def test_theme_linedraw(self):
p = self.g + labs(title='Theme Linedraw') + theme_linedraw()
if six.PY2:
# Small displacement in title
assert p + _theme == ('theme_linedraw', {'tol': 8})
else:
assert p + _theme == 'theme_linedraw'
def test_theme_linedraw(self):
p = self.g + labs(title='Theme Linedraw') + theme_linedraw()
if six.PY2:
# Small displacement in title
assert p + _theme == ('theme_linedraw', {'tol': 8})
else:
assert p + _theme == 'theme_linedraw'
def graph(df):
graph = (ggplot(data=df,
mapping=aes(x='Time', y='NDVI'))
+ geom_line(size =2, color = 'green')
+geom_point()
+theme_linedraw()
+ theme(axis_text_x= element_text(rotation=45, hjust=1))
+scales.ylim(0,1)
+ geom_area(fill = "green", alpha = .4)
)
return graph
def batch_plots(self):
# First, put together active leak data and output for live plotting functionality
# (no AL plot here currently)
dfs = self.active_leak_dfs
for i in range(len(dfs)):
n_cols = dfs[i].shape[1]
dfs[i]['mean'] = dfs[i].iloc[:, 0:n_cols].mean(axis=1)
dfs[i]['std'] = dfs[i].iloc[:, 0:n_cols].std(axis=1)
dfs[i]['low'] = dfs[i].iloc[:, 0:n_cols].quantile(0.025, axis=1)
dfs[i]['high'] = dfs[i].iloc[:, 0:n_cols].quantile(0.975, axis=1)
dfs[i]['program'] = self.directories[i]
# Move reference program to the top of the list
for i, df in enumerate(dfs):
if df['program'].iloc[0] == self.ref_program:
dfs.insert(0, dfs.pop(i))
# Arrange dfs for plot 1
dfs_p1 = dfs.copy()
for i in range(len(dfs_p1)):
# Reshape
dfs_p1[i] = pd.melt(dfs_p1[i], id_vars=['datetime', 'mean',
'std', 'low', 'high', 'program'])
# Combine dataframes into single dataframe for plotting
df_p1 = dfs_p1[0]
for i in dfs_p1[1:]:
df_p1 = df_p1.append(i, ignore_index=True)
# Output Emissions df for other uses (e.g. live plot)
df_p1.to_csv(self.output_directory + 'mean_active_leaks.csv', index=True)
# Now repeat for emissions (which will actually be used for batch plotting)
dfs = self.emission_dfs
for i in range(len(dfs)):
n_cols = dfs[i].shape[1]
dfs[i]['mean'] = dfs[i].iloc[:, 0:n_cols].mean(axis=1)
dfs[i]['std'] = dfs[i].iloc[:, 0:n_cols].std(axis=1)
dfs[i]['low'] = dfs[i].iloc[:, 0:n_cols].quantile(0.025, axis=1)
dfs[i]['high'] = dfs[i].iloc[:, 0:n_cols].quantile(0.975, axis=1)
dfs[i]['program'] = self.directories[i]
# Move reference program to the top of the list
for i, df in enumerate(dfs):
if df['program'].iloc[0] == self.ref_program:
dfs.insert(0, dfs.pop(i))
# Arrange dfs for plot 1
dfs_p1 = dfs.copy()
for i in range(len(dfs_p1)):
# Reshape
dfs_p1[i] = pd.melt(dfs_p1[i], id_vars=['datetime', 'mean',
'std', 'low', 'high', 'program'])
# Combine dataframes into single dataframe for plotting
df_p1 = dfs_p1[0]
for i in dfs_p1[1:]:
df_p1 = df_p1.append(i, ignore_index=True)
# Output Emissions df for other uses (e.g. live plot)
df_p1.to_csv(self.output_directory + 'mean_emissions.csv', index=True)
# Make plots from list of dataframes - one entry per dataframe
pn.theme_set(pn.theme_linedraw())
plot1 = (pn.ggplot(None) + pn.aes('datetime', 'value', group='program') +
pn.geom_ribbon(df_p1, pn.aes(ymin='low', ymax='high', fill='program'), alpha=0.2) +
pn.geom_line(df_p1, pn.aes('datetime', 'mean', colour='program'), size=1) +
pn.ylab('Daily emissions (kg/site)') + pn.xlab('') +
