def energies_paper_train_nilm_models_for_ampds2_dataset(top_n: int = 3):
"""
只从ampds2_dataset中的training_set中选取top_n个（默认3个）appliance。分别是HPE, FRE and CDE。
这里是符合nilmtk标准的算法。
torch的算法单独处理
:return:
"""
# 准备训练数据
training_set, test_set, _ = get_training_set_and_test_set_for_ampds2_dataset(
)
top_n_train_elec = training_set.select_using_appliances(
original_name=['HPE', 'FRE', 'CDE'])
# 模型save的路径
models_path = Path('../../../Data/Results/Energies_paper/Ampds2')
models_path.mkdir(parents=True, exist_ok=True)
# 训练所有模型
models = {'CO': CombinatorialOptimisation(), 'FHMM': FHMM()}
sample_period = 60 # 都是down sample到60s
for this_model_name, this_model in models.items():
this_model_file = models_path / (this_model_name + '.pkl')
if try_to_find_file(this_model_file):
this_model.import_model(this_model_file)
else:
print("*" * 20)
print(this_model_name)
print("*" * 20)
start = time.time()
this_model.train(top_n_train_elec, sample_period=sample_period)
this_model.export_model(this_model_file)
end = time.time()
print("Runtime =", end - start, "seconds.")
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")
print("....")
train = DataSet('C:/Users/20552/Desktop/HMM/HMM/NMLTK/iawe.h5')
test = DataSet('C:/Users/20552/Desktop/HMM/HMM/NMLTK/iawe.h5')
test_use = DataSet('C:/Users/20552/Desktop/HMM/HMM/NMLTK/iawe.h5')
building = 1
train.set_window(end="2013-07-13")
test.set_window(start="2013-07-13")
test_use.set_window(start="2013-07-13")
train_elec = train.buildings[1].elec
test_elec = test.buildings[1].elec
#test_use_elec = test_use.buildings[1].elec
print(test_elec)
#top_5_train_elec = train_elec.submeters().select_top_k(k=10)
top_5_train_elec = train_elec.submeters().select_top_k(k=5)
classifiers = {'CO':CombinatorialOptimisation(), 'FHMM':FHMM()}
classifiers = {'FHMM':FHMM()}
predictions = {}
sample_period = 5
for clf_name, clf in classifiers.items():
print("*"*20)
print(clf_name)
print("*" *20)
clf.train(top_5_train_elec, sample_period=sample_period)
for i in range(50):
ep=1-i*0.02
#test_elec = laplace(test_elec,ep)
temp=[]
temp_1=[]
for j in range(5):
gt, predictions[clf_name] = predict(clf, test_elec,5, train.metadata['timezone'],ep)
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
# Since the methods use randomized initialization, let's fix a seed here
# to make this notebook reproducible
import numpy.random
numpy.random.seed(42)
sample_period = 120
predictions = []
gts = []
fhmm = FHMM()
for building in range(5):
print('*' * 20 )
print('Casa : {}'.format(building))
print('Usando o metodo FHHM...')
print('*' * 20 )
fhmm.train(top_5_train_elec[building], sample_period=sample_period)
gt, prediction = predict(fhmm, test_elec[building], sample_period, train.metadata['timezone'])
gts.append(gt)
predictions.append(prediction)
for i in range(5):
appliance_labels = [m.label() for m in gts[i].columns.values]
gts[i].columns = appliance_labels
predictions[i].columns = appliance_labels
thread_processamento.start()
for b in buffer:
response.write(b.encode())
self.wfile.write(response.getvalue())
print("[OK] Carregando base de dados da casa: " + str(HOUSE))
buffer = []
train = DataSet('banco_unifei_casa_2.h5')
#Enumera todas as casas
buildings = [i for i in range(3)]
#Vetor que guarda os dados de todas as casas
train_elec = [None for i in range(3)]
for building in buildings:
train_elec[building] = train.buildings[building + 1].elec
print("[OK] Treinamento inicializado...")
numpy.random.seed(42)
sample_period = 120
predictions = []
gts = []
fhmm = FHMM()
fhmm.train(train_elec[0], sample_period=sample_period)
print("[OK] Processo de desagregacao iniciado...")
httpd = HTTPServer((SERVER_IP, PORT), SimpleHTTPRequestHandler)
print("[OK] Servidor HTTP Estabelecido com sucesso")
httpd.serve_forever()