def test_dam_train(self):
quick_data_dir = os.path.join(self.config_data_1.data_path["DB"],
"quickdata")
data_dir = os.path.join(quick_data_dir,
"allnonref_85-05_nan-0.1_00-1.0")
# for inv model, datamodel of train and test are same
data_model_8595 = GagesModel.load_datamodel(
data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
t_range1_train = self.config_data_1.model_dict["data"]["tRangeTrain"]
gages_model1_train = GagesModel.update_data_model(
self.config_data_1,
data_model_8595,
t_range_update=t_range1_train,
data_attr_update=True)
t_range2_train = self.config_data_2.model_dict["data"]["tRangeTrain"]
gages_model2_train = GagesModel.update_data_model(
self.config_data_2,
data_model_8595,
t_range_update=t_range2_train,
data_attr_update=True)
nid_dir = os.path.join(
"/".join(self.config_data_1.data_path["DB"].split("/")[:-1]),
"nid", "quickdata")
nid_input = NidModel.load_nidmodel(
nid_dir,
nid_file=self.nid_file,
nid_source_file_name='nid_source.txt',
nid_data_file_name='nid_data.shp')
gage_main_dam_purpose = unserialize_json(
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
gage_main_dam_purpose_lst = list(gage_main_dam_purpose.values())
gage_main_dam_purpose_unique = np.unique(gage_main_dam_purpose_lst)
with torch.cuda.device(1):
for i in range(0, gage_main_dam_purpose_unique.size):
data_input1 = GagesDamDataModel(gages_model1_train, nid_input,
True, gage_main_dam_purpose)
gages_input1 = choose_which_purpose(
data_input1, purpose=gage_main_dam_purpose_unique[i])
data_input2 = GagesDamDataModel(gages_model2_train, nid_input,
True, gage_main_dam_purpose)
gages_input2 = choose_which_purpose(
data_input2, purpose=gage_main_dam_purpose_unique[i])
data_model = GagesInvDataModel(gages_input1, gages_input2)
# pre_trained_model_epoch = 165
train_lstm_inv(data_model)
def test_dam_coords_storages(self):
quick_data_dir = os.path.join(self.config_data.data_path["DB"],
"quickdata")
data_dir = os.path.join(quick_data_dir,
"conus-all_90-10_nan-0.0_00-1.0")
data_model_train = GagesModel.load_datamodel(
data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
gages_model_train = GagesModel.update_data_model(
self.config_data, data_model_train)
data_model_test = GagesModel.load_datamodel(
data_dir,
data_source_file_name='test_data_source.txt',
stat_file_name='test_Statistics.json',
flow_file_name='test_flow.npy',
forcing_file_name='test_forcing.npy',
attr_file_name='test_attr.npy',
f_dict_file_name='test_dictFactorize.json',
var_dict_file_name='test_dictAttribute.json',
t_s_dict_file_name='test_dictTimeSpace.json')
gages_model_test = GagesModel.update_data_model(
self.config_data,
data_model_test,
train_stat_dict=gages_model_train.stat_dict)
nid_dir = os.path.join(
"/".join(self.config_data.data_path["DB"].split("/")[:-1]), "nid",
"test")
nid_input = NidModel.load_nidmodel(
nid_dir,
nid_source_file_name='nid_source.txt',
nid_data_file_name='nid_data.shp')
gage_main_dam_purpose = unserialize_json(
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
data_input = GagesDamDataModel(gages_model_test, nid_input,
gage_main_dam_purpose)
dam_coords, dam_storages = data_input.coords_of_dams()
serialize_json(dam_coords, os.path.join(nid_dir,
"dam_points_dict.json"))
serialize_json(dam_storages,
os.path.join(nid_dir, "dam_storages_dict.json"))
def test_gages_dam_attr(self):
quick_data_dir = os.path.join(self.config_data.data_path["DB"],
"quickdata")
data_dir = os.path.join(quick_data_dir,
"conus-all_90-10_nan-0.0_00-1.0")
df = GagesModel.load_datamodel(data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
# nid_input = NidModel()
nid_input = NidModel(self.config_data.config_file)
# nid_dir = os.path.join("/".join(self.config_data.data_path["DB"].split("/")[:-1]), "nid", "quickdata")
nid_dir = os.path.join(
