# -*- coding: utf-8 -*-
from pycmbs.plots import GlecklerPlot
import matplotlib.pyplot as plt
# this is just an artificial example illustrating principle usage of the
# Portraet diagram
fig = plt.figure(figsize=(8, 6))
G = GlecklerPlot(fig=fig)
# register models
G.add_model('MPI-ESM-MR')
G.add_model('MPI-ESM-LR')
G.add_model('MPI-ESM-P')
# then register variables
G.add_variable('Ta')
G.add_variable('P')
# after that you can add values to be plotted
# pos=1 top triangle, pos2= lower triangle
# different positions are for different observations
G.add_data('Ta', 'MPI-ESM-MR', 0.5, pos=1)
G.add_data('Ta', 'MPI-ESM-MR', -0.2, pos=2)
G.add_data('Ta', 'MPI-ESM-LR', 0.3, pos=1)
G.add_data('Ta', 'MPI-ESM-LR', 0.2, pos=2)
G.add_data('Ta', 'MPI-ESM-P', 0.05, pos=1)
G.add_data('Ta', 'MPI-ESM-P', -0.1, pos=2)
def test_gleckler_index(self):
"""
test Reichler index/Gleckler plot
"""
# generate sample data
# sample data
tmp = np.zeros((5, 3, 1))
tmp[:,0,0] = np.ones(5)*1.
tmp[:,1,0] = np.ones(5)*2.
tmp[:,2,0] = np.ones(5)*5.
# The data is like ...
#| 1 | 2 | 5 |
#| 1 | 2 | 5 |
#| 1 | 2 | 5 |
#| 1 | 2 | 5 |
#| 1 | 2 | 5 |
x = self.D.copy()
x._temporal_subsetting(0, 4)
x.data = np.ma.array(tmp, mask=tmp!=tmp)
x.std = np.ones(x.data.shape)
x.time[0] = pl.datestr2num('2000-02-15')
x.time[1] = pl.datestr2num('2000-03-15')
x.time[2] = pl.datestr2num('2000-04-15')
x.time[3] = pl.datestr2num('2000-05-15')
x.time[4] = pl.datestr2num('2000-06-15')
y = self.D.copy()
y._temporal_subsetting(0, 4)
tmp = np.ones(x.data.shape) # sample data 2
y.data = np.ma.array(tmp, mask=tmp!=tmp)
y.time[0] = pl.datestr2num('2000-02-15')
y.time[1] = pl.datestr2num('2000-03-15')
y.time[2] = pl.datestr2num('2000-04-15')
y.time[3] = pl.datestr2num('2000-05-15')
y.time[4] = pl.datestr2num('2000-06-15')
# Case 1: same area weights
# cell area
tmp = np.ones((3, 1))
x.cell_area = tmp*1.
#| 1-1 | 2-1 | 5-1 |
#| 1-1 | 2-1 | 5-1 |
#| 1-1 | 2-1 | 5-1 |
#| 1-1 | 2-1 | 5-1 |
#| 1-1 | 2-1 | 5-1 |
#===================
#| 0 | 5 | 5*4**2=5*16. = 80 |
#==> E2 = sqrt(85./(15.))
D = GlecklerPlot()
r = D.calc_index(x, y, 'a', 'b', time_weighting=False)
wt = np.ones(5) / 5.
ref = np.sqrt(((85./15.) * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error
D = GlecklerPlot()
r = D.calc_index(x, y, 'a', 'b')
wt = np.asarray([29., 31., 30., 31., 30.])
wt = wt / wt.sum()
ref = np.sqrt(((85./15.) * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error
# Case 2: Different area weights
# cell area
tmp = np.ones((3, 1))
tmp[1, 0] = 2.
x.cell_area = tmp*1.
#| 1-1=0 | 2-1=1 | 5-1=16 |
#| 1-1=0 | 2-1=1 | 5-1=16 |
#| 1-1=0 | 2-1=1 | 5-1=16 |
#| 1-1=0 | 2-1=1 | 5-1=16 |
#| 1-1=0 | 2-1=1 | 5-1=16 |
#--------------------------
# w = 0.25 w = 0.5 w=0.25|
#--------------------------
# 0.25*0 + 0.5 * 1 + 0.25 * 16 = 0 + 0.5 + 4 = 4.5
# the mean of that is 4.5 for each timestep
# mean because the overall weights are calculated as such that
# they give a total weight if 1
# diagnostic
D = GlecklerPlot()
r = D.calc_index(x, y, 'a', 'b', time_weighting=False)
wt = np.ones(5) / 5.
ref = np.sqrt((4.5 * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error
wt = np.asarray([29., 31., 30., 31., 30.])
wt = wt / wt.sum()
ref = np.sqrt((4.5 * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error
# Case 3: use different std
x.std = np.ones(x.data.shape)
x.std[:, 2, 0] = 0.5
#| 1-1=0 | 2-1=1 | 5-1=16 / 0.5 |
#| 1-1=0 | 2-1=1 | 5-1=16 / 0.5 |
#| 1-1=0 | 2-1=1 | 5-1=16 / 0.5 |
#| 1-1=0 | 2-1=1 | 5-1=16 / 0.5 |
#| 1-1=0 | 2-1=1 | 5-1=16 / 0.5 |
#--------------------------------
# w = 0.25 w = 0.5 w=0.25|
# 0 + 0.5 + 0.25*32 = 0.5 + 8 = 8.5
D = GlecklerPlot()
r = D.calc_index(x, y, 'a', 'b', time_weighting=False)
wt = np.ones(5) / 5.
ref = np.sqrt((8.5 * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error
wt = np.asarray([29., 31., 30., 31., 30.])
wt = wt / wt.sum()
ref = np.sqrt((8.5 * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error
# -*- coding: utf-8 -*-
"""
This file is part of pyCMBS.
