import json
import os
import random
interfaceOpt = 1
# set it the same as which you used to train your model
# ==1 default, the recommended and more interpretable version
# ==0 the "pro" version
# Define root directory of database and output
# Modify this based on your own location of CAMELS dataset and saved models
rootDatabase = os.path.join(os.path.sep, "scratch",
"Camels") # CAMELS dataset root directory
camels.initcamels(
rootDatabase
) # initialize three camels module-scope variables in camels.py: dirDB, gageDict, statDict
rootOut = os.path.join(os.path.sep, "data",
"rnnStreamflow") # Model output root directory
# The directory you defined in training to save the model under the above rootOut
exp_name = "PUR"
exp_disp = "Testrun"
save_path = os.path.join(rootOut, exp_name, exp_disp)
random.seed(159654)
# this random is only used for fractional FDC scenarios and
# to sample which basins in the target region have FDCs.
# same as training, get the 7 regions basin ID for testing
# Define root directory of database and output
# Modify this based on your own location
rootDatabase = os.path.join(os.path.sep, absRoot, 'scratch',
'SNTemp') # dataset root directory:
rootOut = os.path.join(os.path.sep, absRoot, 'TempDemo',
'FirstRun') # Model output root directory:
forcing_path = os.path.join(os.path.sep, rootDatabase, 'Forcing',
'Forcing_new',
'no_dam_forcing_60%_days118sites.feather') #
forcing_data = [] #pd.read_feather(forcing_path)
attr_path = os.path.join(os.path.sep, rootDatabase, 'Forcing', 'attr_new',
'no_dam_attr_temp60%_days118sites.feather')
attr_data = [] #pd.read_feather(attr_path)
camels.initcamels(
forcing_data, attr_data, TempTarget, rootDatabase
) # initialize three camels module-scope variables in camels.py: dirDB, gageDict, statDict
# Define all the configurations into dictionary variables
# three purposes using these dictionaries. 1. saved as configuration logging file. 2. for future testing. 3. can also
# be used to directly train the model when interfaceOpt == 0
# define dataset
optData = default.optDataCamels
optData = default.update(optData,
tRange=Ttrain,
target='StreamTemp',
doNorm=[True, True]) # Update the training period
# define model and update parameters
if torch.cuda.is_available():
optModel = default.optLstm
else: