def test_meter_data_from_csv_daily_freq(sample_metadata):
meter_item = sample_metadata["il-electricity-cdd-hdd-daily"]
meter_data_filename = meter_item["meter_data_filename"]
with resource_stream("eemeter.samples", meter_data_filename) as f:
meter_data = meter_data_from_csv(f, gzipped=True, freq="daily")
assert meter_data.shape == (810, 1)
assert meter_data.index.tz.zone == "UTC"
assert meter_data.index.freq == "D"
def test_meter_data_from_csv_custom_columns(sample_metadata):
with TemporaryFile() as f:
f.write(b"start_custom,kWh\n" b"2017-01-01T00:00:00,10\n")
f.seek(0)
meter_data = meter_data_from_csv(f,
start_col="start_custom",
value_col="kWh")
assert meter_data.shape == (1, 1)
assert meter_data.index.tz.zone == "UTC"
assert meter_data.index.freq is None
def test_meter_data_from_csv(sample_metadata):
meter_item = sample_metadata["il-electricity-cdd-hdd-daily"]
meter_data_filename = meter_item["meter_data_filename"]
fname = resource_filename("eemeter.samples", meter_data_filename)
with gzip.open(fname) as f:
meter_data = meter_data_from_csv(f)
assert meter_data.shape == (810, 1)
assert meter_data.index.tz.zone == "UTC"
assert meter_data.index.freq is None
def eemeter_baseline_daily(file, temperature, install_start, install_end):
"""
This method uses linear regression to create daily load profile to
serve as the counterfactual for the period where the new measure has
been installed. The key part of this model is the temperature changepoint
determined by the heating and cooling degree days (HDD & CDD).
CalTRACK refers to a standardized model used in california to measure
energy efficiency savings from various measures (i.e. LED lightbulbs,
efficient appliances, weatherization, etc.). In this case it will be
used to model energy growth instead of savings.
"""
file = 'data/cchp_daily.csv'
daily_meter_data = eemeter.meter_data_from_csv(file, freq='daily')
# get meter data suitable for fitting a baseline model
baseline_meter_data, warnings = eemeter.get_baseline_data(
daily_meter_data, end=install_start, max_days=365)
# create a design matrix (the input to the model fitting step)
baseline_design_matrix = eemeter.create_caltrack_daily_design_matrix(
baseline_meter_data,
temperature,
)
# build a daily CalTRACK model
baseline_model = eemeter.fit_caltrack_usage_per_day_model(
baseline_design_matrix)
# get a year of reporting period data
reporting_meter_data, warnings = eemeter.get_reporting_data(
daily_meter_data, start=install_end, max_days=365)
# compute metered savings for the year of the reporting period we've selected
metered_growth_dataframe, error_bands = eemeter.metered_savings(
baseline_model,
reporting_meter_data,
temperature,
with_disaggregated=True)
# change signs for load growth
metered_growth_dataframe['metered_savings'] = metered_growth_dataframe[
'metered_savings'].apply(lambda x: x * -1)
# total metered savings
additional_load = metered_growth_dataframe.metered_savings.sum()
# metrics
metrics_raw = baseline_model.json()
r_squared_adj = metrics_raw['r_squared_adj']
cvrmse_adj = metrics_raw['avgs_metrics']['cvrmse_adj']
metrics = [r_squared_adj, cvrmse_adj, additional_load]
return metered_growth_dataframe, metrics, baseline_model
def load_sample(sample):
""" Load meter data, temperature data, and metadata for associated with a
particular sample identifier. Note: samples are simulated, not real, data.
Parameters
----------
sample : :any:`str`
Identifier of sample. Complete list can be obtained with
:any:`eemeter.samples`.
Returns
-------
meter_data, temperature_data, metadata : :any:`tuple` of :any:`pandas.DataFrame`, :any:`pandas.Series`, and :any:`dict`
Meter data, temperature data, and metadata for this sample identifier.
