| |
| import sys, json, numpy as np, polars as pl |
| sys.path.insert(0,'/workspace/huawei/v2work') |
| from cl import matrix |
| from sklearn.metrics import roc_auc_score as A |
| EX=('feat_lr2','feat_tt'); DAY=86400 |
| L=lambda t,c,s,ci: np.load(f'/workspace/huawei/v2work/ens/{t}_c{c}_s{s}.npy')[:,ci] |
| NEED=['us_since_ev','us_since_clk','us_hlen','us_nclk_all','it_imp'] |
| def frame(n): |
| X,m,f=matrix(n,1.0,extra=EX) |
| d=m.with_columns([pl.Series(c,X[:,f.index(c)]) for c in NEED]) |
| la=np.fmin(d['us_since_ev'].to_numpy(),d['us_since_clk'].to_numpy()) |
| dow=((d['ts'].to_numpy()//DAY)+3)%7 |
| seg=lambda x,b,l: np.array(l,dtype=object)[np.digitize(x,b)] |
| d=d.with_columns( |
| pl.Series('user', np.where(d['us_nohist'].to_numpy()==1,'empty',np.where(d['us_cold'].to_numpy()==1,'history-only','warm'))), |
| pl.Series('lastact', seg(la,[3600,DAY],['<1h','1-24h','>=1d'])), |
| pl.Series('stale', seg(d['tm_stale'].to_numpy(),[DAY,2*DAY],['<1d','1-2d','>=2d'])), |
| pl.Series('dow', np.array(['Mon','Tue','Wed','Thu','Fri','Sat','Sun'])[dow]), |
| ) |
| return d |
| ev=frame('eval') |
| |
| out={}; rep=[] |
| def dec(x,edges): return np.digitize(x,edges) |
| for c in (25,26): |
| d=frame(f'val{c}') |
| b0,b1,sl=L('v7base',c,0,1),L('v7base',c,1,1),L('v7slow',c,0,2); p=((b0+b1)/2+sl)/2 |
| d=d.with_columns(pl.Series('p',p)); y=d['clicked'].to_numpy(); tot=A(y,p) |
| if c==25: |
| ue=np.unique(np.nanpercentile(d.group_by('eid').agg(pl.col('us_nclk_all').first())['us_nclk_all'].to_numpy(),np.arange(10,100,10))) |
| ie=np.unique(np.nanpercentile(d['it_imp'].to_numpy(),np.arange(10,100,10))) |
| for D in (d,): |
| pass |
| d=d.with_columns(pl.Series('act_dec',dec(d['us_nclk_all'].to_numpy(),ue)),pl.Series('item_dec',dec(d['it_imp'].to_numpy(),ie))) |
| E=d.group_by('eid').agg(pl.col('clicked').max().alias('ey')) |
| d=d.join(E,on='eid',how='left'); d=d.with_columns(pl.when(pl.col('ey')==1).then(pl.lit('has-click')).otherwise(pl.lit('no-click')).alias('evclick')) |
| if c==25: ev=ev.with_columns(pl.Series('act_dec',dec(ev['us_nclk_all'].to_numpy(),ue)),pl.Series('item_dec',dec(ev['it_imp'].to_numpy(),ie))) |
| res={'auc':round(tot,5),'rows':d.height,'ctr':round(float(y.mean()),5),'segs':{}} |
| for s in ('user','lastact','stale','dow','act_dec','item_dec','evclick'): |
| R=[] |
| for k in sorted(d[s].unique().to_list()): |
| q=d.filter(pl.col(s)==k); yy=q['clicked'].to_numpy() |
| a=round(A(yy,q['p'].to_numpy()),5) if 0<yy.sum()<len(yy) else None |
| es=float((ev[s]==k).mean()) if s in ev.columns else None |
| R.append(dict(seg=str(k),share=round(q.height/d.height,4),ctr=round(float(yy.mean()),5),auc=a,eval_share=None if es is None else round(es,4))) |
| res['segs'][s]=R |
| |
| g=d.group_by('eid').agg(pl.col('ey').first(),(1-(1-pl.col('p').map_batches(lambda x: 1/(1+np.exp(-x)))).product()).alias('pe')) |
| rk=d.filter(pl.col('ey')==1).with_columns(pl.col('p').rank('average').over('eid').alias('rk')).filter(pl.col('clicked')==1)['rk'].to_numpy() |
| j=d.join(g.select('eid','pe'),on='eid',how='left'); pe=j['pe'].to_numpy(); ey=j['ey'].to_numpy() |
| |
| pw=np.log(pe+1e-12)+y*0+0; ow=A(y, pe + y*1e-6 + (ey==1)*(0) ) if False else None |
| zr=d.with_columns(pl.col('p').rank('ordinal').over('eid').alias('r'))['r'].to_numpy() |
| |
| o_within=A(y, np.log(pe+1e-12)*1000 + np.where(y==1,20,zr)) |
| |
| o_between=A(y, p + np.where(ey==1,0,-1e3)) |
| res['decomp']=dict(event_auc=round(A(g['ey'].to_numpy(),g['pe'].to_numpy()),5), |
| within_auc=round(float(((rk-1)/9).mean()),5),top1=round(float((rk==10).mean()),4), |
| oracle_within=round(o_within,5),oracle_between=round(o_between,5), |
| gap_within=round(o_within-tot,5),gap_between=round(o_between-tot,5),event_click_rate=round(float(g['ey'].mean()),4)) |
| out[c]=res |
| json.dump(out,open('/workspace/huawei/research/v7_err_scripts/err.json','w'),indent=1) |
| for c in out: |
| print(c,out[c]['auc'],out[c]['decomp']) |
| for s,R in out[c]['segs'].items(): print(' ',s,[(r['seg'],r['share'],r['eval_share'],r['ctr'],r['auc']) for r in R]) |
|
|