"/".join(self.config_data.data_path["DB"].split("/")[:-1]), "nid",
"test")
save_nidinput(nid_input,
nid_dir,
nid_source_file_name='nid_source.txt',
nid_data_file_name='nid_data.shp')
data_input = GagesDamDataModel(df, nid_input)
serialize_json(data_input.gage_main_dam_purpose,
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
def test_dam_train(self):
"""just test for one purpose as a case"""
with torch.cuda.device(2):
quick_data_dir = os.path.join(self.config_data.data_path["DB"],
"quickdata")
data_dir = os.path.join(quick_data_dir,
"conus-all_90-10_nan-0.0_00-1.0")
df = GagesModel.load_datamodel(
data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
nid_dir = os.path.join(
"/".join(self.config_data.data_path["DB"].split("/")[:-1]),
"nid", "quickdata")
nid_input = NidModel.load_nidmodel(
nid_dir,
nid_file=self.nid_file,
nid_source_file_name='nid_source.txt',
nid_data_file_name='nid_data.shp')
gage_main_dam_purpose = unserialize_json(
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
data_input = GagesDamDataModel(df, nid_input, True,
gage_main_dam_purpose)
purpose_chosen = 'C'
gages_input = choose_which_purpose(data_input,
purpose=purpose_chosen)
master_train(gages_input)
def test_dam_train(self):
with torch.cuda.device(0):
quick_data_dir = os.path.join(self.config_data.data_path["DB"],
"quickdata")
data_dir = os.path.join(quick_data_dir,
"allnonref_85-05_nan-0.1_00-1.0")
data_model_8595 = GagesModel.load_datamodel(
data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
gages_model_train = GagesModel.update_data_model(
self.config_data, data_model_8595)
nid_dir = os.path.join(
"/".join(self.config_data.data_path["DB"].split("/")[:-1]),
"nid", "quickdata")
nid_input = NidModel.load_nidmodel(
nid_dir,
nid_file=self.nid_file,
nid_source_file_name='nid_source.txt',
nid_data_file_name='nid_data.shp')
gage_main_dam_purpose = unserialize_json(
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
data_input = GagesDamDataModel(gages_model_train, nid_input, True,
gage_main_dam_purpose)
gages_input = choose_which_purpose(data_input)
master_train(gages_input)
def test_dam_test(self):
quick_data_dir = os.path.join(self.config_data.data_path["DB"],
"quickdata")
data_dir = os.path.join(quick_data_dir,
"conus-all_90-10_nan-0.0_00-1.0")
data_model_train = GagesModel.load_datamodel(
data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
data_model_test = GagesModel.load_datamodel(
data_dir,
data_source_file_name='test_data_source.txt',
stat_file_name='test_Statistics.json',
flow_file_name='test_flow.npy',
forcing_file_name='test_forcing.npy',
attr_file_name='test_attr.npy',
f_dict_file_name='test_dictFactorize.json',
var_dict_file_name='test_dictAttribute.json',
t_s_dict_file_name='test_dictTimeSpace.json')
gages_model_train = GagesModel.update_data_model(
self.config_data, data_model_train)
gages_model_test = GagesModel.update_data_model(
self.config_data,
data_model_test,
train_stat_dict=gages_model_train.stat_dict)
nid_dir = os.path.join(
"/".join(self.config_data.data_path["DB"].split("/")[:-1]), "nid",
"quickdata")
nid_input = NidModel.load_nidmodel(
nid_dir,
nid_file=self.nid_file,
nid_source_file_name='nid_source.txt',
nid_data_file_name='nid_data.shp')
gage_main_dam_purpose = unserialize_json(
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
data_input = GagesDamDataModel(gages_model_test, nid_input, True,
gage_main_dam_purpose)
gages_input = choose_which_purpose(data_input)
pred, obs = master_test(gages_input)
basin_area = gages_input.data_source.read_attr(
gages_input.t_s_dict["sites_id"], ['DRAIN_SQKM'],
is_return_dict=False)
mean_prep = gages_input.data_source.read_attr(
gages_input.t_s_dict["sites_id"], ['PPTAVG_BASIN'],