(c) 2012- Alexander Loew
For COPYING and LICENSE details, please refer to the LICENSE file
"""
from pycmbs.plots import GlecklerPlot
import matplotlib.pyplot as plt
# this is just an artificial example illustrating principle usage of the
# Portraet diagram
fig = plt.figure(figsize=(8,6))
G = GlecklerPlot(fig=fig)
# register models
G.add_model('MPI-ESM-MR')
G.add_model('MPI-ESM-LR')
G.add_model('MPI-ESM-P')
# then register variables
G.add_variable('Ta')
G.add_variable('P')
# after that you can add values to be plotted
# pos=1 top triangle, pos2= lower triangle
# different positions are for different observations
G.add_data('Ta','MPI-ESM-MR',0.5,pos=1)
G.add_data('Ta','MPI-ESM-MR',-0.2,pos=2)
def test_GlecklerPlot_4obs(self):
G = GlecklerPlot()
G.add_model('echam5')
G.add_model('mpi-esm')
G.add_variable('ta')
G.add_variable('P')
G.add_data('P', 'echam5', 0.5, pos=1)
G.add_data('P', 'echam5', 0.25, pos=2)
G.add_data('P', 'echam5', -0.25, pos=3)
G.add_data('P', 'mpi-esm', -0.25, pos=4)
G.plot()
def test_GlecklerPlot(self):
G = GlecklerPlot()
G.add_model('echam5')
G.add_model('mpi-esm')
G.add_variable('ta')
G.add_variable('P')
G.add_data('ta', 'echam5', 0.5, pos=1)
G.add_data('P', 'echam5', 0.25, pos=1)
G.add_data('P', 'echam5', -0.25, pos=2)
G.add_data('P', 'mpi-esm', -0.25, pos=1)
G.plot()
G.plot_model_error('ta')
G.plot_model_ranking('ta')
G.write_ranking_table('ta',
self._tmpdir + os.sep + 'nix.tex',
fmt='latex')
self.assertTrue(os.path.exists(self._tmpdir + os.sep + 'nix.tex'))
if os.path.exists(self._tmpdir + os.sep + 'nix.tex'):
os.remove(self._tmpdir + os.sep + 'nix.tex')
G.write_ranking_table('ta',
self._tmpdir + os.sep + 'nix1',
fmt='latex')
self.assertTrue(os.path.exists(self._tmpdir + os.sep + 'nix1.tex'))
if os.path.exists(self._tmpdir + os.sep + 'nix1.tex'):
os.remove(self._tmpdir + os.sep + 'nix1.tex')
def main():
plt.close('all')
if len(sys.argv) > 1:
if len(sys.argv) == 2:
# a single argument was provides as option
if sys.argv[1] == 'init':
# copy INI files and a template configuration file
# to current directory
create_dummy_configuration()
sys.exit()
else:
file = sys.argv[1] # name of config file
if not os.path.exists(file):
raise ValueError('Configuration file can not be \
found: %s' % file)
else:
raise ValueError('Currently not more than one command \
line parameter supported!')
else: # default
print('*******************************************')
print('* WELCOME to pycmbs.py *')
print('* Happy benchmarking ... *')
print('*******************************************')
print ''
print 'please specify a configuration filename as argument'
sys.exit()
####################################################################
# CONFIGURATION and OPTIONS
####################################################################
# read configuration file
CF = config.ConfigFile(file)
# read plotting options
PCFG = config.PlotOptions()
PCFG.read(CF)
plot_options = PCFG
####################################################################
# REMOVE previous Data warnings
####################################################################
outdir = CF.options['outputdir']
if outdir[-1] != os.sep:
outdir += os.sep
os.environ['PYCMBS_OUTPUTDIR'] = outdir
os.environ['PYCMBS_OUTPUTFORMAT'] = CF.options['report_format']
os.environ['DATA_WARNING_FILE'] = outdir + 'data_warnings_' \
+ CF.options['report'] + '.log'
if os.path.exists(os.environ['DATA_WARNING_FILE']):
os.remove(os.environ['DATA_WARNING_FILE'])
for thevar in plot_options.options.keys():
if thevar in plot_options.options.keys():
print('Variable: %s' % thevar)
for k in plot_options.options[thevar].keys():
print(' Observation: %s' % k)
if CF.options['basemap']:
f_fast = False
else:
f_fast = True
shift_lon = use_basemap = not f_fast
########################################################################
# TIMES
########################################################################
s_start_time = CF.start_date
s_stop_time = CF.stop_date
start_time = pylab.num2date(pylab.datestr2num(s_start_time))
stop_time = pylab.num2date(pylab.datestr2num(s_stop_time))
########################################################################
# INIT METHODS
########################################################################
# names of analysis scripts for all variables ---
scripts = CF.get_analysis_scripts()
# get dictionary with methods how to read data for model variables to be
# analyzed
variables = CF.variables
varmethods = CF.get_methods4variables(CF.variables)
# READ DATA
# create a Model instance for each model specified
# in the configuration file
#
# read the data for all variables and return a list
# of Data objects for further processing
model_cnt = 1
proc_models = []
for i in range(len(CF.models)):
# assign model information from configuration
data_dir = CF.dirs[i]
model = CF.models[i]
experiment = CF.experiments[i]
# create model object and read data
# results are stored in individual variables namex modelXXXXX
if CF.dtypes[i].upper() == 'CMIP5':
themodel = CMIP5Data(data_dir,
model,
experiment,
varmethods,
intervals=CF.intervals,
lat_name='lat',
