utils/pre_processing.py

"""Data pre-processing functions.

The pre-processing steps are heavily inspired by the following notebook :
https://www.kaggle.com/code/rikdifos/credit-card-approval-prediction-using-ml

Additional steps, mostly including renaming some values or features, were added for better user 
experience.
"""

import numpy
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, FunctionTransformer, KBinsDiscretizer


def _get_pipeline_replace_one_hot(func, value):
    return Pipeline([ 
        ("replace", FunctionTransformer(
            func, 
            kw_args={"value": value},
            feature_names_out='one-to-one',
        )),
        ("one_hot", OneHotEncoder(),),
    ])


def _replace_values_geq(column, value):
    return numpy.where(column >= value, f"{value}_or_more", column)

def _replace_values_eq(column, value):
    for desired_value, values_to_replace in value.items():
        column = numpy.where(numpy.isin(column, values_to_replace), desired_value, column)
    return column

def get_pre_processors():
    pre_processor_user = ColumnTransformer(
        transformers=[
            (
                "replace_num_children",
                _get_pipeline_replace_one_hot(_replace_values_geq, 2),
                ['Num_children']
            ),
            (
                "replace_num_family",
                _get_pipeline_replace_one_hot(_replace_values_geq, 3),
                ['Num_family']
            ),
            (
                "replace_income_type",
                _get_pipeline_replace_one_hot(_replace_values_eq, {"State servant": ["Pensioner", "Student"]}),
                ['Income_type']
            ),
            (
                "replace_education_type",
                _get_pipeline_replace_one_hot(_replace_values_eq, {"Higher education": ["Academic degree"]}),
                ['Education_type']
            ),
            (
                "replace_occupation_type_labor",
                _get_pipeline_replace_one_hot(
                    _replace_values_eq, 
                        {
                            "Labor_work": ["Cleaning staff", "Cooking staff", "Drivers", "Laborers", "Low-skill Laborers", "Security staff", "Waiters/barmen staff"],
                            "Office_work": ["Accountants", "Core staff", "HR staff", "Medicine staff", "Private service staff", "Realty agents", "Sales staff", "Secretaries"],
                            "High_tech_work": ["Managers", "High skill tech staff", "IT staff"],
                        },
                ),
                ['Occupation_type']
            ),
            ('one_hot_housing_fam_status', OneHotEncoder(), ['Housing_type', 'Family_status']),
            ('qbin_total_income', KBinsDiscretizer(n_bins=3, strategy='quantile', encode="onehot"), ['Total_income']),
            ('bin_age', KBinsDiscretizer(n_bins=5, strategy='uniform', encode="onehot"), ['Age']),
        ],
        remainder='passthrough',
        verbose_feature_names_out=False,
    )

    pre_processor_third_party = ColumnTransformer(
        transformers=[
            ('bin_years_employed', KBinsDiscretizer(n_bins=5, strategy='uniform', encode="onehot"), ['Years_employed'])
        ],
        remainder='passthrough',
        verbose_feature_names_out=False,
    )

    return pre_processor_user, pre_processor_third_party


def select_and_pop_features(data, columns):
    new_data = data[columns].copy()
    data.drop(columns, axis=1, inplace=True)
    return new_data