def get_test_data(num_houses):
devices_types_unsampled={}
ids_for_devices={}
db_url='postgresql://*****:*****@db.wiki-energy.org:5432/postgres'
psda.set_url(db_url)
schema = 'shared'
tables= psda.get_table_names(schema)
print tables
table=tables[3]
ids_device_name='air1'
ids_for_devices[ids_device_name]=psda.get_dataids_with_real_values(schema,table,ids_device_name)
device_name='air1'
devices_types_unsampled[device_name]=psda.generate_type_for_appliance_by_dataids(schema,table,device_name,ids_for_devices[ids_device_name][:num_houses])
device_name='use'
devices_types_unsampled[device_name]=psda.generate_type_for_appliance_by_dataids(schema,table,device_name,ids_for_devices[ids_device_name][:num_houses])
#Resamples the data
devices_types={}
devices_types_unsplit={}
sample_rate='1T'
length='D'
for key in devices_types_unsampled:
devices_types_unsplit[key]=devices_types_unsampled[key].resample(sample_rate)
#devices_types[key]=devices_types_unsplit[key].split_by(length)
devices_types[key]=devices_types_unsplit[key]
print "Resampled " + str(key)
return devices_types
def get_type_from_dataset(device_name,schema,table_num,limit=0):
'''
Given the device name
'''
devices_types={}
devices_types_unsampled={}
db_url='postgresql://*****:*****@db.wiki-energy.org:5432/postgres'
psda.set_url(db_url)
table='group1_disaggregated_2013_0'+str(table_num)
ids_for_device=psda.get_dataids_with_real_values(schema,table,device_name)
if(limit>len(ids_for_device) or limit==0):
limit=len(ids_for_device)
device_type_orig=psda.generate_type_for_appliance_by_dataids(schema,
table,device_name,ids_for_device[:limit])
return device_type_orig
def get_type_from_dataset(device_name, table_num, limit=0):
"""
Given the device name
"""
devices_types = {}
devices_types_unsampled = {}
db_url = "postgresql://*****:*****@db.wiki-energy.org:5432/postgres"
psda.set_url(db_url)
schema = "shared"
table = "validated_0" + str(table_num) + "_2014"
ids_for_device = psda.get_dataids_with_real_values(schema, table, device_name)
if limit > len(ids_for_device) or limit == 0:
limit = len(ids_for_device)
device_type_orig = psda.generate_type_for_appliance_by_dataids(schema, table, device_name, ids_for_device[:limit])
return device_type_orig
def get_type_from_dataset(device_name, schema, table_num, limit=0):
'''
Given the device name
'''
devices_types = {}
devices_types_unsampled = {}
db_url = 'postgresql://*****:*****@db.wiki-energy.org:5432/postgres'
psda.set_url(db_url)
table = 'group1_disaggregated_2013_0' + str(table_num)
ids_for_device = psda.get_dataids_with_real_values(schema, table,
device_name)
if (limit > len(ids_for_device) or limit == 0):
limit = len(ids_for_device)
device_type_orig = psda.generate_type_for_appliance_by_dataids(
schema, table, device_name, ids_for_device[:limit])
return device_type_orig
def get_test_data(num_houses):
devices_types_unsampled = {}
ids_for_devices = {}
db_url = 'postgresql://*****:*****@db.wiki-energy.org:5432/postgres'
psda.set_url(db_url)
schema = 'shared'
tables = psda.get_table_names(schema)
print tables
table = tables[3]
ids_device_name = 'air1'
ids_for_devices[ids_device_name] = psda.get_dataids_with_real_values(
schema, table, ids_device_name)
device_name = 'air1'
devices_types_unsampled[
device_name] = psda.generate_type_for_appliance_by_dataids(
schema, table, device_name,
ids_for_devices[ids_device_name][:num_houses])
device_name = 'use'
devices_types_unsampled[
device_name] = psda.generate_type_for_appliance_by_dataids(
schema, table, device_name,
ids_for_devices[ids_device_name][:num_houses])
#Resamples the data
devices_types = {}
devices_types_unsplit = {}
sample_rate = '1T'
length = 'D'
for key in devices_types_unsampled:
devices_types_unsplit[key] = devices_types_unsampled[key].resample(
sample_rate)
#devices_types[key]=devices_types_unsplit[key].split_by(length)
devices_types[key] = devices_types_unsplit[key]
print "Resampled " + str(key)
return devices_types
tables = [u'validated_01_2014',
u'validated_02_2014',
u'validated_03_2014',
u'validated_04_2014',
u'validated_05_2014',]
db_url = "postgresql://*****:*****@db.wiki-energy.org:5432/postgres"
psda.set_url(db_url)
window_length = 10
window_stride = 1
prediction_index = 6
all_ids = []
for month in range(5):
air1_ids = psda.get_dataids_with_real_values(schema,tables[month],'air1')
furnace1_ids = psda.get_dataids_with_real_values(schema,tables[month],'furnace1')
all_ids.append(air1_ids)
all_ids.append(furnace1_ids)
common_ids = da.utils.get_common_ids(all_ids)
n = len(common_ids)
n_train = n/2
n_valid = n/4
n_test = n - (n/2 + n/4)
train_ids = common_ids[:n_train]
valid_ids = common_ids[n_train:n_train+n_valid]
test_ids = common_ids[n_train+n_valid:n_train+n_valid+n_test]
for ids,which in zip([train_ids,valid_ids,test_ids],["train","test","valid"]):
create_dataset(schema,tables[:5],ids,20,which)
import sys
import os.path
sys.path.append(os.path.join(os.pardir,os.pardir))
import disaggregator as da
import disaggregator.PecanStreetDatasetAdapter as psda
import argparse
parser = argparse.ArgumentParser(description='Process some integers.')
