fldpseazm = np.mean(fldpsea[..., :-1], axis=2)
fldcseazmtm = np.mean(fldcseazm, axis=0) # time mean now
fldpseazmtm = np.mean(fldpseazm, axis=0)
plotd = np.zeros((nyr, nlat))
tstat = np.zeros((nyr, nlat))
pval = np.zeros((nyr, nlat))
for yr in years:
if pattcorr == 1:
# do a pattern correlation with time
corrlim = 45 # @@
areas = cutl.calc_cellareas(lat, lon)
areas = areas[lat > corrlim, :]
# areas = ma.masked_where(lmask[lat>corrlim,:]==-1,areas)
weights = areas / np.sum(np.sum(areas, axis=1), axis=0)
# Could also do each year's pattern corr rather than cumulative mean DONE
# OR, use the ens mean pattern as the pattern to compare against -- not useful I think,
# for what we want to know: is the pattern of response for each ensemble member random
# or dependent on the boundary condition.
# @@ Also, would be nice to have multiple variables in one plot and/or multiple simulations
if pattcorryr:
# yearly anomaly pattern corr w/ the time mean pattern
tmp = fldpseazm[yr, lat > corrlim, ...] - fldcseazmtm[lat > corrlim, ...]
else:
# time-integrated anomaly pattern corr w/ the end anomaly pattern
else:
ncparams['levsel'] = level
fldc = np.append(cnc.getNCvar(fnamec,ncfield,timesel='0002-01-01,061-12-31',**ncparams)*conv,
cnc.getNCvar(fnamec2,ncfield,**ncparams)*conv,
axis=0)
fldp = np.append(cnc.getNCvar(fnamep,ncfield,timesel='0002-01-01,061-12-31',**ncparams)*conv,
cnc.getNCvar(fnamep2,ncfield,**ncparams)*conv,
axis=0)
if sia==1:
fldc = cutl.calc_seaicearea(fldc,lat,lon)
fldp = cutl.calc_seaicearea(fldp,lat,lon)
# Prepare the data here: @@
# @@ from hists script:
areas = cutl.calc_cellareas(lat,lon,repeat=fldc.shape)
areas = areas[:,lat>latlim,:]
fldcorig=copy.copy(fldc)
fldporig=copy.copy(fldp)
fldc = fldc[:,lat>latlim,:]
fldp = fldp[:,lat>latlim,:]
if maskland:
lmask = con.get_t63landmask(repeat=fldc.shape)
areas = ma.masked_where(lmask[:,lat>latlim,:]==-1,areas)
fldc = ma.masked_where(lmask[:,lat>latlim,:]==-1,fldc)
fldp = ma.masked_where(lmask[:,lat>latlim,:]==-1,fldp)
mtype='ocn'
elif maskocean:
lmask = con.get_t63landmask(repeat=fldc.shape)
areas = ma.masked_where(lmask[:,lat>latlim,:]!=-1,areas)
fldc = ma.masked_where(lmask[:,lat>latlim,:]!=-1,fldc)
def pattcorr_ensemble(ename, field, latlim=60):
# @@@@@@@@@@@@ is this fully implemented? Don't think so. 12/2/14
if ename=='ANT':
ename='HistIC'
elif ename=='TOT':
ename='HistBC'
enssims = con.build_ensemblesims(ename)
ensnum=len(enssims)
# ======= copied from Canam4_BCpatterncorr-Copy0.py ===========
#ensnum=5
diffdict = {}
pcmeandict = {} # fldp-fldc pattern corr compared to mean BC
pchaddict = {} # fldp-fldc pattern corr compared to hadisst
seadiffdict = {} # seasonal mean
pcseameandict = {}
pcsea2meandict = {} # to test the other pattern corr calc
pcsea2pvalmeandict = {} # to test the other pattern corr calc
# generate weights for the pattern corr
lat = con.get_t63lat()
lon = con.get_t63lon()
areas = cutl.calc_cellareas(lat,lon)
areas = areas[lat>latlim,:]
weights = areas / np.sum(np.sum(areas,axis=1),axis=0)
#for eii in range(1,ensnum+1):
for skey in enssims:
#skey = etype + str(eii)
#casenamec = bcasenamec + skey
#casenamep = bcasenamep + skey
#fnamec = basepath + casenamec+ subdir + casenamec + '_' + field + '_001-121_ts.nc'
#fnamep = basepath + casenamep+ subdir + casenamep + '_' + field + '_001-121_ts.nc'
fnamec,fnamep = con.build_filepathpair(skey,field)
# monthly calc
fldc = cnc.getNCvar(fnamec,ncfield,timesel=timesel)*conv
fldp = cnc.getNCvar(fnamep,ncfield,timesel=timesel)*conv
fldd = fldp-fldc
# take the pattern correlation
flddclimo,flddstd = cutl.climatologize(fldd) # climo first (don't need to do for BCs technically)
flddcclimo,flddcstd = cutl.climatologize(flddc) # climo first. baseline diff data
diffdict[skey] = flddclimo
# for each month, compute pattern corr
pc = np.zeros((12))
for mii,mon in enumerate(con.get_mon()):
tmp = np.squeeze(flddclimo[mii,lat>latlim,...])
