def test_plot_ts(self):
"""测试可视化代码"""
# plot time series
show_me_num = 5
t_s_dict = unserialize_json(self.t_s_dict_file)
sites = np.array(t_s_dict["sites_id"])
t_range = np.array(t_s_dict["t_final_range"])
plot_ts_obs_pred(self.obs, self.pred, sites, t_range, show_me_num)
def test_inv_plot(self):
data_model = GagesModel.load_datamodel(
self.config_data_2.data_path["Temp"],
"2",
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')
flow_pred_file = os.path.join(
data_model.data_source.data_config.data_path['Temp'],
'epoch' + str(self.test_epoch) + 'flow_pred.npy')
flow_obs_file = os.path.join(
data_model.data_source.data_config.data_path['Temp'],
'epoch' + str(self.test_epoch) + 'flow_obs.npy')
pred = unserialize_numpy(flow_pred_file)
obs = unserialize_numpy(flow_obs_file)
pred = pred.reshape(pred.shape[0], pred.shape[1])
obs = obs.reshape(obs.shape[0], obs.shape[1])
inds = statError(obs, pred)
inds['STAID'] = data_model.t_s_dict["sites_id"]
inds_df = pd.DataFrame(inds)
inds_df.to_csv(
os.path.join(self.config_data_2.data_path["Out"], 'data_df.csv'))
# plot box，使用seaborn库
keys = ["Bias", "RMSE", "NSE"]
inds_test = subset_of_dict(inds, keys)
box_fig = plot_diff_boxes(inds_test)
box_fig.savefig(
os.path.join(self.config_data_2.data_path["Out"], "box_fig.png"))
# plot ts
show_me_num = 5
t_s_dict = data_model.t_s_dict
sites = np.array(t_s_dict["sites_id"])
t_range = np.array(t_s_dict["t_final_range"])
time_seq_length = self.config_data_1.model_dict['model']['seqLength']
time_start = np.datetime64(t_range[0]) + np.timedelta64(
time_seq_length - 1, 'D')
t_range[0] = np.datetime_as_string(time_start, unit='D')
ts_fig = plot_ts_obs_pred(obs, pred, sites, t_range, show_me_num)
ts_fig.savefig(
os.path.join(self.config_data_2.data_path["Out"], "ts_fig.png"))
# plot nse ecdf
sites_df_nse = pd.DataFrame({
"sites": sites,
keys[2]: inds_test[keys[2]]
})
plot_ecdf(sites_df_nse, keys[2])
# plot map
gauge_dict = data_model.data_source.gage_dict
plot_map(gauge_dict,
sites_df_nse,
id_col="STAID",
lon_col="LNG_GAGE",
lat_col="LAT_GAGE")
def test_forecast_test(self):
sim_df = GagesModel.load_datamodel(
self.sim_config_data.data_path["Temp"],
"1",
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')
df = GagesModel.load_datamodel(
self.config_data.data_path["Temp"],
"2",
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_input = GagesForecastDataModel(sim_df, df)
pred, obs = test_lstm_forecast(data_input)
pred = pred.reshape(pred.shape[0], pred.shape[1])
obs = obs.reshape(obs.shape[0], obs.shape[1])
inds = statError(obs, pred)
show_me_num = 5
t_s_dict = data_input.model_data.t_s_dict
sites = np.array(t_s_dict["sites_id"])
t_range = np.array(t_s_dict["t_final_range"])
time_seq_length = data_input.model_data.data_source.data_config.model_dict[
'model']['seqLength']
time_start = np.datetime64(t_range[0]) + np.timedelta64(
time_seq_length, 'D')
t_range[0] = np.datetime_as_string(time_start, unit='D')
ts_fig = plot_ts_obs_pred(obs, pred, sites, t_range, show_me_num)
ts_fig.savefig(
os.path.join(self.config_data.data_path["Out"], "ts_fig.png"))
# # plot box，使用seaborn库
keys = ["Bias", "RMSE", "NSE"]
inds_test = subset_of_dict(inds, keys)
box_fig = plot_diff_boxes(inds_test)
box_fig.savefig(
os.path.join(self.config_data.data_path["Out"], "box_fig.png"))
# plot map
sites_df = pd.DataFrame({"sites": sites, keys[2]: inds_test[keys[2]]})
plot_ind_map(df.data_source.all_configs['gage_point_file'], sites_df)
def test_explore_test(self):
models_num = 0
dirs = os.listdir(self.config_data.data_path["Temp"])
for dir_temp in dirs:
if os.path.isdir(
os.path.join(self.config_data.data_path["Temp"],
dir_temp)):
models_num += 1
for count in range(models_num):
print("\n", "testing model", str(count + 1), ":\n")
data_model = GagesModel.load_datamodel(
self.config_data.data_path["Temp"],
