easy-ml/entitys/data_feaure_entity.py

# -*- coding: utf-8 -*-
"""
@author: yq
@time: 2024/11/1
@desc: 
"""

import pandas as pd

from commom import f_format_float


class CandidateFeatureEntity():
    """
    经过特征筛选后的特征信息
    """

    def __init__(self, x_column: str, breaks_list: list = None, iv_max: float = None):
        self._x_column = x_column
        self._breaks_list = breaks_list
        self._iv_max = iv_max

    @property
    def x_column(self):
        return self._x_column

    @property
    def breaks_list(self):
        return self._breaks_list

    @property
    def iv_max(self):
        return self._iv_max


class DataFeatureEntity():
    """
    数据特征准备完毕
    """

    def __init__(self, data: pd.DataFrame, x_columns: list, y_column: str):
        self._data = data
        self._x_columns = x_columns
        self._y_column = y_column

    @property
    def data(self):
        return self._data

    @property
    def x_columns(self):
        return self._x_columns

    @property
    def y_column(self):
        return self._y_column

    def get_Xdata(self):
        return self._data[self._x_columns]

    def get_Ydata(self):
        return self._data[self._y_column]

    def get_odds0(self):
        train_good_len = len(self._data[self._data[self._y_column] == 0])
        train_bad_len = len(self._data[self._data[self._y_column] == 1])
        odds0 = train_bad_len / train_good_len
        return odds0


class DataPreparedEntity():
    """
    训练集测试集特征准备完毕
    """

    def __init__(self, train_data: DataFeatureEntity, val_data: DataFeatureEntity, test_data: DataFeatureEntity,
                 *args, **kwargs):
        self._train_data = train_data
        self._val_data = val_data
        self._test_data = test_data
        self.args = args
        self.kwargs = kwargs

    @property
    def train_data(self):
        return self._train_data

    @property
    def val_data(self):
        return self._val_data

    @property
    def test_data(self):
        return self._test_data


class DataSplitEntity():
    """
    初始数据训练集测试集划分
    """

    def __init__(self, train_data: pd.DataFrame, val_data: pd.DataFrame = None, test_data: pd.DataFrame = None):
        self._train_data = train_data
        self._val_data = val_data
        self._test_data = test_data

    @property
    def train_data(self):
        return self._train_data

    @property
    def val_data(self):
        return self._val_data

    @property
    def test_data(self):
        return self._test_data

    def get_distribution(self, y_column) -> pd.DataFrame:
        df = pd.DataFrame()
        train_data_len = len(self._train_data)
        train_bad_len = len(self._train_data[self._train_data[y_column] == 1])
        train_bad_rate = f"{f_format_float(train_bad_len / train_data_len * 100, 2)}%"

        test_data_len = 0
        test_bad_len = 0
        test_bad_rate = "-"
        if self._test_data is not None:
            test_data_len = len(self._test_data)
            test_bad_len = len(self._test_data[self._test_data[y_column] == 1])
            test_bad_rate = f"{f_format_float(test_bad_len / test_data_len * 100, 2)}%"

        total = train_data_len + test_data_len
        bad_total = train_bad_len + test_bad_len
        bad_rate = f"{f_format_float(bad_total / total * 100, 2)}%"

        df["样本"] = ["训练集", "测试集", "合计"]
        df["样本数"] = [train_data_len, test_data_len, total]
        df["样本占比"] = [f"{f_format_float(train_data_len / total * 100, 2)}%",
                      f"{f_format_float(test_data_len / total * 100, 2)}%", "100%"]
        df["坏样本数"] = [train_bad_len, test_bad_len, bad_total]
        df["坏样本比例"] = [train_bad_rate, test_bad_rate, bad_rate]

        return df


if __name__ == "__main__":
    pass