ModelEvaluate.py 文件源码

def plot_ks_cdf(y_true,y_score,pos_label=1,label_map=None,color_map=None,decimals=0,
                xlabel='Score',ylabel='CumSum',fontsize=12,figsize=(18,8),close=True):
    '''
    ??: ??KS???????????????????
    ???: 
    y_true: ?????series?????????{0,1}?{-1,1}??
    y_score: ?????series????????????????????
    pos_label: int?????positive?????
    label_map: ???????????????{0:'Good',1:'Bad'}?
    color_map: ????????????????{0:'g',1:'r'}?
    decimals: ?????????
    xlabel: ??????xlabel?
    ylabel: ??????ylabel?
    fontsize: int??????
    close: ???????
    ???: 
    ????????{'ks': KS??'split': KS??????'fig': ?????????}?
    '''
    if label_map is None:
        label_map={0:'Good',1:'Bad'}
    ks_dict = {}
    y_true=pd.Series(y_true)
    y_score=pd.Series(y_score)
    y_score_dataframe=pd.concat([y_true,y_score],axis=1)
    ks=cal_ks(y_true,y_score_dataframe,pos_label=pos_label,return_split=False,decimals=decimals)
    score_split=cal_ks(y_true,y_score_dataframe,pos_label=pos_label,return_split=True,decimals=decimals)

    crossfreq = pd.crosstab(y_score.round(decimals),y_true)
    crossdens = crossfreq.cumsum(axis=0) / crossfreq.sum()
    color=crossdens.columns.map(lambda xx: color_map.get(xx,None))
    crossdens=crossdens.rename(columns=label_map)
    crossdens.columns.name=''
    fig = plt.figure(figsize=figsize)
    ax = fig.add_subplot(111)
    crossdens.plot(kind='line',ax=ax,fontsize=fontsize,color=color)
    ax.set_xlabel(xlabel,fontsize=fontsize)
    ax.set_ylabel(ylabel,fontsize=fontsize)
    ax.set_title('CDF Curve (KS=%.2f, SPLIT=%.*f)'%(ks,decimals,score_split),fontsize=fontsize)
    if close:
        plt.close('all')    
    ks_dict['ks'] = ks
    ks_dict['split'] = score_split
    ks_dict['fig'] = fig
    return ks_dict