pn.scale_colour_hue(h=0.15, l=0.25, s=0.9) +
pn.scale_x_datetime(labels=date_format('%Y')) +
pn.scale_y_continuous(trans='log10') +
pn.ggtitle('To reduce uncertainty, use more simulations.') +
pn.labs(color='Program', fill='Program') +
pn.theme(panel_border=pn.element_rect(colour="black", fill=None, size=2),
panel_grid_minor_x=pn.element_blank(),
panel_grid_major_x=pn.element_blank(),
panel_grid_minor_y=pn.element_line(
colour='black', linewidth=0.5, alpha=0.3),
panel_grid_major_y=pn.element_line(
colour='black', linewidth=1, alpha=0.5))
)
plot1.save(self.output_directory + 'program_comparison.png', width=7, height=3, dpi=900)
# Build relative mitigation plots
dfs_p2 = dfs.copy()
for i in dfs_p2[1:]:
i['mean_dif'] = 0
i['std_dif'] = 0
i['mean_ratio'] = 0
i['std_ratio'] = 0
for j in range(len(i)):
ref_mean = dfs_p2[0].loc[dfs_p2[0].index[j], 'mean']
ref_std = dfs_p2[0].loc[dfs_p2[0].index[j], 'std']
alt_mean = i.loc[i.index[j], 'mean']
alt_std = i.loc[i.index[j], 'std']
i.loc[i.index[j], 'mean_dif'] = alt_mean - ref_mean
i.loc[i.index[j], 'std_dif'] = math.sqrt(
math.pow(alt_std, 2) + math.pow(ref_std, 2))
i.loc[i.index[j], 'mean_ratio'] = alt_mean / ref_mean
i.loc[i.index[j], 'std_ratio'] = math.sqrt(
math.pow((alt_std / alt_mean), 2) + math.pow((ref_std / ref_mean), 2))
# Build plotting dataframe
df_p2 = self.dates_trunc.copy().to_frame()
df_p2['program'] = dfs_p2[1]['program']
df_p2['mean_dif'] = dfs_p2[1]['mean_dif']
df_p2['std_dif'] = dfs_p2[1]['std_dif']
df_p2['mean_ratio'] = dfs_p2[1]['mean_ratio']
df_p2['std_ratio'] = dfs_p2[1]['std_ratio']
df_p2['low_dif'] = dfs_p2[1]['mean_dif'] - 2 * dfs_p2[1]['std_dif']
df_p2['high_dif'] = dfs_p2[1]['mean_dif'] + 2 * dfs_p2[1]['std_dif']
df_p2['low_ratio'] = dfs_p2[1]['mean_ratio'] / (dfs_p2[1]
['mean_ratio'] + 2 * dfs_p2[1]['std_ratio'])
df_p2['high_ratio'] = dfs_p2[1]['mean_ratio'] + 2 * dfs_p2[1]['std_ratio']
pd.options.mode.chained_assignment = None
for i in dfs_p2[2:]:
i['low_dif'] = i['mean_dif'] - 2 * i['std_dif']
i['high_dif'] = i['mean_dif'] + 2 * i['std_dif']
i['low_ratio'] = i['mean_ratio'] / (i['mean_ratio'] + 2 * i['std_ratio'])
i['high_ratio'] = i['mean_ratio'] + 2 * i['std_ratio']
short_df = i[['program', 'mean_dif', 'std_dif', 'low_dif',
'high_dif', 'mean_ratio', 'std_ratio', 'low_ratio', 'high_ratio']]
short_df['datetime'] = np.array(self.dates_trunc)
df_p2 = df_p2.append(short_df, ignore_index=True)
# Make plot 2
plot2 = (pn.ggplot(None) + pn.aes('datetime', 'mean_dif', group='program') +
pn.geom_ribbon(
df_p2, pn.aes(ymin='low_dif', ymax='high_dif', fill='program'), alpha=0.2) +
pn.geom_line(df_p2, pn.aes('datetime', 'mean_dif', colour='program'), size=1) +
pn.ylab('Daily emissions difference (kg/site)') + pn.xlab('') +
pn.scale_colour_hue(h=0.15, l=0.25, s=0.9) +
pn.scale_x_datetime(labels=date_format('%Y')) +
pn.ggtitle('Daily differences may be uncertain for small sample sizes') +
# pn.scale_y_continuous(trans='log10') +
pn.labs(color='Program', fill='Program') +
pn.theme(panel_border=pn.element_rect(colour="black", fill=None, size=2),
panel_grid_minor_x=pn.element_blank(),
panel_grid_major_x=pn.element_blank(),
panel_grid_minor_y=pn.element_line(
colour='black', linewidth=0.5, alpha=0.3),
panel_grid_major_y=pn.element_line(