is_return_dict=False)
mean_prep = mean_prep / 365 * 10
pred = _basin_norm(pred, basin_area, mean_prep, to_norm=False)
obs = _basin_norm(obs, basin_area, mean_prep, to_norm=False)
save_result(gages_input.data_source.data_config.data_path['Temp'],
self.test_epoch, pred, obs)
def test_damcls_test_datamodel(self):
quick_data_dir = os.path.join(self.config_data.data_path["DB"], "quickdata")
data_dir = os.path.join(quick_data_dir, "allnonref_85-05_nan-0.1_00-1.0")
data_model_train = GagesModel.load_datamodel(data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json', flow_file_name='flow.npy',
forcing_file_name='forcing.npy', attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
data_model_test = GagesModel.load_datamodel(data_dir,
data_source_file_name='test_data_source.txt',
stat_file_name='test_Statistics.json',
flow_file_name='test_flow.npy',
forcing_file_name='test_forcing.npy',
attr_file_name='test_attr.npy',
f_dict_file_name='test_dictFactorize.json',
var_dict_file_name='test_dictAttribute.json',
t_s_dict_file_name='test_dictTimeSpace.json')
gages_model_train = GagesModel.update_data_model(self.config_data, data_model_train)
df = GagesModel.update_data_model(self.config_data, data_model_test,
train_stat_dict=gages_model_train.stat_dict)
nid_dir = os.path.join("/".join(self.config_data.data_path["DB"].split("/")[:-1]), "nid", "quickdata")
nid_input = NidModel.load_nidmodel(nid_dir, nid_file=self.nid_file,
nid_source_file_name='nid_source.txt', nid_data_file_name='nid_data.shp')
gage_main_dam_purpose = unserialize_json(os.path.join(nid_dir, "dam_main_purpose_dict.json"))
gage_main_dam_purpose_lst = list(gage_main_dam_purpose.values())
gage_main_dam_purpose_unique = np.unique(gage_main_dam_purpose_lst)
data_input = GagesDamDataModel(df, nid_input, True, gage_main_dam_purpose)
for i in range(gage_main_dam_purpose_unique.size):
gages_input = choose_which_purpose(data_input, purpose=gage_main_dam_purpose_unique[i])
save_datamodel(gages_input, gage_main_dam_purpose_unique[i], data_source_file_name='test_data_source.txt',
stat_file_name='test_Statistics.json', flow_file_name='test_flow',
forcing_file_name='test_forcing', attr_file_name='test_attr',
f_dict_file_name='test_dictFactorize.json', var_dict_file_name='test_dictAttribute.json',
t_s_dict_file_name='test_dictTimeSpace.json')
def test_dam_test(self):
quick_data_dir = os.path.join(self.config_data_1.data_path["DB"],
"quickdata")
data_dir = os.path.join(quick_data_dir,
"allnonref_85-05_nan-0.1_00-1.0")
# for inv model, datamodel of train and test are same
data_model_8595 = GagesModel.load_datamodel(
data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
# for 2nd model, datamodel of train and test belong to parts of the test time
data_model_9505 = GagesModel.load_datamodel(
data_dir,
data_source_file_name='test_data_source.txt',
stat_file_name='test_Statistics.json',
flow_file_name='test_flow.npy',
forcing_file_name='test_forcing.npy',
attr_file_name='test_attr.npy',
f_dict_file_name='test_dictFactorize.json',
var_dict_file_name='test_dictAttribute.json',
t_s_dict_file_name='test_dictTimeSpace.json')
t_range1_test = self.config_data_1.model_dict["data"]["tRangeTest"]
# Because we know data of period "90-95", so that we can get its statistics according to this period
gages_model1_test = GagesModel.update_data_model(
self.config_data_1,
data_model_8595,
t_range_update=t_range1_test,
data_attr_update=True)
t_range2_train = self.config_data_2.model_dict["data"]["tRangeTrain"]
t_range2_test = self.config_data_2.model_dict["data"]["tRangeTest"]
gages_model2_train = GagesModel.update_data_model(
self.config_data_2,
data_model_8595,
t_range_update=t_range2_train,
data_attr_update=True)
