def search_data_files(self, **kwargs):
dt_fr = self.dt_fr
dt_to = self.dt_to
diff_days = dttool.get_diff_days(dt_fr, dt_to)
dt0 = dttool.get_start_of_the_day(dt_fr)
for i in range(diff_days + 1):
thisday = dt0 + datetime.timedelta(days=i)
initial_file_dir = kwargs.pop('initial_file_dir', None)
if initial_file_dir is None:
initial_file_dir = self.data_root_dir / thisday.strftime("%Y") / thisday.strftime('%Y%m%d')
file_patterns = [self.data_file_type.replace('-', '_'), thisday.strftime("%Y%m%d"), self.data_file_version]
# remove empty str
file_patterns = [pattern for pattern in file_patterns if str(pattern)]
search_pattern = '*' + '*'.join(file_patterns) + '*'
done = super().search_data_files(
initial_file_dir=initial_file_dir, search_pattern=search_pattern
)
# Validate file paths
if not done and self.allow_download:
done = self.download_data()
if done:
done = super().search_data_files(
initial_file_dir=initial_file_dir, search_pattern=search_pattern)
else:
print('Cannot find files from the online database!')
return done
def search_data_files(self, recursive=True, **kwargs):
dt_fr = self.dt_fr
dt_to = self.dt_to
diff_days = dttool.get_diff_days(dt_fr, dt_to)
day0 = dttool.get_start_of_the_day(dt_fr)
for i in range(diff_days + 1):
thisday = day0 + datetime.timedelta(days=i)
initial_file_dir = self.data_root_dir / thisday.strftime(
'%Y') / thisday.strftime('%Y%m%d')
file_patterns = [
'MillstoneHill',
self.data_file_type.replace(' ', '_'),
thisday.strftime('%Y%m%d')
]
# remove empty str
file_patterns = [
pattern for pattern in file_patterns if str(pattern)
]
search_pattern = '*' + '*'.join(file_patterns) + '*'
if str(self.exp_name_pattern):
search_pattern = '*' + self.exp_name_pattern.replace(
' ', '-') + '*/' + search_pattern
recursive = False
done = super().search_data_files(initial_file_dir=initial_file_dir,
search_pattern=search_pattern,
recursive=recursive)
# Validate file paths
if not done and self.allow_download:
done = self.download_data()
if done:
done = super().search_data_files(
initial_file_dir=initial_file_dir,
search_pattern=search_pattern)
else:
print(
'The requested experiment does not exist in the online database!'
)
if len(done) > 1:
if str(self.exp_name_pattern):
mylog.StreamLogger.error(
"Multiple data files detected! Check the files:")
else:
mylog.StreamLogger.error(
"Multiple data files detected!" +
"Specify the experiment name by the keyword 'exp_name_pattern' if possible."
)
for fp in done:
mylog.simpleinfo.info(fp)
raise KeyError
return done
def download(self):
diff_days = dttool.get_diff_days(self.dt_fr, self.dt_to)
for i in range(diff_days + 1):
dt1 = self.dt_fr + datetime.timedelta(days=i)
fn = '_'.join(['SuperDARN', 'POTMAP', str(self.data_res) + 'min', dt1.strftime('%Y%m%d'), self.pole]) + '.dat'
file_path = self.data_file_root_dir / dt1.strftime('%Y') / fn
self.save_to_netcdf(file_path)
def search_data_files(self, **kwargs):
dt_fr = self.dt_fr
if self.dt_to.hour > 22:
dt_to = self.dt_to + datetime.timedelta(days=1)
else:
dt_to = self.dt_to
diff_days = dttool.get_diff_days(dt_fr, dt_to)
dt0 = dttool.get_start_of_the_day(dt_fr)
for i in range(diff_days + 1):
thisday = dt0 + datetime.timedelta(days=i)
initial_file_dir = kwargs.pop('initial_file_dir', None)
if initial_file_dir is None:
initial_file_dir = self.data_root_dir / self.sat_id.lower(
) / thisday.strftime("%Y%m%d")
file_patterns = [
self.sat_id.upper(),
self.product.upper(),
thisday.strftime("%Y%m%d"),
]
if self.orbit_id is not None:
file_patterns.append(self.orbit_id)
