python LR 数据挖掘代码

在前面特征工程章节中https://blog.csdn.net/u010569893/article/details/93380700 讲到了特征工程的概念和常见的特征工程方法，那么今天将介绍下具体的数据挖掘流程。
以下示例代码中包含了大量的特征工程所涉及的步骤，包括：
缺失样本的过滤、空值的填充、异常值处理、计算特征的IV值、特征选择、特征woe编码、训练集合测试集划分、模型训练、模型评估等一系列数据挖掘的过程，欢迎大家学习和拍砖。。。

代码如下：

from pandas import DataFrame, Series
from functools import partial
from sklearn.preprocessing import KBinsDiscretizer
from sklearn.model_selection import train_test_split
import numpy as np
import math
from numpy import loadtxt
from sklearn.preprocessing import MinMaxScaler
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import roc_auc_score,classification_report,log_loss

def binning(x, nbins=5, strategy='quantile', bin_stat='mean'):

    assert strategy in ['uniform', 'quantile']
    assert bin_stat in ['mean', 'max', 'min']

    _discretizer = KBinsDiscretizer(nbins, strategy=strategy, encode='ordinal')

    _result = _discretizer.fit_transform(x.reshape((-1, 1)))
    #result = []
    #for i in _result:
    #    result.append(i[0])
    #print(result)

    return _result, _discretizer


_WOE_MIN = -10
_WOE_MAX = 10

def woe_single_x(x, y, event=1):
	nbins=5
    if np.unique(x).size <= nbins:
        #离散型特征，使用等宽分桶
        strategy = 'uniform'
    else:
        #连续型特征，使用等频分桶
        strategy = 'quantile'

    x, _discretizer = binning(x, nbins=nbins, strategy=strategy)

    event_total, non_event_tota