gages_model2_test = GagesModel.update_data_model(
self.config_data_2,
data_model_9505,
t_range_update=t_range2_test,
data_attr_update=True,
train_stat_dict=gages_model2_train.stat_dict)
nid_dir = os.path.join(
"/".join(self.config_data_2.data_path["DB"].split("/")[:-1]),
"nid", "quickdata")
nid_input = NidModel.load_nidmodel(
nid_dir,
nid_file=self.nid_file,
nid_source_file_name='nid_source.txt',
nid_data_file_name='nid_data.shp')
gage_main_dam_purpose = unserialize_json(
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
data_input1 = GagesDamDataModel(gages_model1_test, nid_input, True,
gage_main_dam_purpose)
df1 = choose_which_purpose(data_input1)
data_input2 = GagesDamDataModel(gages_model2_test, nid_input, True,
gage_main_dam_purpose)
df2 = choose_which_purpose(data_input2)
with torch.cuda.device(2):
data_model = GagesInvDataModel(df1, df2)
pred, obs = test_lstm_inv(data_model, epoch=self.test_epoch)
basin_area = df2.data_source.read_attr(df2.t_s_dict["sites_id"],
['DRAIN_SQKM'],
is_return_dict=False)
mean_prep = df2.data_source.read_attr(df2.t_s_dict["sites_id"],
['PPTAVG_BASIN'],
is_return_dict=False)
mean_prep = mean_prep / 365 * 10
pred = _basin_norm(pred, basin_area, mean_prep, to_norm=False)
obs = _basin_norm(obs, basin_area, mean_prep, to_norm=False)
save_result(df2.data_source.data_config.data_path['Temp'],
self.test_epoch, pred, obs)
def test_dam_train(self):
quick_data_dir = os.path.join(self.config_data.data_path["DB"],
"quickdata")
sim_data_dir = os.path.join(quick_data_dir,
"allref_85-05_nan-0.1_00-1.0")
data_dir = os.path.join(quick_data_dir,
"allnonref_85-05_nan-0.1_00-1.0")
data_model_sim8595 = GagesModel.load_datamodel(
sim_data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
data_model_8595 = GagesModel.load_datamodel(
data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
sim_gages_model_train = GagesModel.update_data_model(
self.sim_config_data, data_model_sim8595, data_attr_update=True)
gages_model_train = GagesModel.update_data_model(self.config_data,
data_model_8595,
data_attr_update=True)
nid_dir = os.path.join(
"/".join(self.config_data.data_path["DB"].split("/")[:-1]), "nid",
"quickdata")
gage_main_dam_purpose = unserialize_json(
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
gage_main_dam_purpose_lst = list(gage_main_dam_purpose.values())
gage_main_dam_purpose_unique = np.unique(gage_main_dam_purpose_lst)
nid_dir = os.path.join(
"/".join(self.config_data.data_path["DB"].split("/")[:-1]), "nid",
"quickdata")
nid_input = NidModel.load_nidmodel(
nid_dir,
nid_file=self.nid_file,
nid_source_file_name='nid_source.txt',
nid_data_file_name='nid_data.shp')
gage_main_dam_purpose = unserialize_json(
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
data_input = GagesDamDataModel(gages_model_train, nid_input, True,
gage_main_dam_purpose)
with torch.cuda.device(0):
for i in range(0, gage_main_dam_purpose_unique.size):
sim_gages_model_train.update_model_param('train', nEpoch=300)
gages_input = choose_which_purpose(
data_input, purpose=gage_main_dam_purpose_unique[i])
new_temp_dir = os.path.join(
gages_input.data_source.data_config.model_dict["dir"]
["Temp"], gage_main_dam_purpose_unique[i])
new_out_dir = os.path.join(
gages_input.data_source.data_config.model_dict["dir"]
["Out"], gage_main_dam_purpose_unique[i])
gages_input.update_datamodel_dir(new_temp_dir, new_out_dir)
data_model = GagesSimDataModel(sim_gages_model_train,
gages_input)
# pre_trained_model_epoch = 25
# master_train_natural_flow(data_model, pre_trained_model_epoch=pre_trained_model_epoch)
master_train_natural_flow(data_model)
def test_dam_test(self):
quick_data_dir = os.path.join(self.config_data.data_path["DB"],
"quickdata")
sim_data_dir = os.path.join(quick_data_dir,
