def initialize(self, data_vec):
extra_amount = 0 #Create the initial clusters from the 1st bit of data
while True:
current_time = 0
initial_data = data_vec[current_time : current_time + self.settings.init_size - extra_amount]
initial_delta_power = [np.round(initial_data[i + 1] - initial_data[i], 2) for i in range(len(initial_data) - 1)]
initial_events = [i for i in range(len(initial_delta_power)) if (initial_delta_power[i] > self.settings.T_Positive or initial_delta_power[i] < self.settings.T_Negative)]
try:
trial_clusters = gsp.refined_clustering_block(initial_events, initial_delta_power, self.settings.sigma, self.settings.ri)
break
except np.linalg.LinAlgError:
extra_amount += 1
print("\tSVD didn't converge, retrying with {} less data".format(extra_amount))
continue
self.trial_clusters, self.pairs = gsp.pair_clusters_appliance_wise(self.trial_clusters, data_vec, initial_delta_power, self.settings.instancelimit)
return (initial_delta_power, initial_events,self.settings.init_size - extra_amount)
#%% main_val = df.values # get only readings main_ind = df.index # get only timestamp data_vec = main_val signature_database = "signature_database_labelled.csv" #the signatures were extracted of power analysis from April 28th to 30th threshold = 2000 # threshold of DTW algorithm used for appliance power signature matching delta_p = [round(data_vec[i+1] - data_vec[i], 2) for i in range(0, len(data_vec) - 1)] event = [i for i in range(0, len(delta_p)) if (delta_p[i] > T_Positive or delta_p[i] < T_Negative) ] # initial and refined clustering block of Figure 1 in the paper clusters = gsp.refined_clustering_block(event, delta_p, sigma, ri) # Feature matching block of Figure 1 in the paper finalclusters, pairs = gsp.pair_clusters_appliance_wise(clusters, data_vec, delta_p, instancelimit) appliance_pairs = gsp.feature_matching_module(pairs, delta_p, finalclusters, alpha, beta) # create appliance wise disaggregated series power_series, appliance_signatures = gsp.generate_appliance_powerseries(appliance_pairs, delta_p) # label the disaggregated appliance clusters by comparing with signature DB labeled_appliances = gsp.label_appliances(appliance_signatures, signature_database, threshold) # Attach timestamps to generated series power_timeseries = gsp.create_appliance_timeseries(power_series, main_ind) # create pandas dataframe of all series gsp_result = pd.concat(power_timeseries, axis = 1) labels= [i[1] for i in list(labeled_appliances.items())]