parser.add_argument('appliance')
args = parser.parse_args()
db_url = "postgresql://*****:*****@db.wiki-energy.org:5432/postgres"
psda.set_url(db_url)
schema = 'shared'
tables = [u'validated_01_2014',
u'validated_02_2014',
u'validated_03_2014',
u'validated_04_2014',
u'validated_05_2014',]
ids = []
for table in tables:
ids.append(psda.get_dataids_with_real_values(schema,table,args.appliance))
print sorted(da.utils.get_common_ids(ids))
u'validated_02_2014',
u'validated_03_2014',
u'validated_04_2014',
u'validated_05_2014',
]
db_url = "postgresql:/USERNAME:[email protected]:5432/postgres"
psda.set_url(db_url)
window_length = 10
window_stride = 1
prediction_index = 6
all_ids = []
for month in range(5):
air1_ids = psda.get_dataids_with_real_values(schema, tables[month],
'air1')
furnace1_ids = psda.get_dataids_with_real_values(
schema, tables[month], 'furnace1')
all_ids.append(air1_ids)
all_ids.append(furnace1_ids)
common_ids = da.utils.get_common_ids(all_ids)
#n = len(common_ids)
n = 4
n_train = n / 2
n_valid = n / 4
n_test = n - (n / 2 + n / 4)
train_ids = common_ids[:n_train]
valid_ids = common_ids[n_train:n_train + n_valid]
test_ids = common_ids[n_train + n_valid:n_train + n_valid + n_test]
n_classes = 10
print '''You can now get trace information per house. You can also see the
trace of a particular appliance. However this is the point where you are
informed that "seeing" is actually a step that comes after pickling. Do you want to pickle a house? If not you will be asked shortly to pickle a type? Enter yes or no'''
boo = raw_input()
if str(boo) == 'yes':
#house = raw_input('Enter a home id\n')
#appliance = raw_input('Enter an appliance name (this is not actually necessary at\this point):')
#query = 'select * from {0}.{1} where dataid={2}'.format(schema_names[schema], month,house)
#df = p.get_dataframe(query).fillna(0)
# temp = p.clean_dataframe(df,schema,[])
# test = p.get_month_traces_per_dataid(schema,month,house)
print 'you now have a bunch of appliance traces, one trace for each appliance in a house'
print 'here is some information about the first trace '
elif str(boo) == 'no':
print 'ok what appliance do you want?'
app = str(raw_input())
print 'this step takes quite a while'
pecan.set_url(db_url)
dataids = pecan.get_dataids_with_real_values(schema, month, app)
type = pecan.generate_traces_for_appliance_by_dataids(
schema, month, app, dataids)
utils.pickle_object(type, '{}_{}'.format(app, month))
else:
print 'what was that?'
sys.path.append(os.path.join(os.pardir, os.pardir))
import disaggregator as da
import disaggregator.PecanStreetDatasetAdapter as psda
import argparse
parser = argparse.ArgumentParser(description='Process some integers.')
parser.add_argument('appliance')
args = parser.parse_args()
db_url = "postgresql://*****:*****@db.wiki-energy.org:5432/postgres"
psda.set_url(db_url)
schema = 'shared'
tables = [
u'validated_01_2014',
u'validated_02_2014',
u'validated_03_2014',
u'validated_04_2014',
u'validated_05_2014',
]
ids = []
for table in tables:
ids.append(psda.get_dataids_with_real_values(schema, table,
args.appliance))
print sorted(da.utils.get_common_ids(ids))
#house = raw_input('Enter a home id\n')
#appliance = raw_input('Enter an appliance name (this is not actually necessary at\this point):')
#query = 'select * from {0}.{1} where dataid={2}'.format(schema_names[schema], month,house)
#df = p.get_dataframe(query).fillna(0)
# temp = p.clean_dataframe(df,schema,[])
# test = p.get_month_traces_per_dataid(schema,month,house)
print 'you now have a bunch of appliance traces, one trace for each appliance in a house'
print 'here is some information about the first trace '
elif str(boo)=='no':
print 'ok what appliance do you want?'
app = str(raw_input())
print 'this step takes quite a while'
pecan.set_url(db_url)
dataids = pecan.get_dataids_with_real_values(schema,month,app)
type = pecan.generate_traces_for_appliance_by_dataids(schema, month,app,dataids)
utils.pickle_object(type, '{}_{}'.format(app,month))
else:
print 'what was that?'