lon_name='lon',
label=model,
start_time=start_time,
stop_time=stop_time,
shift_lon=shift_lon)
elif CF.dtypes[i].upper() == 'CMIP5RAW':
themodel = CMIP5RAWData(data_dir,
model,
experiment,
varmethods,
intervals=CF.intervals,
lat_name='lat',
lon_name='lon',
label=model,
start_time=start_time,
stop_time=stop_time,
shift_lon=shift_lon)
elif 'CMIP5RAWSINGLE' in CF.dtypes[i].upper():
themodel = CMIP5RAW_SINGLE(data_dir,
model,
experiment,
varmethods,
intervals=CF.intervals,
lat_name='lat',
lon_name='lon',
label=model,
start_time=start_time,
stop_time=stop_time,
shift_lon=shift_lon)
elif CF.dtypes[i].upper() == 'JSBACH_BOT':
themodel = JSBACH_BOT(data_dir,
varmethods,
experiment,
intervals=CF.intervals,
start_time=start_time,
stop_time=stop_time,
name=model,
shift_lon=shift_lon)
elif CF.dtypes[i].upper() == 'JSBACH_RAW':
themodel = JSBACH_RAW(data_dir,
varmethods,
experiment,
intervals=CF.intervals,
name=model,
shift_lon=shift_lon,
start_time=start_time,
stop_time=stop_time)
elif CF.dtypes[i].upper() == 'JSBACH_RAW2':
themodel = JSBACH_RAW2(data_dir,
varmethods,
experiment,
intervals=CF.intervals,
start_time=start_time,
stop_time=stop_time,
name=model,
shift_lon=shift_lon) # ,
# model_dict=model_dict)
elif CF.dtypes[i].upper() == 'JSBACH_SPECIAL':
themodel = JSBACH_SPECIAL(data_dir,
varmethods,
experiment,
intervals=CF.intervals,
start_time=start_time,
stop_time=stop_time,
name=model,
shift_lon=shift_lon) # ,
# model_dict=model_dict)
elif CF.dtypes[i].upper() == 'CMIP3':
themodel = CMIP3Data(data_dir,
model,
experiment,
varmethods,
intervals=CF.intervals,
lat_name='lat',
lon_name='lon',
label=model,
start_time=start_time,
stop_time=stop_time,
shift_lon=shift_lon)
else:
raise ValueError('Invalid model type: %s' % CF.dtypes[i])
# read data for current model
# options that specify regrid options etc.
themodel._global_configuration = CF
themodel.plot_options = plot_options
themodel.get_data()
# copy current model to a variable named modelXXXX
cmd = 'model' + str(model_cnt).zfill(4) + ' = ' \
+ 'themodel.copy(); del themodel'
exec(cmd) # store copy of cmip5 model in separate variable
# append model to list of models ---
proc_models.append('model' + str(model_cnt).zfill(4))
model_cnt += 1
########################################################################
# MULTIMODEL MEAN
# here we have now all the model and variables read.
# The list of all models is contained in the variable proc_models.
f_mean_model = True
if f_mean_model:
# calculate climatological mean values: The models contain already
# climatological information in the variables[] list. Thus there is
# not need to take care for the different timesteps here. This
# should have been handled already in the preprocessing.
# generate instance of MeanModel to store result
MEANMODEL = MeanModel(varmethods, intervals=CF.intervals)
# sum up all models
for i in range(len(proc_models)):
exec('actmodel = ' + proc_models[i] + '.copy()')
MEANMODEL.add_member(actmodel)
del actmodel
# calculate ensemble mean
MEANMODEL.ensmean()
# save mean model to file
# include filename of configuration file
MEANMODEL.save(get_temporary_directory(),
prefix='MEANMODEL_' + file[:-4])
# add mean model to general list of models to process in analysis
proc_models.append('MEANMODEL')
########################################################################
# END MULTIMODEL MEAN
########################################################################
########################################################################
# INIT reporting and plotting and diagnostics
########################################################################
# Gleckler Plot
global_gleckler = GlecklerPlot()
# Report
rep = Report(CF.options['report'],
'pyCMBS report - ' + CF.options['report'],
CF.options['author'],
outdir=outdir,
dpi=300,
format=CF.options['report_format'])
cmd = 'cp ' + os.environ['PYCMBSPATH'] + os.sep + \
'logo' + os.sep + 'Phytonlogo5.pdf ' + rep.outdir
os.system(cmd)
########################################################################
########################################################################
########################################################################
# MAIN ANALYSIS LOOP: perform analysis for each model and variable
########################################################################
########################################################################
########################################################################
skeys = scripts.keys()
for variable in variables:
# register current variable in Gleckler Plot
global_gleckler.add_variable(variable)
# call analysis scripts for each variable
for k in range(len(skeys)):
if variable == skeys[k]:
print 'Doing analysis for variable ... ', variable
print ' ... ', scripts[variable]
# model list is reformatted so it can be evaluated properly
model_list = str(proc_models).replace("'", "")
cmd = 'analysis.' + scripts[variable] + '(' + model_list \
+ ',GP=global_gleckler,shift_lon=shift_lon, \
use_basemap=use_basemap,report=rep,\
interval=CF.intervals[variable],\
plot_options=PCFG)'
eval(cmd)
