def get_seasonal_clim_obs_data(rconfig=None,
vname="TT",
bmp_info=None,
season_to_months=None,
obs_path=None):
"""
:param rconfig:
:param vname: Corresponding model variable name i.e either TT or PR
"""
assert isinstance(rconfig, RunConfig)
if season_to_months is None:
season_to_months = DEFAULT_SEASON_TO_MONTHS
if bmp_info is None:
bmp_info = analysis.get_basemap_info_from_hdf(
file_path=rconfig.data_path)
obs_query_params = dict(start_year=rconfig.start_year,
end_year=rconfig.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats)
# Calculate daily mean temperatures as T = (T(min) + T(max)) * 0.5
if vname == "TT":
tmax_obs_manager = AnuSplinManager(variable="stmx",
folder_path=obs_path)
tmin_obs_manager = AnuSplinManager(variable="stmn",
folder_path=obs_path)
dates, vals_max = tmax_obs_manager.get_daily_clim_fields_interpolated_to(
**obs_query_params)
_, vals_min = tmin_obs_manager.get_daily_clim_fields_interpolated_to(
**obs_query_params)
daily_obs = (dates, (vals_min + vals_max) * 0.5)
elif vname == "PR":
pcp_obs_manager = AnuSplinManager(variable="pcp", folder_path=obs_path)
daily_obs = pcp_obs_manager.get_daily_clim_fields_interpolated_to(
**obs_query_params)
# SWE
elif vname == "I5":
swe_manager = SweDataManager(var_name="SWE", path=obs_path)
daily_obs = swe_manager.get_daily_clim_fields_interpolated_to(
**obs_query_params)
else:
raise Exception("Unknown variable: {}".format(vname))
season_to_obs_data = OrderedDict()
for season, months in season_to_months.items():
season_to_obs_data[season] = np.mean(
[f for d, f in zip(*daily_obs) if d.month in months], axis=0)
return season_to_obs_data
def get_seasonal_clim_obs_data(rconfig=None, vname="TT", bmp_info=None, season_to_months=None, n_agg_x=1, n_agg_y=1):
"""
:param rconfig:
:param vname: Corresponding model variable name i.e either TT or PR
"""
assert isinstance(rconfig, RunConfig)
if season_to_months is None:
season_to_months = DEFAULT_SEASON_TO_MONTHS
if bmp_info is None:
bmp_info = analysis.get_basemap_info_from_hdf(file_path=rconfig.data_path)
# Get Anusplin data managers
obs_path = "/home/huziy/skynet3_rech1/anusplin_links"
pcp_obs_manager = AnuSplinManager(variable="pcp", folder_path=obs_path)
tmax_obs_manager = AnuSplinManager(variable="stmx", folder_path=obs_path)
tmin_obs_manager = AnuSplinManager(variable="stmn", folder_path=obs_path)
if vname == "TT":
dates, vals_max = tmax_obs_manager.get_daily_clim_fields_aggregated_and_interpolated_to(start_year=rconfig.start_year,
end_year=rconfig.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats,
n_agg_x=n_agg_x,
n_agg_y=n_agg_y)
_, vals_min = tmin_obs_manager.get_daily_clim_fields_aggregated_and_interpolated_to(start_year=rconfig.start_year,
end_year=rconfig.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats,
n_agg_x=n_agg_x,
n_agg_y=n_agg_y)
daily_obs = (dates, (vals_min + vals_max) * 0.5)
elif vname == "PR":
daily_obs = pcp_obs_manager.get_daily_clim_fields_aggregated_and_interpolated_to(start_year=rconfig.start_year,
end_year=rconfig.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats,
n_agg_x=n_agg_x,
n_agg_y=n_agg_y)
else:
raise Exception("Unknown variable: {}".format(vname))
season_to_obs_data = OrderedDict()
for season, months in season_to_months.items():
season_to_obs_data[season] = np.mean([f for d, f in zip(*daily_obs) if d.month in months], axis=0)
return season_to_obs_data
def get_seasonal_clim_obs_data(rconfig=None, vname="TT", bmp_info=None, season_to_months=None, obs_path=None):
"""
:param rconfig:
:param vname: Corresponding model variable name i.e either TT or PR
"""
assert isinstance(rconfig, RunConfig)
if season_to_months is None:
season_to_months = DEFAULT_SEASON_TO_MONTHS
if bmp_info is None:
bmp_info = analysis.get_basemap_info_from_hdf(file_path=rconfig.data_path)
obs_query_params = dict(
start_year=rconfig.start_year,
end_year=rconfig.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats
)
# Calculate daily mean temperatures as T = (T(min) + T(max)) * 0.5
if vname == "TT":
tmax_obs_manager = AnuSplinManager(variable="stmx", folder_path=obs_path)
tmin_obs_manager = AnuSplinManager(variable="stmn", folder_path=obs_path)
dates, vals_max = tmax_obs_manager.get_daily_clim_fields_interpolated_to(**obs_query_params)
_, vals_min = tmin_obs_manager.get_daily_clim_fields_interpolated_to(**obs_query_params)
daily_obs = (dates, (vals_min + vals_max) * 0.5)
elif vname == "PR":
pcp_obs_manager = AnuSplinManager(variable="pcp", folder_path=obs_path)
daily_obs = pcp_obs_manager.get_daily_clim_fields_interpolated_to(**obs_query_params)
# SWE
elif vname == "I5":
swe_manager = SweDataManager(var_name="SWE", path=obs_path)
daily_obs = swe_manager.get_daily_clim_fields_interpolated_to(**obs_query_params)
else:
raise Exception("Unknown variable: {}".format(vname))
season_to_obs_data = OrderedDict()
for season, months in season_to_months.items():
season_to_obs_data[season] = np.mean([f for d, f in zip(*daily_obs) if d.month in months], axis=0)
return season_to_obs_data
def get_seasonal_clim_obs_data(rconfig=None,
vname="TT",
bmp_info=None,
season_to_months=None,
n_agg_x=1,
n_agg_y=1):
"""
:param rconfig:
:param vname: Corresponding model variable name i.e either TT or PR
"""
assert isinstance(rconfig, RunConfig)
if season_to_months is None:
season_to_months = DEFAULT_SEASON_TO_MONTHS
if bmp_info is None:
bmp_info = analysis.get_basemap_info_from_hdf(
file_path=rconfig.data_path)
# Get Anusplin data managers
obs_path = "/home/huziy/skynet3_rech1/anusplin_links"
pcp_obs_manager = AnuSplinManager(variable="pcp", folder_path=obs_path)
tmax_obs_manager = AnuSplinManager(variable="stmx", folder_path=obs_path)
tmin_obs_manager = AnuSplinManager(variable="stmn", folder_path=obs_path)
if vname == "TT":
dates, vals_max = tmax_obs_manager.get_daily_clim_fields_aggregated_and_interpolated_to(
start_year=rconfig.start_year,
end_year=rconfig.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats,
n_agg_x=n_agg_x,
n_agg_y=n_agg_y)
_, vals_min = tmin_obs_manager.get_daily_clim_fields_aggregated_and_interpolated_to(
start_year=rconfig.start_year,
end_year=rconfig.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats,
n_agg_x=n_agg_x,
n_agg_y=n_agg_y)
daily_obs = (dates, (vals_min + vals_max) * 0.5)
elif vname == "PR":
daily_obs = pcp_obs_manager.get_daily_clim_fields_aggregated_and_interpolated_to(
start_year=rconfig.start_year,
end_year=rconfig.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats,
n_agg_x=n_agg_x,
n_agg_y=n_agg_y)
else:
raise Exception("Unknown variable: {}".format(vname))
season_to_obs_data = OrderedDict()
for season, months in season_to_months.items():
season_to_obs_data[season] = np.mean(
[f for d, f in zip(*daily_obs) if d.month in months], axis=0)
return season_to_obs_data
def main():
season_to_months = DEFAULT_SEASON_TO_MONTHS
r_config = RunConfig(
data_path=
"/RESCUE/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl.hdf5",
start_year=1980,
