14 · 竞赛：重训 LightGBM 与消融

from pathlib import Path
import sys, json, inspect
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 IPython.display import display, Code
from reclab.competition import data
from reclab.competition.teaching import load_run, style, bar_scores
style()
pd.set_option("display.max_columns", 12)
pd.set_option("display.max_rows", 40)
run, rows, features = load_run()
print("实际训练快照:", run.name)

实际训练快照: 20261030T115556803593-cloud-restore

first_user = rows.query("market == 't1' and partition == 'fit'").userId.iloc[0]
mask = rows.market.eq("t1") & rows.userId.eq(first_user)
graph_columns = [c for c in features if c.startswith("graph_layers") and c != "graph_layers0"]
inspect_columns = ["target_user_rating_count", "target_item_rating_count", "icf_local", "icf_s1", "icf_all_iuf"] + graph_columns[:1]
sample = rows.loc[mask, ["userId", "itemId", "label", "partition"]].join(features.loc[mask, inspect_columns])
display(sample.sort_values("label", ascending=False).head(8))
print("样本正负比:", rows.loc[mask].label.value_counts().to_dict())

样本正负比: {0: 99, 1: 1}

import importlib
import reclab.competition.ranking as ranking_module
import reclab.competition.teaching as teaching_module
importlib.reload(ranking_module)
importlib.reload(teaching_module)
COLUMNS = list(features.columns)
NEGATIVE_KEEP = 99
LEAVES = 15
model, selection, experiment_path = teaching_module.sandbox_ranker(
    columns=COLUMNS, negative_keep=NEGATIVE_KEEP, leaves=LEAVES, tag="manual-baseline")
display(selection)
print("本次配置/模型保存:", experiment_path)

本次配置/模型保存: /Users/lynnlee/Documents/Codex/2026-10-30/task/soutui-lab/artifacts/xmrec/experiments/20261030T115947230728

sampled_model, sampled_selection, sampled_path = teaching_module.sandbox_ranker(
    columns=COLUMNS, negative_keep=9, leaves=LEAVES, tag="negative-sampling-9")
comparison = pd.concat([selection.assign(experiment="99 negatives"), sampled_selection.assign(experiment="9 negatives")])
display(comparison[comparison.market.eq("t1")][["experiment", "users", "ndcg10", "hr10"]])

importance = pd.DataFrame({"feature": COLUMNS, "gain": model.booster_.feature_importance(importance_type="gain")}).sort_values("gain", ascending=False)
display(importance.head(10))
fig, ax = plt.subplots(figsize=(9,4))
top = importance.head(10).sort_values("gain")
ax.barh(top.feature, top.gain, color="#006e60")
ax.set(xlabel="LightGBM split gain (training)", title="Feature importance · t1 notebook experiment")
fig.tight_layout(); plt.show()

Notebook 保存的输出 · 本页未执行

	feature	gain
14	icf_local	76522.053376
17	icf_all_iuf	15161.155351
18	icf_all_rating	8366.501459
16	icf_s3	6512.573406
8	target_user_rating_count	2074.465636
6	t1_train_item_count	1647.045635
20	graph_layers2	1561.719227
7	t1_train_5core_item_count	1298.185287
19	graph_layers0	1192.538080
9	target_user_rating_mean	1163.521230

<Figure size 990x440 with 1 Axes>

candidate = rows.query("market == 't1' and partition == 'select'").index[0]
x = features.loc[[candidate], COLUMNS]
contributions = model.booster_.predict(x, pred_contrib=True, num_threads=1)[0]
raw = model.booster_.predict(x, raw_score=True, num_threads=1)[0]
assert np.isclose(contributions.sum(), raw)
display(pd.DataFrame({"feature": COLUMNS + ["bias"], "log_odds_contribution": contributions}).sort_values("log_odds_contribution", key=abs, ascending=False).head(12))
print("raw score:", round(float(raw), 5), "probability:", round(float(model.predict_proba(x)[0,1]), 5))

raw score: -7.00451 probability: 0.00091