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
parser = argparse.ArgumentParser(description='create appliance detection datasets for pylearn2.')
parser.add_argument('data_dir',type=str,
help='directory in which to store data')
parser.add_argument('prefix',type=str,
help='prefix for dataset files')
args = parser.parse_args()
schema = 'shared'
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
type=str,
help='directory in which to store data')
parser.add_argument('prefix', type=str, help='prefix for dataset files')
args = parser.parse_args()
schema = 'shared'
tables = [
u'validated_01_2014',
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)
def setUp(self):
psda.set_url(settings.PECAN_STREET_DB_URL)
import sys
sys.path.append('../')
#print sys.path
'''
An interface for adapting Pecan Street data.
'''
import disaggregator.PecanStreetDatasetAdapter as pecan
import pickle
import disaggregator.utils as utils
# Open db connection
db_url = "postgresql://*****:*****@db.wiki-energy.org:5432/postgres"
pecan.set_url(db_url)
schema_names = {
'curated': '\"PecanStreet_CuratedSets\"',
'raw': '\"PecanStreet_RawData\"',
'shared': '\"PecanStreet_SharedData\"'
}
print '''There are two datasets you can view right now, one is called curated,
and one is called shared. The shared data set has one minute interval data
for Jan-May 2014, for about 200 homes.
The curated data set has 15 minute interval data for 2013 and 2012 (the largest
interval lasts from 12/12-11/13.
If you want to analyze longer term data, the curated set is recommended,
#print sys.path
'''
An interface for adapting Pecan Street data.
'''
import disaggregator.PecanStreetDatasetAdapter as pecan
import pickle
import disaggregator.utils as utils
# Open db connection
db_url = "postgresql://*****:*****@db.wiki-energy.org:5432/postgres"
pecan.set_url(db_url)
schema_names = {'curated':'\"PecanStreet_CuratedSets\"',
'raw':'\"PecanStreet_RawData\"',
'shared':'\"PecanStreet_SharedData\"'}
print '''There are two datasets you can view right now, one is called curated,
and one is called shared. The shared data set has one minute interval data
for Jan-May 2014, for about 200 homes.
The curated data set has 15 minute interval data for 2013 and 2012 (the largest
interval lasts from 12/12-11/13.
If you want to analyze longer term data, the curated set is recommended,
whereas if you want shorter but more frequent data the shared set
is recommended.
def setUp(self):
psda.set_url(settings.PECAN_STREET_DB_URL)