end_year=2010,
label="CRCM5-L")
bmp_info = analysis.get_basemap_info_from_hdf(file_path=r_config.data_path)
# Validate temperature and precip
model_vars = ["TT", "PR"]
# Get Anusplin data managers
obs_path = "/home/huziy/skynet3_rech1/anusplin_links"
pcp_obs_manager = AnuSplinManager(variable="pcp", folder_path=obs_path)
tmax_obs_manager = AnuSplinManager(variable="stmx", folder_path=obs_path)
tmin_obs_manager = AnuSplinManager(variable="stmn", folder_path=obs_path)
vname_to_obs_data = {}
for vname in model_vars:
if vname == "TT":
dates, vals_max = tmax_obs_manager.get_daily_clim_fields_interpolated_to(
start_year=r_config.start_year,
end_year=r_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats)
_, vals_min = tmin_obs_manager.get_daily_clim_fields_interpolated_to(
start_year=r_config.start_year,
end_year=r_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats)
daily_obs = (dates, (vals_min + vals_max) * 0.5)
elif vname == "PR":
daily_obs = pcp_obs_manager.get_daily_clim_fields_interpolated_to(
start_year=r_config.start_year,
end_year=r_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats)
else:
raise Exception("Unknown variable: {}".format(vname))
season_to_obs_data = OrderedDict()
for season, months in season_to_months.items():
season_to_obs_data[season] = np.mean(
[f for d, f in zip(*daily_obs) if d.month in months], axis=0)
vname_to_obs_data[vname] = season_to_obs_data
plot_all_vars_in_one_fig = True
fig = None
gs = None
row_axes = None
ncols = None
if plot_all_vars_in_one_fig:
plot_utils.apply_plot_params(font_size=12,
width_pt=None,
width_cm=25,
height_cm=12)
fig = plt.figure()
ncols = len(season_to_months) + 1
gs = GridSpec(len(model_vars),
ncols,
width_ratios=(ncols - 1) * [
1.,
] + [
0.05,
])
else:
plot_utils.apply_plot_params(font_size=12,
width_pt=None,
width_cm=25,
height_cm=25)
row = 0
for mname in model_vars:
if plot_all_vars_in_one_fig:
row_axes = [fig.add_subplot(gs[row, col]) for col in range(ncols)]
compare_vars(vname_model=mname,
vname_to_obs=vname_to_obs_data,
r_config=r_config,
season_to_months=season_to_months,
bmp_info_agg=bmp_info,
axes_list=row_axes)
row += 1
# Save the figure if necessary
if plot_all_vars_in_one_fig:
fig_path = img_folder.joinpath("{}.png".format("_".join(model_vars)))
with fig_path.open("wb") as figfile:
fig.savefig(figfile, format="png", bbox_inches="tight")
plt.close(fig)
def plot_corr_fields_and_std(vname="TT",
season_to_months=None,
sim_config=None):
"""
:param vname:
:param season_to_months:
:param sim_config:
"""
bmp_info = analysis.get_basemap_info_from_hdf(
file_path=sim_config.data_path)
# Get Anusplin data managers
obs_path = "/home/huziy/skynet3_rech1/anusplin_links"
pcp_obs_manager = AnuSplinManager(variable="pcp", folder_path=obs_path)
tmax_obs_manager = AnuSplinManager(variable="stmx", folder_path=obs_path)
tmin_obs_manager = AnuSplinManager(variable="stmn", folder_path=obs_path)
season_to_corr = OrderedDict()
season_to_area_mean_corr = OrderedDict()
season_to_area_mean_std_diff = OrderedDict()
season_to_area_mean_obs = OrderedDict()
season_to_area_mean_model = OrderedDict()
season_to_std_diff = OrderedDict()
season_to_years = OrderedDict()
# Convert modelled precip from M/s to mm/day
if vname == "PR":
model_convert_coef = 24 * 3600 * 1000
else:
model_convert_coef = 1
years = None
for season, months in season_to_months.items():
# Obs
if vname == "TT":
years, vals_max = tmax_obs_manager.get_seasonal_fields_interpolated_to(
start_year=sim_config.start_year,
end_year=sim_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats,
months=months)
_, vals_min = tmin_obs_manager.get_seasonal_fields_interpolated_to(
start_year=sim_config.start_year,
end_year=sim_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats,
months=months)
seasonal_obs = (years, (vals_min + vals_max) * 0.5)
elif vname == "PR":
seasonal_obs = pcp_obs_manager.get_seasonal_fields_interpolated_to(
start_year=sim_config.start_year,
end_year=sim_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats,
months=months)
years = seasonal_obs[0]
else:
raise Exception("Unknown variable: {}".format(vname))
season_to_years[season] = years
# Model
seasonal_model = analysis.get_mean_2d_fields_for_months(
path=sim_config.data_path,
var_name=vname,
level=0,
months=months,
start_year=sim_config.start_year,
end_year=sim_config.end_year)
seasonal_model *= model_convert_coef
# 2d fields
season_to_corr[season] = stat_helpers.calculate_correlation_nd(
seasonal_obs[1], seasonal_model)
season_to_corr[season] = np.ma.masked_where(
seasonal_obs[1][0, :, :].mask, season_to_corr[season])
i_arr, j_arr = np.where(~seasonal_obs[1][0, :, :].mask)
season_to_std_diff[season] = np.ma.masked_all_like(
seasonal_obs[1][0, :, :])
season_to_std_diff[season][
i_arr,
j_arr] = (seasonal_model[:, i_arr, j_arr].std(axis=0) -
seasonal_obs[1][:, i_arr, j_arr].std(axis=0)
) / seasonal_obs[1][:, i_arr, j_arr].std(axis=0) * 100
# area averages
season_to_area_mean_obs[season] = seasonal_obs[1][:, i_arr,
j_arr].mean(axis=1)
season_to_area_mean_model[season] = seasonal_model[:, i_arr,
j_arr].mean(axis=1)
season_to_area_mean_corr[season] = np.corrcoef(
season_to_area_mean_obs[season],
season_to_area_mean_model[season])[0, 1]
season_to_area_mean_std_diff[season] = (
season_to_area_mean_model[season].std() -
season_to_area_mean_obs[season].std()
) / season_to_area_mean_obs[season].std() * 100
# plt.figure()
# plt.plot(years, seasonal_obs[1][:, i_arr, j_arr].mean(axis=1), label="obs")
# plt.plot(years, seasonal_model[:, i_arr, j_arr].mean(axis=1), label="model")
# plt.legend()
#
#
# plt.figure()
# im = plt.pcolormesh(season_to_corr[season].T)
# plt.colorbar(im)
# plt.show()
# plotting
plot_utils.apply_plot_params(font_size=8, width_cm=23, height_cm=15)
nrows = 3
gs = gridspec.GridSpec(nrows=nrows,
ncols=len(season_to_months) + 1,
width_ratios=[
1,
] * len(season_to_months) + [
0.05,
])
fig = plt.figure()
xx, yy = bmp_info.get_proj_xy()
clevs_corr = np.arange(-1, 1.1, 0.1)
clevs_std_diff = np.arange(-100, 110, 10)
cmap = "seismic"
cmap_std = "seismic"
cs_corr = None
cs_std = None
for col, season in enumerate(season_to_months):
# Correlation fields
row = 0
ax = fig.add_subplot(gs[row, col])
ax.set_title(season)
if col == 0:
pass
# ax.set_ylabel("Correlation")
cs_corr = bmp_info.basemap.contourf(xx,
yy,
season_to_corr[season],
levels=clevs_corr,
ax=ax,
cmap=cmap)
bmp_info.basemap.drawcoastlines(ax=ax)
row += 1
ax = fig.add_subplot(gs[row, col])
if col == 0:
pass
# ax.set_ylabel(r"$\left( \sigma_{\rm model} - \sigma_{\rm obs.}\right)/\sigma_{\rm obs.} \cdot 100\%$")
cs_std = bmp_info.basemap.contourf(xx,
yy,
season_to_std_diff[season],
levels=clevs_std_diff,
ax=ax,
cmap=cmap_std,
extend="both")
bmp_info.basemap.drawcoastlines(ax=ax)
# area average
row += 1
ax = fig.add_subplot(gs[row, col])
if col == 0:
ax.set_ylabel(varname_to_ts_label[vname])
ax.plot(season_to_years[season],
season_to_area_mean_obs[season],
"k",
label="Obs.")
