settings.py

"All constants used in the project."

from pathlib import Path
import pandas

# The directory of this project
REPO_DIR = Path(__file__).parent

# Main necessary directories
DEPLOYMENT_PATH = REPO_DIR / "deployment_files"
FHE_KEYS = REPO_DIR / ".fhe_keys"
CLIENT_FILES = REPO_DIR / "client_files"
SERVER_FILES = REPO_DIR / "server_files"

# ALl deployment directories
DEPLOYMENT_PATH = DEPLOYMENT_PATH / "model"

# Path targeting pre-processor saved files
PRE_PROCESSOR_USER_PATH = DEPLOYMENT_PATH / 'pre_processor_user.pkl'
PRE_PROCESSOR_BANK_PATH = DEPLOYMENT_PATH / 'pre_processor_bank.pkl'
PRE_PROCESSOR_CS_AGENCY_PATH = DEPLOYMENT_PATH / 'pre_processor_cs_agency.pkl'

# Create the necessary directories
FHE_KEYS.mkdir(exist_ok=True)
CLIENT_FILES.mkdir(exist_ok=True)
SERVER_FILES.mkdir(exist_ok=True)

# Store the server's URL
SERVER_URL = "http://localhost:8000/" 

# Path to data file
DATA_PATH = "data/data.csv"

# Development settings
PROCESSED_INPUT_SHAPE = (1, 39)

CLIENT_TYPES = ["user", "bank", "cs_agency"]
INPUT_INDEXES = {
    "user": 0,
    "bank": 1,
    "cs_agency": 2,
}
INPUT_SLICES = {
    "user": slice(0, 36),  # First position: start from 0
    "bank": slice(36, 37),  # Second position: start from n_feature_user
    "cs_agency": slice(37, 39),  # Third position: start from n_feature_user + n_feature_bank
}

# Fix column order for pre-processing steps
USER_COLUMNS = [
    'Own_car', 'Own_property', 'Mobile_phone', 'Num_children', 'Household_size', 
    'Total_income', 'Age', 'Income_type', 'Education_type', 'Family_status', 'Housing_type', 
    'Occupation_type',
]
BANK_COLUMNS = ["Account_age"]
CS_AGENCY_COLUMNS = ["Years_employed", "Employed"]

_data = pandas.read_csv(DATA_PATH, encoding="utf-8")

def get_min_max(data, column):
    """Get min/max values of a column in order to input them in Gradio's API as key arguments."""
    return {
        "minimum": int(data[column].min()),
        "maximum": int(data[column].max()), 
    }

# App data min and max values
ACCOUNT_MIN_MAX = get_min_max(_data, "Account_age")
CHILDREN_MIN_MAX = get_min_max(_data, "Num_children")
INCOME_MIN_MAX = get_min_max(_data, "Total_income")
AGE_MIN_MAX = get_min_max(_data, "Age")
FAMILY_MIN_MAX = get_min_max(_data, "Household_size")

# Default values
INCOME_VALUE = 12000
AGE_VALUE = 30

# App data choices 
INCOME_TYPES = list(_data["Income_type"].unique())
OCCUPATION_TYPES = list(_data["Occupation_type"].unique())
HOUSING_TYPES = list(_data["Housing_type"].unique())
EDUCATION_TYPES = list(_data["Education_type"].unique())
FAMILY_STATUS = list(_data["Family_status"].unique())
YEARS_EMPLOYED_BINS = ['0-2', '2-5', '5-8', '8-11', '11-18', '18+']

# Years_employed bin order 
YEARS_EMPLOYED_BIN_NAME_TO_INDEX = {bin_name: i for i, bin_name in enumerate(YEARS_EMPLOYED_BINS)}

assert len(YEARS_EMPLOYED_BINS) == len(list(_data["Years_employed"].unique())), (
    "Years_employed bins are not matching the expected list"
)