# remove empty str
file_patterns = [
pattern for pattern in file_patterns if str(pattern)
]
search_pattern = '*' + '*'.join(file_patterns) + '*'
if self.orbit_id is not None:
multiple_files = False
else:
fp_log = initial_file_dir / (self.product.upper() +
'.full.log')
if not fp_log.is_file():
self.download_data(dt_fr=thisday, dt_to=thisday)
multiple_files = True
done = super().search_data_files(
initial_file_dir=initial_file_dir,
search_pattern=search_pattern,
allow_multiple_files=multiple_files,
)
if done and self.orbit_id is not None:
return True
# Validate file paths
if not done and self.allow_download:
done = self.download_data(dt_fr=thisday, dt_to=thisday)
if done:
done = super().search_data_files(
initial_file_dir=initial_file_dir,
search_pattern=search_pattern,
allow_multiple_files=multiple_files)
return done
def get_dt_range_str(self, style='title'):
dt_fr = self._xlim[0]
dt_to = self._xlim[1]
if style == 'title':
diff_days = dttool.get_diff_days(dt1=dt_fr, dt2=dt_to)
if diff_days == 0:
fmt1 = "%Y-%m-%dT%H:%M:%S"
fmt2 = "%H:%M:%S"
else:
fmt1 = "%Y-%m-%dT%H:%M:%S"
fmt2 = fmt1
dt_range_str = dt_fr.strftime(fmt1) + ' - ' + dt_to.strftime(fmt2)
elif style == 'filename':
diff_days = dttool.get_diff_days(dt1=dt_fr, dt2=dt_to)
if diff_days == 0:
fmt1 = "%Y%m%d-%H%M%S"
fmt2 = "%H%M%S"
else:
fmt1 = "%Y%m%d-%H%M%S"
fmt2 = fmt1
dt_range_str = dt_fr.strftime(fmt1) + '-' + dt_to.strftime(fmt2)
return dt_range_str
def search_data_files(self, **kwargs):
dt_fr = self.dt_fr
dt_to = self.dt_to
diff_days = dttool.get_diff_days(dt_fr, dt_to)
day0 = dttool.get_start_of_the_day(dt_fr)
for i in range(diff_days + 1):
thisday = day0 + datetime.timedelta(days=i)
initial_file_dir = self.data_root_dir / self.site / thisday.strftime(
'%Y')
file_patterns = []
if self.data_file_type == 'eiscat-hdf5':
file_patterns.append('EISCAT')
elif self.data_file_type == 'madrigal-hdf5':
file_patterns.append('MAD6400')
elif self.data_file_type == 'eiscat-mat':
pass
file_patterns.append(thisday.strftime('%Y-%m-%d'))
file_patterns.append(self.modulation)
file_patterns.append(self.antenna.lower())
# remove empty str
file_patterns = [
pattern for pattern in file_patterns if str(pattern)
]
search_pattern = '*' + '*'.join(file_patterns) + '*'
if self.data_file_type == 'eiscat-mat':
search_pattern = search_pattern + '/'
done = super().search_data_files(initial_file_dir=initial_file_dir,
search_pattern=search_pattern)
# Validate file paths
if not done and self.allow_download:
done = self.download_data()
if done:
done = super().search_data_files(
initial_file_dir=initial_file_dir,
search_pattern=search_pattern)
else:
print('Cannot find files from the online database!')
return done
def search_data_files(self, **kwargs):
dt_fr = self.dt_fr
dt_to = self.dt_to
diff_days = dttool.get_diff_days(dt_fr, dt_to)
dt0 = dttool.get_start_of_the_day(dt_fr)
for i in range(diff_days + 1):
this_day = dt0 + datetime.timedelta(days=i)
initial_file_dir = kwargs.pop('initial_file_dir',
self.data_root_dir)
file_patterns = [
'EFI' + self.sat_id.upper(),
self.product.upper(),
this_day.strftime('%Y%m%d') + 'T',
]
# remove empty str
file_patterns = [
pattern for pattern in file_patterns if str(pattern)
]
search_pattern = '*' + '*'.join(file_patterns) + '*'
done = super().search_data_files(
initial_file_dir=initial_file_dir,
search_pattern=search_pattern,
allow_multiple_files=True,
)
# Validate file paths
if (not done and self.allow_download) or self.force_download:
done = self.download_data()
if done:
initial_file_dir = self.data_root_dir