ax.plot(season_to_years[season],
season_to_area_mean_model[season],
"r",
label="Mod.")
ax.set_title(r"$r=" +
"{:.2f}, ".format(season_to_area_mean_corr[season]) +
r" \varepsilon_{\sigma} = " +
"{:.1f}".format(season_to_area_mean_std_diff[season]) +
r" \% $")
plt.setp(ax.xaxis.get_majorticklabels(), rotation=70)
assert isinstance(ax, Axes)
ax.xaxis.set_minor_locator(MultipleLocator())
ax.grid()
if col == 0:
ax.legend(loc="upper left")
# add colorbars
col = len(season_to_months)
row = 0
ax = fig.add_subplot(gs[row, col])
plt.colorbar(cs_corr, cax=ax)
row += 1
ax = fig.add_subplot(gs[row, col])
plt.colorbar(cs_std, cax=ax)
from crcm5.analyse_hdf import common_plot_params
fig.tight_layout()
fig.savefig(os.path.join(
img_folder,
"{}_{}-{}_corr_std.png".format(vname, sim_config.start_year,
sim_config.end_year)),
bbox_inches="tight",
dpi=common_plot_params.FIG_SAVE_DPI)
plt.close(fig)
def draw_model_comparison(model_points=None, stations=None, sim_name_to_file_name=None, hdf_folder=None,
start_year=None, end_year=None, cell_manager=None, stfl_name="STFA",
drainage_area_reldiff_min=0.1, plot_upstream_area_averaged=True,
sim_name_to_color=None):
"""
:param model_points: list of model point objects
:param stations: list of stations corresponding to the list of model points
:param cell_manager: is a CellManager instance which can be provided for better performance if necessary
len(model_points) == len(stations) if stations is not None.
if stations is None - then no measured streamflow will be plotted
"""
assert model_points is None or stations is None or len(stations) == len(model_points)
label_list = list(sim_name_to_file_name.keys()) # Needed to keep the order the same for all subplots
path0 = os.path.join(hdf_folder, list(sim_name_to_file_name.items())[0][1])
flow_directions = analysis.get_array_from_file(path=path0, var_name="flow_direction")
lake_fraction = analysis.get_array_from_file(path=path0, var_name="lake_fraction")
# mask lake fraction in the ocean
lake_fraction = np.ma.masked_where((flow_directions <= 0) | (flow_directions > 128), lake_fraction)
accumulation_area_km2 = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_ACCUMULATION_AREA_NAME)
area_m2 = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_CELL_AREA_NAME_M2)
# Try to read cell areas im meters if it is not Ok then try in km2
if area_m2 is not None:
cell_area_km2 = area_m2 * 1.0e-6
else:
cell_area_km2 = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_CELL_AREA_NAME_KM2)
print("cell area ranges from {} to {}".format(cell_area_km2.min(), cell_area_km2.max()))
# print "plotting from {0}".format(path0)
# plt.pcolormesh(lake_fraction.transpose())
# plt.colorbar()
# plt.show()
# exit()
file_scores = open("scores_{0}_{1}-{2}.txt".format("_".join(label_list), start_year, end_year), "w")
file_correlations = open("corr_{0}_{1}-{2}.txt".format("_".join(label_list), start_year, end_year), "w")
file_annual_discharge = open("flow_{0}_{1}-{2}.txt".format("_".join(label_list), start_year, end_year), "w")
text_files = [file_scores, file_correlations, file_annual_discharge]
# write the following columns to the scores file
header_format = "{0:10s}\t{1:10s}\t{2:10s}\t" + "\t".join(["{" + str(i + 3) + ":10s}"
for i in range(len(sim_name_to_file_name))])
line_format = "{0:10s}\t{1:10.1f}\t{2:10.1f}\t" + "\t".join(["{" + str(i + 3) + ":10.1f}"
for i in range(len(sim_name_to_file_name))])
header_ns = ("ID", "DAo", "DAm",) + tuple(["NS({0})".format(key) for key in sim_name_to_file_name])
file_scores.write(header_format.format(*header_ns) + "\n")
header_qyear = ("ID", "DAo", "DAm",) + tuple(["Qyear({0})".format(key) for key in label_list]) + \
("Qyear(obs)",)
header_format_qyear = header_format + "\t{" + str(len(label_list) + 3) + ":10s}"
file_annual_discharge.write(header_format_qyear.format(*header_qyear) + "\n")
lons2d, lats2d, basemap = analysis.get_basemap_from_hdf(file_path=path0)
# Create a cell manager if it is not provided
if cell_manager is None:
cell_manager = CellManager(flow_directions, accumulation_area_km2=accumulation_area_km2,
lons2d=lons2d, lats2d=lats2d)
if stations is not None:
# Get the list of the corresponding model points
station_to_modelpoint = cell_manager.get_model_points_for_stations(
station_list=stations,
lake_fraction=lake_fraction,
drainaige_area_reldiff_limit=drainage_area_reldiff_min)
station_list = list(station_to_modelpoint.keys())
station_list.sort(key=lambda st1: st1.latitude, reverse=True)
mp_list = [station_to_modelpoint[st] for st in station_list]
else:
mp_list = model_points
station_list = None
# sort so that the northernmost stations appear uppermost
mp_list.sort(key=lambda mpt: mpt.latitude, reverse=True)
# set ids to the model points so they can be distinguished easier
model_point.set_model_point_ids(mp_list)
# ###Uncomment the lines below for the validation plot in paper 2
# brewer2mpl.get_map args: set name set type number of colors
# bmap = brewer2mpl.get_map("Set1", "qualitative", 9)
# Change the default colors
# mpl.rcParams["axes.color_cycle"] = bmap.mpl_colors
# For the streamflow only plot
ncols = 3
nrows = max(len(mp_list) // ncols, 1)
if ncols * nrows < len(mp_list):
nrows += 1
figure_stfl = plt.figure(figsize=(4 * ncols, 3 * nrows))
gs_stfl = gridspec.GridSpec(nrows=nrows, ncols=ncols)
# a flag which signifies if a legend should be added to the plot, it is needed so we ahve only one legend per plot
legend_added = False
ax_stfl = None
all_years = [y for y in range(start_year, end_year + 1)]
if station_list is not None:
processed_stations = station_list
else:
processed_stations = [None] * len(mp_list)
processed_model_points = mp_list
plot_point_positions_with_upstream_areas(processed_stations, processed_model_points, basemap,
cell_manager, lake_fraction_field=lake_fraction)
if plot_upstream_area_averaged:
# create obs data managers
anusplin_tmin = AnuSplinManager(variable="stmn")
anusplin_tmax = AnuSplinManager(variable="stmx")
anusplin_pcp = AnuSplinManager(variable="pcp")
daily_dates, obs_tmin_fields = anusplin_tmin.get_daily_clim_fields_interpolated_to(
start_year=start_year, end_year=end_year,
lons_target=lons2d, lats_target=lats2d)
_, obs_tmax_fields = anusplin_tmax.get_daily_clim_fields_interpolated_to(
start_year=start_year, end_year=end_year,
lons_target=lons2d, lats_target=lats2d)
_, obs_pcp_fields = anusplin_pcp.get_daily_clim_fields_interpolated_to(
start_year=start_year, end_year=end_year,
lons_target=lons2d, lats_target=lats2d)
swe_path = "/skynet3_rech1/huziy/swe_ross_brown/swe.nc4"
if not os.path.isfile(os.path.realpath(swe_path)):
raise IOError("SWE-obs file {} does not exist".format(swe_path))
