# DEBUG:
ci=dblob['ci']
pv=dblob['pval']
import pandas as pd
# calc whether ens means are sig different @@@@
if shadeens != None: # right now, will never be none. Should change that. @@@
# calc anom range vs mean anom for the given field within given ensemble
allensdt,allensmdt = con.build_ensembles(shadeens,dblob,calctype='diff')
for ens in shadeens:
ensdf=pd.DataFrame(allensdt[ens])
#ensmdf=pd.DataFrame(allensmdt[ens])
ensrng = ensdf.max(axis=1)-ensdf.min(axis=1)
ensrat = ensrng / ensdf.mean(axis=1)
print ens + ' RANGE: '
print str(ensrng)
print ens + ' MEAN: '
print str(ensdf.mean(axis=1))
print ens + ' RATIO*100: '
print str(ensrat*100)
if len(shadeens)>1:
sh.calc_ensemblestats(dblob,shadeens,seas=seasons)
def calc_ensemblestats(datablob,ensnames, seas=None,siglevel=0.05):
"""
datablob: 'diff' should be scalar regional mean anomalies
ensnames: a tuple of ensemble names in the datablob.
must match ensname in sims dictionary. e.g. histIC, histBC
seas: 2 or 3 month seasons
@@ add return vals
"""
## diffdt = datablob['diff']
## sims=diffdt.keys()
## simspdt = con.get_simpairsdict()
if seas==None:
seasons=('SON','DJF','MAM','JJA')
else:
seasons=seas
# Need all members of ensemble, plus mean to do ttest between
# ensemble means. This ttest is NOT in time, but across
# ensemble members. Thus, n=5 for TOT and ANT.
# return tstat, pval, stddev # all across ensemble, not in time.
allensdt,allensmdt = con.build_ensembles(ensnames, datablob,calctype='diff')
## allensdt={}; allensmdt={};
## for ensname in ensnames:
## ensdt={}; ensmdt={}
## print ensname
## for skey in sims: # for each simulation check if it's in the ensemble
## if simspdt[skey]['pert']['ensname']==ensname:
## # create an ensemble dict
## ensdt[skey] = datablob['diff'][skey]
## if simspdt[skey]['pert']['ensname']==ensname+'mean':
## ensmdt[skey] = datablob['diff'][skey]
## allensdt[ensname] = ensdt # dict of ens -> dict of sims in ens --> data
## allensmdt[ensname] = ensmdt # just the ensemble mean
# end loop through ens
ensdf1 = pd.DataFrame(allensdt[ensnames[0]])
ensdf2 = pd.DataFrame(allensdt[ensnames[1]])
ensm1 = allensmdt[ensnames[0]] # need DataFrame for this? should just be a val for each season
ensm2 = allensmdt[ensnames[1]]
for sea in seasons:
print sea
e1 = ensdf1.loc[sea]
e2 = ensdf2.loc[sea]
print sea
print ensnames[0] + ' MEAN: ' + str(e1.mean()) + ' STD: ' + str(e1.std())
print ensnames[1] + ' MEAN: ' + str(e2.mean()) + ' STD: ' + str(e2.std())
tstat, pval = sp.stats.ttest_ind(e1,e2)
print 'TSTAT: ' + str(tstat) + ' PVAL: ' + str(pval)
if pval<=siglevel:
print 'The ensemble means are significantly different (' + str(1-siglevel) + ')'
fstat, fpval = sp.stats.f_oneway(e1,e2)
print 'FSTAT: ' + str(fstat) + ' PVAL: ' + str(fpval)
if fpval<=siglevel:
print 'The ensemble means are significantly different (' + str(1-siglevel) + ')'
lstat, lpval = sp.stats.levene(e1,e2)
print 'LSTAT: ' + str(lstat) + ' PVAL: ' + str(lpval)
if lpval<=siglevel:
print 'The ensemble variances are significantly different (' + str(1-siglevel) + ')'
print '@@@@ not done, still need to add return vals'
