easy-ml/feature/feature_utils.py

# -*- coding:utf-8 -*-
"""
@author: yq
@time: 2023/12/28
@desc:  特征工具类
"""
import pandas as pd
from sklearn.preprocessing import KBinsDiscretizer
from entitys import DataSplitEntity
from enums import BinsStrategyEnum


def f_get_bins(data: DataSplitEntity, feat: str, strategy: str='quantile', nbins: int=10) -> pd.DataFrame:
    # 等频分箱
    if strategy == BinsStrategyEnum.QUANTILE.value:
        kbin_encoder = KBinsDiscretizer(n_bins=nbins, encode='ordinal', strategy='quantile')
        feature_binned = kbin_encoder.fit_transform(data[feat])
        return feature_binned.astype(int).astype(str)
    # 等宽分箱
    if strategy == BinsStrategyEnum.WIDTH.value:
        bin_width = (data[feat].max() - data[feat].min()) / nbins
        return pd.cut(data[feat], bins=nbins, labels=[f'Bin_{i}' for i in range(1, nbins + 1)])


def f_get_woe(data: DataSplitEntity) -> pd.DataFrame:
    pass


def f_get_iv(data: DataSplitEntity) -> pd.DataFrame:
    pass


def f_get_psi(data: DataSplitEntity) -> pd.DataFrame:
    pass


def f_get_corr(data: DataSplitEntity) -> pd.DataFrame:
    pass


def f_get_ivf(data: DataSplitEntity) -> pd.DataFrame:
    pass