########################################################################
# GLECKLER PLOT finalization ...
########################################################################
# generate Gleckler analysis plot for all variables and models analyzed ///
global_gleckler.plot(vmin=-0.1,
vmax=0.1,
nclasses=16,
show_value=False,
ticks=[-0.1, -0.05, 0., 0.05, 0.1])
oname = outdir + 'gleckler.pkl'
if os.path.exists(oname):
os.remove(oname)
pickle.dump(global_gleckler.models,
open(outdir + 'gleckler_models.pkl', 'w'))
pickle.dump(global_gleckler.variables,
open(outdir + 'gleckler_variables.pkl', 'w'))
pickle.dump(global_gleckler.data, open(outdir + 'gleckler_data.pkl', 'w'))
pickle.dump(global_gleckler._raw_data,
open(outdir + 'gleckler_rawdata.pkl', 'w'))
rep.section('Summary error statistics')
rep.subsection('Gleckler metric')
rep.figure(global_gleckler.fig,
caption='Gleckler et al. (2008) model performance index',
width='10cm')
global_gleckler.fig.savefig(outdir + 'portraet_diagram.png',
dpi=200,
bbox_inches='tight')
global_gleckler.fig.savefig(outdir + 'portraet_diagram.pdf',
dpi=200,
bbox_inches='tight')
plt.close(global_gleckler.fig.number)
# generate dictionary with observation labels for each variable
labels_dict = {}
for variable in variables:
if variable not in PCFG.options.keys():
continue
varoptions = PCFG.options[variable]
thelabels = {}
for k in varoptions.keys(): # keys of observational datasets
if k == 'OPTIONS':
continue
else:
# only add observation to legend,
# if option in INI file is set
if varoptions[k]['add_to_report']:
# generate dictionary for GlecklerPLot legend
thelabels.update(
{int(varoptions[k]['gleckler_position']): k})
labels_dict.update({variable: thelabels})
del thelabels
# legend for gleckler plot ///
lcnt = 1
for variable in variables:
if variable not in PCFG.options.keys():
continue
varoptions = PCFG.options[variable]
thelabels = labels_dict[variable]
fl = global_gleckler._draw_legend(thelabels, title=variable.upper())
if fl is not None:
rep.figure(fl, width='8cm', bbox_inches=None)
fl.savefig(outdir + 'legend_portraet_' + str(lcnt).zfill(5) +
'.png',
bbox_inches='tight',
dpi=200)
plt.close(fl.number)
del fl
lcnt += 1
# plot model ranking between different observational datasets ///
rep.subsection('Model ranking consistency')
for v in global_gleckler.variables:
rep.subsubsection(v.upper())
tmpfig = global_gleckler.plot_model_ranking(v,
show_text=True,
obslabels=labels_dict[v])
if tmpfig is not None:
rep.figure(tmpfig,
width='8cm',
bbox_inches=None,
caption='Model RANKING for different observational \
datasets: ' + v.upper())
plt.close(tmpfig.number)
del tmpfig
# write a table with model ranking
tmp_filename = outdir + 'ranking_table_' + v + '.tex'
rep.open_table()
global_gleckler.write_ranking_table(v,
tmp_filename,
fmt='latex',
obslabels=labels_dict[v])
rep.input(tmp_filename)
rep.close_table(caption='Model rankings for variable ' + v.upper())
# plot absolute model error
tmpfig = global_gleckler.plot_model_error(v, obslabels=labels_dict[v])
if tmpfig is not None:
rep.figure(tmpfig,
width='8cm',
bbox_inches=None,
caption='Model ERROR for different observational \
datasets: ' + v.upper())
plt.close(tmpfig.number)
del tmpfig
########################################################################
# CLEAN up and finish
########################################################################
plt.close('all')
rep.close()
print('##########################################')
print('# BENCHMARKING FINIHSED! #')
print('##########################################')
def test_GlecklerPlot_InvalidNumberOfObservations(self):
G = GlecklerPlot()
G.add_model('echam5')
G.add_model('mpi-esm')
G.add_variable('ta')
G.add_data('ta', 'echam5', 0.5, pos=1)
G.add_data('ta', 'echam5', 0.25, pos=2)
G.add_data('ta', 'echam5', -0.25, pos=3)
G.add_data('ta', 'mpi-esm', -0.25, pos=4)
G.add_data('ta', 'mpi-esm', -0.25, pos=5)
with self.assertRaises(ValueError):
G.plot()
def test_GlecklerPlot(self):
G = GlecklerPlot()
G.add_model('echam5')
G.add_model('mpi-esm')
G.add_variable('ta')
G.add_variable('P')
G.add_data('ta', 'echam5', 0.5,pos=1)
G.add_data('P', 'echam5',0.25,pos=1)
G.add_data('P', 'echam5',-0.25,pos=2)
G.add_data('P', 'mpi-esm',-0.25,pos=1)
G.plot()
G.plot_model_error('ta')
G.plot_model_ranking('ta')
G.write_ranking_table('ta', self._tmpdir + os.sep + 'nix.tex', fmt='latex')
self.assertTrue(os.path.exists(self._tmpdir + os.sep + 'nix.tex'))
if os.path.exists(self._tmpdir + os.sep + 'nix.tex'):
os.remove(self._tmpdir + os.sep + 'nix.tex')
G.write_ranking_table('ta', self._tmpdir + os.sep + 'nix1', fmt='latex')
self.assertTrue(os.path.exists(self._tmpdir + os.sep + 'nix1.tex'))
if os.path.exists(self._tmpdir + os.sep + 'nix1.tex'):
os.remove(self._tmpdir + os.sep + 'nix1.tex')
def test_GlecklerPlot_4obs(self):
G = GlecklerPlot()
G.add_model('echam5')
G.add_model('mpi-esm')
G.add_variable('ta')
G.add_variable('P')
G.add_data('P', 'echam5', 0.5,pos=1)
G.add_data('P', 'echam5',0.25,pos=2)
G.add_data('P', 'echam5',-0.25,pos=3)
G.add_data('P', 'mpi-esm',-0.25,pos=4)
G.plot()
def test_GlecklerPlot_InvalidNumberOfObservations(self):
G = GlecklerPlot()
G.add_model('echam5')
G.add_model('mpi-esm')
G.add_variable('ta')
G.add_data('ta', 'echam5', 0.5,pos=1)
G.add_data('ta', 'echam5',0.25,pos=2)
G.add_data('ta', 'echam5',-0.25,pos=3)
G.add_data('ta', 'mpi-esm',-0.25,pos=4)
G.add_data('ta', 'mpi-esm',-0.25,pos=5)
with self.assertRaises(ValueError):
G.plot()
def main():
plt.close('all')
if len(sys.argv) > 1:
if len(sys.argv) == 2:
# a single argument was provides as option
if sys.argv[1] == 'init':
# copy INI files and a template configuration file
# to current directory
create_dummy_configuration()
sys.exit()
else:
file = sys.argv[1] # name of config file
if not os.path.exists(file):
raise ValueError('Configuration file can not be \
found: %s' % file)
else:
raise ValueError('Currently not more than one command \
line parameter supported!')
