Model/model_data/simulation_system/core/Settings.py

# Using a simply python file as settings for now
# TODO: migrate to dynaconf
from pathlib import Path

METRIC_FILENAME = "metrics.csv"

OPTIMISE_METRIC = "mean_absolute_error"
BEST_MODEL_COLUMN_NAME = "best_model"

# TODO: remove these setting elsewhere for CML
RESIDUAL_TRUE_LABEL = "true"
RESIDUAL_PREDICTION_LABEL = "pred"
RESIDUAL_FILE = "residual.png"
SEABORN_RESIDUAL_AXIS_FONTSIZE = 12
SEABORN_RESIDUAL_TITLE_FONTSIZE = 22
SEABORN_RESIDUAL_STYLE = "whitegrid"
SEABORN_RESIDUAL_ASPECT_RATIO = "equal"
SEABORN_RESIDUAL_PLOT_DPI = 120
SEABORN_RESIDUAL_RANGE = [-100, 100]
SEABORN_RESIDUAL_LINE_COLOUR = "black"
SEABORN_RESIDUAL_LINE_WIDTH = 1

# Can move to a hyperparmeters file
# If anything we might want to have a file that can be loaded and sent to this script
MODEL_HYPERPARAMETERS = {
    "autogluon": {
        "problem_type": "regression",
        "eval_metric": "mean_absolute_error",
        "time_limit": 45,
        "presets": "medium_quality",
        "excluded_model_types": None,
    }
}

TIMESTAMP_FORMAT = "%Y_%m_%d_%H_%M_%S"

RANDOM_SEED = 0
SUBSAMPLE_FACTOR = 200

TRAIN_AND_VALIDATION_DATA_NAME = "train_validation_data.parquet"
TEST_DATA_NAME = "test_data.parquet"

REGISTRY_FILE = "model_registry.csv"
MODEL_DIRECTORY = "model_directory"
BASE_REGISTRY_PATH = Path(__file__).parent.parent / MODEL_DIRECTORY
PREDICTION_LOCATION = Path("predictions")
PREDICTION_FILE = "prediction.json"
METADATA_FILE = "metadata.json"
MODEL_FOLDER = "model"
METRICS_FOLDER = "metrics"
DEPLOYMENT_FOLDER = "deployment"

TOTAL_FLOOR_AREA_NATIONAL_AVERAGE = 70
FLOOR_HEIGHT_NATIONAL_AVERAGE = 2.45

# If we have multiple records for a numerical field, such as floor area,
# we check the margine for error between the biggest and lowest values. If we see large
# swings in measured values, we take the most recent value for this field as we interpret this
# as inaccurate measurements in the past and use the most recent value
MULTIPLE_VALUES_MARGIN_FOR_ERROR = 0.1

COLUMNS_TO_MERGE_ON = [
    "PROPERTY_TYPE",
    "BUILT_FORM",
    "CONSTRUCTION_AGE_BAND",
    "NUMBER_HABITABLE_ROOMS",
    "NUMBER_HEATED_ROOMS",
]

FULLY_GLAZED_DESCRIPTIONS = [
    "Fully double glazed",
    "High performance glazing",
    "Fully triple glazed",
    "Full secondary glazing",
    "Multiple glazing throughout",
]

FIXED_FEATURES = [
    "PROPERTY_TYPE",
    "BUILT_FORM",
    "CONSTRUCTION_AGE_BAND",
    "NUMBER_HABITABLE_ROOMS",
    "CONSTITUENCY",
    "NUMBER_HEATED_ROOMS",
    "FIXED_LIGHTING_OUTLETS_COUNT",
    "FLOOR_HEIGHT",
    "FLOOR_LEVEL",
    "TOTAL_FLOOR_AREA",
]

COMPONENT_FEATURES = [
    "TRANSACTION_TYPE",
    "WALLS_DESCRIPTION",
    "FLOOR_DESCRIPTION",
    "LIGHTING_DESCRIPTION",
    "ROOF_DESCRIPTION",
    "MAINHEAT_DESCRIPTION",
    "HOTWATER_DESCRIPTION",
    "MAIN_FUEL",
    "MECHANICAL_VENTILATION",
    "SECONDHEAT_DESCRIPTION",
    "ENERGY_TARIFF",  # Not sure if this is relevant
    "SOLAR_WATER_HEATING_FLAG",
    "PHOTO_SUPPLY",
    "WINDOWS_DESCRIPTION",
    "GLAZED_TYPE",
    "MULTI_GLAZE_PROPORTION",
    "LOW_ENERGY_LIGHTING",
    "NUMBER_OPEN_FIREPLACES",
    "MAINHEATCONT_DESCRIPTION",
    "EXTENSION_COUNT",
    # 'GLAZED_AREA',  # May not need this since we have MULTI_GLAZE_PROPORTION
]

# For these fields, we take an average if we have multiple values
AVERAGE_FIXED_FEATURES = ["TOTAL_FLOOR_AREA", "FLOOR_HEIGHT"]

# For these fields, we take the latest value if we have multiple values
# Since more recent EPCs have been conducted with more rigour, we assume that the latest value is
# the most accurate
LATEST_FIELD = [
    "NUMBER_HABITABLE_ROOMS",
    "NUMBER_HEATED_ROOMS",
    "FIXED_LIGHTING_OUTLETS_COUNT",
    "FLOOR_LEVEL",
    "CONSTRUCTION_AGE_BAND",  # This is a field we're probably want to use verisk data for
]

# If we see thee features changing, we don't use the EPC, since deem it not to be reliable
MANDATORY_FIXED_FEATURES = ["PROPERTY_TYPE", "BUILT_FORM", "CONSTITUENCY"]

# For particularly old EPC data, we have inconsistent records so we'll only include EPCS that were
# conducted after 2010, since SAP09 was introduced in 2009 an later SAP12 was introduced in England
# and Wales from 31 July 2014
EARLIEST_EPC_DATE = "2014-08-01"

RDSAP_RESPONSE = "CURRENT_ENERGY_EFFICIENCY"
HEAT_DEMAND_RESPONSE = "ENERGY_CONSUMPTION_CURRENT"


def ordinal(n):
    if 10 <= n % 100 <= 20:
        suffix = "th"
    else:
        suffix = {1: "st", 2: "nd", 3: "rd"}.get(n % 10, "th")

    return str(n) + suffix


FLOOR_LEVEL_MAP = {
    "Basement": -1,
    "Ground": 0,
    "ground floor": 0,
    "20+": 20,
    "21st or above": 21,
    **{str(i).zfill(2): i for i in range(0, 21)},
    **{ordinal(i): i for i in range(-1, 21)},
    **{str(i): i for i in range(-1, 21)},
    **{i: i for i in range(-1, 21)},
}

BUILT_FORM_REMAP = {
    "Enclosed End-Terrace": "End-Terrace",
    "Enclosed Mid-Terrace": "Mid-Terrace",
}

DATA_PROCESSOR_SETTINGS = {
    "low_memory": False,
    "epc_minimum_count": 1,
    "column_mappings": {"UPRN": [int, str]},
}