"allref_85-05_nan-0.1_00-1.0")
data_dir = os.path.join(quick_data_dir,
"allnonref_85-05_nan-0.1_00-1.0")
data_model_sim8595 = GagesModel.load_datamodel(
sim_data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
data_model_8595 = GagesModel.load_datamodel(
data_dir,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
data_model_sim9505 = GagesModel.load_datamodel(
sim_data_dir,
data_source_file_name='test_data_source.txt',
stat_file_name='test_Statistics.json',
flow_file_name='test_flow.npy',
forcing_file_name='test_forcing.npy',
attr_file_name='test_attr.npy',
f_dict_file_name='test_dictFactorize.json',
var_dict_file_name='test_dictAttribute.json',
t_s_dict_file_name='test_dictTimeSpace.json')
data_model_9505 = GagesModel.load_datamodel(
data_dir,
data_source_file_name='test_data_source.txt',
stat_file_name='test_Statistics.json',
flow_file_name='test_flow.npy',
forcing_file_name='test_forcing.npy',
attr_file_name='test_attr.npy',
f_dict_file_name='test_dictFactorize.json',
var_dict_file_name='test_dictAttribute.json',
t_s_dict_file_name='test_dictTimeSpace.json')
sim_gages_model_train = GagesModel.update_data_model(
self.sim_config_data, data_model_sim8595, data_attr_update=True)
gages_model_train = GagesModel.update_data_model(self.config_data,
data_model_8595,
data_attr_update=True)
sim_gages_model_test = GagesModel.update_data_model(
self.sim_config_data,
data_model_sim9505,
data_attr_update=True,
train_stat_dict=sim_gages_model_train.stat_dict)
gages_model_test = GagesModel.update_data_model(
self.config_data,
data_model_9505,
data_attr_update=True,
train_stat_dict=gages_model_train.stat_dict)
nid_dir = os.path.join(
"/".join(self.config_data.data_path["DB"].split("/")[:-1]), "nid",
"quickdata")
nid_input = NidModel.load_nidmodel(
nid_dir,
nid_file=self.nid_file,
nid_source_file_name='nid_source.txt',
nid_data_file_name='nid_data.shp')
gage_main_dam_purpose = unserialize_json(
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
gage_main_dam_purpose_lst = list(gage_main_dam_purpose.values())
gage_main_dam_purpose_unique = np.unique(gage_main_dam_purpose_lst)
data_input = GagesDamDataModel(gages_model_test, nid_input, True,
gage_main_dam_purpose)
for i in range(0, gage_main_dam_purpose_unique.size):
sim_gages_model_test.update_model_param('train', nEpoch=300)
gages_input = choose_which_purpose(
data_input, purpose=gage_main_dam_purpose_unique[i])
new_temp_dir = os.path.join(
gages_input.data_source.data_config.model_dict["dir"]["Temp"],
gage_main_dam_purpose_unique[i])
new_out_dir = os.path.join(
gages_input.data_source.data_config.model_dict["dir"]["Out"],
gage_main_dam_purpose_unique[i])
gages_input.update_datamodel_dir(new_temp_dir, new_out_dir)
model_input = GagesSimDataModel(sim_gages_model_test, gages_input)
pred, obs = master_test_natural_flow(model_input,
epoch=self.test_epoch)
basin_area = model_input.data_model2.data_source.read_attr(
model_input.data_model2.t_s_dict["sites_id"], ['DRAIN_SQKM'],
is_return_dict=False)
mean_prep = model_input.data_model2.data_source.read_attr(
model_input.data_model2.t_s_dict["sites_id"], ['PPTAVG_BASIN'],
is_return_dict=False)
mean_prep = mean_prep / 365 * 10
pred = _basin_norm(pred, basin_area, mean_prep, to_norm=False)
obs = _basin_norm(obs, basin_area, mean_prep, to_norm=False)
save_result(
model_input.data_model2.data_source.data_config.
data_path['Temp'], str(self.test_epoch), pred, obs)
plot_we_need(gages_input,
obs,
pred,
id_col="STAID",
lon_col="LNG_GAGE",
lat_col="LAT_GAGE")
def test_gages_nse_dam_attr(self):
figure_dpi = 600
config_data = self.config_data
data_dir = config_data.data_path["Temp"]
data_model = GagesModel.load_datamodel(
data_dir,
data_source_file_name='test_data_source.txt',