swe_manager = SweDataManager(path=swe_path, var_name="SWE")
obs_swe_daily_clim = swe_manager.get_daily_climatology(start_year, end_year)
interpolated_obs_swe_clim = swe_manager.interpolate_daily_climatology_to(obs_swe_daily_clim,
lons2d_target=lons2d,
lats2d_target=lats2d)
values_obs = None
for i, the_model_point in enumerate(mp_list):
ax_stfl = figure_stfl.add_subplot(gs_stfl[i // ncols, i % ncols], sharex=ax_stfl)
assert isinstance(the_model_point, ModelPoint)
# Check the number of years accessible for the station if the list of stations is given
the_station = None if station_list is None else station_list[i]
if the_station is not None:
assert isinstance(the_station, Station)
year_list = the_station.get_list_of_complete_years()
year_list = list(filter(lambda yi: start_year <= yi <= end_year, year_list))
if len(year_list) < 1:
continue
else:
year_list = all_years
fig = plt.figure(figsize=(12, 15))
gs = gridspec.GridSpec(4, 4, wspace=1)
# plot station position
ax = fig.add_subplot(gs[3, 0:2])
upstream_mask = _plot_station_position(ax, the_station, basemap, cell_manager, the_model_point)
# plot streamflows
ax = fig.add_subplot(gs[0:2, 0:2])
dates = None
model_daily_temp_clim = {}
model_daily_precip_clim = {}
model_daily_clim_surf_runoff = {}
model_daily_clim_subsurf_runoff = {}
model_daily_clim_swe = {}
# get model data for the list of years
simlabel_to_vals = {}
for label in label_list:
fname = sim_name_to_file_name[label]
if hdf_folder is None:
fpath = fname
else:
fpath = os.path.join(hdf_folder, fname)
if plot_upstream_area_averaged:
# read temperature data and calculate daily climatologic fileds
_, model_daily_temp_clim[label] = analysis.get_daily_climatology(
path_to_hdf_file=fpath, var_name="TT", level=0, start_year=start_year, end_year=end_year)
# read modelled precip and calculate daily climatologic fields
_, model_daily_precip_clim[label] = analysis.get_daily_climatology(
path_to_hdf_file=fpath, var_name="PR", level=0, start_year=start_year, end_year=end_year)
# read modelled surface runoff and calculate daily climatologic fields
_, model_daily_clim_surf_runoff[label] = analysis.get_daily_climatology(
path_to_hdf_file=fpath, var_name="TRAF", level=0, start_year=start_year, end_year=end_year)
# read modelled subsurface runoff and calculate daily climatologic fields
_, model_daily_clim_subsurf_runoff[label] = analysis.get_daily_climatology(
path_to_hdf_file=fpath, var_name="TDRA", level=0, start_year=start_year, end_year=end_year)
# read modelled swe and calculate daily climatologic fields
_, model_daily_clim_swe[label] = analysis.get_daily_climatology(
path_to_hdf_file=fpath, var_name="I5", level=0, start_year=start_year, end_year=end_year)
dates, values_model = analysis.get_daily_climatology_for_a_point(path=fpath,
var_name=stfl_name,
years_of_interest=year_list,
i_index=the_model_point.ix,
j_index=the_model_point.jy)
ax.plot(dates, values_model, label=label, lw=2)
if sim_name_to_color is None:
ax_stfl.plot(dates, values_model, label=label, lw=2)
else:
ax_stfl.plot(dates, values_model, sim_name_to_color[label], label=label, lw=2)
print(20 * "!!!")
print("{} -> {}".format(label, sim_name_to_color[label]))
print(20 * "!!!")
simlabel_to_vals[label] = values_model
if the_station is not None:
assert isinstance(the_station, Station)
dates, values_obs = the_station.get_daily_climatology_for_complete_years_with_pandas(stamp_dates=dates,
years=year_list)
# To keep the colors consistent for all the variables, the obs Should be plotted last
ax.plot(dates, values_obs, label="Obs.", lw=2)
# no ticklabels for streamflow plot
plt.setp(ax.get_xticklabels(), visible=False)
if sim_name_to_color is None:
ax_stfl.plot(dates, values_obs, label="Obs.", lw=2)
else:
ax_stfl.plot(dates, values_obs, label="Obs.", lw=2, color=sim_name_to_color["Obs."])
# Print excesss from streamflow validation
for label, values_model in simlabel_to_vals.items():
calclulate_spring_peak_err(dates, values_obs, values_model,
st_id="{}: {}".format(label, the_station.id),
da_mod=the_model_point.accumulation_area,
da_obs=the_station.drainage_km2)
ax.set_ylabel(r"Streamflow: ${\rm m^3/s}$")
assert isinstance(ax, Axes)
assert isinstance(fig, Figure)
upstream_area_km2 = np.sum(cell_area_km2[upstream_mask == 1])
# Put some information about the point
if the_station is not None:
lf_upstream = lake_fraction[upstream_mask == 1]
point_info = "{0}".format(the_station.id)
write_annual_flows_to_txt(label_list, simlabel_to_vals, values_obs, file_annual_discharge,
station_id=the_station.id,
da_obs=the_station.drainage_km2, da_mod=the_model_point.accumulation_area)
else:
point_info = "{0}".format(the_model_point.point_id)
ax.annotate(point_info, (0.8, 0.8), xycoords="axes fraction",
bbox=dict(facecolor="white", alpha=0.5),
va="top", ha="right")
ax.legend(loc=(0.0, 1.05), borderaxespad=0, ncol=3)
ax.xaxis.set_minor_formatter(FuncFormatter(lambda x, pos: num2date(x).strftime("%b")[0]))
ax.xaxis.set_minor_locator(MonthLocator(bymonthday=15))
ax.xaxis.set_major_locator(MonthLocator())
ax.grid()
streamflow_axes = ax # save streamflow axes for later use
if not legend_added:
ax_stfl.legend(loc="lower left", bbox_to_anchor=(0, 1.15), borderaxespad=0, ncol=3)
ax_stfl.xaxis.set_minor_formatter(FuncFormatter(lambda x, pos: num2date(x).strftime("%b")[0]))
ax_stfl.xaxis.set_minor_locator(MonthLocator(bymonthday=15))
ax_stfl.xaxis.set_major_locator(MonthLocator())
ax_stfl.set_ylabel(r"Streamflow ${\rm m^3/s}$")
legend_added = True
plt.setp(ax_stfl.get_xmajorticklabels(), visible=False)
ax_stfl.yaxis.set_major_locator(MaxNLocator(nbins=5))
sfmt = ScalarFormatter(useMathText=True)
sfmt.set_powerlimits((-2, 2))
ax_stfl.yaxis.set_major_formatter(sfmt)
ax_stfl.grid()
# annotate streamflow-only panel plot
ax_stfl.annotate(point_info, (0.05, 0.95), xycoords="axes fraction",
bbox=dict(facecolor="white"),
va="top", ha="left")
if plot_upstream_area_averaged:
# plot temperature comparisons (tmod - daily with anusplin tmin and tmax)
ax = fig.add_subplot(gs[3, 2:], sharex=streamflow_axes)
_validate_temperature_with_anusplin(ax, the_model_point, cell_area_km2=cell_area_km2,
upstream_mask=upstream_mask,
daily_dates=daily_dates,
obs_tmin_clim_fields=obs_tmin_fields,
obs_tmax_clim_fields=obs_tmax_fields,
model_data_dict=model_daily_temp_clim,
simlabel_list=label_list)
# plot temperature comparisons (tmod - daily with anusplin tmin and tmax)
ax = fig.add_subplot(gs[2, 2:], sharex=streamflow_axes)
_validate_precip_with_anusplin(ax, the_model_point, cell_area_km2=cell_area_km2,
upstream_mask=upstream_mask,
daily_dates=daily_dates,
obs_precip_clim_fields=obs_pcp_fields,
model_data_dict=model_daily_precip_clim,
