def _parse_netCDF(file_obj):
index = _tools._get_time(file_obj)
mass_concentrations = pd.DataFrame(index = index)
mass_conc_keys = ['total_organics','ammonium','sulfate','nitrate','chloride']
for k in mass_conc_keys:
var = file_obj.variables[k]
data = var[:]
mass_concentrations[k] = pd.Series(var, index = index)
mass_concentrations.columns.name = 'Mass conc. ug/m^3'
mass_concentrations.index.name = 'Time'
# for v in file_obj.variables.keys():
# var = file_obj.variables[v]
# print(v)
# print(var.long_name)
# print(var.shape)
# print('--------')
org_mx = file_obj.variables['org_mx'][:]
org_mx = pd.DataFrame(org_mx, index = index)
org_mx.index.name = 'Time'
org_mx.columns = file_obj.variables['amus'][:]
org_mx.columns.name = 'amus (m/z)'
out = _tools.ArmDict(plottable = ['mass_concentrations', 'Organic mass spectral matrix'])
out['mass_concentrations'] = timeseries.TimeSeries(mass_concentrations)
out['Organic mass spectral matrix'] = timeseries.TimeSeries_2D(org_mx)
return out
def _parse_netCDF(file_obj):
index = _tools._get_time(file_obj)
sd = file_obj.variables['number_concentration_DMA_APS']
df = pd.DataFrame(sd[:])
df.index = index
d = file_obj.variables['diameter']
bins, colnames = diameter_binning.bincenters2binsANDnames(d[:]*1000)
dist = sizedistribution.SizeDist_TS(df,bins,'dNdlogDp')
dist = dist.convert2dVdlogDp()
out = _tools.ArmDict(plottable = ['size_distribution'])
out['size_distribution'] = dist
return out
def _parse_netCDF(file_obj):
"returns a dictionary, with panels in it"
index = _tools._get_time(file_obj)
data = file_obj.variables['hyg_distributions'][:]
growthfactors = file_obj.variables['growthfactors'][:]
size_bins = file_obj.variables['size_bins'][:]* 1000
RH_interDMA = pd.DataFrame(file_obj.variables['RH_interDMA'][:], index = index, columns=size_bins)
RH_interDMA.columns.name = 'size_bin_center_nm'
data = pd.Panel(data, items= index, major_axis = size_bins, minor_axis = growthfactors)
data.items.name = 'Time'
data.major_axis.name = 'size_bin_center_nm'
data.minor_axis.name = 'growthfactors'
out = Tdmahyg(plottable = ['hyg_distributions'], plot_kwargs = dict(xaxis=0, yaxis = 2, sub_set=5, kwargs = dict(vmin = 0)))
# data = _timeseries.TimeSeries_3D(data)
data = timeseries.TimeSeries_3D(data)
# data.RH_interDMA = RH_interDMA
out['hyg_distributions'] = data
out['RH_interDMA'] = RH_interDMA
# out['growthfactors'] = growthfactors
# out['size_bins'] = size_bins
return out
def _parse_netCDF(file_obj):
abs_coeff = ['Ba_G_Dry_10um_PSAP1W_1',
'Ba_G_Dry_1um_PSAP1W_1',
'Ba_B_Dry_10um_PSAP3W_1',
'Ba_G_Dry_10um_PSAP3W_1',
'Ba_R_Dry_10um_PSAP3W_1',
'Ba_B_Dry_1um_PSAP3W_1',
'Ba_G_Dry_1um_PSAP3W_1',
'Ba_R_Dry_1um_PSAP3W_1',
]
scat_coeff = ['Bs_B_Dry_10um_Neph3W_1',
'Bs_G_Dry_10um_Neph3W_1',
'Bs_R_Dry_10um_Neph3W_1',
'Bs_B_Wet_10um_Neph3W_2',
'Bs_G_Wet_10um_Neph3W_2',
'Bs_R_Wet_10um_Neph3W_2',
'Bs_B_Dry_1um_Neph3W_1',
'Bs_G_Dry_1um_Neph3W_1',
'Bs_R_Dry_1um_Neph3W_1',
'Bs_B_Wet_1um_Neph3W_2',
'Bs_G_Wet_1um_Neph3W_2',
'Bs_R_Wet_1um_Neph3W_2',
]
bscat_coeff_vars = ['Bbs_B_Dry_10um_Neph3W_1',
'Bbs_G_Dry_10um_Neph3W_1',
'Bbs_R_Dry_10um_Neph3W_1',
'Bbs_B_Wet_10um_Neph3W_2',
'Bbs_G_Wet_10um_Neph3W_2',
'Bbs_R_Wet_10um_Neph3W_2',
'Bbs_B_Dry_1um_Neph3W_1',
'Bbs_G_Dry_1um_Neph3W_1',
'Bbs_R_Dry_1um_Neph3W_1',
'Bbs_B_Wet_1um_Neph3W_2',
'Bbs_G_Wet_1um_Neph3W_2',
'Bbs_R_Wet_1um_Neph3W_2',
]
RH = ['RH_NephVol_Dry',
'RH_NephVol_Wet']
def var2ts(file_obj, var_list, index, column_name):
"""extracts the list of variables from the file_obj and puts them all in one data frame"""
df = pd.DataFrame(index = index)
for var in var_list:
variable = file_obj.variables[var]
data = variable[:]
fill_value = variable.missing_data
data = np.ma.masked_where(data == fill_value, data)
df[var] = pd.Series(data, index = index)
df.index.name = 'Time'
df.columns.name = column_name
out = timeseries.TimeSeries(df)
return out
index = _tools._get_time(file_obj)
out = _tools.ArmDict(plottable= ['abs_coeff', 'scatt_coeff', 'back_scatt'] )
out['abs_coeff'] = var2ts(file_obj, abs_coeff, index, 'abs_coeff_1/Mm')
out['scatt_coeff'] = var2ts(file_obj, scat_coeff, index, 'scatt_coeff_1/Mm')
out['back_scatt'] = var2ts(file_obj, bscat_coeff_vars, index, 'back_scatt_1/Mm')
out['RH'] = var2ts(file_obj, RH, index, 'RH')
out.info = info
return out
