y_noise = 0.0
y_total = 0.0
calc_done = [0, 0]
calc_total = [0, 0]
unexpected_event = 0
adapted_event = 0
adapted_errors = 0
multi_switches_count = 0
y_est_lst = []
print()
folds = Folding(
dataset_loader(datasets_dir % dataset,
labels,
precision,
denoised,
verbose=False), folds)
for (fold, priors, testing) in folds:
del priors
tm_start = time()
sshmm = sshmms[fold]
obs_id = list(testing)[0]
obs = list(testing[obs_id])
hidden = [i for i in testing[labels].to_records(index=False)]
print()
print(
'Begin evaluation testing on observations, compare against ground truth...'
)
n_appliance = 11 # from 1 - 19
for n_appliance in range(1, 20):
args = model_args.loc[n_appliance - 1, :]
modeldb = args[0]
dataset = args[1]
precision = args[2]
max_obs = args[3]
denoised = args[4] == 'denoised'
max_states = args[5]
folds = args[6]
ids = args[7].split(',')
datasets_dir = './data/%s.csv'
data = dataset_loader(datasets_dir % dataset, ids, precision=precision, denoised=denoised)
# test ikhmm
ob = data.BME.head(1440)
hmm = IterativeKmeansHMM(ob, max_k=10, std_thres=1)
centers = hmm.iterative_kmeans()
# showing the first day
# data.WHE.iloc[0:1440].plot() # whole house current profile for day 1
# data.iloc[0:1440, 1:n_appliance+1].sum(1).plot()
# defining problem
days = 3 # as the same length in SparseNILM demo
length = 1440 * days # 1 minute interval, 7 days
aggregate = data.WHE.tail(36 * 1440) # test on the last 36 days
hmms = collections.OrderedDict()
for data in jdata:
sshmm = SuperStateHMM()
sshmm._fromdict(data)
sshmms.append(sshmm)
del jdata
labels = sshmms[0].labels
print('\tModel lables are: ', labels)
print()
print('Testing %s algorithm load disagg...' % algo_name)
acc = Accuracy(len(labels), folds)
test_times = []
#%%
print()
folds_tot = Folding(
dataset_loader(datasets_dir % dataset, labels, precision, denoised), folds)
for (fold, priors, testing) in folds_tot:
del priors
tm_start = time()
sshmm = sshmms[fold]
obs_id = list(testing)[0]
obs = list(testing[obs_id])
hidden = [i for i in testing[labels].to_records(index=False)]
print()
print(
'Begin evaluation testing on observations, compare against ground truth...'
)
print()
print('Parameters:', sys.argv[1:])
(modeldb, dataset, precision, max_obs, denoised, max_states, folds, ids) = sys.argv[1:]
precision = float(precision)
max_obs = float(max_obs)
denoised = denoised == 'denoised'
max_states = int(max_states)
folds = int(folds)
ids = ids.split(',')
datasets_dir = './datasets/%s.csv'
logs_dir = './logs/%s.log'
models_dir = './models/%s.json'
print()
sshmms = []
train_times = []
folds = Folding(dataset_loader(datasets_dir % dataset, ids, precision, denoised), folds)
for (fold, priors, testing) in folds:
del testing
tm_start = time()
print()
print('Creating load PMFs and finding load states...')
print('\tMax partitions per load =', max_states)
pmfs = []
for id in ids:
pmfs.append(EmpiricalPMF(id, max_obs * precision, list(priors[id])))
pmfs[-1].quantize(max_states, ε)
print()
print('Creating compressed SSHMM...')
incro = 1 / precision