simlabel_list=label_list)
# plot mean upstream surface runoff
ax = fig.add_subplot(gs[0, 2:], sharex=streamflow_axes)
_plot_upstream_surface_runoff(ax, the_model_point, cell_area_km2=cell_area_km2,
upstream_mask=upstream_mask,
daily_dates=daily_dates,
model_data_dict=model_daily_clim_surf_runoff,
simlabel_list=label_list)
# plot mean upstream subsurface runoff
ax = fig.add_subplot(gs[1, 2:], sharex=streamflow_axes, sharey=ax)
_plot_upstream_subsurface_runoff(ax, the_model_point, cell_area_km2=cell_area_km2,
upstream_mask=upstream_mask,
daily_dates=daily_dates,
model_data_dict=model_daily_clim_subsurf_runoff,
simlabel_list=label_list)
# plot mean upstream swe comparison
ax = fig.add_subplot(gs[2, 0:2], sharex=streamflow_axes)
print("Validating SWE for ", the_station.id, "--" * 20)
_validate_swe_with_ross_brown(ax, the_model_point, cell_area_km2=cell_area_km2,
upstream_mask=upstream_mask,
daily_dates=daily_dates,
model_data_dict=model_daily_clim_swe,
obs_swe_clim_fields=interpolated_obs_swe_clim,
simlabel_list=label_list)
if the_station is not None:
im_name = "comp_point_with_obs_{0}_{1}_{2}.png".format(the_station.id,
the_station.source,
"_".join(label_list))
im_folder_path = os.path.join(images_folder, the_station.source)
else:
im_name = "comp_point_with_obs_{0}_{1}.png".format(the_model_point.point_id,
"_".join(label_list))
im_folder_path = os.path.join(images_folder, "outlets_point_comp")
# create a folder for a given source of observed streamflow if it does not exist yet
if not os.path.isdir(im_folder_path):
os.mkdir(im_folder_path)
im_path = os.path.join(im_folder_path, im_name)
if plot_upstream_area_averaged:
fig.savefig(im_path, dpi=cpp.FIG_SAVE_DPI, bbox_inches="tight", transparent=True)
plt.close(fig)
# return # temporary plot only one point
assert isinstance(figure_stfl, Figure)
figure_stfl.tight_layout()
figure_stfl.savefig(os.path.join(images_folder,
"comp_point_with_obs_{0}.png".format("_".join(label_list))),
bbox_inches="tight", transparent=True, dpi=cpp.FIG_SAVE_DPI)
plt.close(figure_stfl)
# close information text files
for f in text_files:
f.close()
def plot_corr_fields_and_std(vname="TT", season_to_months=None, sim_config=None):
"""
:param vname:
:param season_to_months:
:param sim_config:
"""
bmp_info = analysis.get_basemap_info_from_hdf(file_path=sim_config.data_path)
# Get Anusplin data managers
obs_path = "/home/huziy/skynet3_rech1/anusplin_links"
pcp_obs_manager = AnuSplinManager(variable="pcp", folder_path=obs_path)
tmax_obs_manager = AnuSplinManager(variable="stmx", folder_path=obs_path)
tmin_obs_manager = AnuSplinManager(variable="stmn", folder_path=obs_path)
season_to_corr = OrderedDict()
season_to_area_mean_corr = OrderedDict()
season_to_area_mean_std_diff = OrderedDict()
season_to_area_mean_obs = OrderedDict()
season_to_area_mean_model = OrderedDict()
season_to_std_diff = OrderedDict()
season_to_years = OrderedDict()
# Convert modelled precip from M/s to mm/day
if vname == "PR":
model_convert_coef = 24 * 3600 * 1000
else:
model_convert_coef = 1
years = None
for season, months in season_to_months.items():
# Obs
if vname == "TT":
years, vals_max = tmax_obs_manager.get_seasonal_fields_interpolated_to(start_year=sim_config.start_year,
end_year=sim_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats,
months=months)
_, vals_min = tmin_obs_manager.get_seasonal_fields_interpolated_to(start_year=sim_config.start_year,
end_year=sim_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats, months=months)
seasonal_obs = (years, (vals_min + vals_max) * 0.5)
elif vname == "PR":
seasonal_obs = pcp_obs_manager.get_seasonal_fields_interpolated_to(start_year=sim_config.start_year,
end_year=sim_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats,
months=months)
years = seasonal_obs[0]
else:
raise Exception("Unknown variable: {}".format(vname))
season_to_years[season] = years
# Model
seasonal_model = analysis.get_mean_2d_fields_for_months(path=sim_config.data_path, var_name=vname, level=0,
months=months, start_year=sim_config.start_year, end_year=sim_config.end_year)
seasonal_model *= model_convert_coef
# 2d fields
season_to_corr[season] = stat_helpers.calculate_correlation_nd(seasonal_obs[1], seasonal_model)
season_to_corr[season] = np.ma.masked_where(seasonal_obs[1][0, :, :].mask, season_to_corr[season])
i_arr, j_arr = np.where(~seasonal_obs[1][0, :, :].mask)
season_to_std_diff[season] = np.ma.masked_all_like(seasonal_obs[1][0, :, :])
season_to_std_diff[season][i_arr, j_arr] = (seasonal_model[:, i_arr, j_arr].std(axis=0) - seasonal_obs[1][:, i_arr, j_arr].std(axis=0)) / seasonal_obs[1][:, i_arr, j_arr].std(axis=0) * 100
# area averages
season_to_area_mean_obs[season] = seasonal_obs[1][:, i_arr, j_arr].mean(axis=1)
season_to_area_mean_model[season] = seasonal_model[:, i_arr, j_arr].mean(axis=1)
season_to_area_mean_corr[season] = np.corrcoef(season_to_area_mean_obs[season], season_to_area_mean_model[season])[0, 1]
season_to_area_mean_std_diff[season] = (season_to_area_mean_model[season].std() - season_to_area_mean_obs[season].std()) / season_to_area_mean_obs[season].std() * 100
# plt.figure()
# plt.plot(years, seasonal_obs[1][:, i_arr, j_arr].mean(axis=1), label="obs")
# plt.plot(years, seasonal_model[:, i_arr, j_arr].mean(axis=1), label="model")
# plt.legend()
#
#
# plt.figure()
# im = plt.pcolormesh(season_to_corr[season].T)
# plt.colorbar(im)
# plt.show()
# plotting
plot_utils.apply_plot_params(font_size=8, width_cm=23, height_cm=15)
nrows = 3
gs = gridspec.GridSpec(nrows=nrows, ncols=len(season_to_months) + 1, width_ratios=[1, ] * len(season_to_months) + [0.05, ])
fig = plt.figure()
xx, yy = bmp_info.get_proj_xy()
clevs_corr = np.arange(-1, 1.1, 0.1)
clevs_std_diff = np.arange(-100, 110, 10)
cmap = "seismic"
cmap_std = "seismic"
cs_corr = None
cs_std = None
for col, season in enumerate(season_to_months):
# Correlation fields
row = 0
ax = fig.add_subplot(gs[row, col])
ax.set_title(season)
if col == 0:
pass
# ax.set_ylabel("Correlation")
cs_corr = bmp_info.basemap.contourf(xx, yy, season_to_corr[season], levels=clevs_corr, ax=ax, cmap=cmap)
bmp_info.basemap.drawcoastlines(ax=ax)
row += 1
ax = fig.add_subplot(gs[row, col])
if col == 0:
pass
# ax.set_ylabel(r"$\left( \sigma_{\rm model} - \sigma_{\rm obs.}\right)/\sigma_{\rm obs.} \cdot 100\%$")
cs_std = bmp_info.basemap.contourf(xx, yy, season_to_std_diff[season], levels=clevs_std_diff, ax=ax, cmap=cmap_std, extend="both")
bmp_info.basemap.drawcoastlines(ax=ax)
# area average
row += 1
ax = fig.add_subplot(gs[row, col])
if col == 0:
ax.set_ylabel(varname_to_ts_label[vname])
ax.plot(season_to_years[season], season_to_area_mean_obs[season], "k", label="Obs.")
