def making_histogram_files(filename_list, wk_dir):
"""
Read in data and create histogram cubes, save these to netcdf files.
Arguments:
* filename_list
List of precipitation timeseries files
* wk_dir
Path to output directory
"""
desc = {}
for fname in filename_list:
print("Loading cube for", fname)
fname_tmp = os.path.basename(fname)
hname = os.path.join(wk_dir,
".".join(fname_tmp.split(".")[:-1]) + "_hist.nc")
ppndata1 = make_hist_maps.read_data_cube(fname)
ppn_hist_cube = make_hist_maps.make_hist_ppn(ppndata1)
iris.save(ppn_hist_cube, hname)
desc.update({
os.path.relpath(hname, start=wk_dir): {
"long_name":
"iris histogram cubes",
"description":
"histograms saved individually for model and obs data"
}
})
update_json("data", desc, wk_dir + "/output.json")
return
def plot_histogram_maps(hist_filename1, hist_filename2, runtitle,
plotname_root):
"""
Plot histogram maps
"""
ppn_hist_cube1 = make_hist_maps.read_data_cube(hist_filename1)
ppn_hist_cube2 = make_hist_maps.read_data_cube(hist_filename2)
avg_rain_bins_a, avg_rain_bins_frac_a = make_hist_maps.calc_rain_contr(
ppn_hist_cube1)
avg_rain_bins_b, avg_rain_bins_frac_b = make_hist_maps.calc_rain_contr(
ppn_hist_cube2)
# (optional) Define how you want to lump the bins together (below is the default)
all_ppn_bounds = [(0.005, 10.), (10., 50.), (50., 100.), (100., 3000.)]
# Plot as actual contributions for specific region, e.g. 60 to 160E,10S to 10N
plotname = '{}_actual_contributions.png'.format(plotname_root)
plot_hist_maps.plot_rain_contr(avg_rain_bins_a,
avg_rain_bins_b,
plotname,
runtitle,
'Timescale 1',
'Timescale 2',
all_ppn_bounds,
region=[60.0, -10.0, 160.0, 10.0])
# Plot as fractional contributions
plotname = '{}_fractional_contributions.png'.format(plotname_root)
plot_hist_maps.plot_rain_contr(avg_rain_bins_frac_a,
avg_rain_bins_frac_b,
plotname,
runtitle,
'Timescale 1',
'Timescale 2',
all_ppn_bounds,
region=[60.0, -10.0, 160.0, 10.0],
frac=1)
return
def making_histogram_files(data_filename1, data_filename2, hist_filename1,
hist_filename2):
"""
Read in data and create histogram cubes, save these to netcdf files.
Arguments:
* data_filename1,data_filename2
input filenames of time-varying precipitation data
* hist_filename1,hist_filename2
chosen filenames for output histogram cubes (netcdf files)
"""
ppndata1 = make_hist_maps.read_data_cube(data_filename1)
ppn_hist_cube1 = make_hist_maps.make_hist_ppn(ppndata1)
iris.save(ppn_hist_cube1, hist_filename1)
ppndata2 = make_hist_maps.read_data_cube(data_filename2)
ppn_hist_cube2 = make_hist_maps.make_hist_ppn(ppndata2)
iris.save(ppn_hist_cube2, hist_filename2)
return
def plot_metric(filename1, filename2, dataname1, dataname2, season, timescale,
dates, maskfile, plotname):
"""
Args:
* filename1,filename2:
files containing histogram counts for two datasets, which must be on the same grid.
filename2 data are the baseline (e.g. obs) against which data in filename1
will be compared.
* dataname1,dataname2:
names of datasets in filename1, filename2 (e.g. a model name and obs name,
or two model names)
* season:
string descriptor of season for which data in filenames apply (e.g. 'JJA')
* timescale:
string descriptor of time frequency of original data (e.g. '3-hourly')
* dates:
string descriptor of dates to which histograms apply
* maskfile:
filename for land/sea fraction dataset (on same grid as both filenames)
with values ranging from 0.0 = no land, to 1.0 = all land.
* plotname:
filename for plot
Example usage:
index, indexl, indexs, indextrop, indexnhml, indexshml=plot_metric(filename1,filename2,dataname,season,'3-hourly','1990-2014',maskfile,plotname)
"""
seasonc = season.upper()
ppn_hist_cube1 = read_data_cube(filename1)
ppn_hist_cube2 = read_data_cube(filename2)
tot_rain_bins_seas_a, tot_rain_bins_frac_a = calc_rain_contr(
ppn_hist_cube1)
tot_rain_bins_seas_b, tot_rain_bins_frac_b = calc_rain_contr(
ppn_hist_cube2)