colour='black', linewidth=1, alpha=0.5))
)
plot2.save(self.output_directory + 'relative_mitigation.png', width=7, height=3, dpi=900)
# Make plot 3
plot3 = (pn.ggplot(None) + pn.aes('datetime', 'mean_ratio', group='program') +
pn.geom_ribbon(df_p2, pn.aes(
ymin='low_ratio', ymax='high_ratio', fill='program'), alpha=0.2) +
pn.geom_hline(yintercept=1, size=0.5, colour='blue') +
pn.geom_line(df_p2, pn.aes('datetime', 'mean_ratio', colour='program'), size=1) +
pn.ylab('Emissions ratio') + pn.xlab('') +
pn.scale_colour_hue(h=0.15, l=0.25, s=0.9) +
pn.scale_x_datetime(labels=date_format('%Y')) +
pn.ggtitle(
'Blue line represents equivalence. \nIf uncertainty is high, use more '
'simulations and/or sites. \nLook also at ratio of mean daily emissions'
'over entire timeseries.') +
pn.labs(color='Program', fill='Program') +
pn.theme(panel_border=pn.element_rect(colour="black", fill=None, size=2),
panel_grid_minor_x=pn.element_blank(),
panel_grid_major_x=pn.element_blank(),
panel_grid_minor_y=pn.element_line(
colour='black', linewidth=0.5, alpha=0.3),
panel_grid_major_y=pn.element_line(
colour='black', linewidth=1, alpha=0.5))
)
plot3.save(self.output_directory + 'relative_mitigation2.png', width=7, height=3, dpi=900)
# ---------------------------------------
# ------ Figure to compare costs ------
dfs = self.cost_dfs
for i in range(len(dfs)):
n_cols = dfs[i].shape[1]
dfs[i]['mean'] = dfs[i].iloc[:, 0:n_cols].mean(axis=1)
dfs[i]['std'] = dfs[i].iloc[:, 0:n_cols].std(axis=1)
dfs[i]['low'] = dfs[i].iloc[:, 0:n_cols].quantile(0.025, axis=1)
dfs[i]['high'] = dfs[i].iloc[:, 0:n_cols].quantile(0.975, axis=1)
dfs[i]['program'] = self.directories[i]
# Move reference program to the top of the list
for i, df in enumerate(dfs):
if df['program'].iloc[0] == self.ref_program:
dfs.insert(0, dfs.pop(i))
# Arrange dfs for plot 1
dfs_p1 = dfs.copy()
for i in range(len(dfs_p1)):
# Reshape
dfs_p1[i] = pd.melt(dfs_p1[i], id_vars=['datetime', 'mean',
'std', 'low', 'high', 'program'])
# Combine dataframes into single dataframe for plotting
df_p1 = dfs_p1[0]
for i in dfs_p1[1:]:
df_p1 = df_p1.append(i, ignore_index=True)
# Output Emissions df for other uses (e.g. live plot)
df_p1.to_csv(self.output_directory + 'rolling_cost_estimates.csv', index=True)
# Make plots from list of dataframes - one entry per dataframe
pn.theme_set(pn.theme_linedraw())
plot1 = (pn.ggplot(None) + pn.aes('datetime', 'value', group='program') +
pn.geom_ribbon(df_p1, pn.aes(ymin='low', ymax='high', fill='program'), alpha=0.2) +
pn.geom_line(df_p1, pn.aes('datetime', 'mean', colour='program'), size=1) +
pn.ylab('Estimated cost per facility') + pn.xlab('') +
pn.scale_colour_hue(h=0.15, l=0.25, s=0.9) +
pn.scale_x_datetime(labels=date_format('%Y')) +
# pn.scale_y_continuous(trans='log10') +
pn.labs(color='Program', fill='Program') +
pn.theme(panel_border=pn.element_rect(colour="black", fill=None, size=2),
panel_grid_minor_x=pn.element_blank(),
panel_grid_major_x=pn.element_blank(),
panel_grid_minor_y=pn.element_line(
colour='black', linewidth=0.5, alpha=0.3),
panel_grid_major_y=pn.element_line(
colour='black', linewidth=1, alpha=0.5))
)
plot1.save(self.output_directory + 'cost_estimate_temporal.png', width=7, height=3, dpi=900)
########################################