done = super().search_data_files(
initial_file_dir=initial_file_dir,
search_pattern=search_pattern,
allow_multiple_files=True)
return done
def load_data(self):
dataset = netCDF4.Dataset(self.file_path)
variables = {}
metadata = {}
if self.pole == 'N':
pole = self.pole
pole_str = 'NORTH'
elif self.pole == 'S':
pole = self.pole
pole_str = 'SOUTH'
else:
raise ValueError
# Time and Position
# sectime = int(np.array(dataset.variables['TIME']).flatten()[0])
# doy = int(np.array(dataset.variables['DOY']).flatten()[0])
# year = int(np.array(dataset.variables['YEAR']).flatten()[0])
# dt0 = dttool.convert_doy_to_datetime(year, doy)
starting_time = datetime.datetime.strptime(dataset.STARTING_TIME,
"%Y%j%H%M%S")
variables['STARTING_TIME'] = starting_time
stopping_time = datetime.datetime.strptime(dataset.STOPPING_TIME,
"%Y%j%H%M%S")
variables['STOPPING_TIME'] = stopping_time
dt0 = dttool.get_start_of_the_day(starting_time)
variables['SC_LAT'] = np.array(dataset.variables['LATITUDE'])
variables['SC_LON'] = np.array(dataset.variables['LONGITUDE'])
variables['SC_ALT'] = np.array(dataset.variables['ALTITUDE'])
variables['GRID_MLAT'] = np.array(
dataset.variables['LATITUDE_GEOMAGNETIC_GRID_MAP'])
variables['GRID_MLON'] = np.array(
dataset.variables['LONGITUDE_GEOMAGNETIC_' + pole_str +
'_GRID_MAP'])
variables['GRID_MLT'] = np.array(dataset.variables['MLT_GRID_MAP'])
if self.pole == 'S':
variables['GRID_MLAT'] = -variables['GRID_MLAT']
variables['GRID_UT'] = np.array(dataset.variables['UT_' + pole])
lat = np.array(variables['GRID_MLAT'])
ut = np.array(variables['GRID_UT'])
lat = np.where(ut == 0, np.nan, lat)
if self.pole == 'N':
ind_mid_t = np.where(lat == np.nanmax(lat.flatten()))
else:
ind_mid_t = np.where(lat == np.nanmin(lat.flatten()))
sectime0 = variables['GRID_UT'][ind_mid_t][0] * 3600
diff_days = dttool.get_diff_days(starting_time, stopping_time)
if diff_days > 0 and sectime0 < 0.5 * 86400.:
dt = dt0 + datetime.timedelta(seconds=int(sectime0 + 86400))
else:
dt = dt0 + datetime.timedelta(seconds=int(sectime0))
variables['DATETIME'] = dt
invalid_ut_inds = np.where(ut == 0)
# Auroral map, #colors: 0: '1216', 1: '1304', 2: '1356', 3: 'LBHS', 4: 'LBHL'.
variables['EMISSION_SPECTRA'] = [
'1216', '1304', '1356', 'LBHS', 'LBHL'
]
disk_aur = np.array(dataset.variables['DISK_RADIANCEDATA_INTENSITY_' +
pole_str])
# disk_aur[:, invalid_ut_inds] = np.nan
disk_aur[disk_aur <= 0] = 0.1
variables['GRID_AUR_1216'] = disk_aur[0, ::]
variables['GRID_AUR_1216'][invalid_ut_inds] = np.nan
variables['GRID_AUR_1304'] = disk_aur[1, ::]
variables['GRID_AUR_1304'][invalid_ut_inds] = np.nan
variables['GRID_AUR_1356'] = disk_aur[2, ::]
variables['GRID_AUR_1356'][invalid_ut_inds] = np.nan
variables['GRID_AUR_LBHS'] = disk_aur[3, ::]
variables['GRID_AUR_LBHS'][invalid_ut_inds] = np.nan
variables['GRID_AUR_LBHL'] = disk_aur[4, ::]
variables['GRID_AUR_LBHL'][invalid_ut_inds] = np.nan
# Auroral oval boundary
variables['AOB_EQ_MLAT'] = np.array(
dataset.variables[pole_str + '_GEOMAGNETIC_LATITUDE'])
variables['AOB_EQ_MLON'] = np.array(
dataset.variables[pole_str + '_GEOMAGNETIC_LONGITUDE'])
variables['AOB_EQ_MLT'] = np.array(
dataset.variables[pole_str + '_MAGNETIC_LOCAL_TIME'])
variables['AOB_PL_MLAT'] = np.array(
dataset.variables[pole_str + '_POLAR_GEOMAGNETIC_LATITUDE'])
variables['AOB_PL_MLON'] = np.array(
dataset.variables[pole_str + '_POLAR_GEOMAGNETIC_LONGITUDE'])
variables['AOB_PL_MLT'] = np.array(
dataset.variables[pole_str + '_POLAR_MAGNETIC_LOCAL_TIME'])
