18 · 真实广告点击：概率、校准与模拟拍卖

from pathlib import Path
import sys
ROOT=Path.cwd()
if not (ROOT/'reclab').is_dir(): ROOT=ROOT.parent
sys.path.insert(0,str(ROOT))
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from reclab.ads import latest
from reclab.paths import ARTIFACTS
receipt, result=latest()
folder=ARTIFACTS/'experiments/ads'/receipt['run_id']
print('Shared run:', receipt['run_id'])
print(result['scope'])
display(pd.DataFrame(result['splits']).T)
assert sum(x['n'] for x in result['splits'].values())==receipt['config']['rows']
print('Feature duplicate rows:',result['feature_duplicate_rows'])
print('Grouping uses features only; no temporal/user holdout is claimed.')

Shared run: 20261030T125738-f82b6582
Criteo official sampled click logs: first 200,000 rows of one 766,864-row parquet shard (2015-02-15). Real CTR task on a subsampled distribution. Auction is a separate synthetic market.

Feature duplicate rows: 1
Grouping uses features only; no temporal/user holdout is claimed.

summary=pd.DataFrame([{'method':r['method'],**{k:r['audit'][k] for k in ['auc','logloss','brier','ece']},'fit_seconds':r['fit_seconds']} for r in result['rows']])
display(summary.round(6))
print('GBDT family selected by select logloss:',result['selected_base'])
fig,axes=plt.subplots(1,2,figsize=(11,4))
for row in result['rows']:
    if row['method'] in [result['selected_base'],'selected_sigmoid','selected_isotonic']:
        bins=row['audit']['reliability']
        axes[0].plot([b['mean_probability'] for b in bins],[b['click_rate'] for b in bins],marker='o',label=row['method'])
axes[0].plot([0,1],[0,1],'k--',alpha=.5)
axes[0].set(xlabel='Mean predicted probability',ylabel='Observed click rate',title='Audit reliability: sparse high bins')
axes[0].legend(fontsize=8)
axes[1].barh(summary.method,summary.logloss)
axes[1].set(xlabel='Audit logloss (lower is better)',title='All baselines and negative results')
fig.tight_layout()
preview=ROOT/'artifacts/notebook-previews';preview.mkdir(parents=True,exist_ok=True)
fig.savefig(preview/'18_probability.png',dpi=140)
plt.show()

Notebook 保存的输出 · 本页未执行

	method	auc	logloss	brier	ece	fit_seconds
0	train_prior	0.500000	0.145515	0.032048	0.000272	0.000000
1	linear_onehot	0.721468	0.135423	0.031193	0.004382	4.102396
2	gbdt_80	0.706329	0.136029	0.031221	0.001738	0.555461
3	gbdt_160	0.703035	0.137404	0.031358	0.005350	0.932227
4	selected_sigmoid	0.706329	0.135968	0.031219	0.001149	0.008740
5	selected_isotonic	0.703064	0.136437	0.031302	0.001163	0.006879

GBDT family selected by select logloss: gbdt_80

<Figure size 1100x400 with 2 Axes>

print(result['paired_sigmoid'])
display(pd.DataFrame([{'segment':s['segment'],'n':s['raw']['n'],'CTR':s['raw']['click_rate'],'raw_logloss':s['raw']['logloss'],'sigmoid_logloss':s['sigmoid']['logloss']} for s in result['segments']]))
failures=result['failures']
print('Eight highest sigmoid-loss audit exposures: clicked count =',sum(r['label'] for r in failures))
print('Detailed failure rows and all per-row predictions stay in the ignored local artifact directory.')
print('Explain: rare positive misses, missingness and unseen categories are hypotheses; anonymous features cannot establish causes.')

{'calibrated_minus_raw_logloss': -6.130390957040765e-05, 'iid_row_bootstrap_95': [-0.00016953362229380587, 6.253575759107997e-05], 'replicates': 300, 'limitation': 'conditional on fitted models; repeated/related rows and one shard limit independence and generalization'}

Eight highest sigmoid-loss audit exposures: clicked count = 8
Detailed failure rows and all per-row predictions stay in the ignored local artifact directory.
Explain: rare positive misses, missingness and unseen categories are hypotheses; anonymous features cannot establish causes.

from reclab.auction import market, simulate
synthetic=market(seed=42)
controls=[('bid x1',simulate(synthetic,multiplier=1.,paced=True)),('bid x0.5',simulate(synthetic,multiplier=.5,paced=True))]
display(pd.DataFrame([{'policy':name,**{k:r[k] for k in ['spend','expected_click_value','expected_advertiser_surplus','clicks','budget_ok']}} for name,r in controls]))
fig,ax=plt.subplots(figsize=(8,4))
for name,r in controls:
    ax.plot([t['fraction'] for t in r['trace']],[sum(t['spend']) for t in r['trace']],label=name)
    assert r['budget_ok']
    assert all(max(t['spend'])<=60*t['fraction']+1e-8 for t in r['trace'])
ax.plot([0,1],[0,180],'k--',label='Combined paced budget ceiling')
ax.set(xlabel='Request fraction',ylabel='Simulated cumulative spend',title='Synthetic second-price impression market')
ax.legend();fig.tight_layout();fig.savefig(preview/'18_market.png',dpi=140);plt.show()
print('All fixed-seed policies:')
display(pd.DataFrame([{'policy':r['name'],'seed':r['seed'],'simulated_revenue':r['spend'],'expected_value':r['expected_click_value'],'budget_ok':r['budget_ok']} for r in result['simulations']]))

Notebook 保存的输出 · 本页未执行

	policy	spend	expected_click_value	expected_advertiser_surplus	clicks	budget_ok
0	bid x1	179.352946	363.687988	184.335042	181	True
1	bid x0.5	179.667495	594.607116	414.939622	297	True

<Figure size 800x400 with 1 Axes>

All fixed-seed policies:

	policy	seed	simulated_revenue	expected_value	budget_ok
0	flat	41	179.946768	310.260151	True
1	value	41	179.954436	312.713379	True
2	value_paced	41	179.523495	362.738625	True
3	value_paced_halfbid	41	179.584778	588.807349	True
4	flat	42	179.958459	320.400544	True
5	value	42	179.950958	325.099130	True
6	value_paced	42	179.352946	363.687988	True
7	value_paced_halfbid	42	179.667495	594.607116	True
8	flat	43	179.880956	302.367394	True
9	value	43	179.955613	328.793557	True
10	value_paced	43	179.534714	362.467222	True
11	value_paced_halfbid	43	179.659235	589.567131	True