def _get_discharge(config: Config, basin: str) -> pd.Series:
if config.dataset == 'camels_us':
_, area = camelsus.load_camels_us_forcings(config.data_dir, basin,
'daymet')
return camelsus.load_camels_us_discharge(config.data_dir, basin, area)
else:
raise NotImplementedError
def _load_basin_data(self, basin: str) -> pd.DataFrame:
"""Load input and output data from text files."""
# get forcings
dfs = []
if not any(f.endswith('_hourly') for f in self.cfg.forcings):
raise ValueError('Forcings include no hourly forcings set.')
for forcing in self.cfg.forcings:
if forcing[-7:] == '_hourly':
df = self.load_hourly_data(basin, forcing)
else:
# load daily CAMELS forcings and upsample to hourly
df, _ = camelsus.load_camels_us_forcings(
self.cfg.data_dir, basin, forcing)
df = df.resample('1H').ffill()
if len(self.cfg.forcings) > 1:
# rename columns
df = df.rename(
columns={
col: f"{col}_{forcing}"
for col in df.columns if 'qobs' not in col.lower()
})
dfs.append(df)
df = pd.concat(dfs, axis=1)
# collapse all input features to a single list, to check for 'QObs(mm/d)'.
all_features = self.cfg.target_variables
if isinstance(self.cfg.dynamic_inputs, dict):
for val in self.cfg.dynamic_inputs.values():
all_features = all_features + val
elif isinstance(self.cfg.dynamic_inputs, list):
all_features = all_features + self.cfg.dynamic_inputs
# catch also QObs(mm/d)_shiftX or _copyX features
if any([x.startswith("QObs(mm/d)") for x in all_features]):
# add daily discharge from CAMELS, using daymet to get basin area
_, area = camelsus.load_camels_us_forcings(self.cfg.data_dir,
basin, "daymet")
discharge = camelsus.load_camels_us_discharge(
self.cfg.data_dir, basin, area)
discharge = discharge.resample('1H').ffill()
df["QObs(mm/d)"] = discharge
# only warn for missing netcdf files once for each forcing product
self._warn_slow_loading = False
# replace invalid discharge values by NaNs
qobs_cols = [col for col in df.columns if 'qobs' in col.lower()]
for col in qobs_cols:
df.loc[df[col] < 0, col] = np.nan
# add stage, if requested
if 'gauge_height_m' in self.cfg.target_variables:
df = df.join(load_hourly_us_stage(self.cfg.data_dir, basin))
df.loc[df['gauge_height_m'] < 0, 'gauge_height_m'] = np.nan
# convert discharge to 'synthetic' stage, if requested
if 'synthetic_qobs_stage_meters' in self.cfg.target_variables:
attributes = camelsus.load_camels_us_attributes(
data_dir=self.cfg.data_dir, basins=[basin])
with open(self.cfg.rating_curve_file, 'rb') as f:
rating_curves = pickle.load(f)
df['synthetic_qobs_stage_meters'] = np.nan
if basin in rating_curves.keys():
discharge_m3s = df[
'qobs_mm_per_hour'].values / 1000 * attributes.area_gages2[
basin] * 1e6 / 60**2
df['synthetic_qobs_stage_meters'] = rating_curves[
basin].discharge_to_stage(discharge_m3s)
return df