variables['MAOB_EQ_MLAT'] = np.array(
dataset.variables['MODEL_' + pole_str + '_GEOMAGNETIC_LATITUDE'])
variables['MAOB_EQ_MLON'] = np.array(
dataset.variables['MODEL_' + pole_str + '_GEOMAGNETIC_LONGITUDE'])
variables['MAOB_EQ_MLT'] = np.array(
dataset.variables['MODEL_' + pole_str + '_MAGNETIC_LOCAL_TIME'])
variables['MAOB_PL_MLAT'] = np.array(
dataset.variables['MODEL_' + pole_str +
'_POLAR_GEOMAGNETIC_LATITUDE'])
variables['MAOB_PL_MLON'] = np.array(
dataset.variables['MODEL_' + pole_str +
'_POLAR_GEOMAGNETIC_LONGITUDE'])
variables['MAOB_PL_MLT'] = np.array(
dataset.variables['MODEL_' + pole_str +
'_POLAR_MAGNETIC_LOCAL_TIME'])
metadata.setdefault('ORBIT_ID', dataset.STARTING_ORBIT_NUMBER)
dataset.close()
self.variables = variables
self.metadata = metadata
def download_files(self):
"""
Get a list of the urls from input date
and datatype and download the files
and also move them to the corresponding
folders.!!!
"""
diff_days = dttool.get_diff_days(self.dt_fr, self.dt_to)
dt0 = dttool.get_start_of_the_day(self.dt_fr)
for iday in range(diff_days + 1):
thisday = dt0 + datetime.timedelta(days=iday)
# construct day of year from date
doy = thisday.timetuple().tm_yday
doy_str = "{:03d}".format(doy)
if self.file_type in ['l1b', 'edr-aur', 'edr-iono']:
payload_type = self.file_type
elif self.file_type in ['sdr-limb', 'sdr-disk', 'sdr2-disk']:
payload_type = 'sdr'
elif self.file_type in ['edr-night-disk', 'edr-day-disk']:
payload_type = 'edr-disk'
elif self.file_type in ['edr-night-limb', 'edr-day-limb']:
payload_type = 'edr-limb'
elif self.file_type in ['edr-gaim-disk', 'edr-gaim-lim']:
payload_type = 'edr-gaim'
else:
raise NotImplementedError
payload = {
"spc": self.sat_id,
"type": payload_type,
"Doy": doy_str,
"year": "{:d}".format(thisday.year)
}
# get a list of the files from dmsp ssusi website
# based on the data type and date
r = requests.get(self.url_base + "data_retriver/",
params=payload,
verify=True)
soup = bs4.BeautifulSoup(r.text, 'html.parser')
div_filelist = soup.find("div", {"id": "filelist"})
href_list = div_filelist.find_all(href=True)
url_list = [self.url_base + href["href"] for href in href_list]
import natsort
url_list = natsort.natsorted(url_list, reverse=False)
for f_url in url_list:
# we only need data files which have .NC
if ".NC" not in f_url:
continue
# If working with sdr data use only
# sdr-disk files
if self.file_type.upper() not in f_url:
continue
if self.orbit_id is not None:
if len(self.orbit_id) != 5:
raise ValueError
if self.orbit_id not in f_url:
continue
file_dir = self.data_file_root_dir / self.sat_id.lower(
) / thisday.strftime("%Y%m%d")
file_dir.mkdir(parents=True, exist_ok=True)
file_name = f_url.split('/')[-1]
file_path = file_dir / file_name
if file_path.is_file():
self.done = True
mylog.simpleinfo.info(
"The file {} exists.".format(file_name))
continue
mylog.simpleinfo.info(
"Downloading {} from the online database ...".format(
file_name))
rf = requests.get(f_url, verify=True)
file_name = rf.url.split("/")[-1]
with open(file_path, "wb") as ssusi_data:
ssusi_data.write(rf.content)
mylog.simpleinfo.info(
"Done. The file has been saved to {}".format(file_dir))
self.done = True
if self.orbit_id is not None:
return
# self.file_dir = file_dir
# self.file_name = file_name
if self.orbit_id is None and self.done:
fp_log = file_dir / (self.file_type.upper() + '.full.log')
fp_log.touch()
if not self.done:
mylog.StreamLogger.warning(
"Cannot find the requested data on {} from the online database!"
.format(thisday.strftime("%Y-%m-%d")))