stat_file_name='test_Statistics.json',
flow_file_name='test_flow.npy',
forcing_file_name='test_forcing.npy',
attr_file_name='test_attr.npy',
f_dict_file_name='test_dictFactorize.json',
var_dict_file_name='test_dictAttribute.json',
t_s_dict_file_name='test_dictTimeSpace.json')
gages_id = data_model.t_s_dict["sites_id"]
exp_lst = [
"basic_exp37", "basic_exp39", "basic_exp40", "basic_exp41",
"basic_exp42", "basic_exp43"
]
self.inds_df, pred_mean, obs_mean = load_ensemble_result(
config_data.config_file,
exp_lst,
config_data.config_file.TEST_EPOCH,
return_value=True)
show_ind_key = 'NSE'
plt.rcParams['font.family'] = 'serif'
plt.rcParams['font.serif'] = ['Times New Roman'
] + plt.rcParams['font.serif']
# plot NSE-DOR
attr_lst = ["RUNAVE7100", "STOR_NOR_2009"]
attrs_runavg_stor = data_model.data_source.read_attr(
gages_id, attr_lst, is_return_dict=False)
run_avg = attrs_runavg_stor[:, 0] * (10**(-3)) * (10**6
) # m^3 per year
nor_storage = attrs_runavg_stor[:, 1] * 1000 # m^3
dors = nor_storage / run_avg
# dor = 0 is not totally same with dam_num=0 (some dammed basins' dor is about 0.00),
# here for zero-dor we mainly rely on dam_num = 0
attr_dam_num = ["NDAMS_2009"]
attrs_dam_num = data_model.data_source.read_attr(gages_id,
attr_dam_num,
is_return_dict=False)
df = pd.DataFrame({
"DOR": dors,
"DAM_NUM": attrs_dam_num[:, 0],
show_ind_key: self.inds_df[show_ind_key].values
})
hydro_logger.info("statistics of dors:\n %s", df.describe())
hydro_logger.info("percentiles of dors:\n %s", df.quantile(q=0.95))
hydro_logger.info("ecdf of dors:\n %s", ecdf(dors))
# boxplot
# add a column to represent the dor range for the df
dor_value_range_lst = [[0, 0], [0, 0.02], [0.02, 0.05], [0.05, 0.1],
[0.1, 0.2], [0.2, 0.4], [0.4, 0.8],
[0.8, 10000]]
dor_range_lst = ["0"] + [
str(dor_value_range_lst[i][0]) + "-" +
str(dor_value_range_lst[i][1])
for i in range(1,
len(dor_value_range_lst) - 1)
] + [">" + str(dor_value_range_lst[-1][0])]
# add a column to represent the dam_num range for the df
dam_num_value_range_lst = [[0, 0], [0, 1], [1, 3], [3, 5], [5, 10],
[10, 20], [20, 50], [50, 10000]]
dam_num_range_lst = ["0", "1"] + [
str(dam_num_value_range_lst[i][0]) + "-" +
str(dam_num_value_range_lst[i][1])
for i in range(2,
len(dam_num_value_range_lst) - 1)
] + [">" + str(dam_num_value_range_lst[-1][0])]
def in_which_range(value_temp):
if value_temp == 0:
return "0"
the_range = [
a_range for a_range in dor_value_range_lst
if a_range[0] < value_temp <= a_range[1]
]
if the_range[0][0] == dor_value_range_lst[-1][0]:
the_range_str = ">" + str(the_range[0][0])
else:
the_range_str = str(the_range[0][0]) + "-" + str(
the_range[0][1])
return the_range_str
def in_which_dam_num_range(value_tmp):
if value_tmp == 0:
return "0"
if value_tmp == 1:
return "1"
the_ran = [
a_ran for a_ran in dam_num_value_range_lst
if a_ran[0] < value_tmp <= a_ran[1]
]
if the_ran[0][0] == dam_num_value_range_lst[-1][0]:
the_ran_str = ">" + str(the_ran[0][0])
else:
the_ran_str = str(the_ran[0][0]) + "-" + str(the_ran[0][1])
return the_ran_str
df["DOR_RANGE"] = df["DOR"].apply(in_which_range)
df["DAM_NUM_RANGE"] = df["DAM_NUM"].apply(in_which_dam_num_range)
df.loc[(df["DAM_NUM"] > 0) & (df["DOR_RANGE"] == "0"),
"DOR_RANGE"] = dor_range_lst[1]
shown_nse_range_boxplots = [-0.5, 1.0]
sns.set(font="serif", font_scale=1.5, color_codes=True)
plot_boxs(df,
"DOR_RANGE",
show_ind_key,
ylim=shown_nse_range_boxplots,
order=dor_range_lst)
plt.savefig(os.path.join(
config_data.data_path["Out"],
'NSE~DOR-boxplots-' + str(shown_nse_range_boxplots) + '.png'),
dpi=figure_dpi,
bbox_inches="tight")
plt.figure()
shown_nse_range_boxplots = [0, 1.0]
sns.set(font="serif", font_scale=1.5, color_codes=True)
plot_boxs(df,
"DAM_NUM_RANGE",
