def csat_no_cal(files, outname, where):
v = vcm.VCM(files, verbose=False)
cal = v.get_vcm('cal333+cal05+cal20+cal80')
csat = v.get_vcm('csat')
calcloudy = np.sum(cal, axis=1)
csatcloudy = np.sum(csat, axis=1)
csatonly = np.where((csatcloudy > 0) & (calcloudy == 0))[0]
print 100. * csatonly.shape[0] / calcloudy.shape[0]
vcm_csatonly = np.zeros_like(csat)
vcm_csatonly[csatonly, :] = csat[csatonly, :]
csatcloudy[calcloudy > 0] = 0
dset = da.Dataset()
time_axis = da.Axis(v.time, 'tai_time')
alt_axis = da.Axis(v.altitude, 'altitude')
dset['lon'] = da.DimArray(v.lon, [time_axis])
dset['lat'] = da.DimArray(v.lat, [time_axis])
dset['csat'] = da.DimArray(vcm_csatonly, [time_axis, alt_axis])
dset['cloudpts'] = da.DimArray(csatcloudy, [time_axis])
check_out_dir(where)
dset.write_nc(where + outname, 'w', zlib=True, complevel=9)
def vcm_dataset_from_l2_orbit(filename):
#print 'Creating vcm dataset from l2 file ' + filename
l2 = calipso_l2.Cal2(filename)
lon, lat = l2.coords()
tai_time = l2.time()
nl, base, top = l2.layers()
havg = l2.horizontal_averaging()
ltype = l2.layer_type()
tai_time_min, tai_time_max = l2.time_bounds()
tropo = l2.tropopause_height()
elevation = l2.dem_surface_elevation()[:,1]
l2.close()
tropo[lat < -60] = 11.
tropo[lat > 60] = 11.
dset = da.Dataset()
time_axis = da.Axis(tai_time, 'tai_time')
alt_axis = da.Axis(vcm_alt, 'altitude')
for havg_vcm in havgs_vcm:
vcm = vcm_from_layers(nl, base, top, havg, ltype, tropo, only_havg=havg_vcm)
vcm_name = 'cal%02d' % (havg_vcm)
dset[vcm_name] = da.DimArray(vcm, [time_axis, alt_axis])
dset['lon'] = da.DimArray(lon, [time_axis])
dset['lat'] = da.DimArray(lat, [time_axis])
dset['time_min'] = da.DimArray(tai_time_min, [time_axis])
dset['time_max'] = da.DimArray(tai_time_max, [time_axis])
dset['elevation'] = da.DimArray(elevation, [time_axis])
return dset
def reindex_vcms(vcm, vcm5, vcmc):
# vcmc can be None
mintime5, maxtime5 = vcm5['time_min'].values, vcm5['time_max'].values
nprof5 = mintime5.shape[0]
time333 = vcm['time']
nprof333 = time333.shape[0]
# first find 333m profiles indexes for a given 5km profile
n1, n2 = np.zeros(nprof5, 'int16'), np.zeros(nprof5, 'int16')
n = 0
for i in np.r_[0:nprof5]:
n1[i] = n
while n < nprof333 and time333[n] < maxtime5[i]:
n += 1
n2[i] = n
# print 'Range for profile5 %d = %d - %d' % (i, n1[i], n2[i])
# reindex all flags on the same 333m coordinates
time_axis = da.Axis(vcm['time'], 'tai_time')
alt_axis = da.Axis(vcm['altitude'], 'altitude')
reindexed = da.Dataset()
reindexed['lon'] = da.DimArray(vcm['lon'], [
time_axis,
])
reindexed['lat'] = da.DimArray(vcm['lat'], [
time_axis,
])
reindexed['cal333'] = da.DimArray(vcm['cal333'], [time_axis, alt_axis])
# remap CALIPSO flag
for vcm_name in 'cal05', 'cal20', 'cal80':
this_vcm = remap_profiles(vcm5[vcm_name].values, n1, n2, nprof333)
reindexed[vcm_name] = da.DimArray(this_vcm,
labels=reindexed['cal333'].labels,
dims=reindexed['cal333'].dims)
# remap cloudsat flag
if vcmc is None:
this_vcm = np.ones_like(vcm['cal333'], 'int8') * -1.
else:
vcmc.values = remove_ground_clutter(vcmc.values,
vcm5['elevation'].values,
vcm5['cal05'].altitude)
this_vcm = remap_profiles(vcmc.values, n1, n2, nprof333)
reindexed['csat'] = da.DimArray(this_vcm,
labels=reindexed['cal333'].labels,
dims=reindexed['cal333'].dims)
# Now we have
# cal333, cal05, cal20, cal80, csat in reindexed.
return reindexed
def my_read_vcm_nc(f=f):
nc = netCDF4.Dataset(f, 'r')
time = nc.variables['tai_time'][:]
alt = nc.variables['altitude'][:]
lon = nc.variables['lon'][:]
lat = nc.variables['lat'][:]
cal333 = nc.variables['cal333'][:]
time_axis = da.Axis(time, 'time')
alt_axis = da.Axis(alt, 'alt')
lon = da.DimArray(lon, time_axis)
lat = da.DimArray(lon, time_axis)
cal333 = da.DimArray(cal333, [time_axis, alt_axis])
def cf_from_vcm_orbit(vcm_orbit, layers):
print 'Creating vcm from ', vcm_orbit
# read data
v = vcm.VCM(vcm_orbit, verbose=False)
print '%d profiles' % (v.lon.shape[0])
lon_axis = da.Axis(lonbins[:-1], 'lon')
lat_axis = da.Axis(latbins[:-1], 'lat')
# gridded number of profiles
h, xx, yy = np.histogram2d(v.lon, v.lat, bins=(lonbins, latbins))
out = da.Dataset()
out['nprof'] = da.DimArray(h * 3, [lon_axis, lat_axis])
out['nprof'].longname = 'Number of measured profiles'
for layer in layers:
altrange = layers[layer]
altidx = np.where((v.altitude >= altrange[0])
& (v.altitude < altrange[1]))[0]
for vcm_name in vcm_names:
# number of cloudy profiles in grid and altitude range
this_vcm = v.get_vcm(vcm_name)
assert this_vcm is not None
if layer == 'total':
t = this_vcm
else:
t = np.take(this_vcm, altidx, axis=1)
cloudy_profile = np.sum(t, axis=1)
np.clip(cloudy_profile, 0, 3, out=cloudy_profile)
h, xx, yy = np.histogram2d(v.lon,
v.lat,
bins=(lonbins, latbins),
weights=cloudy_profile)
outname = vcm_name + '_cprof_%s' % (layer)
out[outname] = da.DimArray(h, [lon_axis, lat_axis])
out[outname].longname = 'Number of cloudy profiles from cloud mask = ' + vcm_name + ' at altitudes %5.2f - %5.2f' % (
altrange[0], altrange[1])
return out
def my_read_nc_lon(f=f):
nc = netCDF4.Dataset(f, 'r')
time = nc.variables['tai_time'][:]
lon = nc.variables['lon'][:]
nc.close()
axis = da.Axis(time, 'time')
d1 = da.DimArray(lon, axis)
return d1
def zone_vcm_from_vcm_orbit(vcm_orbit, latbins=latbins):
# read data
#print 'opening ' + vcm_orbit
v = vcm.VCM(vcm_orbit, verbose=False)
nlat = latbins.shape[0]
nalt = v.altitude.shape[0]
out = da.Dataset()
# ilatbins = vector with nprof indexes containing bin numbers
ilatbins = np.digitize(v.lat, latbins)
lat_axes = da.Axis(latbins[:-1], 'lat')
nprof, xx = np.histogram(v.lat, bins=latbins)
out['nprof'] = da.DimArray(nprof * 3, [lat_axes])
alt_axes = da.Axis(v.altitude, 'altitude')
for name in vcm_names:
this_vcm = v.get_vcm(name)
zone_vcm = np.zeros([nlat-1, nalt], dtype='uint16')
prof_is_cloudy = np.sum(this_vcm, axis=1)
np.clip(prof_is_cloudy, 0, 3, out=prof_is_cloudy)
cprof, xx = np.histogram(v.lat, bins=latbins, weights=prof_is_cloudy)
out[name + '_cprof'] = da.DimArray(cprof, [lat_axes])
for i,ilatbin in enumerate(ilatbins[:-1]):
if prof_is_cloudy[i] > 0:
zone_vcm[ilatbin,:] += np.take(this_vcm, i, axis=0)
out[name] = da.DimArray(zone_vcm, [lat_axes, alt_axes], longname='Number of cloudy points in lat-z bin, considering ' + name)
return out
def cflon(f, altmin, latbounds):
# altmin is an array
v = vcm.VCM(f, verbose=False)
out = da.Dataset()
lon_axis = da.Axis(lonbins[:-1], 'lon')
# number of profiles per lon bin
h, xx = np.histogram(v.lon, bins=lonbins)
out['nprof'] = da.DimArray(h, [lon_axis])
out['nprof'].longname = 'Number of measured profiles'
for n in names:
cv = v.get_vcm(n)
assert cv is not None
# clip latitudes
latidx = (v.lat >= latbounds[0]) & (v.lat < latbounds[1])
cv = np.take(cv, latidx, axis=0)
lon = np.take(v.lon, latidx, axis=0)
outdict = dict()
for a in altmin:
idx = np.where(v.altitude >= a)[0]
cloudy = np.take(cv, idx, axis=1)
cloudy = np.sum(cloudy, axis=1)
np.clip(cloudy, 0, 1, out=cloudy)
h, xx = np.histogram(v.lon, bins=lonbins, weights=cloudy)
outdict[a] = da.DimArray(h, [
lon_axis,
])
outname = n + '_cprof'
out[outname] = da.stack(outdict, axis='altmin')
out[outname].longname = 'Number of cloudy profiles from cloud mask = ' + n
return out