCrpssInput(1960, hind, obs, ensemble_size, length)
crpssDict = self.crpssDict()
crpssDict['decadals'] = hindcasts.keys()
crpssDict['observation'] = 'HadCrut'
crpssDict['leadtimes'] = '1'
crpss = Crpss(**crpssDict)
crpss.inputRemapped = hindcasts
crpss.observationRemapped = observations
crpss.analyze()
factor = length/(length-2.)
factor2 = ensemble_size/(ensemble_size-1.)
ensspread = np.mean((factor2*np.var(hind,axis=1)))**0.5
hind_mean = np.mean(hind,axis=1)
#calculte crossvalidated mean
hind_mean_anom = hind_mean.copy()
crossval = np.zeros((length))
for i in range(length):
tmp = np.delete(hind_mean,i)
crossval[i] = np.mean(tmp)
hind_mean_anom[i] = hind_mean[i] - crossval[i]
hind_mean = hind_mean_anom.copy()
#remove conditional bias
bias = condBias(hind, obs)
for i in range(length):
hind[i,:] = hind[i,:] - crossval[i]
hind[i,:] = hind[i,:] + (bias-1)*hind_mean[i]
hind_mean_corrected = np.mean(hind,axis=1)
RMSE = (factor*np.mean((np.mean(hind,axis=1)-obs)**2))**0.5
#calculate crpss_goal
crps1 = np.zeros((length))
crps2 = np.zeros((length))
for i in range(length):
crps1[i] = crps(ensspread, hind_mean_corrected[i], obs[i])
crps2[i] = crps(RMSE,hind_mean_corrected[i],obs[i])
crpss_goal = 1 - np.mean(crps1)/np.mean(crps2)
#test spreadscore
tf = crpss.outputDir+'1-1/baseline1_output_mpi-esm-lr_decs4e_input1/ensemble_spread/1_1_tas_baseline1_output_mpi-esm-lr_decs4e_1960-1979_ensspread_vs_referror.nc'
t1 = FileHandler.openNetCDFFile(tf,mode='var')
self.assertAlmostEqual(t1[12,12],ensspread/RMSE,2)
#test crpss ens vs ref
tf = crpss.outputDir+'1-1/baseline1_output_mpi-esm-lr_decs4e_input1/ensemble_spread/1_1_tas_baseline1_output_mpi-esm-lr_decs4e_1960-1979_ens-vs-ref_crpss.nc'
t1 = FileHandler.openNetCDFFile(tf,mode='var')
self.assertAlmostEqual(t1[12,12],crpss_goal,2)
def main(argv=None): # IGNORE:C0111
'''Command line options.'''
if argv is None:
argv = sys.argv[1:]
args, lastargs = getopt.getopt(argv, _short_args, _args)
for flag,arg in args:
if flag=='-h' or flag=='--help':
return printHelp()
murcss_dict = getMurcssDict()
for arg in lastargs:
if '=' not in arg:
raise CommandError("Invalid format for query: %s" % arg)
items = arg.split('=')
key, value = items[0], ''.join(items[1:])
murcss_dict[key] = value
murcss_dict['decadals'] = map(int,murcss_dict['decadals'].split(','))
murcss_dict['bootstrap_number'] = int(murcss_dict['bootstrap_number'])
analysis_type = murcss_dict.pop('analysis_type')
if analysis_type == 'map':
murcss_dict['fieldmean'] = False
murcss_dict['zonalmean'] = False
elif analysis_type == 'fieldmean':
murcss_dict['fieldmean'] = True
murcss_dict['zonalmean'] = False
elif analysis_type == 'zonalmean':
murcss_dict['fieldmean'] = False
murcss_dict['zonalmean'] = True
output_type = murcss_dict.pop('output_type')
if output_type == 'basic':
murcss_dict['basic_output'] = True
else:
murcss_dict['basic_output'] = False
#Check for right metics value
metrics = murcss_dict.pop('metrics')
if metrics not in ['all','accuracy','ensemble_spread']:
raise Exception, '%s is not a valid option. Only valid options for metric are: "all", "ensemble_spread", and "accuracy".' % (metrics)
if metrics in ['all','accuracy']:
print '#######################'
print 'Calculating the MSSS'
print '#######################'
#Calculation of MSESS
if(not murcss_dict['significance']):
msss_dict = murcss_dict.copy()
msss_dict.pop('bootstrap_number')
msss_dict.pop('significance')
msss = Msss(**msss_dict)
msss.prepareInput()
msss.analyze()
msss.deleteCache()
else:
from metrics.msssBootstrap import main
msss = main(murcss_dict.copy(),'..')