else: # default
file = 'pyCMBS.cfg'
print('*******************************************')
print('* WELCOME to pycmbs.py *')
print('* Happy benchmarking ... *')
print('*******************************************')
####################################################################
# CONFIGURATION and OPTIONS
####################################################################
# read configuration file
CF = config.ConfigFile(file)
# read plotting options
PCFG = config.PlotOptions()
PCFG.read(CF)
plot_options = PCFG
####################################################################
# REMOVE previous Data warnings
####################################################################
outdir = CF.options['outputdir']
if outdir[-1] != os.sep:
outdir += os.sep
os.environ['PYCMBS_OUTPUTDIR'] = CF.options['outputdir']
os.environ['PYCMBS_OUTPUTFORMAT'] = CF.options['report_format']
os.environ['DATA_WARNING_FILE'] = outdir + 'data_warnings_' \
+ CF.options['report'] + '.log'
if os.path.exists(os.environ['DATA_WARNING_FILE']):
os.remove(os.environ['DATA_WARNING_FILE'])
# init regions
REGIONS = config.AnalysisRegions()
for thevar in plot_options.options.keys():
if thevar in plot_options.options.keys():
print('Variable: %s' % thevar)
for k in plot_options.options[thevar].keys():
print(' Observation: %s' % k)
if CF.options['basemap']:
f_fast = False
else:
f_fast = True
shift_lon = use_basemap = not f_fast
########################################################################
# TIMES
########################################################################
s_start_time = CF.start_date
s_stop_time = CF.stop_date
start_time = pylab.num2date(pylab.datestr2num(s_start_time))
stop_time = pylab.num2date(pylab.datestr2num(s_stop_time))
model_dict = {'rain': {'CMIP5':
{
'variable': 'pr',
'unit': 'mm/day',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': 'ensmean',
'model_prefix': 'Amon',
'file_format': 'nc',
'scale_factor': 86400.,
'valid_mask': 'ocean'
},
'JSBACH_RAW2':
{
'variable': 'precip_acc',
'unit': 'mm/day',
'lat_name': 'lat',
'lon_name': 'lon',
'file_format': 'nc',
'scale_factor': 86400.,
'valid_mask': 'global'
}
},
'evap': {'CMIP5':
{
'variable': 'evspsbl',
'unit': 'mm/day',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': 'ensmean',
'file_format': 'nc',
'model_prefix': 'Amon',
'scale_factor': 86400.,
'valid_mask': 'ocean'
}
},
'twpa': {'CMIP5':
{
'variable': 'clwvi',
'unit': 'kg/m^2',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': 'ensmean',
'file_format': 'nc',
'model_prefix': 'Amon',
'scale_factor': 1.,
'valid_mask': 'ocean'
}
},
'wind': {'CMIP5':
{
'variable': 'sfcWind',
'unit': 'm/s',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': 'ensmean',
'file_format': 'nc',
'model_prefix': 'Amon',
'scale_factor': 1.,
'valid_mask': 'ocean'
}
},
'wvpa': {'CMIP5':
{
'variable': 'prw',
'unit': 'kg m^2',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': 'ensmean',
'file_format': 'nc',
'model_prefix': 'Amon',
'scale_factor': 1,
'valid_mask': 'ocean'
}
},
'late': {'CMIP5':
{
'variable': 'hfls',
'unit': 'W/m^2',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': 'ensmean',
'file_format': 'nc',
'model_prefix': 'Amon',
'scale_factor': 1,
'valid_mask': 'ocean'
}
},
'hair': {'CMIP5':
{
'variable': 'huss',
'unit': '$kg/kg^2$',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': 'ensmean',
'file_format': 'nc',
'model_prefix': 'Amon',
'scale_factor': 1,
'valid_mask': 'ocean'
}
},
'seaice_concentration': {'CMIP5':
{
'variable': 'sic',
'unit': '-',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': 'ens_mean_185001-200512',
'file_format': 'nc',
'model_prefix': 'OImon',
'scale_factor': 1,
'valid_mask': 'ocean',
'custom_path': '/home/m300028/shared/dev/svn/pyCMBS/dirk'
},
'CMIP3':
{
'variable': 'SICOMO',
'unit': '-',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': '1860-2100.ext',
'file_format': 'nc',
'model_prefix': '',
'scale_factor': 100.,
'valid_mask': 'ocean',
'custom_path': '/home/m300028/shared/dev/svn/pyCMBS/dirk',
'level': 0
},
},
'seaice_extent': {'CMIP5':
{
'variable': 'sic',
'unit': '-',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': 'ens_mean_185001-200512',
'file_format': 'nc',
'model_prefix': 'OImon',
'scale_factor': 1,
'valid_mask': 'ocean',
