def refresh_gjw_metadata(gjw_path, output_filename):
"""
Parameters
----------
gjw_path : str
The root path of the gjw dataset.
output_filename : str
The destination filename (including path and suffix), will default if not specified
directory and file structure
nilm_gjw_data
building<1>
elec
4-POWER_REAL_FINE <date> Dump.csv
5-POWER_REACTIVE_STANDARD <date> Dump.csv
...
...
building<n>
HDF5
nilm_gjw_data.hdf5
metadata
building1.yaml
dataset.yaml
meter_devices.yaml
other files
"""
if gjw_path is None: gjw_path = home_dir
check_directory_exists(gjw_path)
os.chdir(gjw_path)
gjw_path = os.getcwd(
) # sort out potential issue with slashes or backslashes
if output_filename is None:
output_filename = join(home_dir, 'HDF5', 'nilm_gjw_data.hdf5')
convert_yaml_to_hdf5(join(gjw_path, 'metadata'), output_filename)
print("Done refreshing metadata")
def convert_combed(combed_path, hdf_filename):
"""
Parameters
----------
combed_path : str
The root path of the combed dataset.
hdf_filename : str
The destination HDF5 filename (including path and suffix).
"""
check_directory_exists(combed_path)
# Open HDF5 file
store = pd.HDFStore(hdf_filename, 'w', complevel=9, complib='zlib')
chan = 1
for building, meter_array in SUBMETER_PATHS.iteritems():
for meter in meter_array:
key = Key(building=1, meter=chan)
dfs = []
total = pd.DataFrame()
for attribute in column_mapping.keys():
filename_attribute = join(combed_path, building, str(meter), "%s.csv" %attribute )
print(filename_attribute)
dfs.append(pd.read_csv(filename_attribute, parse_dates = True, index_col = 0, header = True, names=[attribute]))
total = pd.concat(dfs, axis = 1)
total.rename(columns=lambda x: column_mapping[x], inplace=True)
total.columns.set_names(LEVEL_NAMES, inplace=True)
store.put(str(key), total, format='table')
store.flush()
chan = chan+ 1
convert_yaml_to_hdf5(join(_get_module_directory(), 'metadata'),
hdf_filename)
print("Done converting COMBED to HDF5!")
def refresh_gjw_metadata(gjw_path, output_filename):
"""
Parameters
----------
gjw_path : str
The root path of the gjw dataset.
output_filename : str
The destination filename (including path and suffix), will default if not specified
directory and file structure
nilm_gjw_data
building<1>
elec
4-POWER_REAL_FINE <date> Dump.csv
5-POWER_REACTIVE_STANDARD <date> Dump.csv
...
...
building<n>
HDF5
nilm_gjw_data.hdf5
metadata
building1.yaml
dataset.yaml
meter_devices.yaml
other files
"""
if gjw_path is None: gjw_path = home_dir
check_directory_exists(gjw_path)
os.chdir(gjw_path)
gjw_path = os.getcwd() # sort out potential issue with slashes or backslashes
if output_filename is None:
output_filename =join(home_dir,'HDF5','nilm_gjw_data.hdf5')
convert_yaml_to_hdf5(join(gjw_path, 'metadata'),output_filename)
print("Done refreshing metadata")
def convert_combed(combed_path, output_filename, format='HDF'):
"""
Parameters
----------
combed_path : str
The root path of the combed dataset.
output_filename : str
The destination HDF5 filename (including path and suffix).
"""
check_directory_exists(combed_path)
# Open store
store = get_datastore(output_filename, format, mode='w')
for building_name, building_mapping in overall_dataset_mapping.iteritems():
for load_name, load_mapping in building_mapping.iteritems():
for load_mapping_path, meter_number in load_mapping.iteritems():
building_number = building_number_mapping[building_name]
key = Key(building=building_number, meter=meter_number)
dfs = []
for attribute in column_mapping.keys():
filename_attribute = join(combed_path, building_name, load_name, load_mapping_path, "%s.csv" %attribute)
print(filename_attribute)
dfs.append(pd.read_csv(filename_attribute, parse_dates=True, index_col=0, header=True, names=[attribute]))
total = pd.concat(dfs, axis=1)
total = total.tz_localize('UTC').tz_convert('Asia/Kolkata')
total.rename(columns=lambda x: column_mapping[x], inplace=True)
total.columns.set_names(LEVEL_NAMES, inplace=True)
assert total.index.is_unique
store.put(str(key), total)
convert_yaml_to_hdf5(join(_get_module_directory(), 'metadata'),
output_filename)
print("Done converting COMBED to HDF5!")
def convert_ampds(input_path, output_filename, format='HDF'):
"""
Convert AMPds R2013 as seen on Dataverse. Download the files
as CSVs and put them in the `input_path` folder for conversion.
Download URL: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/MXB7VO
Parameters:
-----------
input_path: str
The path of the directory where all the csv
files are supposed to be stored
output_filename: str
The path of the h5 file where all the
standardized data is supposed to go. The path
should refer to a particular file and not just a
random directory in order for this to work.
format: str
Defaults to HDF5
Example usage:
--------------
convert('/AMPds/electricity', 'store.h5')
"""
check_directory_exists(input_path)
files = [
f for f in listdir(input_path)
if isfile(join(input_path, f)) and '.csv' in f and '.swp' not in f
]
# Sorting Lexicographically
files.sort()
# Remove Whole Home and put it at top
files.remove("WHE.csv")
files.insert(0, "WHE.csv")
assert isdir(input_path)
store = get_datastore(output_filename, format, mode='w')
for i, csv_file in enumerate(files):
key = Key(building=1, meter=(i + 1))
print('Loading file #', (i + 1), ' : ', csv_file, '. Please wait...')
df = pd.read_csv(join(input_path, csv_file))
# Due to fixed width, column names have spaces :(
df.columns = [x.replace(" ", "") for x in df.columns]
df.index = pd.to_datetime(df[TIMESTAMP_COLUMN_NAME],
unit='s',
utc=True)
df = df.drop(TIMESTAMP_COLUMN_NAME, 1)
df = df.tz_convert(TIMEZONE)
df.rename(columns=lambda x: columnNameMapping[x], inplace=True)
df.columns.set_names(LEVEL_NAMES, inplace=True)
df = df.apply(pd.to_numeric, errors='ignore')
df = df.dropna()
df = df.astype(np.float32)
store.put(str(key), df)
print("Done with file #", (i + 1))
store.close()
metadata_path = join(_get_module_directory(), 'metadata')
print('Processing metadata...')
convert_yaml_to_hdf5(metadata_path, output_filename)
def _convert(input_path,
data_store,
measurement_mapping_func,
sort_index=True,
drop_duplicates=False):
meter_to_machine = {
1: "MainTerminal",
2: "ChipPress",
3: "ChipSaw",
4: "HighTemperatureOven",
5: "PickAndPlaceUnit",
6: "ScreenPrinter",
7: "SolderingOven",
8: "VacuumOven",
9: "VacuumPump1",
10: "VacuumPump2",
11: "WashingMachine",
}
check_directory_exists(input_path)
print("Loading factory 1...", end="... ")
chans = _find_all_channels(input_path, meter_to_machine)
for chan_id, filename in chans.items():
print(chan_id, end=" ")
stdout.flush()
key = Key(building=1, meter=chan_id)
measurements = measurement_mapping_func(chan_id)
df = _load_csv(filename,
measurements,
sort_index=sort_index,
drop_duplicates=drop_duplicates)
data_store.put(str(key), df)
print()
def test_all_datasets(directory):
print("Testing all data sets started at: {}".format(time.now()))
print("-"*60)
check_directory_exists(directory)
datasets = [f for f in listdir(directory) if isfile(join(directory, f)) and
'.h5' in f and '.swp' not in f]
for dataset in datasets:
test_single_dataset(dataset)
def convert_combed(combed_path, output_filename, format='HDF'):
"""
Parameters
----------
combed_path : str
The root path of the combed dataset.
output_filename : str
The destination HDF5 filename (including path and suffix).
"""
check_directory_exists(combed_path)
# Open store
store = get_datastore(output_filename, format, mode='w')
any_file_converted = False
for building_name, building_mapping in iteritems(overall_dataset_mapping):
for load_name, load_mapping in iteritems(building_mapping):
for load_mapping_path, meter_number in iteritems(load_mapping):
building_number = building_number_mapping[building_name]
key = Key(building=building_number, meter=meter_number)
dfs = []
for attribute in column_mapping.keys():
filename_attribute = join(combed_path, building_name, load_name, load_mapping_path, "%s.csv" %attribute)
if not os.path.isfile(filename_attribute):
# File not found directly in the combed_path provided
# Try adding 'iiitd' to it
filename_attribute = join(combed_path, 'iiitd', building_name, load_name, load_mapping_path, "%s.csv" %attribute)
if os.path.isfile(filename_attribute):
exists = True
print(filename_attribute)
df = pd.read_csv(filename_attribute, names=["timestamp", attribute])
df.index = pd.to_datetime(df["timestamp"], unit='ms')
df = df.drop("timestamp", 1)
dfs.append(df)
else:
exists = False
if exists:
total = pd.concat(dfs, axis=1)
total = total.tz_localize('UTC').tz_convert('Asia/Kolkata')
total.columns = pd.MultiIndex.from_tuples([column_mapping[x] for x in total.columns])
total.columns.set_names(LEVEL_NAMES, inplace=True)
assert total.index.is_unique
store.put(str(key), total)
any_file_converted = True
if not any_file_converted:
raise RuntimeError('No files converted, did you specify the correct path?')
convert_yaml_to_hdf5(
join(get_module_directory(), 'dataset_converters', 'combed', 'metadata'),
output_filename
)
print("Done converting COMBED to HDF5!")
def _convert(input_path, store, tz, sort_index=True):
"""
Parameters
----------
input_path : str
The root path of the REFIT dataset.
store : DataStore
The NILMTK DataStore object.
measurement_mapping_func : function
Must take these parameters:
- house_id
- chan_id
Function should return a list of tuples e.g. [('power', 'active')]
tz : str
Timezone e.g. 'US/Eastern'
sort_index : bool
"""
check_directory_exists(input_path)
# Iterate though all houses and channels
# house 14 is missing!
houses = [
1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 20, 21
]
nilmtk_house_id = 0
for house_id in houses:
nilmtk_house_id += 1
print("Loading house", house_id, end="... ")
stdout.flush()
csv_filename = join(input_path, 'House_' + str(house_id) + '.csv')
# The clean version already includes header, so we
# just skip the text version of the timestamp
usecols = [
'Unix', 'Aggregate', 'Appliance1', 'Appliance2', 'Appliance3',
'Appliance4', 'Appliance5', 'Appliance6', 'Appliance7',
'Appliance8', 'Appliance9'
]
df = _load_csv(csv_filename, usecols, tz)
if sort_index:
df = df.sort_index() # might not be sorted...
chan_id = 0
for col in df.columns:
chan_id += 1
print(chan_id, end=" ")
stdout.flush()
key = Key(building=nilmtk_house_id, meter=chan_id)
chan_df = pd.DataFrame(df[col])
chan_df.columns = pd.MultiIndex.from_tuples([('power', 'active')])
# Modify the column labels to reflect the power measurements recorded.
chan_df.columns.set_names(LEVEL_NAMES, inplace=True)
store.put(str(key), chan_df)
print('')
def convert_ampds(input_path, output_filename, format='HDF'):
"""
Convert AMPds R2013 as seen on Dataverse. Download the files
as CSVs and put them in the `input_path` folder for conversion.
Download URL: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/MXB7VO
Parameters:
-----------
input_path: str
The path of the directory where all the csv
files are supposed to be stored
output_filename: str
The path of the h5 file where all the
standardized data is supposed to go. The path
should refer to a particular file and not just a
random directory in order for this to work.
format: str
Defaults to HDF5
Example usage:
--------------
convert('/AMPds/electricity', 'store.h5')
"""
check_directory_exists(input_path)
files = [f for f in listdir(input_path) if isfile(join(input_path, f)) and
'.csv' in f and '.swp' not in f]
# Sorting Lexicographically
files.sort()
# Remove Whole Home and put it at top
files.remove("WHE.csv")
files.insert(0, "WHE.csv")
assert isdir(input_path)
store = get_datastore(output_filename, format, mode='w')
for i, csv_file in enumerate(files):
key = Key(building=1, meter=(i + 1))
print('Loading file #', (i + 1), ' : ', csv_file, '. Please wait...')
df = pd.read_csv(join(input_path, csv_file))
# Due to fixed width, column names have spaces :(
df.columns = [x.replace(" ", "") for x in df.columns]
df.index = pd.to_datetime(df[TIMESTAMP_COLUMN_NAME], unit='s', utc=True)
df = df.drop(TIMESTAMP_COLUMN_NAME, 1)
df = df.tz_convert(TIMEZONE)
df.rename(columns=lambda x: columnNameMapping[x], inplace=True)
df.columns.set_names(LEVEL_NAMES, inplace=True)
df = df.apply(pd.to_numeric, errors='ignore')
df = df.dropna()
df = df.astype(np.float32)
store.put(str(key), df)
print("Done with file #", (i + 1))
store.close()
metadata_path = join(get_module_directory(), 'dataset_converters', 'ampds', 'metadata')
print('Processing metadata...')
convert_yaml_to_hdf5(metadata_path, output_filename)
def convert_combed(combed_path, output_filename, format='HDF'):
"""
Parameters
----------
combed_path : str
The root path of the combed dataset.
output_filename : str
The destination HDF5 filename (including path and suffix).
"""
check_directory_exists(combed_path)
# Open store
store = get_datastore(output_filename, format, mode='w')
any_file_converted = False
for building_name, building_mapping in iteritems(overall_dataset_mapping):
for load_name, load_mapping in iteritems(building_mapping):
for load_mapping_path, meter_number in iteritems(load_mapping):
building_number = building_number_mapping[building_name]
key = Key(building=building_number, meter=meter_number)
dfs = []
for attribute in column_mapping.keys():
filename_attribute = join(combed_path, building_name, load_name, load_mapping_path, "%s.csv" %attribute)
if not os.path.isfile(filename_attribute):
# File not found directly in the combed_path provided
# Try adding 'iiitd' to it
filename_attribute = join(combed_path, 'iiitd', building_name, load_name, load_mapping_path, "%s.csv" %attribute)
if os.path.isfile(filename_attribute):
exists = True
print(filename_attribute)
df = pd.read_csv(filename_attribute, names=["timestamp", attribute])
df.index = pd.to_datetime(df["timestamp"], unit='ms')
df = df.drop("timestamp", 1)
dfs.append(df)
else:
exists = False
if exists:
total = pd.concat(dfs, axis=1)
total = total.tz_localize('UTC').tz_convert('Asia/Kolkata')
total.columns = pd.MultiIndex.from_tuples([column_mapping[x] for x in total.columns])
total.columns.set_names(LEVEL_NAMES, inplace=True)
assert total.index.is_unique
store.put(str(key), total)
any_file_converted = True
if not any_file_converted:
raise RuntimeError('No files converted, did you specify the correct path?')
convert_yaml_to_hdf5(join(_get_module_directory(), 'metadata'),
output_filename)
print("Done converting COMBED to HDF5!")
def _convert(input_path, store, tz, sort_index=True):
"""
Parameters
----------
input_path : str
The root path of the REFIT dataset.
store : DataStore
The NILMTK DataStore object.
measurement_mapping_func : function
Must take these parameters:
- house_id
- chan_id
Function should return a list of tuples e.g. [('power', 'active')]
tz : str
Timezone e.g. 'US/Eastern'
sort_index : bool
"""
check_directory_exists(input_path)
# Iterate though all houses and channels
# house 14 is missing!
houses = [1,2,3,4,5,6,7,8,9,10,11,12,13,15,16,17,18,19,20,21]
nilmtk_house_id = 0
for house_id in houses:
nilmtk_house_id += 1
print("Loading house", house_id, end="... ")
stdout.flush()
csv_filename = join(input_path, 'House_' + str(house_id) + '.csv')
# The clean version already includes header, so we
# just skip the text version of the timestamp
usecols = ['Unix','Aggregate','Appliance1','Appliance2','Appliance3','Appliance4','Appliance5','Appliance6','Appliance7','Appliance8','Appliance9']
df = _load_csv(csv_filename, usecols, tz)
if sort_index:
df = df.sort_index() # might not be sorted...
chan_id = 0
for col in df.columns:
chan_id += 1
print(chan_id, end=" ")
stdout.flush()
key = Key(building=nilmtk_house_id, meter=chan_id)
chan_df = pd.DataFrame(df[col])
chan_df.columns = pd.MultiIndex.from_tuples([('power', 'active')])
# Modify the column labels to reflect the power measurements recorded.
chan_df.columns.set_names(LEVEL_NAMES, inplace=True)
store.put(str(key), chan_df)
print('')
def _convert(input_path,
store,
measurement_mapping_func,
tz,
sort_index=True,
drop_duplicates=False):
"""
Parameters
----------
input_path : str
The root path of the DEPS dataset.
store : DataStore
The NILMTK DataStore object.
measurement_mapping_func : function
Must take these parameters:
- classroom_id
- chan_id
Function should return a list of tuples e.g. [('power', 'active')]
tz : str
Timezone e.g. 'US/Eastern'
sort_index : bool
Defaults to True
drop_duplicates : bool
Remove entries with duplicated timestamp (keeps the first value)
Defaults to False for backwards compatibility.
"""
check_directory_exists(input_path)
# Iterate though all classrooms and channels
classrooms = _find_all_classrooms(input_path)
for classroom_id in classrooms:
print("Loading data from 'Aula 2.2 Bis' to classroom N°",
classroom_id,
end=" ... Loading channels ")
stdout.flush()
chans = _find_all_chans(input_path, classroom_id)
for chan_id in chans:
print(chan_id, end=" ")
stdout.flush()
key = Key(building=classroom_id, meter=chan_id)
measurements = measurement_mapping_func(classroom_id, chan_id)
csv_filename = _get_csv_filename(input_path, key)
df = _load_csv(csv_filename,
measurements,
tz,
sort_index=sort_index,
drop_duplicates=drop_duplicates)
store.put(str(key), df)
print()
def convert_ampds(inputPath, hdfFilename):
'''
Parameters:
-----------
inputPath: str
The path of the directory where all the csv
files are supposed to be stored
hdfFilename: str
The path of the h5 file where all the
standardized data is supposed to go. The path
should refer to a particular file and not just a
random directory in order for this to work.
Example usage:
--------------
convert('/AMPds/electricity', 'store.h5')
'''
check_directory_exists(inputPath)
files = [f for f in listdir(inputPath) if isfile(join(inputPath, f)) and
'.csv' in f and '.swp' not in f]
# Sorting Lexicographically
files.sort()
print(files)
# Remove Whole Home and put it at top
files.remove("WHE.csv")
files.insert(0, "WHE.csv")
assert isdir(inputPath)
store = HDFStore(hdfFilename)
for i, csv_file in enumerate(files):
key = Key(building=1, meter=(i + 1))
print('Loading file #', (i + 1), ' : ', csv_file, '. Please wait...')
df = pd.read_csv(join(inputPath, csv_file))
# Due to fixed width, column names have spaces :(
df.columns = [x.replace(" ", "") for x in df.columns]
df.index = pd.to_datetime(df["TIMESTAMP"], unit='s', utc = True)
df = df.drop('TIMESTAMP', 1)
df = df.tz_localize('GMT').tz_convert('America/Vancouver')
df.rename(columns=lambda x: columnNameMapping[x], inplace=True)
df.columns.set_names(LEVEL_NAMES, inplace=True)
df = df.convert_objects(convert_numeric=True)
df = df.dropna()
df = df.astype(np.float32)
store.put(str(key), df, format='Table')
store.flush()
print("Done with file #", (i + 1))
store.close()
metadataPath = join(_get_module_directory(), 'metadata')
print('Processing metadata...')
convert_yaml_to_hdf5(metadataPath, hdfFilename)
def convert_ampds(input_path, output_filename, format="HDF"):
"""
Parameters:
-----------
input_path: str
The path of the directory where all the csv
files are supposed to be stored
output_filename: str
The path of the h5 file where all the
standardized data is supposed to go. The path
should refer to a particular file and not just a
random directory in order for this to work.
format: str
Defaults to HDF5
Example usage:
--------------
convert('/AMPds/electricity', 'store.h5')
"""
check_directory_exists(input_path)
files = [f for f in listdir(input_path) if isfile(join(input_path, f)) and ".csv" in f and ".swp" not in f]
# Sorting Lexicographically
files.sort()
# Remove Whole Home and put it at top
files.remove("WHE.csv")
files.insert(0, "WHE.csv")
assert isdir(input_path)
store = get_datastore(output_filename, format, mode="w")
for i, csv_file in enumerate(files):
key = Key(building=1, meter=(i + 1))
print("Loading file #", (i + 1), " : ", csv_file, ". Please wait...")
df = pd.read_csv(join(input_path, csv_file))
# Due to fixed width, column names have spaces :(
df.columns = [x.replace(" ", "") for x in df.columns]
df.index = pd.to_datetime(df[TIMESTAMP_COLUMN_NAME], unit="s", utc=True)
df = df.drop(TIMESTAMP_COLUMN_NAME, 1)
df = df.tz_localize("GMT").tz_convert(TIMEZONE)
df.rename(columns=lambda x: columnNameMapping[x], inplace=True)
df.columns.set_names(LEVEL_NAMES, inplace=True)
df = df.convert_objects(convert_numeric=True)
df = df.dropna()
df = df.astype(np.float32)
store.put(str(key), df)
print("Done with file #", (i + 1))
store.close()
metadata_path = join(_get_module_directory(), "metadata")
print("Processing metadata...")
convert_yaml_to_hdf5(metadata_path, output_filename)
def convert_combed(combed_path, output_filename, format='HDF'):
"""
Parameters
----------
combed_path : str
The root path of the combed dataset.
output_filename : str
The destination HDF5 filename (including path and suffix).
"""
check_directory_exists(combed_path)
# Open store
store = get_datastore(output_filename, format, mode='w')
for building_name, building_mapping in iteritems(overall_dataset_mapping):
for load_name, load_mapping in iteritems(building_mapping):
for load_mapping_path, meter_number in iteritems(load_mapping):
building_number = building_number_mapping[building_name]
key = Key(building=building_number, meter=meter_number)
dfs = []
for attribute in column_mapping.keys():
filename_attribute = join(combed_path, building_name,
load_name, load_mapping_path,
"%s.csv" % attribute)
if os.path.isfile(filename_attribute):
exists = True
print(filename_attribute)
df = pd.read_csv(filename_attribute,
header=True,
names=["timestamp", attribute])
df.index = pd.to_datetime(df["timestamp"], unit='ms')
df = df.drop("timestamp", 1)
dfs.append(df)
else:
exists = False
if exists:
total = pd.concat(dfs, axis=1)
total = total.tz_localize('UTC').tz_convert('Asia/Kolkata')
total.rename(columns=lambda x: column_mapping[x],
inplace=True)
total.columns.set_names(LEVEL_NAMES, inplace=True)
assert total.index.is_unique
store.put(str(key), total)
convert_yaml_to_hdf5(join(_get_module_directory(), 'metadata'),
output_filename)
print("Done converting COMBED to HDF5!")
def convert_iawe(iawe_path, output_filename, format="HDF"):
"""
Parameters
----------
iawe_path : str
The root path of the iawe dataset.
output_filename : str
The destination filename (including path and suffix).
"""
check_directory_exists(iawe_path)
idx = pd.DatetimeIndex(start=START_DATETIME, end=END_DATETIME, freq=FREQ)
idx = idx.tz_localize('GMT').tz_convert(TIMEZONE)
# Open data store
store = get_datastore(output_filename, format, mode='w')
electricity_path = join(iawe_path, "electricity")
# Mains data
for chan in range(1, 12):
key = Key(building=1, meter=chan)
filename = join(electricity_path, "%d.csv" % chan)
print('Loading ', chan)
df = pd.read_csv(filename, dtype=np.float64, na_values='\\N')
df.drop_duplicates(subset=["timestamp"], inplace=True)
df.index = pd.to_datetime(df.timestamp.values, unit='s', utc=True)
df = df.tz_convert(TIMEZONE)
df = df.drop(TIMESTAMP_COLUMN_NAME, 1)
df.columns = pd.MultiIndex.from_tuples(
[column_mapping[x] for x in df.columns], names=LEVEL_NAMES)
df = df.apply(pd.to_numeric, errors='ignore')
df = df.dropna()
df = df.astype(np.float32)
df = df.sort_index()
df = df.resample("1T").mean()
df = reindex_fill_na(df, idx)
assert df.isnull().sum().sum() == 0
store.put(str(key), df)
store.close()
metadata_dir = join(get_module_directory(), 'dataset_converters', 'iawe',
'metadata')
convert_yaml_to_hdf5(metadata_dir, output_filename)
print("Done converting iAWE to HDF5!")
def convert_iawe(iawe_path, output_filename, format="HDF"):
"""
Parameters
----------
iawe_path : str
The root path of the iawe dataset.
output_filename : str
The destination filename (including path and suffix).
"""
check_directory_exists(iawe_path)
idx = pd.DatetimeIndex(start=START_DATETIME, end=END_DATETIME, freq=FREQ)
idx = idx.tz_localize('GMT').tz_convert(TIMEZONE)
# Open data store
store = get_datastore(output_filename, format, mode='w')
electricity_path = join(iawe_path, "electricity")
# Mains data
for chan in range(1, 12):
key = Key(building=1, meter=chan)
filename = join(electricity_path, "%d.csv" % chan)
print('Loading ', chan)
df = pd.read_csv(filename, dtype=np.float64, na_values='\\N')
df.drop_duplicates(subset=["timestamp"], inplace=True)
df.index = pd.to_datetime(df.timestamp.values, unit='s', utc=True)
df = df.tz_convert(TIMEZONE)
df = df.drop(TIMESTAMP_COLUMN_NAME, 1)
df.rename(columns=lambda x: column_mapping[x], inplace=True)
df.columns.set_names(LEVEL_NAMES, inplace=True)
df = df.apply(pd.to_numeric, errors='ignore')
df = df.dropna()
df = df.astype(np.float32)
df = df.sort_index()
df = df.resample("1T").mean()
df = reindex_fill_na(df, idx)
assert df.isnull().sum().sum() == 0
store.put(str(key), df)
store.close()
metadata_dir = join(get_module_directory(), 'dataset_converters', 'iawe', 'metadata')
convert_yaml_to_hdf5(metadata_dir, output_filename)
print("Done converting iAWE to HDF5!")
def _convert_to_datastore(input_path, store, tz):
check_directory_exists(input_path)
homes = _get_all_homes(input_path)
for home in homes:
home_id = int(re.search("home_([\d]*).csv", home).group(1))
csv_filename = join(input_path, home)
dtype_dict = {m: np.float32 for m in MAJOR_LOAD}
dtype_dict[TIME_INDEX] = pd.datetime
whole_df = pd.read_csv(csv_filename, index_col=TIME_INDEX, dtype=dtype_dict)
del whole_df.index.name
print ("processing ", home_id, end="... ")
for meter in MAJOR_LOAD:
meter_id = int(MAJOR_LOAD.index(meter))+1
table_key = Key(building=home_id, meter=meter_id)
table_df = _load_csv(whole_df, meter, tz)
table_df.sort_index()
store.put(str(table_key), table_df)
print (meter, end=" ")
print ("finished", end="!")
print ()
def _convert(input_path, hdf_filename, measurement_mapping_func, tz):
"""
Parameters
----------
input_path : str
The root path of the REDD low_freq dataset.
hdf_filename : str
The destination HDF5 filename (including path and suffix).
measurement_mapping_func : function
Must take these parameters:
- house_id
- chan_id
Function should return a list of tuples e.g. [('power', 'active')]
tz : str
Timezone e.g. 'US/Eastern'
"""
check_directory_exists(input_path)
# Open HDF5 file
store = pd.HDFStore(hdf_filename, 'w', complevel=9, complib='zlib')
# Iterate though all houses and channels
houses = _find_all_houses(input_path)
for house_id in houses:
print("Loading house", house_id, end="... ")
stdout.flush()
chans = _find_all_chans(input_path, house_id)
for chan_id in chans:
print(chan_id, end=" ")
stdout.flush()
key = Key(building=house_id, meter=chan_id)
measurements = measurement_mapping_func(house_id, chan_id)
csv_filename = _get_csv_filename(input_path, key)
df = _load_csv(csv_filename, measurements, tz)
df = df.sort_index() # raw REDD data isn't always sorted
store.put(str(key), df, format='table')
store.flush()
print()
store.close()
def convert_iawe(iawe_path, hdf_filename):
"""
Parameters
----------
iawe_path : str
The root path of the iawe dataset.
hdf_filename : str
The destination HDF5 filename (including path and suffix).
"""
check_directory_exists(iawe_path)
# Open HDF5 file
store = pd.HDFStore(hdf_filename, 'w', complevel=9, complib='zlib')
electricity_path = join(iawe_path, "electricity")
# Mains data
for chan in range(1, 13):
key = Key(building=1, meter=chan)
filename = join(electricity_path, "%d.csv" % chan)
print('Loading ', chan)
df = pd.read_csv(filename)
df.index = pd.to_datetime(
(df.timestamp.values * 1E9).astype(int), utc=True)
df = df.tz_convert('Asia/Kolkata')
df = df.drop('timestamp', 1)
df.rename(columns=lambda x: column_mapping[x], inplace=True)
df.columns.set_names(LEVEL_NAMES, inplace=True)
df = df.convert_objects(convert_numeric=True)
df = df.dropna()
df = df.astype(np.float32)
df = df.sort_index()
store.put(str(key), df, format='table')
store.flush()
store.close()
convert_yaml_to_hdf5(join(_get_module_directory(), 'metadata'),
hdf_filename)
print("Done converting iAWE to HDF5!")
def convert_iawe(iawe_path, output_filename, format="HDF"):
"""
Parameters
----------
iawe_path : str
The root path of the iawe dataset.
output_filename : str
The destination filename (including path and suffix).
"""
check_directory_exists(iawe_path)
# Open data store
store = get_datastore(output_filename, format, mode='w')
electricity_path = join(iawe_path, "electricity")
# Mains data
for chan in range(1, 13):
key = Key(building=1, meter=chan)
filename = join(electricity_path, "%d.csv" % chan)
print('Loading ', chan)
df = pd.read_csv(filename)
df.drop_duplicates(subset=["timestamp"], inplace=True)
df.index = pd.to_datetime(df.timestamp.values, unit='s', utc=True)
df = df.tz_convert(TIMEZONE)
df = df.drop(TIMESTAMP_COLUMN_NAME, 1)
df.rename(columns=lambda x: column_mapping[x], inplace=True)
df.columns.set_names(LEVEL_NAMES, inplace=True)
df = df.convert_objects(convert_numeric=True)
df = df.dropna()
df = df.astype(np.float32)
df = df.sort_index()
store.put(str(key), df)
store.close()
convert_yaml_to_hdf5(join(_get_module_directory(), 'metadata'),
output_filename)
print("Done converting iAWE to HDF5!")
def _convert(input_path, store, measurement_mapping_func, tz, sort_index=True):
"""
Parameters
----------
input_path : str
The root path of the LAB dataset.
store : DataStore
The NILMTK DataStore object.
measurement_mapping_func : function
Must take these parameters:
- house_id
- chan_id
Function should return a list of tuples e.g. [('power', 'active')]
tz : str
Timezone e.g. 'America/Fortaleza'
sort_index : bool
"""
check_directory_exists(input_path)
# Iterate though all houses and channels
houses = _find_all_houses(input_path)
for house_id in houses:
print("Loading house", house_id, end="... ")
stdout.flush()
chans = _find_all_chans(input_path, house_id)
for chan_id in chans:
print(chan_id, end=" ")
stdout.flush()
key = Key(building=house_id, meter=chan_id)
measurements = measurement_mapping_func(house_id, chan_id)
csv_filename = _get_csv_filename(input_path, key)
df = _load_csv(csv_filename, measurements, tz)
if sort_index:
df = df.sort_index() # raw LAB data isn't always sorted
store.put(str(key), df)
print()
def _convert(input_path, store, measurement_mapping_func, tz, sort_index=True):
"""
Parameters
----------
input_path : str
The root path of the REDD low_freq dataset.
store : DataStore
The NILMTK DataStore object.
measurement_mapping_func : function
Must take these parameters:
- house_id
- chan_id
Function should return a list of tuples e.g. [('power', 'active')]
tz : str
Timezone e.g. 'US/Eastern'
sort_index : bool
"""
check_directory_exists(input_path)
# Iterate though all houses and channels
houses = _find_all_houses(input_path)
for house_id in houses:
print("Loading house", house_id, end="... ")
stdout.flush()
chans = _find_all_chans(input_path, house_id)
for chan_id in chans:
print(chan_id, end=" ")
stdout.flush()
key = Key(building=house_id, meter=chan_id)
measurements = measurement_mapping_func(house_id, chan_id)
csv_filename = _get_csv_filename(input_path, key)
df = _load_csv(csv_filename, measurements, tz)
if sort_index:
df = df.sort_index() # raw REDD data isn't always sorted
store.put(str(key), df)
print()
def convert_gjw(gjw_path, output_filename):
"""
Parameters
----------
gjw_path : str
The root path of the gjw dataset.
output_filename : str
The destination filename (including path and suffix), will default if not specified
directory and file structure
nilm_gjw_data
building<1>
elec
4-POWER_REAL_FINE <date> Dump.csv
5-POWER_REACTIVE_STANDARD <date> Dump.csv
...
...
building<n>
HDF5
nilm_gjw_data.hdf5
metadata
building1.yaml
dataset.yaml
meter_devices.yaml
other files
"""
if gjw_path is None: gjw_path = home_dir
check_directory_exists(gjw_path)
os.chdir(gjw_path)
gjw_path = os.getcwd() # sort out potential issue with slashes or backslashes
if output_filename is None:
output_filename =join(home_dir,'HDF5','nilm_gjw_data.hdf5')
# Open data store
print( 'opening datastore', output_filename)
store = get_datastore(output_filename, format, mode='w')
# walk the directory tree from the dataset home directory
#clear dataframe & add column headers
df = pd.DataFrame(columns=[ACTIVE_COLUMN_NAME,REACTIVE_COLUMN_NAME])
found = False
for current_dir, _, files in os.walk(gjw_path):
#unused second parameter of for dirs_in_current_dir
if current_dir.find('.git')!=-1 or current_dir.find('.ipynb') != -1:
#print( 'Skipping ', current_dir)
continue
print( 'checking', current_dir)
m = bld_re.search(current_dir)
if m: #The csv files may be further down the tree so this section may be repeated
building_name = m.group()
building_nbr = int(bld_nbr_re.search(building_name).group())
meter_nbr = 1
key = Key(building=building_nbr, meter=meter_nbr)
for items in fnmatch.filter(files, "4*.csv"):
# process any .CSV files found
found = True
ds = iso_date_re.search(items).group()
# print( 'found files for date:', ds,end=" ")
# found files to process
df1 = _read_file_pair(current_dir,ds) # read two csv files into a dataframe
df = pd.concat([df,df1]) # concatenate the results into one long dataframe
if found:
found = False
df = _prepare_data_for_toolkit(df)
_summarise_dataframe(df,'Prepared for tool kit')
store.put(str(key), df)
#clear dataframe & add column headers
#df = pd.DataFrame(columns=[ACTIVE_COLUMN_NAME,REACTIVE_COLUMN_NAME])
break # only 1 folder with .csv files at present
store.close()
convert_yaml_to_hdf5(join(gjw_path, 'metadata'),output_filename)
print("Done converting gjw to HDF5!")
def convert_eco(dataset_loc, hdf_filename, timezone):
"""
Parameters:
-----------
dataset_loc: str
The root directory where the dataset is located.
hdf_filename: str
The location where the hdf_filename is present.
The directory location has to contain the
hdf5file name for the converter to work.
timezone: str
specifies the timezone of the dataset.