# Cost breakdown by program and method
method_lists = []
for i in range(len(self.directories)):
df = pd.read_csv(
self.output_directory + self.directories[i] + "/timeseries_output_0.csv")
df = df.filter(regex='cost$', axis=1)
df = df.drop(columns=["total_daily_cost"])
method_lists.append(list(df))
costs = [[] for i in range(len(self.all_data))]
for i in range(len(self.all_data)):
for j in range(len(self.all_data[i])):
simcosts = []
for k in range(len(method_lists[i])):
timesteps = len(self.all_data[i][j][method_lists[i][k]])
simcosts.append(
(sum(self.all_data[i][j][method_lists[i][k]])/timesteps/self.n_sites)*365)
costs[i].append(simcosts)
rows_list = []
for i in range(len(costs)):
df_temp = pd.DataFrame(costs[i])
for j in range(len(df_temp.columns)):
dict = {}
dict.update({'Program': self.directories[i]})
dict.update({'Mean Cost': round(df_temp.iloc[:, j].mean())})
dict.update({'St. Dev.': df_temp.iloc[:, j].std()})
dict.update({'Method': method_lists[i][j].replace('_cost', '')})
rows_list.append(dict)
df = pd.DataFrame(rows_list)
# Output Emissions df for other uses
df.to_csv(self.output_directory + 'cost_comparison.csv', index=True)
plot = (
pn.ggplot(
df, pn.aes(
x='Program', y='Mean Cost', fill='Method', label='Mean Cost')) +
pn.geom_bar(stat="identity") + pn.ylab('Cost per Site per Year') + pn.xlab('Program') +
pn.scale_fill_hue(h=0.15, l=0.25, s=0.9) +
pn.geom_text(size=15, position=pn.position_stack(vjust=0.5)) +
pn.theme(
panel_border=pn.element_rect(colour="black", fill=None, size=2),
panel_grid_minor_x=pn.element_blank(),
panel_grid_major_x=pn.element_blank(),
panel_grid_minor_y=pn.element_line(
colour='black', linewidth=0.5, alpha=0.3),
panel_grid_major_y=pn.element_line(
colour='black', linewidth=1, alpha=0.5)))
plot.save(self.output_directory + 'cost_comparison.png', width=7, height=3, dpi=900)
return
def test_theme_linedraw(self):
p = self.g + labs(title='Theme Linedraw') + theme_linedraw()
assert p + _theme == 'theme_linedraw'
def make_plots(leak_df, time_df, site_df, sim_n, spin_up, output_directory):
"""
This function makes a set of standard plots to output at end of simulation.
"""
# Temporarily mute warnings
warnings.filterwarnings('ignore')
pn.theme_set(pn.theme_linedraw())
# Chop off spin-up year (only for plots, still exists in raw output)
time_df_adj = time_df.iloc[spin_up:, ]
# Timeseries plots
plot_time_1 = (
pn.ggplot(time_df_adj, pn.aes('datetime', 'daily_emissions_kg')) +
pn.geom_line(size=2) +
pn.ggtitle('Daily emissions from all sites (kg)') + pn.ylab('') +
pn.xlab('') + pn.scale_x_datetime(labels=date_format('%Y')) + pn.theme(
panel_border=pn.element_rect(colour="black", fill=None, size=2),
panel_grid_minor_x=pn.element_blank(),
panel_grid_major_x=pn.element_blank(),
panel_grid_minor_y=pn.element_line(
colour='black', linewidth=0.5, alpha=0.3),
panel_grid_major_y=pn.element_line(
colour='black', linewidth=1, alpha=0.5)))
plot_time_1.save(output_directory + '/plot_time_emissions_' + sim_n +
'.png',
width=10,
height=3,
dpi=300)
plot_time_2 = (pn.ggplot(time_df_adj, pn.aes('datetime', 'active_leaks')) +
pn.geom_line(size=2) +
pn.ggtitle('Number of active leaks at all sites') +
pn.ylab('') + pn.xlab('') +
pn.scale_x_datetime(labels=date_format('%Y')) +