ax.plot(season_to_years[season], season_to_area_mean_model[season], "r", label="Mod.")
ax.set_title(r"$r=" + "{:.2f}, ".format(season_to_area_mean_corr[season]) + r" \varepsilon_{\sigma} = " + "{:.1f}".format(season_to_area_mean_std_diff[season]) + r" \% $")
plt.setp(ax.xaxis.get_majorticklabels(), rotation=70)
assert isinstance(ax, Axes)
ax.xaxis.set_minor_locator(MultipleLocator())
ax.grid()
if col == 0:
ax.legend(loc="upper left")
# add colorbars
col = len(season_to_months)
row = 0
ax = fig.add_subplot(gs[row, col])
plt.colorbar(cs_corr, cax=ax)
row += 1
ax = fig.add_subplot(gs[row, col])
plt.colorbar(cs_std, cax=ax)
from crcm5.analyse_hdf import common_plot_params
fig.tight_layout()
fig.savefig(os.path.join(img_folder, "{}_{}-{}_corr_std.png".format(vname, sim_config.start_year, sim_config.end_year)), bbox_inches="tight", dpi=common_plot_params.FIG_SAVE_DPI)
plt.close(fig)
def main():
season_to_months = DEFAULT_SEASON_TO_MONTHS
r_config = RunConfig(
data_path="/RESCUE/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl.hdf5",
start_year=1980, end_year=2010, label="CRCM5-L"
)
bmp_info = analysis.get_basemap_info_from_hdf(file_path=r_config.data_path)
# Validate temperature and precip
model_vars = ["TT", "PR"]
# Get Anusplin data managers
obs_path = "/home/huziy/skynet3_rech1/anusplin_links"
pcp_obs_manager = AnuSplinManager(variable="pcp", folder_path=obs_path)
tmax_obs_manager = AnuSplinManager(variable="stmx", folder_path=obs_path)
tmin_obs_manager = AnuSplinManager(variable="stmn", folder_path=obs_path)
vname_to_obs_data = {}
for vname in model_vars:
if vname == "TT":
dates, vals_max = tmax_obs_manager.get_daily_clim_fields_interpolated_to(start_year=r_config.start_year,
end_year=r_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats)
_, vals_min = tmin_obs_manager.get_daily_clim_fields_interpolated_to(start_year=r_config.start_year,
end_year=r_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats)
daily_obs = (dates, (vals_min + vals_max) * 0.5)
elif vname == "PR":
daily_obs = pcp_obs_manager.get_daily_clim_fields_interpolated_to(start_year=r_config.start_year,
end_year=r_config.end_year,
lons_target=bmp_info.lons,
lats_target=bmp_info.lats)
else:
raise Exception("Unknown variable: {}".format(vname))
season_to_obs_data = OrderedDict()
for season, months in season_to_months.items():
season_to_obs_data[season] = np.mean([f for d, f in zip(*daily_obs) if d.month in months], axis=0)
vname_to_obs_data[vname] = season_to_obs_data
plot_all_vars_in_one_fig = True
fig = None
gs = None
row_axes = None
ncols = None
if plot_all_vars_in_one_fig:
plot_utils.apply_plot_params(font_size=12, width_pt=None, width_cm=25, height_cm=12)
fig = plt.figure()
ncols = len(season_to_months) + 1
gs = GridSpec(len(model_vars), ncols, width_ratios=(ncols - 1) * [1., ] + [0.05, ])
else:
plot_utils.apply_plot_params(font_size=12, width_pt=None, width_cm=25, height_cm=25)
row = 0
for mname in model_vars:
if plot_all_vars_in_one_fig:
row_axes = [fig.add_subplot(gs[row, col]) for col in range(ncols)]
compare_vars(vname_model=mname, vname_to_obs=vname_to_obs_data, r_config=r_config,
season_to_months=season_to_months,
bmp_info_agg=bmp_info,
axes_list=row_axes)
row += 1
# Save the figure if necessary
if plot_all_vars_in_one_fig:
fig_path = img_folder.joinpath("{}.png".format("_".join(model_vars)))
with fig_path.open("wb") as figfile:
fig.savefig(figfile, format="png", bbox_inches="tight")
plt.close(fig)
def do_4_seasons(start_year=1980, end_year=2010):
# Creates one file per simulation containing biases for 4 seasons
season_to_months = {
"Winter": [12, 1, 2],
"Spring": list(range(3, 6)),
# "Summer": list(range(6, 9)),
# "Fall": list(range(9, 11))
}
season_to_plot_indices = {
"Winter": (0, 0),
"Spring": (0, 1),
"Summer": (1, 0),
"Fall": (1, 1)
}
simlabel_to_path = {
# "CRCM5-R-CanESM2-current": "/skynet3_rech1/huziy/hdf_store/cc-canesm2-driven/quebec_0.1_crcm5-r-cc-canesm2-1980-2010.hdf5",
# "CRCM5-R": "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-r.hdf5",
"CRCM5-NL": "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-r.hdf5",
"CRCM5-L1":
"/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r.hdf5",
# "CRCM5-HCD-RL-INTFL-ECOCLIMAP": "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_spinup_ecoclimap.hdf",
# "CRCM5-HCD-RL-INTFL-ECOCLIMAP-ERA075": "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_spinup_ecoclimap_era075.hdf"
# "CRCM5-L-CanESM2": "/RESCUE/skynet3_rech1/huziy/hdf_store/cc-canesm2-driven/quebec_0.1_crcm5-hcd-rl-cc-canesm2-1980-2010.hdf5"
}
print("Period of interest: {0}-{1}".format(start_year, end_year))
lake_fraction = analysis.get_array_from_file(
list(simlabel_to_path.items())[-1][1],
var_name=infovar.HDF_LAKE_FRACTION_NAME)
pcp_obs_manager = AnuSplinManager(variable="pcp")
tmax_obs_manager = AnuSplinManager(variable="stmx")
tmin_obs_manager = AnuSplinManager(variable="stmn")
tmax_obs_manager = None
tmin_obs_manager = None
swe_obs_manager = SweDataManager(var_name="SWE")
station_ids = ["104001", "093806", "093801", "081002", "081007", "080718"]
for simlabel, path in simlabel_to_path.items():
# Validate precipitations
validate_precip(model_file=path,
obs_manager=pcp_obs_manager,
season_to_months=season_to_months,
simlabel=simlabel,
season_to_plot_indices=season_to_plot_indices,
start_year=start_year,
end_year=end_year,
station_ids_list=station_ids)
#
# # Validate daily maximum temperature
validate_temperature(model_file=path,
obs_manager=tmax_obs_manager,
season_to_months=season_to_months,
simlabel=simlabel,
season_to_plot_indices=season_to_plot_indices,
start_year=start_year,
end_year=end_year,
model_var_name="TT_max")
validate_temperature(model_file=path,
obs_manager=tmin_obs_manager,
season_to_months=season_to_months,
simlabel=simlabel,
season_to_plot_indices=season_to_plot_indices,
start_year=start_year,
end_year=end_year,
model_var_name="TT_min")
# validate swe
validate_swe(model_file=path,
obs_manager=swe_obs_manager,
season_to_months=season_to_months,
simlabel=simlabel,
season_to_plot_indices=season_to_plot_indices,
start_year=start_year,
end_year=end_year,
lake_fraction=lake_fraction,
station_ids_list=station_ids)
def draw_model_comparison(model_points=None, stations=None, sim_name_to_file_name=None, hdf_folder=None,
start_year=None, end_year=None, cell_manager=None,
plot_upstream_averages=True):
"""
:param model_points: list of model point objects
:param stations: list of stations corresponding to the list of model points
:param cell_manager: is a CellManager instance which can be provided for better performance if necessary
len(model_points) == len(stations) if stations is not None.
