def create_dataset(schema,tables,ids, n_classes, which = None):
all_instances = psda.generate_instances_for_appliances_by_dataids(schema,tables,
['use','air1','furnace1'],ids,sample_rate='15T')
X_arrays = []
y_arrays = []
sorted_classes = np.linspace(0,1,n_classes + 1)[:-1]
for instances,dataid in zip(all_instances,ids):
use = instances[0].traces[0]
use.series.fillna(0,inplace=True)
use.series = use.series.astype(float).clip(0.0000001)
air1 = instances[1].traces[0]
furnace1 = instances[2].traces[0]
total_air = da.utils.aggregate_traces([air1,furnace1],{})
total_air.series.fillna(0,inplace=True)
total_air.series = total_air.series.astype(float)
ratio_series = total_air.series/use.series
ratios = da.appliance.ApplianceTrace(ratio_series,{})
use_windows = use.get_windows(window_length,window_stride)
ratio_windows = ratios.get_windows(window_length,window_stride)
X_arrays.append(use_windows)
ratio_windows = ratio_windows[:,prediction_index].clip(0,1)
classes = np.searchsorted(sorted_classes,ratio_windows,side='right') - 1
y_arrays.append(classes_to_onehot(classes,n_classes))
X = np.concatenate(X_arrays,axis=0)
y = np.concatenate(y_arrays,axis=0)
dataset = ds.DenseDesignMatrix(X=X,y=y)
with open(os.path.join(args.data_dir,args.prefix+'_'+which+'.pkl'),'w') as f:
pickle.dump(dataset,f)
def create_dataset(schema, tables, ids, n_classes, which=None):
all_instances = psda.generate_instances_for_appliances_by_dataids(
schema, tables, ['use', 'air1', 'furnace1'], ids, sample_rate='15T')
X_arrays = []
y_arrays = []
sorted_classes = np.linspace(0, 1, n_classes + 1)[:-1]
for instances, dataid in zip(all_instances, ids):
use = instances[0].traces[0]
use.series.fillna(0, inplace=True)
use.series = use.series.astype(float).clip(0.0000001)
air1 = instances[1].traces[0]
furnace1 = instances[2].traces[0]
total_air = da.utils.aggregate_traces([air1, furnace1], {})
total_air.series.fillna(0, inplace=True)
total_air.series = total_air.series.astype(float)
ratio_series = total_air.series / use.series
ratios = da.appliance.ApplianceTrace(ratio_series, {})
use_windows = use.get_windows(window_length, window_stride)
ratio_windows = ratios.get_windows(window_length, window_stride)
X_arrays.append(use_windows)
ratio_windows = ratio_windows[:, prediction_index].clip(0, 1)
classes = np.searchsorted(sorted_classes, ratio_windows,
side='right') - 1
y_arrays.append(classes_to_onehot(classes, n_classes))
X = np.concatenate(X_arrays, axis=0)
y = np.concatenate(y_arrays, axis=0)
dataset = ds.DenseDesignMatrix(X=X, y=y)
with open(os.path.join(args.data_dir, args.prefix + '_' + which + '.pkl'),
'w') as f:
pickle.dump(dataset, f)
def create_dataset(schema,tables,ids, n_classes, which = None):
all_instances = psda.generate_instances_for_appliances_by_dataids(schema,tables,
['use','air1','furnace1'],ids,sample_rate='15T')
energy_arrays = []
temperature_arrays = []
time_arrays = []
weekday_arrays = []
target_arrays = []
sorted_classes = np.linspace(0,1,n_classes + 1)[:-1]
for instances,dataid in zip(all_instances,ids):
# format use correctly
use = instances[0].traces[0]
use.series.fillna(0,inplace=True)
use.series = use.series.astype(float).clip(0.0000001)
use_windows = use.get_windows(window_length,window_stride)
# create features sources
energy_arrays.append(use_windows)
temperature_arrays.append(np.tile([70],(use_windows.shape[0],1)))
time_arrays.append(np.tile([12],(use_windows.shape[0],1)))
weekday_arrays.append(np.tile([1,0,0,0,0,0,0],(use_windows.shape[0],1)))
# determine targets
air1 = instances[1].traces[0]
furnace1 = instances[2].traces[0]
total_air = da.utils.aggregate_traces([air1,furnace1],{})
total_air.series.fillna(0,inplace=True)
