def energy_per_dataframe(electricity, sample_period_multiplier=20, unit="kwh"):
"""pre-processes electricity and then gets total energy per channel,
after masking out all gaps in mains.
Returns
-------
mains_total_energy, totals_per_appliance
total_mains_energy : float
totals_per_appliance : pd.Series
each key is an ApplianceName
each value is total energy
"""
# TODO: this might be an ugly hack to resolve circular dependencies.
from nilmtk.preprocessing.electricity.building import mask_appliances_with_mains
from nilmtk.preprocessing.electricity.single import insert_zeros
# remove 'unmetered' and 'subpanels' from appliances
electricity.appliances = electricity.remove_channels_from_appliances()
# Sum split mains and DualSupply appliances
electricity = electricity.sum_split_supplies()
# TODO: Select common measurements. Maybe use electricity.select_common_measurements?
# MEASUREMENT_PREFERENCES = [Measurement('power', 'active'),
# Measurement('power', 'apparent')]
# # Check if all channels share at least one Measurement (e.g. ('power', 'active'))
# common_measurements = find_common_measurements(electricity)
# common_measurement = None
# for measurement_preference in MEASUREMENT_PREFERENCES:
# if measurement_preference in common_measurements:
# common_measurement = measurement_preference
# print("Using common_measurement:", common_measurement)
# break
# if common_measurements is None and require_common_measurements:
# raise NoCommonMeasurementError
# Find large gaps in mains data and ignore those gaps for all appliance channels
electricity = mask_appliances_with_mains(electricity, sample_period_multiplier)
# Drop NaNs on all channels
electricity = apply_func_to_values_of_dicts(electricity, lambda df: df.dropna(), ["appliances", "mains"])
# Insert_zeros on appliance data.
print("Inserting zeros... may take a little while...", end="")
sys.stdout.flush()
single_insert_zeros = lambda df: insert_zeros(df, sample_period_multiplier=sample_period_multiplier)
electricity = apply_func_to_values_of_dicts(electricity, single_insert_zeros, ["appliances", "mains"])
print("done inserting zeros")
# Total energy used for mains
total_mains_energy = get_total_energy_per_dict(electricity, "mains", unit)
totals_per_appliance = {}
for name, df in electricity.appliances.iteritems():
totals_per_appliance[name] = single.energy(df, unit=unit)
return total_mains_energy, pd.Series(totals_per_appliance)
def get_total_energy_per_dict(electricity, dict_="mains", unit="kwh"):
total_energy = 0.0
for df in electricity.__dict__[dict_].values():
energy_for_df = single.energy(df, unit)
total_energy += energy_for_df
return total_energy