if stations is None - then no measured streamflow will be plotted
"""
assert model_points is None or stations is None or len(stations) == len(model_points)
path0 = os.path.join(hdf_folder, list(sim_name_to_file_name.items())[0][1])
flow_directions = analysis.get_array_from_file(path=path0, var_name="flow_direction")
lake_fraction = analysis.get_array_from_file(path=path0, var_name="lake_fraction")
accumulation_area_km2 = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_ACCUMULATION_AREA_NAME)
cell_area_km2 = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_CELL_AREA_NAME_M2)
# print "plotting from {0}".format(path0)
# plt.pcolormesh(lake_fraction.transpose())
# plt.colorbar()
# plt.show()
# exit()
file_scores = open(
"scores_{0}_{1}-{2}.txt".format("_".join(list(sim_name_to_file_name.keys())), start_year, end_year),
"w")
# write the following columns to the scores file
header_format = "{0:10s}\t{1:10s}\t{2:10s}\t" + "\t".join(["{" + str(i + 3) + ":10s}"
for i in range(len(sim_name_to_file_name))])
line_format = "{0:10s}\t{1:10.1f}\t{1:10.1f}\t" + "\t".join(["{" + str(i + 3) + ":10.1f}"
for i in range(len(sim_name_to_file_name))])
header = ("ID", "DAo", "DAm",) + tuple(["NS({0})".format(key) for key in sim_name_to_file_name])
file_scores.write(header_format.format(*header) + "\n")
lons2d, lats2d, basemap = analysis.get_basemap_from_hdf(file_path=path0)
# Create a cell manager if it is not provided
if cell_manager is None:
cell_manager = CellManager(flow_directions, accumulation_area_km2=accumulation_area_km2,
lons2d=lons2d, lats2d=lats2d)
if stations is not None:
# Get the list of the corresponding model points
station_to_modelpoint_list = cell_manager.get_lake_model_points_for_stations(station_list=stations,
lake_fraction=lake_fraction,
nneighbours=1)
station_list = list(station_to_modelpoint_list.keys())
station_list.sort(key=lambda st1: st1.latitude, reverse=True)
processed_stations = station_list
else:
mp_list = model_points
station_list = None
# sort so that the northernmost stations appear uppermost
mp_list.sort(key=lambda mpt: mpt.latitude, reverse=True)
# set ids to the model points so they can be distinguished easier
model_point.set_model_point_ids(mp_list)
processed_stations = mp_list
station_to_modelpoint_list = {}
# brewer2mpl.get_map args: set name set type number of colors
bmap = brewer2mpl.get_map("Set1", "qualitative", 9)
# Change the default colors
mpl.rcParams["axes.color_cycle"] = bmap.mpl_colors
# For the streamflow only plot
ncols = 3
nrows = max(len(station_to_modelpoint_list) // ncols, 1)
if ncols * nrows < len(station_to_modelpoint_list):
nrows += 1
figure_panel = plt.figure()
gs_panel = gridspec.GridSpec(nrows=nrows + 1, ncols=ncols)
# a flag which signifies if a legend should be added to the plot, it is needed so we ahve only one legend per plot
legend_added = False
label_list = list(sim_name_to_file_name.keys()) # Needed to keep the order the same for all subplots
all_years = [y for y in range(start_year, end_year + 1)]
# processed_model_points = mp_list
# plot_point_positions_with_upstream_areas(processed_stations, processed_model_points, basemap, cell_manager)
if plot_upstream_averages:
# create obs data managers
anusplin_tmin = AnuSplinManager(variable="stmn")
anusplin_tmax = AnuSplinManager(variable="stmx")
anusplin_pcp = AnuSplinManager(variable="pcp")
daily_dates, obs_tmin_fields = anusplin_tmin.get_daily_clim_fields_interpolated_to(
start_year=start_year, end_year=end_year,
lons_target=lons2d, lats_target=lats2d)
_, obs_tmax_fields = anusplin_tmax.get_daily_clim_fields_interpolated_to(
start_year=start_year, end_year=end_year,
lons_target=lons2d, lats_target=lats2d)
_, obs_pcp_fields = anusplin_pcp.get_daily_clim_fields_interpolated_to(
start_year=start_year, end_year=end_year,
lons_target=lons2d, lats_target=lats2d)
swe_manager = SweDataManager(var_name="SWE")
obs_swe_daily_clim = swe_manager.get_daily_climatology(start_year, end_year)
interpolated_obs_swe_clim = swe_manager.interpolate_daily_climatology_to(obs_swe_daily_clim,
lons2d_target=lons2d,
lats2d_target=lats2d)
# clear the folder with images (to avoid confusion of different versions)
_remove_previous_images(processed_stations[0])
ax_panel = figure_panel.add_subplot(gs_panel[0, :])
plot_positions_of_station_list(ax_panel, station_list,
[station_to_modelpoint_list[s][0] for s in station_list],
basemap=basemap, cell_manager=cell_manager, fill_upstream_areas=False)
ax_to_share = None
for i, the_station in enumerate(station_list):
# +1 due to the plot with station positions
ax_panel = figure_panel.add_subplot(gs_panel[1 + i // ncols, i % ncols],
sharex=ax_to_share)
if ax_to_share is None:
ax_to_share = ax_panel
# Check the number of years accessible for the station if the list of stations is given
if the_station is not None:
assert isinstance(the_station, Station)
year_list = the_station.get_list_of_complete_years()
year_list = list(filter(lambda yi: start_year <= yi <= end_year, year_list))
if len(year_list) < 1:
continue
print("Working on station: {0}".format(the_station.id))
else:
year_list = all_years
fig = plt.figure()
gs = gridspec.GridSpec(4, 4, wspace=1)
# plot station position
ax = fig.add_subplot(gs[3, 0:2])
upstream_mask = _plot_station_position(ax, the_station, basemap, cell_manager,
station_to_modelpoint_list[the_station][0])
# plot streamflows
ax = fig.add_subplot(gs[0:2, 0:2])
dates = None
model_daily_temp_clim = {}
model_daily_precip_clim = {}
model_daily_clim_surf_runoff = {}
model_daily_clim_subsurf_runoff = {}
model_daily_clim_swe = {}
model_daily_clim_evap = {}
# get model data for the list of years
for label in label_list:
fname = sim_name_to_file_name[label]
fpath = os.path.join(hdf_folder, fname)
if plot_upstream_averages:
# read temperature data and calculate daily climatologic fileds
dates, model_daily_temp_clim[label] = analysis.get_daily_climatology(
path_to_hdf_file=fpath, var_name="TT", level=1, start_year=start_year, end_year=end_year)
# read modelled precip and calculate daily climatologic fields
_, model_daily_precip_clim[label] = analysis.get_daily_climatology(
path_to_hdf_file=fpath, var_name="PR", level=None, start_year=start_year, end_year=end_year)
# read modelled surface runoff and calculate daily climatologic fields
_, model_daily_clim_surf_runoff[label] = analysis.get_daily_climatology(
path_to_hdf_file=fpath, var_name="TRAF", level=1, start_year=start_year, end_year=end_year)
# read modelled subsurface runoff and calculate daily climatologic fields
_, model_daily_clim_subsurf_runoff[label] = analysis.get_daily_climatology(
path_to_hdf_file=fpath, var_name="TDRA", level=1, start_year=start_year, end_year=end_year)