# Limit region to 60S-60N to fit with use of GPM-IMERG observations
# Could be omitted or made optional according to which two datasets are being compared.
ce = iris.coords.CoordExtent('longitude', 0.0, 360.0)
ce2 = iris.coords.CoordExtent('latitude', -59, 59)
tot_rain_bins_frac_a.coord('longitude').circular = True
if tot_rain_bins_frac_a.coord('longitude').bounds is None:
tot_rain_bins_frac_a.coord('longitude').guess_bounds()
tot_rain_bins_frac_a.coord('latitude').guess_bounds()
tot_rain_bins_frac_a1 = tot_rain_bins_frac_a.intersection(ce, ce2)
tot_rain_bins_frac_b.coord('longitude').circular = True
if tot_rain_bins_frac_b.coord('longitude').bounds is None:
tot_rain_bins_frac_b.coord('longitude').guess_bounds()
tot_rain_bins_frac_b.coord('latitude').guess_bounds()
tot_rain_bins_frac_b1 = tot_rain_bins_frac_b.intersection(ce, ce2)
minf = tot_rain_bins_frac_a1.copy()
minf.data = np.minimum(tot_rain_bins_frac_a1.data,
tot_rain_bins_frac_b1.data)
skill = minf.collapsed('precipitation_flux', iris.analysis.SUM, mdtol=1)
# Get mask (currently total rain <1 mm/day)
bin_mid2 = np.exp(
np.log(0.005) + np.sqrt(
np.linspace(0.5, 98.5, 99) *
((np.square(np.log(120.) - np.log(0.005))) / 59.)))
bin_mid = np.zeros(100)
bin_mid[1:] = bin_mid2[0:99]
bin_mid3 = bin_mid.reshape(100, 1, 1)
lshista = iris.load_cube(filename1)
tot_events = lshista.collapsed('precipitation_flux', iris.analysis.SUM)
tot_events.data = np.ma.masked_where(tot_events.data == 0.0,
tot_events.data)
tot_rain_bins = lshista * bin_mid3
tot_rain_boxa = tot_rain_bins.collapsed('precipitation_flux',
iris.analysis.SUM) / tot_events
lshistb = iris.load_cube(filename2)
lshistb.coord('latitude').coord_system = lshista.coord(
'latitude').coord_system
lshistb.coord('longitude').coord_system = lshista.coord(
'longitude').coord_system
tot_events = lshistb.collapsed('precipitation_flux', iris.analysis.SUM)
tot_events.data = np.ma.masked_where(tot_events.data == 0.0,
tot_events.data)
tot_rain_bins = lshistb * bin_mid3
tot_rain_boxb = tot_rain_bins.collapsed('precipitation_flux',
iris.analysis.SUM) / tot_events
tot_rain_boxa.data = np.ma.masked_where(tot_rain_boxa.data < 1.0,
tot_rain_boxa.data)
tot_rain_boxb.data = np.ma.masked_where(tot_rain_boxb.data < 1.0,
tot_rain_boxb.data)
tot_events = tot_rain_boxa * tot_rain_boxb
# Extract same area as skill is calculated for
tot_events.coord('longitude').circular = True
if tot_events.coord('longitude').bounds is None:
tot_events.coord('longitude').guess_bounds()
tot_events.coord('latitude').guess_bounds()
tot_events1 = tot_events.intersection(ce, ce2)
# Apply land/sea mask to get sea or land only
lsmask = iris.load_cube(maskfile)
lsmask.coord('latitude').coord_system = lshista.coord(
'latitude').coord_system
lsmask.coord('longitude').coord_system = lshista.coord(
'longitude').coord_system
lsmask.coord('longitude').circular = True
if lsmask.coord('longitude').bounds is None:
lsmask.coord('longitude').guess_bounds()
lsmask.coord('latitude').guess_bounds()
lsmasks = lsmask.intersection(ce, ce2)
lsmaskl = lsmask.intersection(ce, ce2)
lsmasks.data = np.ma.masked_where(lsmasks.data >= 0.5, lsmasks.data)
lsmaskl.data = np.ma.masked_where(lsmaskl.data < 0.5, lsmaskl.data)
lsmasksea = lsmasks * tot_events1
lsmaskland = lsmaskl * tot_events1
# Mask the skill cube and calculate index as rms over region
skill.data.mask = tot_events1.data.mask
grid_areas = iris.analysis.cartography.area_weights(skill)
index = skill.collapsed(['latitude', 'longitude'],
iris.analysis.RMS,
weights=grid_areas)
skilltrop = skill.extract(
iris.Constraint(latitude=lambda cell: -15 <= cell <= 15))
grid_areas = iris.analysis.cartography.area_weights(skilltrop)
indextrop = skilltrop.collapsed(['latitude', 'longitude'],
iris.analysis.RMS,
weights=grid_areas)
skillnhml = skill.extract(
iris.Constraint(latitude=lambda cell: 30 <= cell <= 60))