'custom_path': '/home/m300028/shared/dev/svn/pyCMBS/dirk'
},
'CMIP3':
{
'variable': 'SICOMO',
'unit': '-',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': '1860-2100.ext',
'file_format': 'nc',
'model_prefix': '',
'scale_factor': 100.,
'valid_mask': 'ocean',
'custom_path': '/home/m300028/shared/dev/svn/pyCMBS/dirk',
'level': 0
},
},
'budg': {'CMIP5':
{
'variable': 'budg',
'unit': 'mm/d',
'lat_name': 'lat',
'lon_name': 'lon',
'model_suffix': 'ensmean',
'file_format': 'nc',
'model_prefix': 'Amon',
'scale_factor': 86400.,
'valid_mask': 'ocean',
'custom_path': '/net/nas2/export/eo/workspace/m300036/pycmbs-cmsaf/data'
}
},
'sis': {'JSBACH_RAW2':
{
'variable': 'swdown_acc',
'unit': '$W/m^2$',
'lat_name': 'lat',
'lon_name': 'lon',
'file_format': 'nc',
'scale_factor': 1.,
'valid_mask': 'land'
},
'CMIP5':
{
'valid_mask': 'land'
}
},
'surface_upward_flux': {'JSBACH_RAW2':
{
'variable': 'swdown_reflect_acc',
'unit': '$W/m^2$',
'lat_name': 'lat',
'lon_name': 'lon',
'file_format': 'nc',
'scale_factor': 1.,
'valid_mask': 'land'
}
},
'albedo_vis': {'JSBACH_RAW2':
{
'variable': 'var14',
'unit': '-',
'lat_name': 'lat',
'lon_name': 'lon',
'file_format': 'nc',
'scale_factor': 1.,
'valid_mask': 'land'
}
},
'albedo_nir': {'JSBACH_RAW2':
{
'variable': 'var15',
'unit': '-',
'lat_name': 'lat',
'lon_name': 'lon',
'file_format': 'nc',
'scale_factor': 1.,
'valid_mask': 'land'
}
},
'temperature': {
'JSBACH_RAW2':
{
'variable': 'temp2',
'unit': 'K',
'lat_name': 'lat',
'lon_name': 'lon',
'file_format': 'nc',
'scale_factor': 1.,
'valid_mask': 'global'
}
}
}
########################################################################
# INIT METHODS
########################################################################
# names of analysis scripts for all variables ---
scripts = CF.get_analysis_scripts()
# get dictionary with methods how to read data for variables to be analyzed
variables = CF.variables
varmethods = CF.get_methods4variables(variables, model_dict)
#/// READ DATA ///
"""
create a Model instance for each model specified
in the configuration file
read the data for all variables and return a list
of Data objects for further processing
"""
model_cnt = 1
proc_models = []
for i in range(len(CF.models)):
# assign model information from configuration
data_dir = CF.dirs[i]
model = CF.models[i]
experiment = CF.experiments[i]
#--- create model object and read data ---
# results are stored in individual variables namex modelXXXXX
if CF.dtypes[i].upper() == 'CMIP5':
themodel = CMIP5Data(data_dir, model, experiment, varmethods,
intervals=CF.intervals, lat_name='lat',
lon_name='lon', label=model,
start_time=start_time,
stop_time=stop_time,
shift_lon=shift_lon)
elif CF.dtypes[i].upper() == 'CMIP5RAW':
themodel = CMIP5RAWData(data_dir, model, experiment, varmethods,
intervals=CF.intervals, lat_name='lat',
lon_name='lon', label=model,
start_time=start_time,
stop_time=stop_time,
shift_lon=shift_lon)
elif CF.dtypes[i].upper() == 'JSBACH_BOT':
themodel = JSBACH_BOT(data_dir, varmethods, experiment,
intervals=CF.intervals,
start_time=start_time,
stop_time=stop_time,
name=model, shift_lon=shift_lon)
elif CF.dtypes[i].upper() == 'JSBACH_RAW':
themodel = JSBACH_RAW(data_dir, varmethods, experiment,
intervals=CF.intervals,
name=model,
shift_lon=shift_lon,
start_time=start_time,
stop_time=stop_time
)
elif CF.dtypes[i].upper() == 'JSBACH_RAW2':
themodel = JSBACH_RAW2(data_dir, varmethods, experiment,
intervals=CF.intervals,
start_time=start_time,
stop_time=stop_time,
name=model, shift_lon=shift_lon,
model_dict=model_dict)
elif CF.dtypes[i].upper() == 'CMIP3':
themodel = CMIP3Data(data_dir, model, experiment, varmethods,
intervals=CF.intervals, lat_name='lat',
lon_name='lon', label=model,
start_time=start_time,
stop_time=stop_time,
shift_lon=shift_lon)
else:
raise ValueError('Invalid model type: %s' % CF.dtypes[i])
#--- read data for current model ---
# options that specify regrid options etc.
themodel.plot_options = plot_options
themodel.get_data()
# copy current model to a variable named modelXXXX ---
cmd = 'model' + str(model_cnt).zfill(4) + ' = ' \
+ 'themodel.copy(); del themodel'
exec(cmd) # store copy of cmip5 model in separate variable
# append model to list of models ---
proc_models.append('model' + str(model_cnt).zfill(4))