"""
# Creating a new HDF File
store = pd.HDFStore(hdf_filename, 'w', complevel=9, complib='blosc')
check_directory_exists(dataset_loc)
directory_list = [i for i in listdir(dataset_loc) if '.txt' not in i]
directory_list.sort()
print(directory_list)
found_any_sm = False
found_any_plug = False
# Traversing every folder
for folder in directory_list:
if folder[0] == '.' or folder[-3:] == '.h5':
print('Skipping ', folder)
continue
#Building number and meter_flag
building_no = int(folder[:2])
meter_flag = None
if 'sm_csv' in folder:
meter_flag = 'sm'
elif 'plugs' in folder:
meter_flag = 'plugs'
else:
print('Skipping folder', folder)
continue
print('Computing for folder', folder)
dir_list = [i for i in listdir(join(dataset_loc, folder)) if isdir(join(dataset_loc,folder,i))]
dir_list.sort()
if meter_flag == 'plugs' and len(dir_list) < 3:
# Try harder to find the subfolders
folder = join(folder, folder[:2])
dir_list = [i for i in listdir(join(dataset_loc, folder)) if isdir(join(dataset_loc,folder,i))]
print('Current dir list:', dir_list)
for fl in dir_list:
print('Computing for folder ', fl)
fl_dir_list = [i for i in listdir(join(dataset_loc,folder,fl)) if '.csv' in i]
fl_dir_list.sort()
if meter_flag == 'sm':
for fi in fl_dir_list:
found_any_sm = True
df = pd.read_csv(join(dataset_loc,folder,fl,fi), names=[i for i in range(1,17)], dtype=np.float32)
for phase in range(1,4):
key = str(Key(building=building_no, meter=phase))
df_phase = df.loc[:,[1+phase, 5+phase, 8+phase, 13+phase]]
# get reactive power
power = df_phase.loc[:, (1+phase, 13+phase)].values
reactive = power[:,0] * np.tan(power[:,1] * np.pi / 180)
df_phase['Q'] = reactive
df_phase.index = pd.DatetimeIndex(start=fi[:-4], freq='s', periods=86400, tz='GMT')
df_phase = df_phase.tz_convert(timezone)
sm_column_name = {
1+phase:('power', 'active'),
5+phase:('current', ''),
8+phase:('voltage', ''),
13+phase:('phase_angle', ''),
'Q': ('power', 'reactive'),
}
df_phase.columns = pd.MultiIndex.from_tuples([
sm_column_name[col] for col in df_phase.columns
])
power_active = df_phase['power', 'active']
tmp_before = np.size(power_active)
df_phase = df_phase[power_active != -1]
power_active = df_phase['power', 'active']
tmp_after = np.size(power_active)
if tmp_before != tmp_after:
print('Removed missing measurements - Size before: ' + str(tmp_before) + ', size after: ' + str(tmp_after))
df_phase.columns.set_names(LEVEL_NAMES, inplace=True)
if not key in store:
store.put(key, df_phase, format='Table')
else:
store.append(key, df_phase, format='Table')
store.flush()
print('Building', building_no, ', Meter no.', phase,
'=> Done for ', fi[:-4])
else:
#Meter number to be used in key
meter_num = int(fl) + 3
key = str(Key(building=building_no, meter=meter_num))
current_folder = join(dataset_loc,folder,fl)
if not fl_dir_list:
raise RuntimeError("No CSV file found in " + current_folder)
#Getting dataframe for each csv file seperately
for fi in fl_dir_list:
found_any_plug = True
df = pd.read_csv(join(current_folder, fi), names=[1], dtype=np.float64)
df.index = pd.DatetimeIndex(start=fi[:-4].replace('.', ':'), freq='s', periods=86400, tz = 'GMT')
df.columns = pd.MultiIndex.from_tuples(plugs_column_name.values())
df = df.tz_convert(timezone)
df.columns.set_names(LEVEL_NAMES, inplace=True)
tmp_before = np.size(df.power.active)
df = df[df.power.active != -1]
tmp_after = np.size(df.power.active)
if (tmp_before != tmp_after):
print('Removed missing measurements - Size before: ' + str(tmp_before) + ', size after: ' + str(tmp_after))
# If table not present in hdf5, create or else append to existing data
if not key in store:
store.put(key, df, format='Table')
print('Building',building_no,', Meter no.',meter_num,'=> Done for ',fi[:-4])
else:
store.append(key, df, format='Table')
store.flush()
print('Building',building_no,', Meter no.',meter_num,'=> Done for ',fi[:-4])
if not found_any_plug or not found_any_sm:
raise RuntimeError('The files were not found! Please check the folder structure. Extract each ZIP file into a folder with its base name (e.g. extract "01_plugs_csv.zip" into a folder named "01_plugs_csv", etc.)')
print("Data storage completed.")
store.close()
# Adding the metadata to the HDF5file
print("Proceeding to Metadata conversion...")
meta_path = join(
get_module_directory(),
'dataset_converters',
'eco',
'metadata'
)
convert_yaml_to_hdf5(meta_path, hdf_filename)
print("Completed Metadata conversion.")
def test_all(path_to_directory):
'''
path_to_directory: Contains the h5 files on which the tests are supposed to be run
'''
check_directory_exists(path_to_directory)
#files=[f for f in listdir(path_to_directory) and '.h5' in f and '.swp' not in f]
files = [f for f in listdir(path_to_directory) if isfile(join(path_to_directory, f)) and
'.h5' in f and '.swp' not in f]
files.sort()
print ("Datasets collected and sorted. Processing...")
try:
for i, file in enumerate(files):
current_file=DataSet(join(path_to_directory, file))
print ("Printing metadata for current file...done.")
print_dict(current_file.metadata)
print (" Loading file # ", i, " : ", file, ". Please wait.")
for building_number in range(1, len(current_file.buildings)+1):
#Examine metadata for a single house
elec=current_file.buildings[building_number].elec
print ("The dataset being processed is : ", elec.dataset())
print ("Metadata for current file: ")
print_dict(current_file.buildings[building_number].metadata)
print ("Appliance label information: ", elec.appliance_label())
#print (elec.appliances)
print ("Appliances:- ")
for i in elec.appliances:
print (i)
print ("Examining sub-metered appliances...")
print ("Collecting stats on meters...Done.")
print (elec._collect_stats_on_all_meters)
print ("Timeframe: ", elec.get_timeframe())
print ("Available power AC types: ", elec.available_power_ac_types())
print ("Clearing cache...done.")
elec.clear_cache()
print ("Testing if there are meters from multiple buildings. Result returned by method: ", elec.contains_meters_from_multiple_buildings())
# TODO: Find a better way to test the correlation function
# print ("Testing the correlation function. ", elec.correlation(elec))
print ("List of disabled meters: ", elec.disabled_meters)
print ("Trying to determine the dominant appliance: ")
try:
elec.dominant_appliance()
except RuntimeError:
print ('''More than one dominant appliance in MeterGroup! (The dominant appliance per meter should be manually specified in the metadata. If it isn't and if there are multiple appliances for a meter then NILMTK assumes all appliances on that meter are dominant. NILMTK can't automatically distinguish between multiple appliances on the same meter (at least, not without using NILM!))''')
pass
print ("Dropout rate: ", elec.dropout_rate())
try:
print ("Calculating energy per meter:")
print (elec.energy_per_meter())
print ("Calculating total entropy")
print (elec.entropy())
print ("Calculating entropy per meter: ")
print (elec.entropy_per_meter())
except ValueError:
print ("ValueError: Total size of array must remain unchanged.")
pass
print ("Calculating fraction per meter.")
print (elec.fraction_per_meter())
#print ("Average energy per period: ", elec.average_energy_per_period())
print ("Executing functions...")
lis=[]
func=""
'''for function in dir(elec):
try:
start=time.time()
if ("__" not in function or "dataframe_of_meters" not in function):
func=getattr(elec, function)
print ("Currently executing ", function, ". Please wait...")
print (func())
# print ("cProfile stats - printed")
# cProfile.run("func")
end=time.time()
print ("Time taken for the entire process : ", (end - start))
except AttributeError:
print ("Attribute error occured. ")
except TypeError:
lis.append(function)
print ("Warning: TypeError")
pass'''
print ("Plotting wiring hierarchy of meters....")
elec.draw_wiring_graph()
## DISAGGREGATION STARTS HERE
appliance_type="unknown"
#TODO : appliance_type should cycle through all appliances and check for each of them. For this, use a list.