show_ind_key,
ylim=shown_nse_range_boxplots,
order=dam_num_range_lst)
plt.savefig(os.path.join(
config_data.data_path["Out"],
'NSE~DAM_NUM-boxplots-' + str(shown_nse_range_boxplots) + '.png'),
dpi=figure_dpi,
bbox_inches="tight")
nums_in_dor_range = [
df[df["DOR_RANGE"] == a_range_rmp].shape[0]
for a_range_rmp in dor_range_lst
]
ratios_in_dor_range = [
a_num / df.shape[0] for a_num in nums_in_dor_range
]
hydro_logger.info(
"the number and ratio of basins in each dor range\n: %s \n %s",
nums_in_dor_range, ratios_in_dor_range)
nums_in_dam_num_range = [
df[df["DAM_NUM_RANGE"] == a_range_rmp].shape[0]
for a_range_rmp in dam_num_range_lst
]
ratios_in_dam_num_range = [
a_num / df.shape[0] for a_num in nums_in_dam_num_range
]
hydro_logger.info(
"the number and ratio of basins in each dam_num range\n: %s \n %s",
nums_in_dam_num_range, ratios_in_dam_num_range)
# regplot
plt.figure()
sns.set(font="serif", font_scale=1.5, color_codes=True)
sr = sns.regplot(x="DOR",
y=show_ind_key,
data=df[df[show_ind_key] >= 0],
scatter_kws={'s': 10})
show_dor_max = df.quantile(
q=0.95)["DOR"] # 30 # max(dors) # 0.8 # 10
show_dor_min = min(dors)
plt.ylim(0, 1)
plt.xlim(show_dor_min, show_dor_max)
plt.savefig(os.path.join(
config_data.data_path["Out"],
'NSE~DOR-shown-max-' + str(show_dor_max) + '.png'),
dpi=figure_dpi,
bbox_inches="tight")
# jointplot
# dor_range = [0.2, 0.9]
dor_range = [0.002, 0.2]
# plt.figure()
sns.set(font="serif", font_scale=1.5, color_codes=True)
# g = sns.jointplot(x="DOR", y=show_ind_key, data=df[(df["DOR"] < 1) & (df[show_ind_key] >= 0)], kind="reg",
# marginal_kws=dict(bins=25))
# g = sns.jointplot(x="DOR", y=show_ind_key, data=df[(df["DOR"] < 1) & (df[show_ind_key] >= 0)], kind="hex",
# color="b", marginal_kws=dict(bins=50))
g = sns.jointplot(
x="DOR",
y=show_ind_key,
data=df[(df["DOR"] < dor_range[1]) & (df["DOR"] > dor_range[0]) &
(df[show_ind_key] >= 0)],
kind="hex",
color="b")
g.ax_marg_x.set_xlim(dor_range[0], dor_range[1])
# g.ax_marg_y.set_ylim(-0.5, 1)
plt.savefig(os.path.join(
config_data.data_path["Out"],
'NSE~DOR(range-)' + str(dor_range) + '-jointplot.png'),
dpi=figure_dpi,
bbox_inches="tight")
nid_dir = os.path.join(
"/".join(self.config_data.data_path["DB"].split("/")[:-1]), "nid",
"test")
nid_input = NidModel.load_nidmodel(
nid_dir,
nid_source_file_name='nid_source.txt',
nid_data_file_name='nid_data.shp')
gage_main_dam_purpose = unserialize_json(
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
data_input = GagesDamDataModel(data_model, nid_input,
gage_main_dam_purpose)
dam_coords = unserialize_json_ordered(
os.path.join(nid_dir, "dam_points_dict.json"))
dam_storages = unserialize_json_ordered(
os.path.join(nid_dir, "dam_storages_dict.json"))
dam_ids_1 = list(gage_main_dam_purpose.keys())
dam_ids_2 = list(dam_coords.keys())
dam_ids_3 = list(dam_storages.keys())
assert (all(x < y for x, y in zip(dam_ids_1, dam_ids_1[1:])))
assert (all(x < y for x, y in zip(dam_ids_2, dam_ids_2[1:])))
assert (all(x < y for x, y in zip(dam_ids_3, dam_ids_3[1:])))
sites = list(dam_coords.keys())
c, ind1, idx_lst_nse_range = np.intersect1d(sites,
gages_id,
return_indices=True)
std_storage_in_a_basin = list(map(np.std, dam_storages.values()))
log_std_storage_in_a_basin = list(
map(np.log,
np.array(std_storage_in_a_basin) + 1))
nse_values = self.inds_df["NSE"].values[idx_lst_nse_range]
df = pd.DataFrame({
"DAM_STORAGE_STD": log_std_storage_in_a_basin,
show_ind_key: nse_values
})
plt.figure()
sns.set(font="serif", font_scale=1.5, color_codes=True)
g = sns.regplot(x="DAM_STORAGE_STD",
y=show_ind_key,
data=df[df[show_ind_key] >= 0],
scatter_kws={'s': 10})
show_max = max(log_std_storage_in_a_basin)
show_min = min(log_std_storage_in_a_basin)
if show_min < 0:
show_min = 0