grid_areas = iris.analysis.cartography.area_weights(skillnhml)
indexnhml = skillnhml.collapsed(['latitude', 'longitude'],
iris.analysis.RMS,
weights=grid_areas)
skillshml = skill.extract(
iris.Constraint(latitude=lambda cell: -60 <= cell <= -30))
grid_areas = iris.analysis.cartography.area_weights(skillshml)
indexshml = skillshml.collapsed(['latitude', 'longitude'],
iris.analysis.RMS,
weights=grid_areas)
skill = minf.collapsed('precipitation_flux', iris.analysis.SUM, mdtol=1)
skill.data.mask = lsmasksea.data.mask
skilltst = skill.extract(
iris.Constraint(latitude=lambda cell: -30 <= cell <= 30))
grid_areas = iris.analysis.cartography.area_weights(skilltst)
indexs = skilltst.collapsed(['latitude', 'longitude'],
iris.analysis.RMS,
weights=grid_areas)
skill = minf.collapsed('precipitation_flux', iris.analysis.SUM, mdtol=1)
skill.data.mask = lsmaskland.data.mask
skilltst = skill.extract(
iris.Constraint(latitude=lambda cell: -30 <= cell <= 30))
grid_areas = iris.analysis.cartography.area_weights(skilltst)
indexl = skilltst.collapsed(['latitude', 'longitude'],
iris.analysis.RMS,
weights=grid_areas)
print(
dataname1, dataname2,
'Index = %0.2f, Index (land) = %0.2f, Index (sea) = %0.2f, Index (tropics) = %0.2f, Index (NH mid-lat) = %0.2f, Index (SH mid-lat) = %0.2f'
% (index.data, indexl.data, indexs.data, indextrop.data,
indexnhml.data, indexshml.data))
skill = minf.collapsed('precipitation_flux', iris.analysis.SUM, mdtol=1)
skill.data.mask = tot_events1.data.mask
cf = qplt.pcolormesh(skill, vmin=0.5, vmax=0.95)
ax = plt.gca()
gl = ax.gridlines(draw_labels=True)
gl.xlabels_top = False
ax.coastlines()
plt.title(dataname1 + ' vs ' + dataname2 + ' ' + timescale + ' ' +
seasonc + ' ' + dates + '\nIndex = %0.2f' % (index.data))
plt.savefig(plotname)
plt.close()
return index, indexl, indexs, indextrop, indexnhml, indexshml
def plot_histogram_maps(hist_filenames, plotname_root, wk_dir, region, ext,
settings):
"""
Plot histogram maps
"""
hist_filename1 = hist_filenames[0]
hist_filename2 = hist_filenames[1]
ppn_hist_cube1 = make_hist_maps.read_data_cube(hist_filename1)
ppn_hist_cube2 = make_hist_maps.read_data_cube(hist_filename2)
avg_rain_bins_a, avg_rain_bins_frac_a = make_hist_maps.calc_rain_contr(
ppn_hist_cube1)
avg_rain_bins_b, avg_rain_bins_frac_b = make_hist_maps.calc_rain_contr(
ppn_hist_cube2)
ppn_names = make_runtitle([hist_filename1, hist_filename2], settings)
ppn1_name = ppn_names[hist_filename1].replace("_", " ")
ppn2_name = ppn_names[hist_filename2].replace("_", " ")
names = make_runtitle([hist_filename1, hist_filename2],
settings,
model_only=True)
runtitle = "{0} vs {1}".format(names[hist_filename1].replace("_", " "),
names[hist_filename2].replace("_", " "))
# (optional) Define how you want to lump the bins together (below is the default)
all_ppn_bounds = [(0.005, 10.), (10., 50.), (50., 100.), (100., 3000.)]
# Plot as actual contributions for specific region, e.g. 60 to 160E,10S to 10N
desc = {}
plotname = '{0}_actual_contributions{1}'.format(plotname_root, ext)
plotname = os.path.join(wk_dir, plotname)
plot_hist_maps.plot_rain_contr(avg_rain_bins_a,
avg_rain_bins_b,
plotname,
runtitle,
ppn1_name,
ppn2_name,
all_ppn_bounds,
region=region)
desc.update({
os.path.relpath(plotname, start=wk_dir): {
"description":
"Actual contribution of each timescale for region {0}".format(
region)
}
})
# Plot as fractional contributions
plotname = '{0}_fractional_contributions{1}'.format(plotname_root, ext)
plotname = os.path.join(wk_dir, plotname)
plot_hist_maps.plot_rain_contr(avg_rain_bins_frac_a,
avg_rain_bins_frac_b,
plotname,
runtitle,
ppn1_name,
ppn2_name,
all_ppn_bounds,
region=region,
frac=1)
desc.update({
os.path.relpath(plotname, start=wk_dir): {
"description":
"Fractional contribution of each timescale for region {0}".format(
region)
}
})
update_json("plots", desc, wk_dir + "/output.json")
return