def main():
# Whether to compute Advanced Statistics (in most cases this is NOT needed)
ADVANCED_STATS = False
logging.basicConfig()
# Example logging configuration for file and console output
# logging.json: Normal logging example
# logging_noisy.json: Turns on all debugging information
# logging_quiet.json: Only logs error messages
with open("logging.json", "r") as logging_config:
logging.config.dictConfig(json.load(logging_config))
# Uses the 'epathermostat' logging
logger = logging.getLogger("epathermostat")
logger.debug("Starting...")
# Set to True to log additional warning messages, False to only display on
# console
logging.captureWarnings(True)
# data_dir = os.path.join("..", "tests", "data", "single_stage")
# data_dir = os.path.join("..", "tests", "data", "two_stage")
data_dir = os.path.join("..", "tests", "data", "two_stage_ert")
metadata_filename = os.path.join(data_dir, "epa_two_stage_metadata.csv")
# Use this to save the weather cache to local disk files
# thermostats = from_csv(metadata_filename, verbose=True, save_cache=True,
# cache_path='/tmp/epa_weather_files/')
# Verbose will override logging to display the imported thermostats. Set to
# "False" to use the logging level instead
thermostats = from_csv(metadata_filename, verbose=True)
output_dir = "."
metrics = multiple_thermostat_calculate_epa_field_savings_metrics(thermostats)
output_filename = os.path.join(output_dir, "thermostat_example_output.csv")
metrics_out = metrics_to_csv(metrics, output_filename)
stats = compute_summary_statistics(metrics_out)
if ADVANCED_STATS:
stats_advanced = compute_summary_statistics(
metrics_out, advanced_filtering=True
)
product_id = "test_product"
certification_filepath = os.path.join(
data_dir, "thermostat_example_certification.csv"
)
certification_to_csv(stats, certification_filepath, product_id)
stats_filepath = os.path.join(data_dir, "thermostat_example_stats.csv")
summary_statistics_to_csv(stats, stats_filepath, product_id)
if ADVANCED_STATS:
stats_advanced_filepath = os.path.join(
data_dir, "thermostat_example_stats_advanced.csv"
)
summary_statistics_to_csv(stats_advanced, stats_advanced_filepath, product_id)
def test_certification(combined_dataframe):
_, fname_stats = tempfile.mkstemp()
_, fname_cert = tempfile.mkstemp()
product_id = "FAKE"
stats_df = compute_summary_statistics(combined_dataframe)
certification_df = certification_to_csv(stats_df, fname_cert, product_id)
assert certification_df.shape == (5, 8)
def test_iqr_filtering(thermostat_emg_aux_constant_on_outlier):
thermostats_iqflt = list(thermostat_emg_aux_constant_on_outlier)
# Run the metrics / statistics with the outlier thermostat in place
iqflt_metrics = multiple_thermostat_calculate_epa_field_savings_metrics(
thermostats_iqflt, how="entire_dataset")
iqflt_output_dataframe = pd.DataFrame(iqflt_metrics,
columns=EXPORT_COLUMNS)
iqflt_summary_statistics = compute_summary_statistics(
iqflt_output_dataframe)
# Remove the outlier thermostat
thermostats_noiq = []
for thermostat in list(thermostats_iqflt):
if thermostat.thermostat_id != "thermostat_single_emg_aux_constant_on_outlier":
thermostats_noiq.append(thermostat)
if len(thermostats_noiq) == 5:
raise ValueError("Try again")
# Re-run the metrics / statistics with the outlier thermostat removed
noiq_metrics = multiple_thermostat_calculate_epa_field_savings_metrics(
thermostats_noiq, how="entire_dataset")
noiq_output_dataframe = pd.DataFrame(noiq_metrics, columns=EXPORT_COLUMNS)
noiq_summary_statistics = compute_summary_statistics(noiq_output_dataframe)
# Verify that the IQFLT removed the outliers by comparing this with the
# metrics with the outlier thermostat already removed.
for column in range(0, len(iqflt_summary_statistics)):
fields_iqflt = [
x for x in iqflt_summary_statistics[column] if "IQFLT" in x
]
for field_iqflt in fields_iqflt:
field_noiq = field_iqflt.replace("rhu2IQFLT", "rhu2")
left_side = iqflt_summary_statistics[column][field_iqflt]
right_side = noiq_summary_statistics[column][field_noiq]
if np.isnan(left_side) or np.isnan(right_side):
assert np.isnan(left_side) and np.isnan(right_side)
else:
assert left_side == right_side
def test_compute_summary_statistics(combined_dataframe):
summary_statistics = compute_summary_statistics(combined_dataframe)
assert [len(s) for s in summary_statistics] == [
49,
49,
49,
49,
3057,
1657,
3057,
1657,
]
def test_compute_summary_statistics_advanced(combined_dataframe):
summary_statistics = compute_summary_statistics(
combined_dataframe, advanced_filtering=True)
assert [len(s) for s in summary_statistics] == [
49,
49,
49,
49,
49,
49,
49,
49,
3057,
1657,
3057,
1657,
3057,
1657,
3057,
1657,
]
def test_summary_statistics_to_csv(combined_dataframe):
summary_statistics = compute_summary_statistics(combined_dataframe)
_, fname = tempfile.mkstemp()
product_id = "FAKE"
stats_df = summary_statistics_to_csv(summary_statistics, fname, product_id)
assert isinstance(stats_df, pd.DataFrame)
stats_df_reread = pd.read_csv(fname)
assert stats_df_reread.shape == (3225, 5)
def test_compute_summary_statistics_advanced(combined_dataframe):
summary_statistics = compute_summary_statistics(
combined_dataframe, advanced_filtering=True)
assert [len(s) for s in summary_statistics] == [
49,
49,
49,
49,
49,
49,
49,
49,
3057,
1657,
3057,
1657,
3057,
1657,
3057,
1657,
]
def test_summary_statistics_to_csv(combined_dataframe):
summary_statistics = compute_summary_statistics(combined_dataframe)
def test_summary_statistics_to_csv(combined_dataframe):
summary_statistics = compute_summary_statistics(combined_dataframe)