pn.theme(panel_border=pn.element_rect(
colour="black", fill=None, size=2),
panel_grid_minor_x=pn.element_blank(),
panel_grid_major_x=pn.element_blank(),
panel_grid_minor_y=pn.element_line(
colour='black', linewidth=0.5, alpha=0.3),
panel_grid_major_y=pn.element_line(
colour='black', linewidth=1, alpha=0.5)))
plot_time_2.save(output_directory + '/plot_time_active_' + sim_n + '.png',
width=10,
height=3,
dpi=300)
# Site-level plots
plot_site_1 = (
pn.ggplot(site_df, pn.aes('cum_frac_sites', 'cum_frac_emissions')) +
pn.geom_line(size=2) + pn.theme(
panel_border=pn.element_rect(colour="black", fill=None, size=2),
panel_grid_minor_x=pn.element_blank(),
panel_grid_major_x=pn.element_blank(),
panel_grid_minor_y=pn.element_line(
colour='black', linewidth=0.5, alpha=0.3),
panel_grid_major_y=pn.element_line(
colour='black', linewidth=1, alpha=0.5)) +
pn.xlab('Cumulative fraction of sites') +
pn.ylab('Cumulative fraction of emissions') +
pn.ggtitle('Empirical cumulative distribution of site-level emissions')
)
plot_site_1.save(output_directory + '/site_cum_dist_' + sim_n + '.png',
width=5,
height=4,
dpi=300)
# Leak plots
plot_leak_1 = (pn.ggplot(leak_df, pn.aes('days_active')) +
pn.geom_histogram(colour='gray') +
pn.theme(panel_border=pn.element_rect(
colour="black", fill=None, size=2),
panel_grid_minor_x=pn.element_blank(),
panel_grid_major_x=pn.element_blank(),
panel_grid_minor_y=pn.element_line(
colour='black', linewidth=0.5, alpha=0.3),
panel_grid_major_y=pn.element_line(
colour='black', linewidth=1, alpha=0.5)) +
pn.ggtitle('Distribution of leak duration') +
pn.xlab('Number of days the leak was active') +
pn.ylab('Count'))
plot_leak_1.save(output_directory + '/leak_active_hist' + sim_n + '.png',
width=5,
height=4,
dpi=300)
plot_leak_2 = (pn.ggplot(
leak_df, pn.aes('cum_frac_leaks', 'cum_frac_rate', colour='status')) +
pn.geom_line(size=2) +
pn.scale_colour_hue(h=0.15, l=0.25, s=0.9) +
pn.theme(panel_border=pn.element_rect(
colour="black", fill=None, size=2),
panel_grid_minor_x=pn.element_blank(),
panel_grid_major_x=pn.element_blank(),
panel_grid_minor_y=pn.element_line(
colour='black', linewidth=0.5, alpha=0.3),
panel_grid_major_y=pn.element_line(
colour='black', linewidth=1, alpha=0.5)) +
pn.xlab('Cumulative fraction of leak sources') +
pn.ylab('Cumulative leak rate fraction') +
pn.ggtitle('Fractional cumulative distribution'))
plot_leak_2.save(output_directory + '/leak_cum_dist1_' + sim_n + '.png',
width=4,
height=4,
dpi=300)
plot_leak_3 = (pn.ggplot(
leak_df, pn.aes('cum_frac_leaks', 'cum_rate', colour='status')) +
pn.geom_line(size=2) +
pn.scale_colour_hue(h=0.15, l=0.25, s=0.9) +
pn.theme(panel_border=pn.element_rect(
colour="black", fill=None, size=2),
panel_grid_minor_x=pn.element_blank(),
panel_grid_major_x=pn.element_blank(),
panel_grid_minor_y=pn.element_line(
colour='black', linewidth=0.5, alpha=0.3),
panel_grid_major_y=pn.element_line(
colour='black', linewidth=1, alpha=0.5)) +
pn.scale_y_continuous(trans='log10') +
pn.xlab('Cumulative fraction of leak sources') +
pn.ylab('Cumulative emissions (kg/day)') +
pn.ggtitle('Absolute cumulative distribution'))
plot_leak_3.save(output_directory + '/leak_cum_dist2_' + sim_n + '.png',
width=4,
height=4,
dpi=300)
return