selected_appliance=nilmtk.global_meter_group.select_using_appliances(type=appliance_type)
appliance_restricted = MeterGroup(selected_appliance.meters)
if ((appliance_restricted.proportion_of_upstream_total_per_meter()) is not None):
proportion_per_appliance = appliance_restricted.proportion_of_upstream_total_per_meter()
proportion_per_appliance.plot(kind='bar');
plt.title('Appliance energy as proportion of total building energy');
plt.ylabel('Proportion');
plt.xlabel('Appliance (<appliance instance>, <building instance>, <dataset name>)');
selected_appliance.select(building=building_number).total_energy()
selected_appliance.select(building=1).plot();
appliance_restricted = MeterGroup(selected_appliance.meters)
daily_energy = pd.DataFrame([meter.average_energy_per_period(offset_alias='D')
for meter in appliance_restricted.meters])
daily_energy.plot(kind='hist');
plt.title('Histogram of daily energy');
plt.xlabel('energy (kWh)');
plt.ylabel('Occurences');
plt.legend().set_visible(False)
current_file.store.window=TimeFrame(start='2012-04-01 00:00:00-05:00', end='2012-04-02 00:00:00-05:00')
#elec.plot();
fraction = elec.submeters().fraction_per_meter().dropna()
labels = elec.get_appliance_labels(fraction.index)
plt.figure(figsize=(8,8))
fraction.plot(kind='pie', labels=labels);
elec.select_using_appliances(category='heating')
elec.select_using_appliances(category='single-phase induction motor')
co = CombinatorialOptimisation()
co.train(elec)
for model in co.model:
print_dict(model)
disag_filename = join(data_dir, 'ampds-disag.h5')
output = HDFDataStore(disag_filename, 'w')
co.disaggregate(elec.mains(), output)
output.close()
disag = DataSet(disag_filename)
disag_elec = disag.buildings[building_number].elec
f1 = f1_score(disag_elec, elec)
f1.index = disag_elec.get_appliance_labels(f1.index)
f1.plot(kind='bar')
plt.xlabel('appliance');
plt.ylabel('f-score');
disag_elec.plot()
disag.store.close()
except AttributeError:
print ("AttributeError occured while executing. This means that the value returned by proportion_per_appliance = appliance_restricted.proportion_of_upstream_total_per_meter() is None")
pass
def convert_eco(dataset_loc, hdf_filename, timezone):
"""
Parameters:
-----------
dataset_loc: str
The root directory where the dataset is located.
hdf_filename: str
The location where the hdf_filename is present.
The directory location has to contain the
hdf5file name for the converter to work.
timezone: str
specifies the timezone of the dataset.
"""
# Creating a new HDF File
store = pd.HDFStore(hdf_filename, 'w', complevel=9, complib='blosc')
check_directory_exists(dataset_loc)
directory_list = [i for i in listdir(dataset_loc) if '.txt' not in i]
directory_list.sort()
print directory_list
# Traversing every folder
for folder in directory_list:
if folder[0] == '.' or folder[-3:] == '.h5':
print 'Skipping ', folder
continue
print 'Computing for folder',folder
#Building number and meter_flag
building_no = int(folder[:2])
meter_flag = 'sm' if 'sm_csv' in folder else 'plugs'
dir_list = [i for i in listdir(join(dataset_loc, folder)) if isdir(join(dataset_loc,folder,i))]
dir_list.sort()
print 'Current dir list:',dir_list
for fl in dir_list:
print 'Computing for folder ',fl
fl_dir_list = [i for i in listdir(join(dataset_loc,folder,fl)) if '.csv' in i]
fl_dir_list.sort()
if meter_flag == 'sm':
for fi in fl_dir_list:
df = pd.read_csv(join(dataset_loc,folder,fl,fi), names=[i for i in range(1,17)], dtype=np.float32)
for phase in range(1,4):
key = str(Key(building=building_no, meter=phase))
df_phase = df.ix[:,[1+phase, 5+phase, 8+phase, 13+phase]]
# get reactive power
power = df_phase.as_matrix([1+phase, 13+phase])
reactive = power[:,0] * np.tan(power[:,1] * np.pi / 180)
df_phase['Q'] = reactive
df_phase.index = pd.DatetimeIndex(start=fi[:-4], freq='s', periods=86400, tz='GMT')
df_phase = df_phase.tz_convert(timezone)
sm_column_name = {1+phase:('power', 'active'),
5+phase:('current', ''),
8+phase:('voltage', ''),
13+phase:('phase_angle', ''),
'Q': ('power', 'reactive'),
};
df_phase.rename(columns=sm_column_name, inplace=True)
tmp_before = np.size(df_phase.power.active)
df_phase = df_phase[df_phase.power.active != -1]
tmp_after = np.size(df_phase.power.active)
if (tmp_before != tmp_after):
print('Removed missing measurements - Size before: ' + str(tmp_before) + ', size after: ' + str(tmp_after))
df_phase.columns.set_names(LEVEL_NAMES, inplace=True)
if not key in store:
store.put(key, df_phase, format='Table')
else:
store.append(key, df_phase, format='Table')
store.flush()
print 'Building',building_no,', Meter no.',phase,'=> Done for ',fi[:-4]
else:
#Meter number to be used in key
meter_num = int(fl) + 3
key = str(Key(building=building_no, meter=meter_num))
#Getting dataframe for each csv file seperately
for fi in fl_dir_list:
df = pd.read_csv(join(dataset_loc,folder,fl ,fi), names=[1], dtype=np.float64)
df.index = pd.DatetimeIndex(start=fi[:-4], freq='s', periods=86400, tz = 'GMT')
df.rename(columns=plugs_column_name, inplace=True)
df = df.tz_convert(timezone)
df.columns.set_names(LEVEL_NAMES, inplace=True)
tmp_before = np.size(df.power.active)
df = df[df.power.active != -1]
tmp_after = np.size(df.power.active)
if (tmp_before != tmp_after):
print('Removed missing measurements - Size before: ' + str(tmp_before) + ', size after: ' + str(tmp_after))
# If table not present in hdf5, create or else append to existing data
if not key in store:
store.put(key, df, format='Table')
print 'Building',building_no,', Meter no.',meter_num,'=> Done for ',fi[:-4]
else:
store.append(key, df, format='Table')
store.flush()
print 'Building',building_no,', Meter no.',meter_num,'=> Done for ',fi[:-4]
print "Data storage completed."
store.close()
# Adding the metadata to the HDF5file
print "Proceeding to Metadata conversion..."
meta_path = join(_get_module_directory(), 'metadata')
convert_yaml_to_hdf5(meta_path, hdf_filename)
print "Completed Metadata conversion."
def _convert(input_path, store, measurement_mapping_func, tz, sort_index=True):
"""
Parameters
----------
input_path : str
The root path of the REDD low_freq dataset.
store : DataStore
The NILMTK DataStore object.
measurement_mapping_func : function
Must take these parameters:
- house_id
- chan_id
Function should return a list of tuples e.g. [('power', 'active')]
tz : str
Timezone e.g. 'US/Eastern'
sort_index : bool
"""
check_directory_exists(input_path)
houses = _find_all_houses(input_path)
years = []
# Iterating though all Homes
b_cnt = 0
for house_id in houses:
b_cnt = b_cnt + 1
print('Loading Home:', house_id, end='... ')
stdout.flush()
years = _find_year(input_path, house_id)
meters_paths_csv = []
df_all_years = pd.DataFrame()
for y in years:
mains_df = pd.DataFrame()
meters_paths_csv = _find_all_csv_paths(input_path, house_id, y)
data_frames = []
if not meters_paths_csv:
continue
else:
k = 1
for path in meters_paths_csv:
# 1.Concat csv files of all meters in each year, to get all
# appliances in 1 dataframe per year
temp_df = pd.read_csv(path)
if k == 1:
k = 0
if 'use [kW]' in temp_df.columns:
mains_df = temp_df['use [kW]']
elif 'Usage [kW]' in temp_df.columns:
mains_df = temp_df['Usage [kW]']
if 'Date & Time' in temp_df.columns:
date_time_df = temp_df['Date & Time']
# Preprocess/clean dataframe by removing unusabe columns
temp_df = _preprocess_csv(temp_df)
data_frames.append(temp_df)
df_year = reduce(
lambda left, right: left.join(
right, lsuffix='_1', rsuffix='_2'), data_frames)
# Add columns 'Date & Time' and 'use [kW]'
df_year.insert(0, 'Date & Time', date_time_df)
df_year.insert(1, 'use', mains_df)
# Append all years data to 1 dataframe
df_all_years = df_all_years.append(df_year,
ignore_index=True,
sort=False)
# Change index to datetime format
df_all_years['Date & Time'] = pd.to_datetime(
df_all_years['Date & Time'], utc=True)
df_all_years.set_index('Date & Time', inplace=True)
df_all_years = df_all_years.tz_convert('US/Eastern')
# Append key value pairs to DataStore
chan_id = 0
for col in df_all_years.columns:
chan_id += 1
print(chan_id, end=' ')
stdout.flush()
key = Key(building=b_cnt, meter=chan_id)
chan_df = pd.DataFrame(df_all_years[col])
chan_df.columns = pd.MultiIndex.from_tuples([('power', 'active')])
chan_df.columns.set_names(LEVEL_NAMES, inplace=True)
store.put(str(key), chan_df)
print()
def convert_eco(dataset_loc, hdf_filename, timezone):
"""
Parameters:
-----------
dataset_loc: str
The root directory where the dataset is located.
hdf_filename: str
The location where the hdf_filename is present.
The directory location has to contain the
hdf5file name for the converter to work.
timezone: str
specifies the timezone of the dataset.