# read modelled swe and calculate daily climatologic fields
_, model_daily_clim_swe[label] = analysis.get_daily_climatology(
path_to_hdf_file=fpath, var_name="I5", level=None, start_year=start_year, end_year=end_year)
values_model = None
# lake level due to evap/precip
values_model_evp = None
lf_total = 0
for the_model_point in station_to_modelpoint_list[the_station]:
if the_model_point.lake_fraction is None:
mult = 1.0
else:
mult = the_model_point.lake_fraction
lf_total += mult
# Calculate lake depth variation for this simulation, since I forgot to uncomment it in the model
if label.lower() != "crcm5-hcd-r":
assert isinstance(the_model_point, ModelPoint)
_, temp = analysis.get_daily_climatology_for_a_point(path=fpath,
var_name="CLDP",
years_of_interest=year_list,
i_index=the_model_point.ix,
j_index=the_model_point.jy)
if values_model is None:
values_model = mult * np.asarray(temp)
else:
values_model = mult * np.asarray(temp) + values_model
else:
raise NotImplementedError("Cannot handle lake depth for {0}".format(label))
if label.lower() in ["crcm5-hcd-rl", "crcm5-l2"]:
dates, temp = analysis.get_daily_climatology_for_a_point_cldp_due_to_precip_evap(
path=fpath, i_index=the_model_point.ix, j_index=the_model_point.jy,
year_list=year_list, point_label=the_station.id)
if values_model_evp is None:
values_model_evp = mult * np.asarray(temp)
else:
values_model_evp = mult * np.asarray(temp) + values_model_evp
values_model /= float(lf_total)
values_model = values_model - np.mean(values_model)
print("lake level anomaly ranges for {0}:{1:.8g};{2:.8g}".format(label, values_model.min(),
values_model.max()))
ax.plot(dates, values_model, label=label, lw=2)
ax_panel.plot(dates, values_model, label=label, lw=2)
if values_model_evp is not None:
# normalize cldp
values_model_evp /= float(lf_total)
# convert to m/s
values_model_evp /= 1000.0
values_model_evp = values_model_evp - np.mean(values_model_evp)
ax.plot(dates, values_model_evp, label=label + "(P-E)", lw=2)
ax_panel.plot(dates, values_model_evp, label=label + "(P-E)", lw=2)
if the_station is not None:
print(type(dates[0]))
dates, values_obs = the_station.get_daily_climatology_for_complete_years_with_pandas(stamp_dates=dates,
years=year_list)
# To keep the colors consistent for all the variables, the obs Should be plotted last
ax.plot(dates, values_obs - np.mean(values_obs), label="Obs.", lw=2, color="k")
ax_panel.plot(dates, values_obs - np.mean(values_obs), label="Obs.", lw=2, color="k")
# calculate nash sutcliff coefficient and skip if too small
ax.set_ylabel(r"Level variation: (${\rm m}$)")
assert isinstance(ax, Axes)
assert isinstance(fig, Figure)
upstream_area_km2 = np.sum(cell_area_km2[upstream_mask == 1])
# Put some information about the point
if the_station is not None:
point_info = "{0}".format(the_station.id)
else:
point_info = "{0}".format(the_model_point.point_id)
ax.annotate(point_info, (0.9, 0.9), xycoords="axes fraction", bbox=dict(facecolor="white"))
ax_panel.annotate(point_info, (0.96, 0.96), xycoords="axes fraction", bbox=dict(facecolor="white"),
va="top", ha="right")
ax.legend(loc=(0.0, 1.05), borderaxespad=0, ncol=3)
ax.xaxis.set_major_formatter(FuncFormatter(lambda val, pos: num2date(val).strftime("%b")[0]))
# ax.xaxis.set_minor_locator(MonthLocator())
ax.xaxis.set_major_locator(MonthLocator())
ax.grid()
streamflow_axes = ax # save streamflow axes for later use
if not legend_added:
ax_panel.legend(loc=(0.0, 1.1), borderaxespad=0.5, ncol=1)
ax_panel.xaxis.set_minor_formatter(FuncFormatter(lambda val, pos: num2date(val).strftime("%b")[0]))
ax_panel.xaxis.set_minor_locator(MonthLocator(bymonthday=15))
ax_panel.xaxis.set_major_locator(MonthLocator())
ax_panel.xaxis.set_major_formatter(FuncFormatter(lambda val, pos: ""))
ax_panel.set_ylabel(r"Level variation (${\rm m}$)")
legend_added = True
ax_panel.yaxis.set_major_locator(MaxNLocator(nbins=5))
ax_panel.grid()
if plot_upstream_averages:
# plot temperature comparisons (tmod - daily with anusplin tmin and tmax)
ax = fig.add_subplot(gs[3, 2:], sharex=streamflow_axes)
success = _validate_temperature_with_anusplin(ax, the_model_point, cell_area_km2=cell_area_km2,
upstream_mask=upstream_mask,
daily_dates=daily_dates,
obs_tmin_clim_fields=obs_tmin_fields,
obs_tmax_clim_fields=obs_tmax_fields,
model_data_dict=model_daily_temp_clim,
simlabel_list=label_list)
# plot temperature comparisons (tmod - daily with anusplin tmin and tmax)
ax = fig.add_subplot(gs[2, 2:], sharex=streamflow_axes)
_validate_precip_with_anusplin(ax, the_model_point, cell_area_km2=cell_area_km2,
upstream_mask=upstream_mask,
daily_dates=daily_dates,
obs_precip_clim_fields=obs_pcp_fields,
model_data_dict=model_daily_precip_clim,
simlabel_list=label_list)
# plot mean upstream surface runoff
ax = fig.add_subplot(gs[0, 2:], sharex=streamflow_axes)
_plot_upstream_surface_runoff(ax, the_model_point, cell_area_km2=cell_area_km2,
upstream_mask=upstream_mask,
daily_dates=daily_dates,
model_data_dict=model_daily_clim_surf_runoff,
simlabel_list=label_list)
# plot mean upstream subsurface runoff
ax = fig.add_subplot(gs[1, 2:], sharex=streamflow_axes, sharey=ax)
_plot_upstream_subsurface_runoff(ax, the_model_point, cell_area_km2=cell_area_km2,
upstream_mask=upstream_mask,
daily_dates=daily_dates,
model_data_dict=model_daily_clim_subsurf_runoff,
simlabel_list=label_list)
# plot mean upstream swe comparison
ax = fig.add_subplot(gs[2, 0:2], sharex=streamflow_axes)
_validate_swe_with_ross_brown(ax, the_model_point, cell_area_km2=cell_area_km2,
upstream_mask=upstream_mask,
daily_dates=daily_dates,
model_data_dict=model_daily_clim_swe,
obs_swe_clim_fields=interpolated_obs_swe_clim,
simlabel_list=label_list)
if the_station is not None:
im_name = "comp_point_with_obs_{0}_{1}_{2}.pdf".format(the_station.id,
the_station.source,
"_".join(label_list))
im_folder_path = os.path.join(images_folder, the_station.source + "_levels")
else:
im_name = "comp_point_with_obs_{0}_{1}.pdf".format(the_model_point.point_id,
"_".join(label_list))
im_folder_path = os.path.join(images_folder, "outlets_point_comp_levels")
# create a folder for a given source of observed streamflow if it does not exist yet
if not os.path.isdir(im_folder_path):
os.mkdir(im_folder_path)
im_path = os.path.join(im_folder_path, im_name)
if plot_upstream_averages:
fig.savefig(im_path, dpi=cpp.FIG_SAVE_DPI, bbox_inches="tight")
plt.close(fig)
assert isinstance(figure_panel, Figure)
figure_panel.tight_layout()
figure_panel.savefig(
os.path.join(images_folder, "comp_lake-levels_at_point_with_obs_{0}.png".format("_".join(label_list))),
bbox_inches="tight")
plt.close(figure_panel)
file_scores.close()
