def preprocess_redd(building, freq):
building.utility.electric = building.utility.electric.sum_split_supplies()
building = prepb.downsample(building, rule=freq)
building = prepb.fill_appliance_gaps(building)
building = prepb.drop_missing_mains(building)
building = prepb.make_common_index(building)
building.utility.electric.mains[(1, 1)].rename(
columns={Measurement('power', 'apparent'): Measurement('power', 'active')}, inplace=True)
building = prepb.filter_top_k_appliances(building, k=6)
return building
def preprocess_iawe(building, freq):
building.utility.electric = building.utility.electric.sum_split_supplies()
building = prepb.filter_out_implausible_values(
building, Measurement('voltage', ''), 160, 260)
building = prepb.filter_datetime(building, '7-13-2013', '8-4-2013')
building = prepb.downsample(building, rule=freq)
building = prepb.fill_appliance_gaps(building)
building = prepb.prepend_append_zeros(
building, '7-13-2013', '8-4-2013', freq, 'Asia/Kolkata')
building = prepb.drop_missing_mains(building)
building = prepb.make_common_index(building)
building = prepb.filter_top_k_appliances(building, k=6)
return building
# Setting the limits to 5 GB RAM usage
megs = 5000
resource.setrlimit(resource.RLIMIT_AS, (megs * 1048576L, -1L))
# Loading data from HDF5 store
dataset = DataSet()
t1 = time.time()
dataset.load_hdf5(EXPORT_PATH)
t2 = time.time()
print("Runtime to import from HDF5 = {:.2f}".format(t2 - t1))
# Experiment on first (and only) building
b = dataset.buildings[1]
# Filtering to include only top 8 appliances
b = filter_top_k_appliances(b, 3)
# Dividing the data into train and test
train, test = train_test_split(b)
# Again subdivide data into train, test for testing on even smaller data
#train, test = train_test_split(train, test_size=.5)
# Initializing FHMM Disaggregator
disaggregator = FHMM()
train_mains = train.utility.electric.mains[
train.utility.electric.mains.keys()[0]][DISAGG_FEATURE]
# Get appliances data
app = train.utility.electric.appliances
def preprocess_pecan(building, freq):
building = prepb.downsample(building, rule=freq)
building = prepb.filter_top_k_appliances(building, k=6)
return building