total_air.series = total_air.series.astype(float)
ratio_series = total_air.series/use.series
ratios = da.appliance.ApplianceTrace(ratio_series,{})
ratio_windows = ratios.get_windows(window_length,window_stride)
ratio_windows = ratio_windows[:,prediction_index].clip(0,1)
classes = np.searchsorted(sorted_classes,ratio_windows,side='right') - 1
target_arrays.append(classes_to_onehot(classes,n_classes))
# create data tuple
energy_arrays = np.concatenate(energy_arrays,axis=0)[:,:,np.newaxis,np.newaxis]
temperature_arrays = np.concatenate(temperature_arrays,axis=0)
time_arrays = np.concatenate(time_arrays,axis=0)
weekday_arrays = csr_matrix(np.concatenate(weekday_arrays,axis=0))
target_arrays = csr_matrix(np.concatenate(target_arrays,axis=0))
data = (energy_arrays,temperature_arrays,time_arrays,weekday_arrays,target_arrays)
# define the data specs
space = CompositeSpace([
Conv2DSpace(shape=[10,1],num_channels=1),
VectorSpace(dim=1),
VectorSpace(dim=1),
VectorSpace(dim=7,sparse=True),
VectorSpace(dim=n_classes,sparse=True)])
source = ('features0','features1','features2','features3','targets')
data_specs = (space,source)
dataset = VectorSpacesDataset(data=data,data_specs=data_specs)
with open(os.path.join(args.data_dir,args.prefix+'_'+which+'.pkl'),'w') as f:
pickle.dump(dataset,f)
def create_dataset(schema, tables, ids, n_classes, which=None):
all_instances = psda.generate_instances_for_appliances_by_dataids(
schema, tables, ['use', 'air1', 'furnace1'], ids, sample_rate='15T')
energy_arrays = []
temperature_arrays = []
time_arrays = []
weekday_arrays = []
target_arrays = []
sorted_classes = np.linspace(0, 1, n_classes + 1)[:-1]
for instances, dataid in zip(all_instances, ids):
# format use correctly
use = instances[0].traces[0]
use.series.fillna(0, inplace=True)
use.series = use.series.astype(float).clip(0.0000001)
use_windows = use.get_windows(window_length, window_stride)
# create features sources
energy_arrays.append(use_windows)
temperature_arrays.append(np.tile([70], (use_windows.shape[0], 1)))
time_arrays.append(np.tile([12], (use_windows.shape[0], 1)))
weekday_arrays.append(
np.tile([1, 0, 0, 0, 0, 0, 0], (use_windows.shape[0], 1)))
# determine targets
air1 = instances[1].traces[0]
furnace1 = instances[2].traces[0]
total_air = da.utils.aggregate_traces([air1, furnace1], {})
total_air.series.fillna(0, inplace=True)
total_air.series = total_air.series.astype(float)
ratio_series = total_air.series / use.series
ratios = da.appliance.ApplianceTrace(ratio_series, {})
ratio_windows = ratios.get_windows(window_length, window_stride)
ratio_windows = ratio_windows[:, prediction_index].clip(0, 1)
classes = np.searchsorted(sorted_classes, ratio_windows,
side='right') - 1
target_arrays.append(classes_to_onehot(classes, n_classes))
# create data tuple
energy_arrays = np.concatenate(energy_arrays, axis=0)[:, :, np.newaxis,
np.newaxis]
temperature_arrays = np.concatenate(temperature_arrays, axis=0)
time_arrays = np.concatenate(time_arrays, axis=0)
weekday_arrays = csr_matrix(np.concatenate(weekday_arrays, axis=0))
target_arrays = csr_matrix(np.concatenate(target_arrays, axis=0))
data = (energy_arrays, temperature_arrays, time_arrays, weekday_arrays,
target_arrays)
# define the data specs
space = CompositeSpace([
Conv2DSpace(shape=[10, 1], num_channels=1),
VectorSpace(dim=1),
VectorSpace(dim=1),
VectorSpace(dim=7, sparse=True),
VectorSpace(dim=n_classes, sparse=True)
])
source = ('features0', 'features1', 'features2', 'features3', 'targets')
data_specs = (space, source)
dataset = VectorSpacesDataset(data=data, data_specs=data_specs)
with open(os.path.join(args.data_dir, args.prefix + '_' + which + '.pkl'),
'w') as f:
pickle.dump(dataset, f)