tmpcmp = np.squeeze(flddcclimo[mii,lat>latlim,...])
pc[mii] = cutl.pattcorr(tmp.flatten()*weights.flatten(),tmpcmp.flatten()*weights.flatten())
pcmeandict[skey] = pc # monthly
# seasonal calc
fldcsea = np.zeros((4,len(lat),len(lon)))
fldpsea = np.zeros((4,len(lat),len(lon)))
flddsea = np.zeros((4,len(lat),len(lon)))
pcsea = np.zeros((4))
pcsea2 = np.zeros((4)) # test pattcorr_pearson() @@
pcsea2pval = np.zeros((4)) # test pattcorr_pearson()
for seaii,sea in enumerate(seasons):
fldcsea[seaii,...] = np.mean(cnc.getNCvar(fnamec,ncfield,timesel=timesel,seas=sea)*conv,axis=0)
fldpsea[seaii,...] = np.mean(cnc.getNCvar(fnamep,ncfield,timesel=timesel,seas=sea)*conv,axis=0)
flddsea[seaii,...] = fldpsea[seaii,...]-fldcsea[seaii,...]
tmp = np.squeeze(flddsea[seaii,lat>latlim,...])
tmpcmp = np.squeeze(flddcsea[seaii,lat>latlim,...])
pcsea[seaii] = cutl.pattcorr(tmp.flatten()*weights.flatten(),
tmpcmp.flatten()*weights.flatten())
pcsea2[seaii],pcsea2pval[seaii] = cutl.pattcorr_pearson(tmp.flatten()*weights.flatten(),
tmpcmp.flatten()*weights.flatten())
seadiffdict[skey] = flddsea
pcseameandict[skey] = pcsea
pcsea2meandict[skey] = pcsea2
pcsea2pvalmeandict[skey] = pcsea2pval
# prepare the flux data by averaging, etc
for field in fluxes:
fnamec = basepath + casenamec + subdir + casenamec + '_' + field + '_' + timstr + '_ts.nc'
fnamep = basepath + casenamep + subdir + casenamep + '_' + field + '_' + timstrp + '_ts.nc'
fldc,cstd = cutl.climatologize(cnc.getNCvar(fnamec,field.upper(),timesel=timesel))
fldp,pstd = cutl.climatologize(cnc.getNCvar(fnamep,field.upper(),timesel=timesel))
fldc = ma.masked_where(sicnc<.10,fldc) # masking out non-ice region (as P&M 2014 JClim)
fldp = ma.masked_where(sicnc<.10,fldp)
# now calc area-weighted mean
cellareas = cutl.calc_cellareas(lat,lon,repeat=fldc.shape)
cellareas = ma.masked_where(sicnc<.10,cellareas)
totarea = np.sum(np.sum(cellareas[:,lat>latlim,:],axis=2),axis=1)
totarea = np.tile(totarea,(cellareas.shape[1],cellareas.shape[2],1))
totarea = np.transpose(totarea,(2,0,1))
#cellwgts = cellareas/totarea
fldcam = np.sum(np.sum(fldc[:,lat>latlim,:]*(cellareas[:,lat>latlim,:]/totarea[:,lat>latlim,:]),axis=2),axis=1)
fldpam = np.sum(np.sum(fldp[:,lat>latlim,:]*(cellareas[:,lat>latlim,:]/totarea[:,lat>latlim,:]),axis=2),axis=1)
fluxdict[field] = fldpam - fldcam
fnamecb = basepath + casenamecb + subdir + casenamecb + '_' + field + '_' + timstrb + '_ts.nc'
fnamepb = basepath + casenamepb + subdir + casenamepb + '_' + field + '_' + timstrpb + '_ts.nc'
def pattcorr_withinensemble(ename,fdict,latlim=60,timesel='0002-01-01,0121-12-31'):
""" pattcorr_withinensemble(ename,field,latlim=60)
pattern corr each member of ensemble with each other one
return pctable, pctablesea (DataFrames)
