def get_dates_of_annual_maxima(self, position_index):
"""
"""
return data_select.get_period_maxima_dates(self._data[:, position_index], self.times,
start_month = 1, end_month = 12, event_duration = timedelta(days = 1)
)
def main():
path = 'data/streamflows/hydrosheds_euler9/aex_discharge_1970_01_01_00_00.nc'
#path = "data/streamflows/hydrosheds_rk4_changed_partiotioning/aex_discharge_1970_01_01_00_00.nc"
#path = 'data/streamflows/na/discharge_1990_01_01_00_00_na.nc'
data = pe_calc.get_station_and_corresponding_model_data(path = path)
delete_not_continuous(data)
plot_utils.apply_plot_params(width_pt = None, height_cm=6, font_size = 9)
high_return_periods = [10, 30]
high_start_month = 3
high_end_month = 7
high_event_duration = timedelta(days = 1)
low_return_periods = [2, 5]
low_start_month = 1
low_end_month = 5
low_event_duration = timedelta(days = 15)
#---------------------------high
high_station_return_levels = {}
high_model_return_levels = {}
station_high_dates = []
model_high_dates = []
station_minima = []
station_maxima = []
model_minima = []
model_maxima = []
high_data = []
labels = []
point_ids = []
for station, model_point in data.iteritems():
if station.id not in selected_station_ids:
continue
# @type model_point ModelPoint
if not model_point.get_timeseries_length():
continue
# @type station Station
if not station.get_timeseries_length():
continue
high_values_station = data_select.get_period_maxima(station.values, station.dates,
start_date = None, end_date = None,
start_month = high_start_month,
end_month = high_end_month,
event_duration = high_event_duration)
vals = np.array(high_values_station.values())
high_data.append(high_values_station.values())
labels.append("Observed")
pars_station = gevfit.optimize_stationary_for_period(vals, high_flow = True)
high_values_model = data_select.get_period_maxima(
model_point.get_values_sorted_by_date(),
model_point.get_sorted_dates(),
start_date = None, end_date = None,
start_month = high_start_month,
end_month = high_end_month,
event_duration = high_event_duration)
high_data.append(high_values_model.values())
labels.append("Modelled")
vals = np.array(high_values_model.values())
point_ids.append(station.id)
point_ids.append(station.id)
pars_model = gevfit.optimize_stationary_for_period(vals, high_flow = True)
for ret_period in high_return_periods:
if not high_station_return_levels.has_key(ret_period):
high_station_return_levels[ret_period] = []
high_model_return_levels[ret_period] = []
high_station_return_levels[ret_period].append(gevfit.get_high_ret_level_stationary(pars_station, ret_period))
high_model_return_levels[ret_period].append(gevfit.get_high_ret_level_stationary(pars_model, ret_period))
#gather dates of the high flow events
the_station_high_dates = data_select.get_period_maxima_dates(
station.values, station.dates,
start_date = None, end_date = None,
start_month = high_start_month,
end_month = high_end_month,
event_duration = high_event_duration)
station_high_dates.extend(the_station_high_dates.values())
the_model_high_dates = data_select.get_period_maxima_dates(
model_point.get_values_sorted_by_date(),
# @type model_point ModelPoint
model_point.get_sorted_dates(),
start_date = None, end_date = None,
start_month = high_start_month,
end_month = high_end_month,
event_duration = high_event_duration)
model_high_dates.extend(the_model_high_dates.values())
##save corresponding maximums for the station and model
current_station_maxima = []
current_model_maxima = []
for year, value in high_values_station.iteritems():
if high_values_model.has_key(year):
station_maxima.append(value)
model_maxima.append(high_values_model[year])
current_station_maxima.append(value)
current_model_maxima.append(high_values_model[year])
#plot scatter for low flow for each station separately
plot_scatter( current_station_maxima, current_model_maxima, "observed (${\\rm m^3/s}$)",
"modelled (${\\rm m^3/s}$)",
"high flow values ({0})".format(station.id), different_shapes_and_colors = False)
plt.savefig('high_values_scatter_{0}.png'.format( station.id ), bbox_inches = 'tight')
print "%s: n(high_values) = %d;" % (station.id, len( current_station_maxima ))
##high flow values
plot_scatter( station_maxima, model_maxima, "observed (${\\rm m^3/s}$)",
"modelled (${\\rm m^3/s}$)",
"high flow values", different_shapes_and_colors = False)
plt.savefig('high_values_scatter.png', bbox_inches = 'tight')
plot_boxplot([station_maxima, model_maxima],
title="High flow amplitude",
labels = ["Observed", "Modelled"], file_name="box_high.png")
plot_boxplot(high_data, labels=labels, file_name="box_high_all_sep.png", point_ids=point_ids)
#---------------------------low
low_station_return_levels = {}
low_model_return_levels = {}
station_low_dates = []
model_low_dates = []
low_data = []
