def test_regions_stat(self):
gages_data_model = GagesModel.load_datamodel(
self.config_data.data_path["Temp"],
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')
id_regions_idx, id_regions_sites_ids = ids_of_regions(gages_data_model)
preds, obss, inds_dfs = split_results_to_regions(
gages_data_model, self.test_epoch, id_regions_idx,
id_regions_sites_ids)
regions_name = [
"allref", "cntplain", "esthgnlnd", "mxwdshld", "northest",
"secstplain", "seplains", "wstmnts", "wstplains", "wstxeric"
]
frames = []
x_name = "regions"
y_name = "NSE"
for i in range(len(id_regions_idx)):
# plot box，使用seaborn库
keys = ["NSE"]
inds_test = subset_of_dict(inds_dfs[i], keys)
inds_test = inds_test[keys[0]].values
df_dict_i = {}
str_i = regions_name[i]
df_dict_i[x_name] = np.full([inds_test.size], str_i)
df_dict_i[y_name] = inds_test
df_i = pd.DataFrame(df_dict_i)
frames.append(df_i)
result = pd.concat(frames)
plot_boxs(result, x_name, y_name)
def plot_box_inds(indicators):
"""绘制观测值和预测值比较的时间序列图"""
data = pd.DataFrame(indicators, index=[0])
# 将数据转换为tidy data格式，首先，增加一列名称列，然后剩下的所有值重组到var_name和value_name两列中
indict_name = "indicator"
indicts = pd.Series(data.columns.values, name=indict_name)
data_t = pd.DataFrame(data.values.T)
data_t = pd.concat([indicts, data_t], axis=1)
formatted_data = pd.melt(data_t, [indict_name])
formatted_data = formatted_data.sort_values(by=[indict_name])
plot_boxs(formatted_data, x_name=indict_name, y_name='value')
def plot_box_inds(indicators):
"""plot boxplots in one coordination"""
data = pd.DataFrame(indicators)
# transform data to "tidy data". Firstly add a column，then assign all other values to "var_name" and "value_name" columns
indict_name = "indicator"
indicts = pd.Series(data.columns.values, name=indict_name)
data_t = pd.DataFrame(data.values.T)
data_t = pd.concat([indicts, data_t], axis=1)
formatted_data = pd.melt(data_t, [indict_name])
formatted_data = formatted_data.sort_values(by=[indict_name])
box_fig = plot_boxs(formatted_data, x_name=indict_name, y_name='value')
return box_fig
def test_3factors(self):
data_model = self.data_model
config_data = self.config_data
test_epoch = self.test_epoch
# plot three factors
attr_lst = ["RUNAVE7100", "STOR_NOR_2009"]
usgs_id = data_model.t_s_dict["sites_id"]
attrs_runavg_stor = data_model.data_source.read_attr(
usgs_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_value = nor_storage / run_avg
dors = np.full(len(usgs_id), "dor<0.02")
for i in range(len(usgs_id)):
if dors_value[i] >= 0.02:
dors[i] = "dor≥0.02"
diversions = np.full(len(usgs_id), "no ")
diversion_strs = ["diversion", "divert"]
attr_lst = ["WR_REPORT_REMARKS", "SCREENING_COMMENTS"]
data_attr = data_model.data_source.read_attr_origin(usgs_id, attr_lst)
diversion_strs_lower = [elem.lower() for elem in diversion_strs]
data_attr0_lower = np.array([
elem.lower() if type(elem) == str else elem
for elem in data_attr[0]
])
data_attr1_lower = np.array([
elem.lower() if type(elem) == str else elem
for elem in data_attr[1]
])
data_attr_lower = np.vstack((data_attr0_lower, data_attr1_lower)).T
for i in range(len(usgs_id)):
if is_any_elem_in_a_lst(diversion_strs_lower,
data_attr_lower[i],
include=True):
diversions[i] = "yes"
nid_dir = os.path.join(
"/".join(config_data.data_path["DB"].split("/")[:-1]), "nid",
"test")
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_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:])))
