def plot(self):
''' Plots the used standard load profiles.
'''
plots.latexify(fontsize=12, columns=1)
#sns.set_context("notebook", font_scale=2, rc={"lines.linewidth": 3})
print("Plot Winter.")
ax = self.profiles['Winter'].plot()
ax.set_ylabel('Factor')
ax.set_xlabel('Time of Day')
ax.yaxis.labelpad = 10
print("Plot Summer.")
#plt.gca().xaxis.set_major_locator(dates.HourLocator())
#plt.gca().xaxis.set_major_formatter(dates.DateFormatter('%H:%M'))
ax = self.profiles['Summer'].plot()
ax.set_ylabel('Factor')
ax.set_xlabel('Time of Day')
ax.yaxis.labelpad = 10
#plt.gca().xaxis.set_major_locator(dates.HourLocator())
#plt.gca().xaxis.set_major_formatter(dates.DateFormatter('%H:%M'))
plt.show()
i = 1
merge=True)
def pretty_name_appliance_names(appliance_name_list):
names = [name.replace('_', ' ') for name in appliance_name_list]
names = [name[0].upper() + name[1:] for name in names]
for old, new in [('Htpc', 'Home theatre PC'),
('Boiler', 'Gas boiler'),
('Air conditioner', 'Air conditioning')]:
try:
names[names.index(old)] = new
except ValueError:
pass
return names
plt.close('all')
latexify(columns=2, fig_height=2)
fig, axes = plt.subplots(ncols=4, subplot_kw={'aspect':1})
count = 0
for dataset_name, dataset_path in DATASETS.iteritems():
print("\n------------------", dataset_name, "-----------------")
top_k = proportions[dataset_name][:K]
print(top_k)
fracs = top_k.tolist()
fracs.append(1.0 - sum(fracs))
labels_raw = top_k.index.tolist()
labels_raw.append('others')
colors = get_colors_for_labels(labels_raw)
pretty_labels = pretty_name_appliance_names(labels_raw)
explode = (0.03, 0.03, 0.03, 0.03, 0.03, 0.03)
ax = axes[count]
disaggregator_name, t2 - t1))
disaggregate_time[freq][disaggregator_name] = t2 - t1
# Predicted power and states
predicted_power[disaggregator_name] = disaggregator.predictions
app_ground = test.utility.electric.appliances
ground_truth_power = pd.DataFrame({appliance: app_ground[appliance][DISAGG_FEATURE] for appliance in app_ground})
for metric in metrics:
results[freq][disaggregator_name][metric] = metric_function[
metric](predicted_power[disaggregator_name], ground_truth_power)
results = results['1T']
start = pd.Timestamp("2013-07-27 21:35")
end = pd.Timestamp("2013-07-27 22:35")
latexify(columns=1)
fig, axes = plt.subplots(ncols=3, sharex=True, sharey=True)
plot_series(ground_truth_power[('air conditioner', 2)]
[start:end] / 1e3, ax=axes[0], color='k', date_format=DATE_FORMAT, linewidth=0.5)
plot_series(predicted_power['co']
[('air conditioner', 2)][start:end] / 1e3, ax=axes[1], color='k', date_format=DATE_FORMAT, linewidth=0.5)
plot_series(predicted_power['fhmm']
[('air conditioner', 2)][start:end] / 1e3, ax=axes[2], color='k', date_format=DATE_FORMAT, linewidth=0.5)
for ax in axes:
ax.set_ylim((0, 2))
format_axes(ax)
ax.set_xticklabels(['0', ' ', '30', ' ', '60'], rotation=0)
'UKPD': ApplianceName('washing_machine', 1),
'AMPds': ApplianceName('washer', 1),
'Pecan': ApplianceName('washer', 1),
}
time_datasets = {
'Pecan': [pd.Timestamp("2012-09-05 08:00"), pd.Timestamp("2012-09-05 11:00")],
'REDD': [pd.Timestamp("2011-05-01 17:43"), pd.Timestamp("2011-05-01 23:00")],
'AMPds': [pd.Timestamp("2012-04-02 04:30"), pd.Timestamp("2012-04-02 06:00")],
'iAWE': [pd.Timestamp("2013-07-10 07:22"), pd.Timestamp("2013-07-15 07:30")],
'UKPD': [pd.Timestamp("2013-10-29 10:47"), pd.Timestamp("2013-10-29 12:17")]
}
count = 0
latexify(columns=1, fig_height=1.5)
fig, axes = plt.subplots(ncols=len(DATASETS), sharey=True)
if LOAD_DATASETS:
electrics = {}
for dataset_name, dataset_path in DATASETS.iteritems():
dataset = DataSet()
print("Loading", dataset_path)
dataset.load_hdf5(dataset_path, [1])
building = dataset.buildings[1]
electric = building.utility.electric
electric = electric.sum_split_supplies()
electrics[dataset_name] = electric
for dataset_name, dataset_path in DATASETS.iteritems():
electric = electrics[dataset_name]