for station, model_point in data.iteritems():
if station.id not in selected_station_ids:
continue
#print "retained timeseries lenght of the station %s is %d " % (station.id, station.get_timeseries_length())
# @type model_point ModelPoint
if not model_point.get_timeseries_length():
continue
# @type station Station
if not station.get_timeseries_length():
continue
# print 'station min: %f, max: %f' % (np.min(station.values), np.max(station.values))
# print 'model min: %f, max: %f' % (
# np.min(model_point.get_values_sorted_by_date()),
# np.max(model_point.get_values_sorted_by_date())
# )
low_values_station = data_select.get_period_minima(station.values, station.dates,
start_date = None, end_date = None,
start_month = low_start_month,
end_month = low_end_month,
event_duration = low_event_duration)
low_data.append(low_values_station.values())
vals = np.array(low_values_station.values())
pars_station = gevfit.optimize_stationary_for_period(vals, high_flow = False)
low_values_model = data_select.get_period_minima(
model_point.get_values_sorted_by_date(),
model_point.get_sorted_dates(),
start_date = None, end_date = None,
start_month = low_start_month,
end_month = low_end_month,
event_duration = low_event_duration)
vals = np.array(low_values_model.values())
low_data.append(low_values_model.values())
pars_model = gevfit.optimize_stationary_for_period(vals, high_flow = False)
#gather dates of the low flow events
the_station_low_dates = data_select.get_period_minima_dates(
station.values, station.dates,
start_date = None, end_date = None,
start_month = low_start_month,
end_month = low_end_month,
event_duration = low_event_duration)
station_low_dates.extend(the_station_low_dates.values())
the_model_low_dates = data_select.get_period_minima_dates(
model_point.get_values_sorted_by_date(),
model_point.get_sorted_dates(),
start_date = None, end_date = None,
start_month = low_start_month,
end_month = low_end_month,
event_duration = low_event_duration)
model_low_dates.extend(the_model_low_dates.values())
for ret_period in low_return_periods:
if not low_station_return_levels.has_key(ret_period):
low_station_return_levels[ret_period] = []
low_model_return_levels[ret_period] = []
low_station_return_levels[ret_period].append(gevfit.get_low_ret_level_stationary(pars_station, ret_period))
low_model_return_levels[ret_period].append(gevfit.get_low_ret_level_stationary(pars_model, ret_period))
##save corresponding maxima for the station and model
current_station_minima = []
current_model_minima = []
for year, value in low_values_station.iteritems():
if low_values_model.has_key(year):
current_station_minima.append(value)
current_model_minima.append(low_values_model[year])
station_minima.append(value)
model_minima.append(low_values_model[year])
##plot temporal dependency
ts = sorted(low_values_station.keys())
values_at_ts = []
for the_t in ts:
values_at_ts.append(low_values_station[the_t])
plt.figure()
plt.plot(ts, values_at_ts)
plt.ylabel('low flow')
plt.xlabel('time')
plt.title(station.id)
plt.savefig('lows_in_time_%s.png' % station.id)
#plot scatter for low flow for each station separately
plot_scatter( current_station_minima, current_model_minima, "observed (${\\rm m^3/s}$)",
"modelled (${\\rm m^3/s}$)",
"low flow values ({0})".format(station.id), different_shapes_and_colors = False)
plt.savefig('low_values_scatter_{0}.png'.format( station.id ), bbox_inches = 'tight')
print "%s: n(low_values) = %d;" % (station.id, len( current_station_minima ))
#draw return levels
fig = plt.figure()
gs = gridspec.GridSpec(1,2)
ax = fig.add_subplot(gs[0,0])
plot_scatter(high_station_return_levels,
high_model_return_levels,
xlabel="Observed return levels",
ylabel="Modelled return levels", new_figure=False,
title="(a) High flow"
)
ax.xaxis.set_major_formatter(FuncFormatter(hide_even_pos_ax_labels))
fig.add_subplot(gs[0,1])
plot_scatter(low_station_return_levels,
low_model_return_levels,
xlabel="Observed return levels",
ylabel="Modelled return levels",
title="(b) Low flow",
new_figure=False)
plt.tight_layout()
plt.savefig("rl_scatter.png")
plot_scatter( station_minima, model_minima, "observed", "modelled",
"low flow values", different_shapes_and_colors = False)
plt.savefig('low_values_scatter.png', bbox_inches = 'tight')
plot_boxplot([station_minima, model_minima],
title="Low flow amplitude",
labels = ["Observed", "Modelled"], file_name="box_low.png")
plot_boxplot(low_data, labels=labels, file_name="box_low_all_sep.png", point_ids= point_ids)
#plot dates of the high and low flow occurences
#before uncommenting figure out why the x and y arrays are of different sizes
# plot_dates_scatter(model_high_dates, station_high_dates, model_low_dates, station_low_dates)
# plt.savefig('occurences_scatter.png')
# plt.show()
pass