"""
# @@ need diffdict
field=fdict['field']
ncfield=fdict['ncfield']
conv=fdict['conv']
seasons=('SON','DJF','MAM','JJA')
if ename=='ANT':
ename='histIC'
elif ename=='TOT':
ename='histBC'
enssims = con.build_ensemblesims(ename)
ensnum=len(enssims)
print 'ENSSIMS: ' # @@@
print enssims # @@
# generate weights for the pattern corr
lat = con.get_t63lat()
lon = con.get_t63lon()
areas = cutl.calc_cellareas(lat,lon)
areas = areas[lat>latlim,:]
weights = areas / np.sum(np.sum(areas,axis=1),axis=0)
# ========= create diffdict first =====
diffdict={}
seadiffdict={}
for skey in enssims:
fnamec,fnamep = con.build_filepathpair(skey,field)
# monthly calc
fldc = cnc.getNCvar(fnamec,ncfield,timesel=timesel)*conv
fldp = cnc.getNCvar(fnamep,ncfield,timesel=timesel)*conv
fldd = fldp-fldc
# Monthly
flddclimo,flddstd = cutl.climatologize(fldd) # climo first (don't need to do for BCs technically)
#flddcclimo,flddcstd = cutl.climatologize(flddc) # climo first. baseline diff data
diffdict[skey] = flddclimo
print skey + ' ' + str(flddclimo.shape) # @@@
# Seasonal
flddsea = np.zeros((4,len(lat),len(lon)))
for seaii,sea in enumerate(seasons):
fldcsea = np.mean(cnc.getNCvar(fnamec,ncfield,timesel=timesel,seas=sea)*conv,axis=0)
fldpsea = np.mean(cnc.getNCvar(fnamep,ncfield,timesel=timesel,seas=sea)*conv,axis=0)
flddsea[seaii,...] = fldpsea-fldcsea
seadiffdict[skey] = flddsea
# ======= Now do pattern corrs within ensemble ====
# ======= copied from Canam4_BCpatterncorr-Copy0.py ===========
outterdict= dict.fromkeys(enssims)
for skey1 in enssims:
outfld = diffdict[skey1]
innerdict = dict.fromkeys(enssims)
for skey2 in enssims:
#print skey1 + ' compared to ' + skey2
infld = diffdict[skey2]
# for each month, compute pattern corr
pc = np.zeros((12))
for mii,mon in enumerate(con.get_mon()):
tmp = np.squeeze(infld[mii,lat>latlim,...])
tmpcmp = np.squeeze(outfld[mii,lat>latlim,...])
pc[mii] = cutl.pattcorr(tmp.flatten()*weights.flatten(),
tmpcmp.flatten()*weights.flatten())
innerdict[skey2] = pc
outterdict[skey1] = innerdict
pctable = pd.DataFrame(outterdict) # 5x5
# seasonal
outterdictsea= dict.fromkeys(enssims)
for skey1 in enssims:
outfld = seadiffdict[skey1]
innerdictsea = dict.fromkeys(enssims)
for skey2 in enssims:
#print skey1 + ' compared to ' + skey2
infld = seadiffdict[skey2]
# for each season, compute pattern corr
pcsea = np.zeros((4))
for seaii,sea in enumerate(seasons):
tmp = np.squeeze(infld[seaii,lat>latlim,...])
tmpcmp = np.squeeze(outfld[seaii,lat>latlim,...])
pcsea[seaii] = cutl.pattcorr(tmp.flatten()*weights.flatten(),
tmpcmp.flatten()*weights.flatten())
innerdictsea[skey2] = pcsea
outterdictsea[skey1] = innerdictsea
pctablesea = pd.DataFrame(outterdictsea) # 5x5
return pctable, pctablesea