if metrics in ['all','ensemble_spread']:
print '#######################'
print 'Calculating the CRPSS for Model1'
print '#######################'
crpss1 = Crpss(output=murcss_dict['output'],
output_plots=murcss_dict['output_plots'],
basic_output=murcss_dict['basic_output'],
decadals=murcss_dict['decadals'],
variable=murcss_dict['variable'],
project = murcss_dict['project1'],
product1=murcss_dict['product1'],
institute1=murcss_dict['institute1'],
model=murcss_dict['model1'],
experiment=murcss_dict['experiment1'],
ensemblemembers=murcss_dict['ensemblemembers1'],
observation = murcss_dict['observation'],
leadtimes=murcss_dict['leadtimes'],
result_grid=murcss_dict['result_grid'],
maskMissingValues=murcss_dict['maskMissingValues'],
bootstrapSwitch=murcss_dict['significance'],
bootstrap_number=murcss_dict['bootstrap_number'],
level=murcss_dict['level'],
lonlatbox=murcss_dict['lonlatbox'],
fieldmean=murcss_dict['fieldmean'],
zonalmean=murcss_dict['zonalmean'],
cache=murcss_dict['cache'],
baseDir = murcss_dict['baseDir'])
if metrics != 'ensemble_spread':
crpss1.outputDir = msss.outputDir
crpss1.outputPlots = msss.outputPlots
crpss1.prepareInput()
crpss1.analyze()
crpss1.deleteCache()
print '#######################'
print 'Calculating the CRPSS for Model2'
print '#######################'
crpss2 = Crpss(output=murcss_dict['output'],
output_plots=murcss_dict['output_plots'],
basic_output=murcss_dict['basic_output'],
decadals=murcss_dict['decadals'],
variable=murcss_dict['variable'],
project = murcss_dict['project2'],
product1=murcss_dict['product2'],
institute1=murcss_dict['institute2'],
model=murcss_dict['model2'],
experiment=murcss_dict['experiment2'],
ensemblemembers=murcss_dict['ensemblemembers2'],
observation = murcss_dict['observation'],
leadtimes=murcss_dict['leadtimes'],
result_grid=murcss_dict['result_grid'],
maskMissingValues=murcss_dict['maskMissingValues'],
bootstrapSwitch=murcss_dict['significance'],
bootstrap_number=murcss_dict['bootstrap_number'],
level=murcss_dict['level'],
lonlatbox=murcss_dict['lonlatbox'],
fieldmean=murcss_dict['fieldmean'],
zonalmean=murcss_dict['zonalmean'],
cache=murcss_dict['cache'],
input_part='input2',
baseDir = murcss_dict['baseDir'])
if metrics != 'ensemble_spread':
crpss2.outputDir = msss.outputDir
crpss2.outputPlots = msss.outputPlots
crpss2.prepareInput()
crpss2.analyze()
crpss2.deleteCache()
import metrics.msss, metrics.metricAbstract, metrics.filehandler, metrics.taylorplot, metrics.crpss, metrics.msssBootstrap
del metrics.msss.cdo, metrics.metricAbstract.cdo, metrics.filehandler.cdo, metrics.taylorplot.cdo, metrics.crpss.cdo, metrics.msssBootstrap.cdo
print 'Calculation finished.'
print 'Plots produced in %s' %(msss.outputPlots,)