def benchmarks(house_id):
redd_train = DataSet(REDD_FILE)
redd_test = DataSet(REDD_FILE)
# set up training and test sets
redd_train.set_window(end=TRAIN_END)
redd_test.set_window(start=TRAIN_END)
# get top N_DEV devices
house = redd_train.buildings[house_id]
test_elec = redd_test.buildings[house_id].elec
top_apps = house.elec.submeters().select_top_k(k=N_DEV)
# store mains data
test_mains = next(test_elec.mains().load())
truth = {}
predictions = {}
# benchmark classifier 1
co = CombinatorialOptimisation()
start = time.time()
print("*" *20)
print('Combinatorial Optimisation: ')
print("*" *20)
co.train(top_apps, sample_period=SAMPLE_PERIOD)
truth['CO'], predictions['CO'] = predict(co, test_elec, SAMPLE_PERIOD, redd_train.metadata['timezone'])
end = time.time()
print("Runtime: ", end-start)
# benchmark classifier 2
fhmm = FHMM()
start = time.time()
print("*" *20)
print('Factorial Hidden Markov Model: ')
print("*" *20)
fhmm.train(top_apps, sample_period=SAMPLE_PERIOD)
truth['FHMM'], predictions['FHMM'] = predict(fhmm, test_elec, SAMPLE_PERIOD, redd_train.metadata['timezone'])
end = time.time()
print("Runtime: ", end-start)
# add mains to truth
truth['CO']['Main'] = test_mains
truth['FHMM']['Main'] = test_mains
return truth, predictions
def test_fhmm_correctness(self):
elec = self.dataset.buildings[1].elec
fhmm = FHMM()
fhmm.train(elec)
mains = elec.mains()
output = HDFDataStore('output.h5', 'w')
fhmm.disaggregate(mains, output, sample_period=1)
for meter in range(2, 4):
df1 = output.store.get('/building1/elec/meter{}'.format(meter))
df2 = self.dataset.store.store.get(
'/building1/elec/meter{}'.format(meter))
self.assertEqual((df1 == df2).sum().values[0], len(df1.index))
self.assertEqual(len(df1.index), len(df2.index))
output.close()
remove("output.h5")
def test_fhmm_correctness(self):
elec = self.dataset.buildings[1].elec
fhmm = FHMM()
fhmm.train(elec)
mains = elec.mains()
output = HDFDataStore('output.h5', 'w')
fhmm.disaggregate(mains, output, sample_period=1)
for meter in range(2, 4):
df1 = output.store.get('/building1/elec/meter{}'.format(meter))
df2 = self.dataset.store.store.get(
'/building1/elec/meter{}'.format(meter))
self.assertEqual((df1 == df2).sum().values[0], len(df1.index))
self.assertEqual(len(df1.index), len(df2.index))
output.close()
remove("output.h5")
def fhmm(dataset_path, train_building, train_start, train_end, val_building,
val_start, val_end, test_building, test_start, test_end, meter_key,
sample_period):
# Start tracking time
start = time.time()
# Prepare dataset and options
# print("========== OPEN DATASETS ============")
dataset_path = dataset_path
train = DataSet(dataset_path)
train.set_window(start=train_start, end=train_end)
val = DataSet(dataset_path)
val.set_window(start=val_start, end=val_end)
test = DataSet(dataset_path)
test.set_window(start=test_start, end=test_end)
train_building = train_building
test_building = test_building
meter_key = meter_key
sample_period = sample_period
train_elec = train.buildings[train_building].elec
val_elec = val.buildings[val_building].elec
test_elec = test.buildings[test_building].elec
appliances = [meter_key]
selected_meters = [train_elec[app] for app in appliances]
selected_meters.append(train_elec.mains())
selected = MeterGroup(selected_meters)
fhmm = FHMM()
# print("========== TRAIN ============")
fhmm.train(selected, sample_period=sample_period)
# print("========== DISAGGREGATE ============")
# Validation
val_disag_filename = 'disag-out-val.h5'
output = HDFDataStore(val_disag_filename, 'w')
fhmm.disaggregate(val_elec.mains(), output_datastore=output)
output.close()
# Test
test_disag_filename = 'disag-out-test.h5'