purpose_regions[gage_main_dam_purpose_unique[i]] = sites_id
id_regions_idx = []
id_regions_sites_ids = []
regions_name = []
show_min_num = 10
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)
if c.size < show_min_num:
continue
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)
regions_name.append(key)
preds, obss, inds_dfs = split_results_to_regions(
data_model, test_epoch, id_regions_idx, id_regions_sites_ids)
frames = []
x_name = "purposes"
y_name = "NSE"
hue_name = "DOR"
col_name = "diversion"
for i in range(len(id_regions_idx)):
# plot box，使用seaborn库
keys = ["NSE"]
inds_test = subset_of_dict(inds_dfs[i], keys)
inds_test = inds_test[keys[0]].values
df_dict_i = {}
str_i = regions_name[i]
df_dict_i[x_name] = np.full([inds_test.size], str_i)
df_dict_i[y_name] = inds_test
df_dict_i[hue_name] = dors[id_regions_idx[i]]
df_dict_i[col_name] = diversions[id_regions_idx[i]]
# df_dict_i[hue_name] = nor_storage[id_regions_idx[i]]
df_i = pd.DataFrame(df_dict_i)
frames.append(df_i)
result = pd.concat(frames)
plot_boxs(result, x_name, y_name, ylim=[0, 1.0])
plt.savefig(os.path.join(config_data.data_path["Out"],
'purpose_distribution.png'),
dpi=500,
bbox_inches="tight")
# g = sns.catplot(x=x_name, y=y_name, hue=hue_name, col=col_name,
# data=result, kind="swarm",
# height=4, aspect=.7)
sns.set(font_scale=1.5)
fig, ax = plt.subplots()
fig.set_size_inches(11.7, 8.27)
g = sns.catplot(ax=ax,
x=x_name,
y=y_name,
hue=hue_name,
col=col_name,
data=result,
palette="Set1",
kind="box",
dodge=True,
showfliers=False)
# g.set(ylim=(-1, 1))
plt.savefig(os.path.join(config_data.data_path["Out"],
'3factors_distribution.png'),
dpi=500,
bbox_inches="tight")
plt.show()
def test_scatter_diversion(self):
attr_lst = ["RUNAVE7100", "STOR_NOR_2009"]
sites_nonref = self.data_model.t_s_dict["sites_id"]
attrs_runavg_stor = self.data_model.data_source.read_attr(
sites_nonref, 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
diversion_yes = True
diversion_no = False
source_data_diversion = GagesSource.choose_some_basins(
self.config_data,
self.config_data.model_dict["data"]["tRangeTrain"],
screen_basin_area_huc4=False,
diversion=diversion_yes)
source_data_nodivert = GagesSource.choose_some_basins(
self.config_data,
self.config_data.model_dict["data"]["tRangeTrain"],
screen_basin_area_huc4=False,
diversion=diversion_no)
sites_id_diversion = source_data_diversion.all_configs[
'flow_screen_gage_id']
sites_id_nodivert = source_data_nodivert.all_configs[
'flow_screen_gage_id']
divert_regions = {}
divert_regions["diversion"] = sites_id_diversion
divert_regions["not_diverted"] = sites_id_nodivert
id_regions_idx = []
id_regions_sites_ids = []
regions_name = []
df_id_region = np.array(self.data_model.t_s_dict["sites_id"])
for key, value in divert_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)
regions_name.append(key)
preds, obss, inds_dfs = split_results_to_regions(
self.data_model, self.test_epoch, id_regions_idx,
id_regions_sites_ids)
frames = []
x_name = "is_diverted"
y_name = "NSE"
hue_name = "DOR"
# hue_name = "STOR"
for i in range(len(id_regions_idx)):
# plot box，使用seaborn库
keys = ["NSE"]
inds_test = subset_of_dict(inds_dfs[i], keys)
inds_test = inds_test[keys[0]].values
df_dict_i = {}
str_i = regions_name[i]
df_dict_i[x_name] = np.full([inds_test.size], str_i)
df_dict_i[y_name] = inds_test
df_dict_i[hue_name] = dors[id_regions_idx[i]]
# df_dict_i[hue_name] = nor_storage[id_regions_idx[i]]
df_i = pd.DataFrame(df_dict_i)
