2021-09-22

'''标签编码（LabelEncoder）'''
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
le.fit([1,5,67,100])
print(le.classes_)
le.transform([1,1,100,67,5])

''' 独热编码（OneHotEncoder）'''
from sklearn import preprocessing #引入数据预处理模块
ohe = preprocessing.OneHotEncoder()
ohe.fit([[0, 0, 3], [1, 1, 0], [0, 2, 1], [1, 0, 2]])#先fit
ohe.transform([[0, 1, 3]]).toarray()#后transform

 '''WOE编码：有监督的编码方式，将预测类别的集中度的属性作为编码的数值
 优势：将特征的值规范到相近的尺度上，具有业务含义（经验上将，WOE的绝对值波动范围在0.1~3）
 缺陷：需要每箱中同时包含好、坏两个类别'''
def CalcWOE(df, col, target):
    '''
    :param df: dataframe containing feature and target
    :param col: 注意col这列已经经过分箱了，现在计算每箱的WOE和总的IV。
    :param target: good/bad indicator
    :return: 返回每箱的WOE(字典类型）和总的IV之和。
    '''
    total = df.groupby([col])[target].count()
    total = pd.DataFrame({'total': total})
    bad = df.groupby([col])[target].sum()
    bad = pd.DataFrame({'bad': bad})
    regroup = total.merge(bad, left_index=True, right_index=True, how='left')
    regroup.reset_index(level=0, inplace=True)
    N = sum(regroup['total'])
    B = sum(regroup['bad'])
    regroup['good'] = regroup['total'] - regroup['bad']
    G = N - B
    regroup['bad_pcnt'] = regroup['bad'].map(lambda x: x*1.0/B)
    regroup['good_pcnt'] = regroup['good'].map(lambda x: x * 1.0 / G)
    regroup['WOE'] = regroup.apply(lambda x: np.log(x.good_pcnt*1.0/x.bad_pcnt),axis = 1)
    WOE_dict = regroup[[col,'WOE']].set_index(col).to_dict(orient='index')
    IV = regroup.apply(lambda x: (x.good_pcnt-x.bad_pcnt)*np.log(x.good_pcnt*1.0/x.bad_pcnt),axis = 1)
    IV = sum(IV)
    return {"WOE": WOE_dict, 'IV':IV}