"""
# Creating a new HDF File
store = pd.HDFStore(hdf_filename, 'w')
check_directory_exists(dataset_loc)
directory_list = [i for i in listdir(dataset_loc) if '.txt' not in i]
directory_list.sort()
print directory_list
# Traversing every folder
for folder in directory_list:
print 'Computing for folder',folder
#Building number and meter_flag
building_no = int(folder[:2])
meter_flag = 'sm' if 'sm_csv' in folder else 'plugs'
dir_list = [i for i in listdir(join(dataset_loc, folder)) if isdir(join(dataset_loc,folder,i))]
dir_list.sort()
print 'Current dir list:',dir_list
for fl in dir_list:
#Meter number to be used in key
meter_num = 1 if meter_flag == 'sm' else int(fl) + 1
print 'Computing for Meter no.',meter_num
fl_dir_list = [i for i in listdir(join(dataset_loc,folder,fl)) if '.csv' in i]
fl_dir_list.sort()
key = Key(building=building_no, meter=meter_num)
for fi in fl_dir_list:
#Getting dataframe for each csv file seperately
df_fl = _get_df(join(dataset_loc,folder,fl),fi,meter_flag)
df_fl.sort_index(ascending=True,inplace=True)
df_fl = df_fl.tz_convert(timezone)
# If table not present in hdf5, create or else append to existing data
if not key in store:
store.put(str(key), df_fl, format='Table')
else:
store.append(str(key), df_fl, format='Table')
store.flush()
print 'Building',building_no,', Meter no.',meter_num,'=> Done for ',fi[:-4]
print "Data storage completed."
store.close()
# Adding the metadata to the HDF5file
print "Proceeding to Metadata conversion..."
meta_path = join(_get_module_directory(), 'metadata')
convert_yaml_to_hdf5(meta_path, hdf_filename)
print "Completed Metadata conversion."
def convert_eco(dataset_loc, hdf_filename, timezone):
"""
Parameters:
-----------
dataset_loc: str
The root directory where the dataset is located.
hdf_filename: str
The location where the hdf_filename is present.
The directory location has to contain the
hdf5file name for the converter to work.
timezone: str
specifies the timezone of the dataset.
"""
# Creating a new HDF File
store = pd.HDFStore(hdf_filename, 'w', complevel=9, complib='blosc')
check_directory_exists(dataset_loc)
directory_list = [i for i in listdir(dataset_loc) if '.txt' not in i]
directory_list.sort()
print(directory_list)
# Traversing every folder
for folder in directory_list:
if folder[0] == '.' or folder[-3:] == '.h5':
print('Skipping ', folder)
continue
print('Computing for folder', folder)
#Building number and meter_flag
building_no = int(folder[:2])
meter_flag = 'sm' if 'sm_csv' in folder else 'plugs'
dir_list = [
i for i in listdir(join(dataset_loc, folder))
if isdir(join(dataset_loc, folder, i))
]
dir_list.sort()
print('Current dir list:', dir_list)
for fl in dir_list:
print('Computing for folder ', fl)
fl_dir_list = [
i for i in listdir(join(dataset_loc, folder, fl))
if '.csv' in i
]
fl_dir_list.sort()
if meter_flag == 'sm':
for fi in fl_dir_list:
df = pd.read_csv(join(dataset_loc, folder, fl, fi),
names=[i for i in range(1, 17)],
dtype=np.float32)
for phase in range(1, 4):
key = str(Key(building=building_no, meter=phase))
df_phase = df.ix[:, [
1 + phase, 5 + phase, 8 + phase, 13 + phase
]]
# get reactive power
power = df_phase.as_matrix([1 + phase, 13 + phase])
reactive = power[:, 0] * np.tan(
power[:, 1] * np.pi / 180)
df_phase['Q'] = reactive
df_phase.index = pd.DatetimeIndex(start=fi[:-4],
freq='s',
periods=86400,
tz='GMT')
df_phase = df_phase.tz_convert(timezone)
sm_column_name = {
1 + phase: ('power', 'active'),
5 + phase: ('current', ''),
8 + phase: ('voltage', ''),
13 + phase: ('phase_angle', ''),
'Q': ('power', 'reactive'),
}
df_phase.rename(columns=sm_column_name, inplace=True)
tmp_before = np.size(df_phase.power.active)
df_phase = df_phase[df_phase.power.active != -1]
tmp_after = np.size(df_phase.power.active)
if (tmp_before != tmp_after):
print(
'Removed missing measurements - Size before: '
+ str(tmp_before) + ', size after: ' +
str(tmp_after))
df_phase.columns.set_names(LEVEL_NAMES, inplace=True)
if not key in store:
store.put(key, df_phase, format='Table')
else:
store.append(key, df_phase, format='Table')
store.flush()
print('Building', building_no, ', Meter no.', phase,
'=> Done for ', fi[:-4])
else:
#Meter number to be used in key
meter_num = int(fl) + 3
key = str(Key(building=building_no, meter=meter_num))
#Getting dataframe for each csv file seperately
for fi in fl_dir_list:
df = pd.read_csv(join(dataset_loc, folder, fl, fi),
names=[1],
dtype=np.float64)
df.index = pd.DatetimeIndex(start=fi[:-4],
freq='s',
periods=86400,
tz='GMT')
df.rename(columns=plugs_column_name, inplace=True)
df = df.tz_convert(timezone)
df.columns.set_names(LEVEL_NAMES, inplace=True)
tmp_before = np.size(df.power.active)
df = df[df.power.active != -1]
tmp_after = np.size(df.power.active)
if (tmp_before != tmp_after):
print('Removed missing measurements - Size before: ' +
str(tmp_before) + ', size after: ' +
str(tmp_after))
# If table not present in hdf5, create or else append to existing data
if not key in store:
store.put(key, df, format='Table')
print('Building', building_no, ', Meter no.',
meter_num, '=> Done for ', fi[:-4])
else:
store.append(key, df, format='Table')
store.flush()
print('Building', building_no, ', Meter no.',
meter_num, '=> Done for ', fi[:-4])
print("Data storage completed.")
store.close()
# Adding the metadata to the HDF5file
print("Proceeding to Metadata conversion...")
meta_path = join(_get_module_directory(), 'metadata')
convert_yaml_to_hdf5(meta_path, hdf_filename)
print("Completed Metadata conversion.")
def _convert(input_path,
store,
measurement_mapping_func,
tz,
valid_home_id,
sort_index=True,
drop_duplicates=False):
"""
Parameters
----------
input_path : str
The root path of the ideal low_freq dataset.
store : DataStore
The NILMTK DataStore object.
measurement_mapping_func : function
Must take these parameters:
- house_id
- chan_id
Function should return a list of tuples e.g. [('power', 'active')]
tz : str
Timezone e.g. 'US/Eastern'
sort_index : bool
Defaults to True
drop_duplicates : bool
Remove entries with duplicated timestamp (keeps the first value)
Defaults to False for backwards compatibility.
"""
check_directory_exists(input_path)
#each file containg mains/appliance is linked with a house and sensor id
filename, houses, sensor, category = _find_all_houses_sensor(
input_path, valid_home_id)
assert (len(houses) == len(sensor))
for id in range(len(houses)):
if (category[id] == 'electric-appliance'):
stdout.flush()
key = Key(building=houses[id], meter=int(sensor[id]))
csv_filename = join(input_path, filename[id])
measurements = measurement_mapping_func(houses[id], sensor[id],
category[id])
df = _load_csv(csv_filename,
measurements,
tz,
sort_index=sort_index,
drop_duplicates=drop_duplicates)
store.put(str(key), df)
elif (category[id] == 'electric-mains'):
combined_meters = sensor[id].split('c')
stdout.flush()
key = Key(building=houses[id], meter=int(combined_meters[0]))
csv_filename = join(input_path, filename[id])
measurements = measurement_mapping_func(houses[id], sensor[id],
category[id])
df = _load_csv(csv_filename,
measurements,
tz,
sort_index=sort_index,
drop_duplicates=drop_duplicates)
store.put(str(key), df)
print("Instance number:" + str(id))
print("Loading for home id:" + str(houses[id]) + "and sensor id:" +
sensor[id] + "........")
def convert_sortd(input_path, output_filename, format='HDF'):
"""Converts the dataset to NILMTK HDF5 format.
For more information about the SOR test dataset, contact Samuel Marisa.
Parameters
----------
input_path : str
The root path of the dataset. It is assumed that the YAML
metadata is in 'input_path/metadata'.
output_filename : str
The destination filename (including path and suffix).
format : str
format of output. Either 'HDF' or 'CSV'. Defaults to 'HDF'
Example usage:
--------------
convert('/sortd', 'store.h5')
"""
print(
'Attempting to convert the SORTD dataset at %s into %s in NILMTK %s format...'