output = HDFDataStore(test_disag_filename, 'w')
fhmm.disaggregate(test_elec.mains(), output_datastore=output)
output.close()
# print("========== RESULTS ============")
# Validation
result_val = DataSet(val_disag_filename)
res_elec_val = result_val.buildings[val_building].elec
rpaf_val = metrics.recall_precision_accuracy_f1(res_elec_val[meter_key],
val_elec[meter_key])
val_metrics_results_dict = {
'recall_score':
rpaf_val[0],
'precision_score':
rpaf_val[1],
'accuracy_score':
rpaf_val[2],
'f1_score':
rpaf_val[3],
'mean_absolute_error':
metrics.mean_absolute_error(res_elec_val[meter_key],
val_elec[meter_key]),
'mean_squared_error':
metrics.mean_square_error(res_elec_val[meter_key],
val_elec[meter_key]),
'relative_error_in_total_energy':
metrics.relative_error_total_energy(res_elec_val[meter_key],
val_elec[meter_key]),
'nad':
metrics.nad(res_elec_val[meter_key], val_elec[meter_key]),
'disaggregation_accuracy':
metrics.disaggregation_accuracy(res_elec_val[meter_key],
val_elec[meter_key])
}
# Test
result = DataSet(test_disag_filename)
res_elec = result.buildings[test_building].elec
rpaf = metrics.recall_precision_accuracy_f1(res_elec[meter_key],
test_elec[meter_key])
test_metrics_results_dict = {
'recall_score':
rpaf[0],
'precision_score':
rpaf[1],
'accuracy_score':
rpaf[2],
'f1_score':
rpaf[3],
'mean_absolute_error':
metrics.mean_absolute_error(res_elec[meter_key], test_elec[meter_key]),
'mean_squared_error':
metrics.mean_square_error(res_elec[meter_key], test_elec[meter_key]),
'relative_error_in_total_energy':
metrics.relative_error_total_energy(res_elec[meter_key],
test_elec[meter_key]),
'nad':
metrics.nad(res_elec[meter_key], test_elec[meter_key]),
'disaggregation_accuracy':
metrics.disaggregation_accuracy(res_elec[meter_key],
test_elec[meter_key])
}
# end tracking time
end = time.time()
time_taken = end - start # in seconds
# model_result_data = {
# 'algorithm_name': 'FHMM',
# 'datapath': dataset_path,
# 'train_building': train_building,
# 'train_start': str(train_start.date()) if train_start != None else None ,
# 'train_end': str(train_end.date()) if train_end != None else None ,
# 'test_building': test_building,
# 'test_start': str(test_start.date()) if test_start != None else None ,
# 'test_end': str(test_end.date()) if test_end != None else None ,
# 'appliance': meter_key,
# 'sampling_rate': sample_period,
#
# 'algorithm_info': {
# 'options': {
# 'epochs': None
# },
# 'hyperparameters': {
# 'sequence_length': None,
# 'min_sample_split': None,
# 'num_layers': None
# },
# 'profile': {
# 'parameters': None
# }
# },
#
# 'metrics': metrics_results_dict,
#
# 'time_taken': format(time_taken, '.2f'),
# }
model_result_data = {
'val_metrics': val_metrics_results_dict,
'test_metrics': test_metrics_results_dict,
'time_taken': format(time_taken, '.2f'),
'epochs': None,
}
# Close digag_filename
result.store.close()
result_val.store.close()
# Close Dataset files
train.store.close()
val.store.close()
test.store.close()
return model_result_data
out = {}
for b_id, building in building_chunk_items[home_group]:
try:
if b_id in existing_files_names:
print("Skipping", b_id)
continue
print b_id
out[b_id] = {}
start = time.time()
#cls_dict = {"Hart":Hart85()}
cls_dict = {
"CO": CombinatorialOptimisation(),
"FHMM": FHMM(),
"Hart": Hart85()
}
elec = building.elec
mains = elec.mains()
train = DataSet(ds_path)
test = DataSet(ds_path)
split_point = datetime.date(2013, 7, 16)
train.set_window(end=split_point)
#test.set_window(start=split_point)
train_elec = train.buildings[b_id].elec
test_elec = test.buildings[b_id].elec
test_mains = test_elec.mains()
# AC elec
#Intersection of index