frames.append(df_i)
result = pd.concat(frames)
# can remove high hue value to keep a good map
plot_boxs(result, x_name, y_name, ylim=[-1.0, 1.0])
# plot_boxs(result, x_name, y_name, uniform_color="skyblue", swarm_plot=True, hue=hue_name, colormap=True,
# ylim=[-1.0, 1.0])
cmap_str = 'viridis'
# cmap = plt.get_cmap('Spectral')
cbar_label = hue_name
plt.title('Distribution of w/wo diversion')
swarmplot_with_cbar(cmap_str,
cbar_label, [-1, 1.0],
x=x_name,
y=y_name,
hue=hue_name,
palette=cmap_str,
data=result)
def test_scatter_dam_purpose(self):
attr_lst = ["RUNAVE7100", "STOR_NOR_2009"]
sites_nonref = self.data_model.t_s_dict["sites_id"]
attrs_runavg_stor = self.data_model.data_source.read_attr(
sites_nonref, 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
nid_dir = os.path.join(self.config_data.data_path["DB"], "nid", "test")
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 = []
regions_name = []
show_min_num = 10
df_id_region = np.array(self.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)
if c.size < show_min_num:
continue
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)
regions_name.append(key)
preds, obss, inds_dfs = split_results_to_regions(
self.data_model, self.test_epoch, id_regions_idx,
id_regions_sites_ids)
frames = []
x_name = "purposes"
y_name = "NSE"
hue_name = "DOR"
# hue_name = "STOR"
for i in range(len(id_regions_idx)):
# plot box，使用seaborn库
keys = ["NSE"]
inds_test = subset_of_dict(inds_dfs[i], keys)
inds_test = inds_test[keys[0]].values
df_dict_i = {}
str_i = regions_name[i]
df_dict_i[x_name] = np.full([inds_test.size], str_i)
df_dict_i[y_name] = inds_test
df_dict_i[hue_name] = dors[id_regions_idx[i]]
# df_dict_i[hue_name] = nor_storage[id_regions_idx[i]]
df_i = pd.DataFrame(df_dict_i)
frames.append(df_i)
result = pd.concat(frames)
# can remove high hue value to keep a good map
plot_boxs(result, x_name, y_name, ylim=[-1.0, 1.0])
plt.savefig(os.path.join(self.config_data.data_path["Out"],
'purpose_distribution_test.png'),
dpi=500,
bbox_inches="tight")
plt.show()
# plot_boxs(result, x_name, y_name, uniform_color="skyblue", swarm_plot=True, hue=hue_name, colormap=True,
# ylim=[-1.0, 1.0])
cmap_str = 'viridis'
# cmap = plt.get_cmap('Spectral')
cbar_label = hue_name
plt.title('Distribution of different purposes')
swarmplot_with_cbar(cmap_str,
cbar_label, [-1, 1.0],
x=x_name,
y=y_name,
hue=hue_name,
palette=cmap_str,
data=result)
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()
# plot box with seaborn
keys = ["NSE"]
inds_test = subset_of_dict(inds_dfs[i], keys)
inds_test = inds_test[keys[0]].values
df_dict_i = {}
str_i = regions_name[i]
df_dict_i[x_name] = np.full([inds_test.size], str_i)
df_dict_i[y_name] = inds_test
df_dict_i[hue_name] = dors[id_regions_idx[i]]
df_dict_i[col_name] = diversions[id_regions_idx[i]]
# df_dict_i[hue_name] = nor_storage[id_regions_idx[i]]
df_i = pd.DataFrame(df_dict_i)
frames.append(df_i)
result = pd.concat(frames)
plt.figure()
plot_boxs(result, x_name, y_name, ylim=[-0.4, 1.0], rotation=0)
plt.savefig(os.path.join(config_data.data_path["Out"],
'purpose_distribution.png'),
dpi=FIGURE_DPI,
bbox_inches="tight")
# g = sns.catplot(x=x_name, y=y_name, hue=hue_name, col=col_name,
# data=result, kind="swarm",
# height=4, aspect=.7)
fig, ax = plt.subplots()
fig.set_size_inches(11.7, 8.27)
sns.set(font="serif", font_scale=1.5, color_codes=True)
g = sns.catplot(
ax=ax,
x=x_name,
y=y_name,
hue=hue_name,