woe特征转换

大家好，欢迎来到IT知识分享网。

woe特征转换

class CattoWoe(BaseEstimator, TransformerMixin):
    """
    Parameters
    ----------
    label : the label column name
    Attributes
    ----------
    woe_dict : dict of intervals,example {'col1':{'xx':0.235}}
    Examples
    --------
    please refer to the readme example
    """

    def __init__(self,label,self_woedict=None):
        self.label=label
        self.self_woedict=self_woedict

    def fit(self, df):
        """
        df : data only dataframe type
        """
        self.df=df
        self.woe_dict=woe_transform(df,self.label)
        return self

    # @classmethod
    def transform(self, X=None):
        """Transform X using one-hot encoding.
        Parameters
        ----------
        X : dataframe, if you not input it will use fit data, 
            the data not contain label column
        self_woedict: the woe dict by this model fit and save to the file
        Returns
        -------
        df : type dataframe,woe data
        """
        df= X if X is not None else self.df
        woe_dict= self.self_woedict if self.self_woedict !=None else self.woe_dict
        cols=list(filter(lambda item:item not in [self.label,'num'],df.columns))
        for attr in cols:
            df[attr] = df[attr].map(woe_dict[attr])
        if X is None:
            df.drop(['num'],axis=1,inplace=True)
        return df

def woe_transform(df,label):
    #�?前只能�?�理两类�?题，对于多类的可以考虑计算WOE后乘以类�?的占比，相当于加入先验�?�率�?
#     save_path = _data_dir / 'woe_iv4.xlsx'
    writer = pd.ExcelWriter(r"C:\Users\Administrator\Desktop\project\评分卡\woe_iv4.xlsx")
    labels=df[label].unique()
    label_one=labels[0]
    label_two=labels[1]
    df['num']=df.index
    offset = 0
    def woe_(attr,offset):
        pt = pd.pivot_table(df, index=label,columns=attr, values='num', aggfunc='count').T
        if pt.empty:
            dict_v=dict(zip(df[attr].unique(),[0]))
            return dict_v,offset
            #todo
        else:
            pt['WOEi'] = np.log((pt[label_one] / pt[label_one].sum()) /
                            (pt[label_two] / pt[label_two].sum())).round(4)
            pt['IVi'] = pt.WOEi.mul((pt[label_one] / pt[label_one].sum()) -
                            (pt[label_two] / pt[label_two].sum())).round(3)
            iv = pt.IVi.sum()
            pt = pt.fillna(0)
            key = pt.index.tolist()
            value = pt.WOEi.tolist()
            dict_v = dict(zip(key, value))
            pt.to_excel(writer, 'woe明细', startrow=offset)
            offset += (pt.shape[0] + 2)
            return dict_v,offset
    cols=list(filter(lambda item:item not in [label,'num'],df.columns))
    woe_list=[]
    for col in cols:
        dict_v,offset=woe_(col,offset)
        woe_list.append(dict_v)
    writer.save()
    return dict(zip(cols,woe_list))

#woe
Cw=CattoWoe('classification')
wclf=Cw.fit(dff)
wdf=wclf.transform()
wdf

df

dff