model_cnt += 1
########################################################################
# MULTIMODEL MEAN
# here we have now all the model and variables read.
# The list of all models is contained in the variable proc_models.
f_mean_model = True
if f_mean_model:
# calculate climatological mean values: The models contain already
# climatological information in the variables[] list. Thus there is
# not need to take care for the different timesteps here. This
# should have been handled already in the preprocessing.
# generate instance of MeanModel to store result
MEANMODEL = MeanModel(varmethods, intervals=CF.intervals)
# sum up all models
for i in range(len(proc_models)):
exec('actmodel = ' + proc_models[i] + '.copy()')
MEANMODEL.add_member(actmodel)
del actmodel
# calculate ensemble mean
MEANMODEL.ensmean()
# save mean model to file
MEANMODEL.save(get_temporary_directory(), prefix='MEANMODEL_' + file[:-4]) # include filename of configuration file
# add mean model to general list of models to process in analysis
proc_models.append('MEANMODEL')
########################################################################
# END MULTIMODEL MEAN
########################################################################
########################################################################
# INIT reporting and plotting and diagnostics
########################################################################
# Gleckler Plot
global_gleckler = GlecklerPlot()
# Report
rep = Report(CF.options['report'],
'pyCMBS report - ' + CF.options['report'],
CF.options['author'],
outdir=outdir,
dpi=300, format=CF.options['report_format'])
cmd = 'cp ' + os.environ['PYCMBSPATH'] + '/logo/Phytonlogo5.pdf ' + rep.outdir
os.system(cmd)
########################################################################
########################################################################
########################################################################
# MAIN ANALYSIS LOOP: perform analysis for each model and variable
########################################################################
########################################################################
########################################################################
skeys = scripts.keys()
for variable in variables:
#/// register current variable in Gleckler Plot
global_gleckler.add_variable(variable)
#/// call analysis scripts for each variable
for k in range(len(skeys)):
if variable == skeys[k]:
print 'Doing analysis for variable ... ', variable
print ' ... ', scripts[variable]
# model list is reformatted so it can be evaluated properly
model_list = str(proc_models).replace("'", "")
cmd = 'analysis.' + scripts[variable] + '(' + model_list \
+ ',GP=global_gleckler,shift_lon=shift_lon, \
use_basemap=use_basemap,report=rep,\
interval=CF.intervals[variable],\
plot_options=PCFG,regions=REGIONS.regions)'
eval(cmd)
########################################################################
# GLECKLER PLOT finalization ...
########################################################################
#/// generate Gleckler analysis plot for all variables and models analyzed ///
global_gleckler.plot(vmin=-0.1, vmax=0.1, nclasses=16, show_value=False, ticks=[-0.1, -0.05, 0., 0.05, 0.1])
oname = outdir + 'gleckler.pkl'
if os.path.exists(oname):
os.remove(oname)
pickle.dump(global_gleckler.models,
open(outdir + 'gleckler_models.pkl', 'w'))
pickle.dump(global_gleckler.variables,
open(outdir + 'gleckler_variables.pkl', 'w'))
pickle.dump(global_gleckler.data,
open(outdir + 'gleckler_data.pkl', 'w'))
pickle.dump(global_gleckler._raw_data,
open(outdir + 'gleckler_rawdata.pkl', 'w'))
rep.section('Summary error statistics')
rep.subsection('Gleckler metric')
rep.figure(global_gleckler.fig,
caption='Gleckler et al. (2008) model performance index',
width='10cm')
global_gleckler.fig.savefig(outdir + 'portraet_diagram.png', dpi=200, bbox_inches='tight')
global_gleckler.fig.savefig(outdir + 'portraet_diagram.pdf', dpi=200, bbox_inches='tight')
plt.close(global_gleckler.fig.number)
# generate dictionary with observation labels for each variable
labels_dict = {}
for variable in variables:
if variable not in PCFG.options.keys():
continue
varoptions = PCFG.options[variable]
thelabels = {}
for k in varoptions.keys(): # keys of observational datasets
if k == 'OPTIONS':
continue
else:
# only add observation to legend,
# if option in INI file is set
if varoptions[k]['add_to_report']:
# generate dictionary for GlecklerPLot legend
thelabels.update({int(varoptions[k]['gleckler_position']): k})
labels_dict.update({variable: thelabels})
del thelabels
#/// legend for gleckler plot ///
lcnt = 1
for variable in variables:
if variable not in PCFG.options.keys():
continue
varoptions = PCFG.options[variable]
thelabels = labels_dict[variable]
fl = global_gleckler._draw_legend(thelabels, title=variable.upper())
rep.figure(fl, width='8cm', bbox_inches=None)
fl.savefig(outdir + 'legend_portraet_' + str(lcnt).zfill(5) + '.png', bbox_inches='tight', dpi=200)
plt.close(fl.number)
del fl
lcnt += 1
#/// plot model ranking between different observational datasets ///
rep.subsection('Model ranking consistency')
for v in global_gleckler.variables:
rep.subsubsection(v.upper())
tmpfig = global_gleckler.plot_model_ranking(v, show_text=True, obslabels=labels_dict[v])
rep.figure(tmpfig, width='8cm', bbox_inches=None,
caption='Model RANKING for different observational \
datasets: ' + v.upper())
plt.close(tmpfig.number)
del tmpfig
# write a table with model ranking
tmp_filename = outdir + 'ranking_table_' + v + '.tex'
rep.open_table()
global_gleckler.write_ranking_table(v, tmp_filename, fmt='latex', obslabels=labels_dict[v])
rep.input(tmp_filename)
rep.close_table(caption='Model rankings for variable ' + v.upper())
# plot absolute model error
tmpfig = global_gleckler.plot_model_error(v, obslabels=labels_dict[v])
rep.figure(tmpfig, width='8cm', bbox_inches=None,
caption='Model ERROR for different observational \
datasets: ' + v.upper())
plt.close(tmpfig.number)
del tmpfig
########################################################################
# CLEAN up and finish
########################################################################
plt.close('all')
rep.close()
print('##########################################')
print('# BENCHMARKING FINIHSED! #')
print('##########################################')
def test_gleckler_index(self):
"""
test Reichler index/Gleckler plot
"""
# generate sample data
# sample data
tmp = np.zeros((5, 3, 1))
tmp[:, 0, 0] = np.ones(5) * 1.
