16 · 深入推荐：负例、序列与索引

from pathlib import Path
import sys, json
ROOT = Path.cwd()
if not (ROOT/'reclab').is_dir(): ROOT = ROOT.parent
sys.path.insert(0,str(ROOT))
import pandas as pd
import matplotlib.pyplot as plt
from reclab.experiments import catalog, result
runs=[r for r in catalog() if r['domain']=='recommendation' and r['state']=='completed' and not r.get('annotation',{}).get('superseded')]
assert runs, '先运行 python -m reclab.deep_recommendation'
receipt=runs[-1]; experiment=result('recommendation',receipt['run_id'])
print(receipt['run_id'], 'samples',experiment['samples'], 'users',experiment['evaluation_users'])
print(experiment['scope'])
frame=pd.DataFrame([{k:v for k,v in row.items() if k not in ('loss','index','shuffled')} for row in experiment['rows']])
display(frame[['encoder','sampler','seed','parameters','ndcg@20','recall@20','coverage@20']])

20261030T123443-578def14 samples 12000 users 339
Bounded real-data ablation; loss is not CTR; popularity proposal uses train-only aggregate frequency; hard negatives are model-selected from 16 unseen-prefix candidates. Validation is a visible development benchmark, not an untouched audit.

means=frame[frame.encoder=='mean'].groupby('sampler')[['ndcg@20','recall@20','coverage@20']].agg(['mean','std'])
display(means)
fig,ax=plt.subplots(figsize=(7,3))
for row in experiment['rows']:
    if row['encoder']=='mean' and row['seed']==42: ax.plot(range(1,len(row['loss'])+1),row['loss'],label=row['sampler'])
ax.set(xlabel='Epoch',ylabel='BPR loss',title='Loss depends on the sampled task');ax.legend();plt.show()

Notebook 保存的输出 · 本页未执行

	ndcg@20		recall@20		coverage@20
	mean	std	mean	std	mean	std
sampler
hard	0.003361	0.002656	0.005247	0.004528	0.2782	0.022062
popular	0.003374	0.000790	0.005194	0.000051	0.4341	0.015415
uniform	0.004466	0.003811	0.004994	0.003580	0.3532	0.003111

<Figure size 700x300 with 1 Axes>

uniform=frame[frame.sampler=='uniform']
display(uniform.groupby('encoder')[['ndcg@20','recall@20','parameters']].mean())
shuffle=pd.DataFrame([{'encoder':r['encoder'],'seed':r['seed'],'original':r['ndcg@20'],'shuffled':r['shuffled']['ndcg@20']} for r in experiment['rows'] if r['sampler']=='uniform'])
display(shuffle)
shuffle.groupby('encoder')[['original','shuffled']].mean().plot.bar(figsize=(7,3),title='Same trained model, shuffled history');plt.tight_layout();plt.show()

Notebook 保存的输出 · 本页未执行

	ndcg@20	recall@20	parameters
encoder
attention	0.004205	0.004942	123504.0
gru	0.002546	0.002603	124224.0
mean	0.004466	0.004994	120624.0

	encoder	seed	original	shuffled
0	mean	42	0.007160	0.007160
1	gru	42	0.002641	0.006853
2	attention	42	0.004672	0.003519
3	mean	2026	0.001771	0.001771
4	gru	2026	0.002450	0.002790
5	attention	2026	0.003738	0.003169

<Figure size 700x300 with 1 Axes>

index=pd.DataFrame([{'seed':r['seed'],**i} for r in experiment['rows'] for i in r.get('index',[])])
assert (index[index.probes==12].exact_top20_overlap==1).all()
display(index)
index.groupby('probes')[['exact_top20_overlap','recall@20']].mean().plot(marker='o',figsize=(7,3));plt.ylim(0,1.05);plt.show()

Notebook 保存的输出 · 本页未执行

	seed	probes	exact_top20_overlap	mean_scanned	seconds	recall@20	ndcg@20	mrr@20	hit_rate@20
0	42	1	0.287463	421.404130	0.034856	0.002371	0.002808	0.005616	0.026549
1	42	4	0.708997	1673.713864	0.079289	0.006380	0.007160	0.012372	0.032448
2	42	12	1.000000	5000.000000	0.185076	0.007526	0.007160	0.010735	0.035398
3	2026	1	0.301622	407.519174	0.034720	0.002246	0.002125	0.004994	0.026549
4	2026	4	0.743215	1643.324484	0.078714	0.001008	0.001674	0.005415	0.020649
5	2026	12	1.000000	5000.000000	0.194151	0.002463	0.001771	0.003196	0.020649

<Figure size 700x300 with 1 Axes>

from reclab.deep_recommendation import Config, SequenceEncoder, negatives
import inspect
print(inspect.getsource(negatives))
assert len(experiment['rows'])==len(receipt['config']['seeds'])*5
assert all(len(r['loss'])==receipt['config']['epochs'] for r in experiment['rows'])
print('PASS: complete controls and index parity checked')

def negatives(history, positives, probability, rng, width=1):
    # Only causal prefix and current target are excluded. Unknown future positives remain unknown.
    out = rng.choice(len(probability), size=(len(history), width), p=probability)
    blocked = [set(row) | {int(pos), 0} for row, pos in zip(history, positives)]
    if any(sum(probability[i] for i in b) >= 1 - 1e-12 for b in blocked):
        raise ValueError('No negative support')
    for row, excluded in enumerate(blocked):
        for _ in range(100):
            bad = np.isin(out[row], list(excluded))
            if not bad.any():
                break
            out[row, bad] = rng.choice(len(probability), size=int(bad.sum()), p=probability)
        else:
            raise RuntimeError('Negative sampling failed')
    return out

PASS: complete controls and index parity checked