"""
sample_metadata = _load_sample_metadata()
metadata = sample_metadata.get(sample)
if metadata is None:
raise ValueError("Sample not found: {}. Try one of these?\n{}".format(
sample,
"\n".join([
" - {}".format(key) for key in sorted(sample_metadata.keys())
]),
))
freq = metadata.get("freq")
if freq not in ("hourly", "daily"):
freq = None
meter_data_filename = metadata["meter_data_filename"]
with resource_stream("eemeter.samples", meter_data_filename) as f:
meter_data = meter_data_from_csv(f, gzipped=True, freq=freq)
temperature_filename = metadata["temperature_filename"]
with resource_stream("eemeter.samples", temperature_filename) as f:
temperature_data = temperature_data_from_csv(f,
gzipped=True,
freq="hourly")
metadata["blackout_start_date"] = pytz.UTC.localize(
parse_date(metadata["blackout_start_date"]))
metadata["blackout_end_date"] = pytz.UTC.localize(
parse_date(metadata["blackout_end_date"]))
return meter_data, temperature_data, metadata
def _get_data(
sample, meter_file, temperature_file, heating_balance_points, cooling_balance_points
):
if sample is not None:
with resource_stream("eemeter.samples", "metadata.json") as f:
metadata = json.loads(f.read().decode("utf-8"))
if sample in metadata:
click.echo("Loading sample: {}".format(sample))
meter_file = resource_stream(
"eemeter.samples", metadata[sample]["meter_data_filename"]
)
temperature_file = resource_stream(
"eemeter.samples", metadata[sample]["temperature_filename"]
)
else:
raise click.ClickException(
"Sample not found. Try one of these?\n{}".format(
"\n".join([" - {}".format(key) for key in sorted(metadata.keys())])
)
)
if meter_file is not None:
gzipped = meter_file.name.endswith(".gz")
meter_data = meter_data_from_csv(meter_file, gzipped=gzipped)
else:
raise click.ClickException("Meter data not specified.")
if temperature_file is not None:
gzipped = temperature_file.name.endswith(".gz")
temperature_data = temperature_data_from_csv(
temperature_file, gzipped=gzipped, freq="hourly"
)
else:
raise click.ClickException("Temperature data not specified.")
return merge_temperature_data(
meter_data,
temperature_data,
heating_balance_points=heating_balance_points,
cooling_balance_points=cooling_balance_points,
)
def eemeter_baseline_ami(file, temperature, install_start, install_end):
"""
This method uses linear regression to create hourly load profile to
serve as the counterfactual for the period where the new measure has
been installed. The two key parts of this model are the temperature
and occupancy binning.
CalTRACK refers to a standardized model used in california to measure
energy efficiency savings from various measures (i.e. LED lightbulbs,
efficient appliances, weatherization, etc.). In this case it will be
used to model energy growth instead of savings.
"""
ami_data = eemeter.meter_data_from_csv(file, freq='hourly')
# get meter data suitable for fitting a baseline model
baseline_meter_data, warnings = eemeter.get_baseline_data(
ami_data, end=install_start, max_days=365)
# create design matrix for occupancy and segmentation
preliminary_design_matrix = (
eemeter.create_caltrack_hourly_preliminary_design_matrix(
baseline_meter_data,
temperature,
))
# build matrix with weights for monthly models of:
# 0.5 = prior month
# 1.0 = current month
# 0.5 = post month
segmentation = eemeter.segment_time_series(
preliminary_design_matrix.index,
'three_month_weighted' # using 3 month weighted approach
)
# assign an occupancy status to each hour of the week (0-167)
occupancy_lookup = eemeter.estimate_hour_of_week_occupancy(
preliminary_design_matrix,
segmentation=segmentation,
)
# assign temperatures to bins
temperature_bins = eemeter.fit_temperature_bins(
preliminary_design_matrix,
segmentation=segmentation,
)
# build a desgin matrix for each monthly segment
segmented_design_matrices = (
eemeter.create_caltrack_hourly_segmented_design_matrices(
preliminary_design_matrix,
segmentation,
occupancy_lookup,
temperature_bins,
))
# build a CalTRACK hourly model
baseline_model = eemeter.fit_caltrack_hourly_model(
segmented_design_matrices, occupancy_lookup, temperature_bins)
# get a year of post installation reporting data
reporting_meter_data, warnings = eemeter.get_reporting_data(
ami_data, start=install_end, max_days=365)
# compute metered load growth for the year of reporitng period
metered_growth_dataframe, error_bands = eemeter.metered_savings(
baseline_model,
reporting_meter_data,
temperature,
with_disaggregated=True)
metered_growth_dataframe['temp'] = temperature # append temperature
# change signs for load growth
metered_growth_dataframe['metered_savings'] = metered_growth_dataframe[
'metered_savings'].apply(lambda x: x * -1)
# totaled load growth
additional_load = metered_growth_dataframe.metered_savings.sum()
# metrics
r_squared_adj_list = []
cvrmse_adj_list = []
# results in a dict
model_results = list(baseline_model.json().values())
results = model_results[6]
for segment, measures in results.items():
for measure, value in measures.items():
if measure == 'r_squared_adj':
r_squared_adj_list.append(value)
if measure == 'cvrmse_adj':
cvrmse_adj_list.append(value)
r_squared_adj = mean(r_squared_adj_list)
cvrmse_adj = mean(cvrmse_adj_list)
metrics = [r_squared_adj, cvrmse_adj, additional_load]
# Return Section
return metered_growth_dataframe, metrics, baseline_model