tmp[:, 1, 0] = np.ones(5) * 2.
tmp[:, 2, 0] = np.ones(5) * 5.
# The data is like ...
#| 1 | 2 | 5 |
#| 1 | 2 | 5 |
#| 1 | 2 | 5 |
#| 1 | 2 | 5 |
#| 1 | 2 | 5 |
x = self.D.copy()
x._temporal_subsetting(0, 4)
x.data = np.ma.array(tmp, mask=tmp != tmp)
x.std = np.ones(x.data.shape)
x.time[0] = pl.datestr2num('2000-02-15')
x.time[1] = pl.datestr2num('2000-03-15')
x.time[2] = pl.datestr2num('2000-04-15')
x.time[3] = pl.datestr2num('2000-05-15')
x.time[4] = pl.datestr2num('2000-06-15')
y = self.D.copy()
y._temporal_subsetting(0, 4)
tmp = np.ones(x.data.shape) # sample data 2
y.data = np.ma.array(tmp, mask=tmp != tmp)
y.time[0] = pl.datestr2num('2000-02-15')
y.time[1] = pl.datestr2num('2000-03-15')
y.time[2] = pl.datestr2num('2000-04-15')
y.time[3] = pl.datestr2num('2000-05-15')
y.time[4] = pl.datestr2num('2000-06-15')
# Case 1: same area weights
# cell area
tmp = np.ones((3, 1))
x.cell_area = tmp * 1.
#| 1-1 | 2-1 | 5-1 |
#| 1-1 | 2-1 | 5-1 |
#| 1-1 | 2-1 | 5-1 |
#| 1-1 | 2-1 | 5-1 |
#| 1-1 | 2-1 | 5-1 |
#===================
#| 0 | 5 | 5*4**2=5*16. = 80 |
#==> E2 = sqrt(85./(15.))
D = GlecklerPlot()
r = D.calc_index(x, y, 'a', 'b', time_weighting=False)
wt = np.ones(5) / 5.
ref = np.sqrt(((85. / 15.) * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error
D = GlecklerPlot()
r = D.calc_index(x, y, 'a', 'b')
wt = np.asarray([29., 31., 30., 31., 30.])
wt = wt / wt.sum()
ref = np.sqrt(((85. / 15.) * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error
# Case 2: Different area weights
# cell area
tmp = np.ones((3, 1))
tmp[1, 0] = 2.
x.cell_area = tmp * 1.
#| 1-1=0 | 2-1=1 | 5-1=16 |
#| 1-1=0 | 2-1=1 | 5-1=16 |
#| 1-1=0 | 2-1=1 | 5-1=16 |
#| 1-1=0 | 2-1=1 | 5-1=16 |
#| 1-1=0 | 2-1=1 | 5-1=16 |
#--------------------------
# w = 0.25 w = 0.5 w=0.25|
#--------------------------
# 0.25*0 + 0.5 * 1 + 0.25 * 16 = 0 + 0.5 + 4 = 4.5
# the mean of that is 4.5 for each timestep
# mean because the overall weights are calculated as such that
# they give a total weight if 1
# diagnostic
D = GlecklerPlot()
r = D.calc_index(x, y, 'a', 'b', time_weighting=False)
wt = np.ones(5) / 5.
ref = np.sqrt((4.5 * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error
wt = np.asarray([29., 31., 30., 31., 30.])
wt = wt / wt.sum()
ref = np.sqrt((4.5 * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error
# Case 3: use different std
x.std = np.ones(x.data.shape)
x.std[:, 2, 0] = 0.5
#| 1-1=0 | 2-1=1 | 5-1=16 / 0.5 |
#| 1-1=0 | 2-1=1 | 5-1=16 / 0.5 |
#| 1-1=0 | 2-1=1 | 5-1=16 / 0.5 |
#| 1-1=0 | 2-1=1 | 5-1=16 / 0.5 |
#| 1-1=0 | 2-1=1 | 5-1=16 / 0.5 |
#--------------------------------
# w = 0.25 w = 0.5 w=0.25|
# 0 + 0.5 + 0.25*32 = 0.5 + 8 = 8.5
D = GlecklerPlot()
r = D.calc_index(x, y, 'a', 'b', time_weighting=False)
wt = np.ones(5) / 5.
ref = np.sqrt((8.5 * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error
wt = np.asarray([29., 31., 30., 31., 30.])
wt = wt / wt.sum()
ref = np.sqrt((8.5 * wt).sum())
t = np.abs(1. - r / ref)
self.assertLess(t, 0.000001) # relative error