# g.ax_marg_x.set_xlim(show_min, show_max)
# g.ax_marg_y.set_ylim(0, 1)
plt.ylim(0, 1)
plt.xlim(show_min, show_max)
plt.savefig(os.path.join(config_data.data_path["Out"],
'NSE~' + "DAM_STORAGE_STD" + '.png'),
dpi=figure_dpi,
bbox_inches="tight")
gages_loc_lat = data_model.data_source.gage_dict["LAT_GAGE"]
gages_loc_lon = data_model.data_source.gage_dict["LNG_GAGE"]
gages_loc = [[gages_loc_lat[i], gages_loc_lon[i]]
for i in range(len(gages_id))]
# calculate index of dispersion, then plot the NSE-dispersion scatterplot
# Geo coord system of gages_loc and dam_coords are both NAD83
coefficient_of_var = list(
map(coefficient_of_variation, gages_loc, dam_coords.values()))
coefficient_of_var_min = min(coefficient_of_var)
coefficient_of_var_max = max(coefficient_of_var)
dispersion_var = "DAM_GAGE_DIS_VAR"
nse_values = self.inds_df["NSE"].values[idx_lst_nse_range]
df = pd.DataFrame({
dispersion_var: coefficient_of_var,
show_ind_key: nse_values
})
plt.figure()
sns.set(font="serif", font_scale=1.5, color_codes=True)
g = sns.regplot(x=dispersion_var,
y=show_ind_key,
data=df[df[show_ind_key] >= 0],
scatter_kws={'s': 10})
show_max = coefficient_of_var_max
show_min = coefficient_of_var_min
if show_min < 0:
show_min = 0
# g.ax_marg_x.set_xlim(show_min, show_max)
# g.ax_marg_y.set_ylim(0, 1)
plt.ylim(0, 1)
plt.xlim(show_min, show_max)
plt.savefig(os.path.join(config_data.data_path["Out"],
'NSE~' + dispersion_var + '.png'),
dpi=figure_dpi,
bbox_inches="tight")
idx_dispersions = list(
map(ind_of_dispersion, gages_loc, dam_coords.values()))
idx_dispersion_min = min(idx_dispersions)
idx_dispersion_max = max(idx_dispersions)
dispersion_var = "DAM_DISPERSION_BASIN"
# nse_range = [0, 1]
# idx_lst_nse_range = inds_df_now[(inds_df_now[show_ind_key] >= nse_range[0]) & (inds_df_now[show_ind_key] < nse_range[1])].index.tolist()
nse_values = self.inds_df["NSE"].values[idx_lst_nse_range]
df = pd.DataFrame({
dispersion_var: idx_dispersions,
show_ind_key: nse_values
})
# g = sns.regplot(x=dispersion_var, y=show_ind_key, data=df[df[show_ind_key] >= 0], scatter_kws={'s': 10})
if idx_dispersion_min < 0:
idx_dispersion_min = 0
plt.ylim(0, 1)
plt.xlim(idx_dispersion_min, idx_dispersion_max)
# plt.figure()
sns.set(font="serif", font_scale=1.5, color_codes=True)
g = sns.jointplot(x=dispersion_var,
y=show_ind_key,
data=df[df[show_ind_key] >= 0],
kind="reg")
g.ax_marg_x.set_xlim(idx_dispersion_min, idx_dispersion_max)
g.ax_marg_y.set_ylim(0, 1)
plt.show()
df = GagesModel.load_datamodel(cfg.CACHE.DATA_DIR,
data_source_file_name='data_source.txt',
stat_file_name='Statistics.json',
flow_file_name='flow.npy',
forcing_file_name='forcing.npy',
attr_file_name='attr.npy',
f_dict_file_name='dictFactorize.json',
var_dict_file_name='dictAttribute.json',
t_s_dict_file_name='dictTimeSpace.json')
nid_input = NidModel(cfg)
nid_dir = os.path.join(cfg.NID.NID_DIR, "test")
save_nidinput(nid_input,
nid_dir,
nid_source_file_name='nid_source.txt',
nid_data_file_name='nid_data.shp')
data_input = GagesDamDataModel(df, nid_input)
serialize_json(data_input.gage_main_dam_purpose,
os.path.join(nid_dir, "dam_main_purpose_dict.json"))
gage_main_dam_purpose = unserialize_json(nid_gene_file)
gage_main_dam_purpose_lst = list(gage_main_dam_purpose.values())
gage_main_dam_purpose_lst_merge = "".join(gage_main_dam_purpose_lst)
gage_main_dam_purpose_unique = np.unique(
list(gage_main_dam_purpose_lst_merge))
# gage_main_dam_purpose_unique = np.unique(gage_main_dam_purpose_lst)
purpose_regions = {}
for i in range(gage_main_dam_purpose_unique.size):
sites_id = []
for key, value in gage_main_dam_purpose.items():
if gage_main_dam_purpose_unique[i] in value:
sites_id.append(key)
assert (all(x < y for x, y in zip(sites_id, sites_id[1:])))