% (input_path, output_filename, format))
# Ensure that the input directory exists
check_directory_exists(input_path)
# Load the dataset metadata
with open(join(input_path, 'metadata/dataset.yaml'), 'r') as stream:
dataset_metadata = yaml.load(stream)
# Open the datastore
store = get_datastore(output_filename, format, mode='w')
# Iterate through all building metadata files found in the dataset
for metadata_file in glob.glob(
join(input_path, 'metadata/building[0-9]*.yaml')):
# Load the building metadata
with open(metadata_file, 'r') as stream:
metadata = yaml.load(stream)
building_id = int(metadata['instance'])
print('==> Loading building %d defined at %s. Please wait...' %
(building_id, metadata_file))
for meter_id, meter_data in metadata['elec_meters'].items():
meter_id = int(meter_id)
key = Key(building=building_id, meter=meter_id)
# Load the raw data from the data location
print(' - Loading meter %s from %s...' %
(meter_id, meter_data['data_location']))
columns = [('power', 'active')]
df = pd.read_csv(join(input_path, meter_data['data_location']),
sep=',',
names=columns,
dtype={m: np.float32
for m in columns})
# Convert the timestamp index column to timezone-aware datetime
df.index = pd.to_datetime(df.index.values, unit='s', utc=True)
df = df.tz_convert(dataset_metadata['timezone'])
#df = pd.read_csv(join(input_path, db_file), sep=';', names=('Datetime', 'P1', 'P2', 'P3'), dtype={'P1': np.float64, 'P2': np.float64, 'P3': np.float64}, parse_dates=[1])
print(df.info())
print(df.head())
#print(df.tail())
print(" - Storing data under key %s in the datastore..." %
(str(key)))
store.put(str(key), df)
print(" - Building %s loaded!" % (building_id))
print("Adding the metadata into the store...")
save_yaml_to_datastore(join(input_path, 'metadata'), store)
print("Closing the store...")
store.close()
print("Done converting SORTD dataset to HDF5!")
def convert_eco(dataset_loc, hdf_filename, timezone):
"""
Parameters:
-----------
dataset_loc: str
The root directory where the dataset is located.
hdf_filename: str
The location where the hdf_filename is present.
The directory location has to contain the
hdf5file name for the converter to work.
timezone: str
specifies the timezone of the dataset.
"""
# Creating a new HDF File
store = pd.HDFStore(hdf_filename, 'w', complevel=9, complib='blosc')
check_directory_exists(dataset_loc)
directory_list = [i for i in listdir(dataset_loc) if '.txt' not in i]
directory_list.sort()
print(directory_list)
found_any_sm = False
found_any_plug = False
# Traversing every folder
for folder in directory_list:
if folder[0] == '.' or folder[-3:] == '.h5':
print('Skipping ', folder)
continue
#Building number and meter_flag
building_no = int(folder[:2])
meter_flag = None
if 'sm_csv' in folder:
meter_flag = 'sm'
elif 'plugs' in folder:
meter_flag = 'plugs'
else:
print('Skipping folder', folder)
continue
print('Computing for folder', folder)
dir_list = [
i for i in listdir(join(dataset_loc, folder))
if isdir(join(dataset_loc, folder, i))
]
dir_list.sort()
if meter_flag == 'plugs' and len(dir_list) < 3:
# Try harder to find the subfolders
folder = join(folder, folder[:2])
dir_list = [
i for i in listdir(join(dataset_loc, folder))
if isdir(join(dataset_loc, folder, i))
]
print('Current dir list:', dir_list)
for fl in dir_list:
print('Computing for folder ', fl)
fl_dir_list = [
i for i in listdir(join(dataset_loc, folder, fl))
if '.csv' in i
]
fl_dir_list.sort()
if meter_flag == 'sm':
for fi in fl_dir_list:
found_any_sm = True
df = pd.read_csv(join(dataset_loc, folder, fl, fi),
names=[i for i in range(1, 17)],
dtype=np.float32)
# SmartMeter
for phase in range(1, 4):
key = str(Key(building=building_no, meter=phase))
df_phase = df.loc[:, [
1 + phase, 5 + phase, 8 + phase, 13 + phase
]]
# get reactive power
power = df_phase.loc[:, (1 + phase, 13 + phase)].values
reactive = power[:, 0] * np.tan(
power[:, 1] * np.pi / 180)
df_phase['Q'] = reactive
df_phase.index = pd.DatetimeIndex(start=fi[:-4],
freq='s',
periods=86400,
tz='GMT')
df_phase = df_phase.tz_convert(timezone)
sm_column_name = {
1 + phase: ('power', 'active'),
5 + phase: ('current', ''),
8 + phase: ('voltage', ''),
13 + phase: ('phase_angle', ''),
'Q': ('power', 'reactive'),
}
df_phase.columns = pd.MultiIndex.from_tuples(
sm_column_name[col] for col in df_phase.columns)
power_active = df_phase['power', 'active']
tmp_before = np.size(power_active)
df_phase = df_phase[power_active != -1]
power_active = df_phase['power', 'active']
tmp_after = np.size(power_active)
if tmp_before != tmp_after:
print(
'Removed missing measurements - Size before: '
+ str(tmp_before) + ', size after: ' +
str(tmp_after))
df_phase.columns.set_names(LEVEL_NAMES, inplace=True)
if not key in store:
store.put(key, df_phase, format='Table')
else:
store.append(key, df_phase, format='Table')
store.flush()
print('Building', building_no, ', Meter no.', phase,
'=> Done for ', fi[:-4])
# Plugs werden auch in Meter uebersetzt und dann aber direkt mit Appliances ergaenzt
else:
#Meter number to be used in key
meter_num = int(fl) + 3
key = str(Key(building=building_no, meter=meter_num))
current_folder = join(dataset_loc, folder, fl)
if not fl_dir_list:
raise RuntimeError("No CSV file found in " +
current_folder)
#Getting dataframe for each csv file seperately
for fi in fl_dir_list:
found_any_plug = True
df = pd.read_csv(join(current_folder, fi),
names=[1],
dtype=np.float64)
df.index = pd.DatetimeIndex(start=fi[:-4].replace(
'.', ':'),
freq='s',
periods=86400,
tz='GMT')
df.columns = pd.MultiIndex.from_tuples(
plugs_column_name.values())
df = df.tz_convert(timezone)
df.columns.set_names(LEVEL_NAMES, inplace=True)
# Check whether measurements removed
tmp_before = np.size(df.power.active)
df = df[df.power.active != -1]
tmp_after = np.size(df.power.active)
if (tmp_before != tmp_after):
print('Removed missing measurements - Size before: ' +
str(tmp_before) + ', size after: ' +
str(tmp_after))
# If table not present in hdf5, create or else append to existing data
if not key in store:
store.put(key, df, format='Table')
print('Building', building_no, ', Meter no.',
meter_num, '=> Done for ', fi[:-4])
else:
store.append(key, df, format='Table')
store.flush()
print('Building', building_no, ', Meter no.',
meter_num, '=> Done for ', fi[:-4])
if not found_any_plug or not found_any_sm:
raise RuntimeError(
'The files were not found! Please check the folder structure. Extract each ZIP file into a folder with its base name (e.g. extract "01_plugs_csv.zip" into a folder named "01_plugs_csv", etc.)'
)
print("Data storage completed.")
store.close()
# Adding the metadata to the HDF5file
print("Proceeding to Metadata conversion...")
meta_path = join(get_module_directory(), 'dataset_converters', 'eco',
'metadata')
convert_yaml_to_hdf5(meta_path, hdf_filename)
print("Completed Metadata conversion.")
def convert_gjw(gjw_path, output_filename):
"""
Parameters
----------
gjw_path : str
The root path of the gjw dataset.
output_filename : str
The destination filename (including path and suffix), will default if not specified
directory and file structure
nilm_gjw_data
building<1>
elec
4-POWER_REAL_FINE <date> Dump.csv
5-POWER_REACTIVE_STANDARD <date> Dump.csv
...
...
building<n>
HDF5
nilm_gjw_data.hdf5
metadata
building1.yaml
dataset.yaml
meter_devices.yaml
other files
"""
if gjw_path is None: gjw_path = home_dir
check_directory_exists(gjw_path)
os.chdir(gjw_path)
gjw_path = os.getcwd(
) # sort out potential issue with slashes or backslashes
if output_filename is None:
output_filename = join(home_dir, 'HDF5', 'nilm_gjw_data.hdf5')
# Open data store
print('opening datastore', output_filename)
store = get_datastore(output_filename, format, mode='w')
# walk the directory tree from the dataset home directory
#clear dataframe & add column headers
df = pd.DataFrame(columns=[ACTIVE_COLUMN_NAME, REACTIVE_COLUMN_NAME])
found = False
for current_dir, _, files in os.walk(gjw_path):
#unused second parameter of for dirs_in_current_dir
if current_dir.find('.git') != -1 or current_dir.find('.ipynb') != -1:
#print( 'Skipping ', current_dir)
continue
print('checking', current_dir)
m = bld_re.search(current_dir)
if m: #The csv files may be further down the tree so this section may be repeated
building_name = m.group()
building_nbr = int(bld_nbr_re.search(building_name).group())
meter_nbr = 1
key = Key(building=building_nbr, meter=meter_nbr)
for items in fnmatch.filter(files, "4*.csv"):
# process any .CSV files found
found = True
ds = iso_date_re.search(items).group()
# print( 'found files for date:', ds,end=" ")
# found files to process
df1 = _read_file_pair(current_dir,
ds) # read two csv files into a dataframe
df = pd.concat(
[df, df1]) # concatenate the results into one long dataframe
if found:
found = False
df = _prepare_data_for_toolkit(df)
_summarise_dataframe(df, 'Prepared for tool kit')
store.put(str(key), df)
#clear dataframe & add column headers
#df = pd.DataFrame(columns=[ACTIVE_COLUMN_NAME,REACTIVE_COLUMN_NAME])
break # only 1 folder with .csv files at present
store.close()
convert_yaml_to_hdf5(join(gjw_path, 'metadata'), output_filename)
print("Done converting gjw to HDF5!")