def corrected_month_average(corrected: pd.DataFrame, simulated: pd.DataFrame, observed: pd.DataFrame,
merged_sim_obs: pd.DataFrame = False, merged_cor_obs: pd.DataFrame = False,
titles: dict = None, outformat: str = 'plotly') -> go.Figure or str:
"""
Calculates and plots the monthly average streamflow. This function uses
hydrostats.data.merge_data on the 3 inputs. If you have already computed these because you are doing a full
comparison of bias correction, you can provide them to save time
Args:
corrected: the response from the geoglows.bias.correct_historical_simulation function
simulated: the csv response from historic_simulation
observed: the dataframe of observed data. Must have a datetime index and a single column of flow values
merged_sim_obs: (optional) if you have already computed it, hydrostats.data.merge_data(simulated, observed)
merged_cor_obs: (optional) if you have already computed it, hydrostats.data.merge_data(corrected, observed)
outformat: either 'plotly' or 'plotly_html' (default plotly)
titles: (dict) Extra info to show on the title of the plot. For example:
{'Reach ID': 1234567, 'Drainage Area': '1000km^2'}
Returns:
plotly.GraphObject: plotly object, especially for use with python notebooks and the .show() method
"""
if corrected is False and simulated is False and observed is False:
if merged_sim_obs is not False and merged_cor_obs is not False:
pass # if you provided the merged dataframes already, we use those
else:
# merge the datasets together
merged_sim_obs = hd.merge_data(sim_df=simulated, obs_df=observed)
merged_cor_obs = hd.merge_data(sim_df=corrected, obs_df=observed)
monthly_avg = hd.monthly_average(merged_sim_obs)
monthly_avg2 = hd.monthly_average(merged_cor_obs)
scatters = [
go.Scatter(x=monthly_avg.index, y=monthly_avg.iloc[:, 1].values, name='Observed Data'),
go.Scatter(x=monthly_avg.index, y=monthly_avg.iloc[:, 0].values, name='Simulated Data'),
go.Scatter(x=monthly_avg2.index, y=monthly_avg2.iloc[:, 0].values, name='Corrected Simulated Data'),
]
layout = go.Layout(
title=_build_title('Monthly Average Streamflow Comparison', titles),
xaxis=dict(title='Month'), yaxis=dict(title='Discharge (m<sup>3</sup>/s)', autorange=True),
showlegend=True)
if outformat == 'plotly':
return go.Figure(data=scatters, layout=layout)
elif outformat == 'plotly_html':
return offline_plot(
go.Figure(data=scatters, layout=layout),
config={'autosizable': True, 'responsive': True},
output_type='div',
include_plotlyjs=False
)
raise ValueError('Invalid outformat chosen. Choose plotly or plotly_html')
def get_monthlyAverages(request):
"""
Get observed data from csv files in Hydroshare
Get historic simulations from ERA Interim
"""
get_data = request.GET
global nomRiver
global nomEstacion
global simulated_df
global observed_df
global corrected_df
try:
'''Merge Data'''
merged_df = hd.merge_data(sim_df=simulated_df, obs_df=observed_df)
merged_df2 = hd.merge_data(sim_df=corrected_df, obs_df=observed_df)
'''Plotting Data'''
monthly_avg = hd.monthly_average(merged_df)
monthly_avg2 = hd.monthly_average(merged_df2)
monthly_avg_obs_Q = go.Scatter(x=monthly_avg.index, y=monthly_avg.iloc[:, 1].values, name='Observed', )
monthly_avg_sim_Q = go.Scatter(x=monthly_avg.index, y=monthly_avg.iloc[:, 0].values, name='Simulated', )
monthly_avg_corr_sim_Q = go.Scatter(x=monthly_avg2.index, y=monthly_avg2.iloc[:, 0].values,
name='Corrected Simulated', )
layout = go.Layout(
title='Monthly Average Streamflow for River {0} at {1}'.format(nomRiver, nomEstacion),
xaxis=dict(title='Months', ), yaxis=dict(title='Discharge (m<sup>3</sup>/s)', autorange=True),
showlegend=True)
chart_obj = PlotlyView(
go.Figure(data=[monthly_avg_obs_Q, monthly_avg_sim_Q, monthly_avg_corr_sim_Q], layout=layout))
context = {
'gizmo_object': chart_obj,
}
return render(request, 'historical_validation_tool_somalia/gizmo_ajax.html', context)
except Exception as e:
print(str(e))
return JsonResponse({'error': 'No data found for the selected station.'})
def test_monthly_average(self):
original_df = pd.read_csv(r'Comparison_Files/monthly_average.csv', index_col=0)
original_df.index = np.array(['01', '02', '03', '04', '05', '06', '07', '08', '09', '10', '11', '12'],
dtype=np.object)
test_df = hd.monthly_average(self.merged_df)
self.assertIsNone(pd.testing.assert_frame_equal(original_df, test_df))
def historic_averages_handler(request, average_type):
"""
Controller for retrieving averages
"""
# handle the parameters from the user
try:
reach_id, region, units, return_format = handle_parameters(request)
units_title, units_title_long = get_units_title(units)
forcing = request.args.get('forcing', 'era_5')
hist_df = get_historical_dataframe(reach_id, region, units, forcing)
except Exception as e:
raise e
hist_df.index = pd.to_datetime(hist_df.index)
if average_type == 'daily':
hist_df = hd.daily_average(hist_df, rolling=True)
else:
hist_df = hd.monthly_average(hist_df)
hist_df.index.name = 'datetime'
if return_format == 'csv':
response = make_response(hist_df.to_csv())
response.headers['content-type'] = 'text/csv'
response.headers[
'Content-Disposition'] = f'attachment; filename=seasonal_average_{forcing}_{reach_id}.csv'
return response
if return_format == "json":
return jsonify({
'region':
region,
'simulation_forcing':
forcing,
'forcing_fullname':
forcing.replace('era_', 'ERA ').title(),
'comid':
reach_id,
'gendate':
datetime.datetime.utcnow().isoformat() + 'Z',
'time_series': {
'datetime': hist_df.index.tolist(),
'flow': hist_df[f'streamflow_{units_title}^3/s'].tolist(),
},
'units': {
'name': 'Streamflow',
'short': f'{units_title}3/s',
'long': f'Cubic {units_title_long} per Second'
}
})
else:
raise ValueError(f'Invalid return_format: {return_format}')
'{0}_{1}_daily_average.png'.format(str(id), name)))
hv.plot(merged_data_df=daily_avg,
legend=('Simulated', 'Observed'),
grid=True,
x_season=True,
title='Daily Average Streamflow for ' + str(id) + ' - ' + name +
'\n River: ' + rio + '. COMID: ' + str(comid),
labels=['Datetime', 'Streamflow (m$^3$/s)'],
linestyles=['b-', 'r-'],
fig_size=(15, 9))
plt.savefig(
path.join(daily_average_out_dir,
'{0}_{1}_daily_average_1.png'.format(str(id), name)))
monthly_avg = hd.monthly_average(merged_df)
monthly_std_error = hd.monthly_std_error(merged_data=merged_df)
hv.plot(merged_data_df=monthly_avg,
legend=('Simulated', 'Observed'),
grid=True,
x_season=True,
title='Monthly Average Streamflow (Standard Error) for ' +
str(id) + ' - ' + name + '\n River: ' + rio + '. COMID: ' +
str(comid),
labels=['Datetime', 'Streamflow (m$^3$/s)'],
linestyles=['b-', 'r-'],
fig_size=(15, 9),
ebars=monthly_std_error,
ecolor=('b', 'r'),
tight_xlim=False)
plt.savefig(