gt_index_utc = gt_overall.index.tz_convert("UTC")
pred_index_utc = pred_overall.index.tz_convert("UTC")
common_index_utc = gt_index_utc.intersection(pred_index_utc)
common_index_local = common_index_utc.tz_convert(timezone)
gt_overall = gt_overall.ix[common_index_local]
pred_overall = pred_overall.ix[common_index_local]
appliance_labels = [m.label() for m in gt_overall.columns.values]
gt_overall.columns = appliance_labels
pred_overall.columns = appliance_labels
return gt_overall, pred_overall
#Run classifiers CO and FHMM
classifiers = {'CO': CombinatorialOptimisation(), 'FHMM': FHMM()}
predictions = {}
sample_period = 6
for clf_name, clf in classifiers.iteritems():
print("*" * 20)
print(clf_name)
print("*" * 20)
clf.train(top_5_train_elec, sample_period=sample_period)
gt, predictions[clf_name] = predict(clf, test_elec, 6,
train.metadata['timezone'])
#Evaluate algorithms by rmse metric
def compute_rmse(gt, pred):
from sklearn.metrics import mean_squared_error
rms_error = {}
train.set_window(end="2011-04-30")
test.set_window(start="2011-04-30")
train_elec = train.buildings[1].elec
test_elec = test.buildings[1].elec
top_5_train_elec = train_elec.submeters().select_top_k(k=5)
np.random.seed(42)
params = {}
#classifiers = {'CO':CombinatorialOptimisation(), 'FHMM':FHMM()}
predictions = {}
sample_period = 120
co = CombinatorialOptimisation()
fhmm = FHMM()
## Train models
co.train(top_5_train_elec, sample_period=sample_period)
fhmm.train(top_5_train_elec, sample_period=sample_period)
## Export models
co.export_model(filename='co.h5')
fhmm.export_model(filename='fhmm.h5')
co.import_model(filename='co.h5')
fhmm.import_model(filename='fhmm.h5')
common_index_local = common_index_utc.tz_convert(timezone)
gt_overall = gt_overall.loc[common_index_local]
pred_overall = pred_overall.loc[common_index_local]
appliance_labels = [m for m in gt_overall.columns.values]
gt_overall.columns = appliance_labels
pred_overall.columns = appliance_labels
return gt_overall, pred_overall
np.random.seed(42)
params = {}
co = CombinatorialOptimisation()
fhmm = FHMM()
#predictions = {}
sample_period = 120
print("*"*20)
print('CO')
print("*" *20)
co.train(top_5_train_elec, sample_period=sample_period)
gt_1, predictions_co = predict(co, test_elec, 120, train.metadata['timezone'])
print("*"*20)
print('FHMM')
print("*" *20)
fhmm.train(top_5_train_elec, sample_period=sample_period)
gt_2, predictions_fhmm = predict(fhmm, test_elec, 120, train.metadata['timezone'])
rmse = {}
rmse['CO'] = nilmtk.utils.compute_rmse(gt_1, predictions_co, pretty=True)
common_index_utc = gt_index_utc.intersection(pred_index_utc)
common_index_local = common_index_utc.tz_convert(timezone)
gt_overall = gt_overall.loc[common_index_local]
pred_overall = pred_overall.loc[common_index_local]
appliance_labels = [m for m in gt_overall.columns.values]
gt_overall.columns = appliance_labels
pred_overall.columns = appliance_labels
return gt_overall, pred_overall
np.random.seed(42)
co = CombinatorialOptimisation()
fhmm = FHMM()
co.import_model(filename='co.h5')
fhmm.import_model(filename='fhmm.h5')
cot, pred_co = predict(co, test_elec, 120, train.metadata['timezone'])
fhmmt, pred_fhmm = predict(fhmm, test_elec, 120, train.metadata['timezone'])
rmse = {}
rmse["CO"] = nilmtk.utils.compute_rmse(cot, pred_co, pretty=True)
rmse["FHMM"] = nilmtk.utils.compute_rmse(fhmmt, pred_fhmm, pretty=True)
for clf_name in classifiers.keys():
rmse[clf_name] = nilmtk.utils.compute_rmse(gt, predictions[clf_name], pretty=True)
def run_fhmm(meters):
# TRAIN FHMM
logger.info("Training FHMM...")
fhmm = FHMM()
fhmm.train(meters)
logger.info("Disag FHMM...")
run_nilmtk_disag(fhmm, 'fhmm')