str(count),
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')
pred, obs = master_test(data_model)
pred = pred.reshape(pred.shape[0], pred.shape[1])
obs = obs.reshape(obs.shape[0], obs.shape[1])
inds = statError(obs, pred)
show_me_num = 5
t_s_dict = data_model.t_s_dict
sites = np.array(t_s_dict["sites_id"])
t_range = np.array(t_s_dict["t_final_range"])
ts_fig = plot_ts_obs_pred(obs, pred, sites, t_range, show_me_num)
ts_fig.savefig(
os.path.join(
data_model.data_source.data_config.data_path["Out"],
"ts_fig.png"))
# # plot box，使用seaborn库
keys = ["Bias", "RMSE", "NSE"]
inds_test = subset_of_dict(inds, keys)
box_fig = plot_diff_boxes(inds_test)
box_fig.savefig(
os.path.join(
data_model.data_source.data_config.data_path["Out"],
"box_fig.png"))
# plot map
sites_df = pd.DataFrame({
"sites": sites,
keys[2]: inds_test[keys[2]]
})
plot_ind_map(data_model.data_source.all_configs['gage_point_file'],
sites_df)
def test_purposes_seperate(self):
quick_data_dir = os.path.join(self.config_data.data_path["DB"],
"quickdata")
data_dir = os.path.join(quick_data_dir,
"allnonref-dam_95-05_nan-0.1_00-1.0")
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')
data_model = GagesModel.update_data_model(self.config_data,
data_model_test)
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)
purpose_regions = {}
for i in range(gage_main_dam_purpose_unique.size):
sites_id = []
for key, value in gage_main_dam_purpose.items():
if value == gage_main_dam_purpose_unique[i]:
sites_id.append(key)
assert (all(x < y for x, y in zip(sites_id, sites_id[1:])))
purpose_regions[gage_main_dam_purpose_unique[i]] = sites_id
id_regions_idx = []
id_regions_sites_ids = []
df_id_region = np.array(data_model.t_s_dict["sites_id"])
for key, value in purpose_regions.items():
gages_id = value
c, ind1, ind2 = np.intersect1d(df_id_region,
gages_id,
return_indices=True)
assert (all(x < y for x, y in zip(ind1, ind1[1:])))
assert (all(x < y for x, y in zip(c, c[1:])))
id_regions_idx.append(ind1)
id_regions_sites_ids.append(c)
pred_all, obs_all = load_result(self.config_data.data_path["Temp"],
self.test_epoch)
pred_all = pred_all.reshape(pred_all.shape[0], pred_all.shape[1])
obs_all = obs_all.reshape(obs_all.shape[0], obs_all.shape[1])
for i in range(9, len(gage_main_dam_purpose_unique)):
pred = pred_all[id_regions_idx[i], :]
obs = obs_all[id_regions_idx[i], :]
inds = statError(obs, pred)
inds['STAID'] = id_regions_sites_ids[i]
inds_df = pd.DataFrame(inds)
inds_df.to_csv(
os.path.join(
self.config_data.data_path["Out"],
gage_main_dam_purpose_unique[i] + "epoch" +
str(self.test_epoch) + 'data_df.csv'))
# plot box，使用seaborn库
keys = ["Bias", "RMSE", "NSE"]
inds_test = subset_of_dict(inds, keys)
box_fig = plot_diff_boxes(inds_test)
box_fig.savefig(
os.path.join(
self.config_data.data_path["Out"],
gage_main_dam_purpose_unique[i] + "epoch" +
str(self.test_epoch) + "box_fig.png"))
# plot ts
sites = np.array(df_id_region[id_regions_idx[i]])
t_range = np.array(data_model.t_s_dict["t_final_range"])
show_me_num = 1
ts_fig = plot_ts_obs_pred(obs, pred, sites, t_range, show_me_num)
ts_fig.savefig(
os.path.join(
self.config_data.data_path["Out"],
gage_main_dam_purpose_unique[i] + "epoch" +
str(self.test_epoch) + "ts_fig.png"))
# plot nse ecdf
sites_df_nse = pd.DataFrame({
"sites": sites,
keys[2]: inds_test[keys[2]]
})
plot_ecdf(
sites_df_nse, keys[2],
os.path.join(
self.config_data.data_path["Out"],
gage_main_dam_purpose_unique[i] + "epoch" +
str(self.test_epoch) + "ecdf_fig.png"))
# plot map
gauge_dict = data_model.data_source.gage_dict
save_map_file = os.path.join(
self.config_data.data_path["Out"],
gage_main_dam_purpose_unique[i] + "epoch" +
str(self.test_epoch) + "map_fig.png")
plot_map(gauge_dict,
sites_df_nse,
save_file=save_map_file,
id_col="STAID",
lon_col="LNG_GAGE",
lat_col="LAT_GAGE")