def create_output_file():
records = {
'ID': 'DWR_Zarate',
'Name': 'Zárate',
'Source': 'C3S_SouthAmerica',
'Lat': '-34.0958',
'Lon': -59.0242,
'Link': 'https://data-rescue.copernicus-climate.eu/lso/1086267',
'Vbl': 'mslp',
'Stat': 'point',
'Units': 'Pa',
'Meta': 'Data policy=GNU GPL v3.0',
'Year': [1902, 1902],
'Month': [9, 9],
'Day': [2, 3],
'Hour': [11, 11],
'Minute': [17, 17],
'Value': [102245, 101952],
'Period': [0, 0],
'Meta2': ['Orig=766.9mm|Orig.time=', 'Orig.=764.7mm|Orig.time='],
'offset': -4
}
obs = SEF.create(records)
SEF.write_file(obs, OUTPUT_PATH)
'DWR_Estc_Pereyra', 'DWR_Puerto_Mili.'
]
# Date to show
year = 1902
month = 8
day = 27
hour = 18
minute = 0 # obs are at 18:17 UTC, but show the field at 18:00
dte = datetime.datetime(year, month, day, hour, minute)
# Load all the Argentine DWR pressures at this time
adf = glob.glob('../../../../sef/Argentinian_DWR/1902/DWR_*_MSLP.tsv')
obs = {'Name': [], 'Latitude': [], 'Longitude': [], 'mslp': []}
for file in adf:
stobs = SEF.read_file(file)
df = stobs['Data']
hhmm = int("%2d%02d" % (dte.hour, 17))
mslp = df.loc[(df['Year'] == dte.year) & (df['Month'] == dte.month) &
(df['Day'] == dte.day) & (df['HHMM'] == hhmm)]
if mslp.empty: continue
if mslp['Value'].values[0] == mslp['Value'].values[0]:
obs['Name'].append(stobs['ID'])
obs['Latitude'].append(stobs['Lat'])
obs['Longitude'].append(stobs['Lon'])
obs['mslp'].append(mslp['Value'].values[0])
obs = pandas.DataFrame(obs)
# Landscape page
aspect = 16 / 9.0
fig = Figure(
type=str,required=True)
args = parser.parse_args()
pickled_20CRdata_dir="%s/sef_comparators/Argentinian_DWR/" % os.getenv('SCRATCH')
# Load the obs
known_bad=False
obs_file="../../../../sef/Argentinian_DWR/1902/%s_T.tsv" % args.id
obs_Tmax_file="../../../../sef/Argentinian_DWR/1902/%s_Tmax.tsv" % args.id
obs_Tmin_file="../../../../sef/Argentinian_DWR/1902/%s_Tmin.tsv" % args.id
if not os.path.isfile(obs_file):
known_bad=True
obs_file="../../../../sef/Argentinian_DWR/known_bad/1902/%s_T.tsv" % args.id
obs_Tmax_file="../../../../sef/Argentinian_DWR/known_bad/1902/%s_Tmax.tsv" % args.id
obs_Tmin_file="../../../../sef/Argentinian_DWR/known_bad/1902/%s_Tmin.tsv" % args.id
obs=SEF.read_file(obs_file)
obs_Tmax=SEF.read_file(obs_Tmax_file)
obs_Tmin=SEF.read_file(obs_Tmin_file)
# load the pickled 20CR data
rdata={}
rmax=0.0
rmin=1000000.0
start_day=datetime.datetime(1902, 2, 1, 0)
end_day =datetime.datetime(1902,12,31, 0)
current_day=start_day
while current_day<=end_day:
for hour in (0,3,6,9,12,15,18,21):
pfile="%s/%04d/%02d/%02d/%02d/%s_air.2m.pkl" % (pickled_20CRdata_dir,
current_day.year,
current_day.month,
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--id", help="Station to compare",
type=str,required=True)
args = parser.parse_args()
known_bad=False
obs_file="../../../../sef/Argentinian_DWR/1902/%s_MSLP.tsv" % args.id
if not os.path.isfile(obs_file):
known_bad=True
obs_file="../../../../sef/Argentinian_DWR/known_bad/1902/%s_MSLP.tsv" % args.id
pickled_20CRdata_dir="%s/sef_comparators/Argentinian_DWR/" % os.getenv('SCRATCH')
# Load the obs
obs=SEF.read_file(obs_file)
# load the pickled 20CR data
rdata={}
rmax=0.0
rmin=1000000.0
start_day=datetime.datetime(1902, 2, 1, 0)
end_day =datetime.datetime(1902,12,31, 0)
current_day=start_day
while current_day<=end_day:
for hour in (0,3,6,9,12,15,18,21):
pfile="%s/%04d/%02d/%02d/%02d/%s_prmsl.pkl" % (pickled_20CRdata_dir,
current_day.year,
current_day.month,
current_day.day,
hour,args.id)
# Get the DWR data for 1902
obs = DWR.load_observations('prmsl', datetime.datetime(1903, 1, 1, 0),
datetime.datetime(1903, 12, 31, 23))
# Where to put the output files
opdir = "%s/../../../sef/UK_DWR/1903" % bindir
if not os.path.isdir(opdir):
os.makedirs(opdir)
stations = list(set(obs['name']))
for station in stations:
obs_s = obs[obs['name'] == station]
ob_hhmm = [
"%2d%02d" % (obs_s['hour'].values[i], obs_s['minute'].values[i])
for i in range(len(obs_s))
]
sef = SEF.create(version='0.0.1')
sef['ID'] = station
sef['Name'] = DWR.pretty_name(station)
sef['Lat'] = obs['latitude'].values[0]
sef['Lon'] = obs['longitude'].values[0]
sef['Alt'] = None
sef['Source'] = None
sef['Repo'] = None
sef['Var'] = 'msl pressure'
sef['Units'] = 'hPa'
sef['Meta'] = 'PTC=T,PGC=T'
sef['Data'] = pandas.DataFrame({
'Year': obs_s['year'].values,
'Month': obs_s['month'].values,
'Day': obs_s['day'].values,
'HHMM': ob_hhmm,
station_height = station_locations[station_locations['SEF_ID'] ==
args.id]['height'].values[0]
except IndexError:
raise Exception("Missing original name for %s" % args.id)
spreadsheet_file = "%s/../raw_data/1903/DATA_1903_%s.csv" % (bindir,
original_name)
if not os.path.isfile(spreadsheet_file):
raise Exception("Missing file %s" % spreadsheet_file)
raw_data = pandas.read_csv(spreadsheet_file, header=1)
n_values = len(raw_data)
# Make a SEF data structure and populate the common elements
# Argentine national time in 1903 was 4h17m behind UTC
#ob_time=[1117 if raw_data['MONTH'].values[i]>8 else 1817 for i in range(n_values)]
ob_time = 1117
common = SEF.create(version='0.0.1')
common['ID'] = args.id
common['Name'] = original_name
common['Lat'] = station_lat
common['Lon'] = station_lon
common['Alt'] = station_height
common['Source'] = None
common['Repo'] = None
common['Data'] = pandas.DataFrame({
'Year': raw_data['YEAR'].values,
'Month': raw_data['MONTH'].values,
'Day': raw_data['DAY'].values,
'HHMM': ob_time
})
# Where to put the output files