Spaces:
Running
Running
File size: 10,299 Bytes
d30d906 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 | """Compare ranking controls without rebuilding indexes or calling an LLM."""
from __future__ import annotations
import argparse
import json
import sys
from datetime import datetime, timezone
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent.parent))
from config import DATA_DIR, DEFAULT_APP_VERSION
import core.search_engine as search_module
from core.search_engine import MenuSearchEngine
from core.version_paths import raw_menus_path
def _answers(item: dict) -> set[str]:
values = item.get("expected_ids")
if values is None and item.get("menu_id"):
values = [item["menu_id"]]
return {str(value).strip() for value in (values or []) if str(value).strip()}
def _rank(predicted: list[str], expected: set[str]) -> int | None:
return next(
(
index
for index, menu_id in enumerate(predicted, 1)
if menu_id in expected
),
None,
)
def _metrics(ranks: list[int | None]) -> dict[str, float]:
total = len(ranks)
return {
"n": total,
"acc1": sum(rank is not None and rank <= 1 for rank in ranks) / total,
"acc3": sum(rank is not None and rank <= 3 for rank in ranks) / total,
"acc5": sum(rank is not None and rank <= 5 for rank in ranks) / total,
"mrr5": sum(1.0 / rank for rank in ranks if rank) / total,
}
def _stage1_matrix() -> list[dict]:
return [
{
"name": "baseline",
"query_expansion": True,
"popularity": 0.005,
"query_top_k": 50,
"query_threshold": 0.85,
"query_weight": 0.4,
},
{
"name": "expansion_off",
"query_expansion": False,
"popularity": 0.005,
"query_top_k": 50,
"query_threshold": 0.85,
"query_weight": 0.4,
},
{
"name": "popularity_off",
"query_expansion": True,
"popularity": 0.0,
"query_top_k": 50,
"query_threshold": 0.85,
"query_weight": 0.4,
},
{
"name": "expansion_popularity_off",
"query_expansion": False,
"popularity": 0.0,
"query_top_k": 50,
"query_threshold": 0.85,
"query_weight": 0.4,
},
]
def _query_index_matrix(
*,
query_expansion: bool,
popularity: float,
) -> list[dict]:
common = {
"query_expansion": query_expansion,
"popularity": popularity,
}
return [
{
**common,
"name": "qidx_control",
"query_top_k": 50,
"query_threshold": 0.85,
"query_weight": 0.4,
},
{
**common,
"name": "qidx_top100",
"query_top_k": 100,
"query_threshold": 0.85,
"query_weight": 0.4,
},
{
**common,
"name": "qidx_top200",
"query_top_k": 200,
"query_threshold": 0.85,
"query_weight": 0.4,
},
{
**common,
"name": "qidx_top50_threshold082",
"query_top_k": 50,
"query_threshold": 0.82,
"query_weight": 0.4,
},
{
**common,
"name": "qidx_top100_threshold082",
"query_top_k": 100,
"query_threshold": 0.82,
"query_weight": 0.4,
},
{
**common,
"name": "qidx_top200_threshold082",
"query_top_k": 200,
"query_threshold": 0.82,
"query_weight": 0.4,
},
{
**common,
"name": "qidx_top50_threshold080",
"query_top_k": 50,
"query_threshold": 0.80,
"query_weight": 0.4,
},
{
**common,
"name": "qidx_top100_threshold080",
"query_top_k": 100,
"query_threshold": 0.80,
"query_weight": 0.4,
},
{
**common,
"name": "qidx_top200_threshold080",
"query_top_k": 200,
"query_threshold": 0.80,
"query_weight": 0.4,
},
{
**common,
"name": "qidx_top200_weight06",
"query_top_k": 200,
"query_threshold": 0.85,
"query_weight": 0.6,
},
]
def _popularity_matrix(*, query_expansion: bool) -> list[dict]:
return [
{
"name": f"popularity_{weight:g}",
"query_expansion": query_expansion,
"popularity": weight,
"query_top_k": 50,
"query_threshold": 0.85,
"query_weight": 0.4,
}
for weight in (0.005, 0.004, 0.003, 0.002, 0.001, 0.0)
]
def _apply(config: dict) -> None:
search_module.QUERY_EXPANSION_ENABLED = config["query_expansion"]
search_module.SEARCH_COUNT_BOOST_WEIGHT = config["popularity"]
search_module.QUERY_INDEX_TOP_K = config["query_top_k"]
search_module.QUERY_IDX_THRESHOLD = config["query_threshold"]
search_module.W_QUERY_IDX = config["query_weight"]
def main() -> None:
parser = argparse.ArgumentParser()
parser.add_argument("--app-version", default=DEFAULT_APP_VERSION)
parser.add_argument("--eval-path", type=Path, default=DATA_DIR / "eval_queries_dev.json")
parser.add_argument(
"--matrix",
choices=("stage1", "popularity", "qidx"),
default="stage1",
)
parser.add_argument(
"--expansion",
choices=("on", "off"),
default="on",
help="base query-expansion setting for the qidx matrix",
)
parser.add_argument(
"--popularity",
type=float,
default=0.005,
help="base search-count boost for the qidx matrix",
)
parser.add_argument("--output", type=Path)
args = parser.parse_args()
rows = json.loads(args.eval_path.read_text(encoding="utf-8"))
available = {
item["menu_id"]
for item in json.loads(
raw_menus_path(args.app_version).read_text(encoding="utf-8")
)
}
rows = [
item
for item in rows
if not item.get("no_match", False) and _answers(item) & available
]
if args.matrix == "stage1":
matrix = _stage1_matrix()
elif args.matrix == "popularity":
matrix = _popularity_matrix(
query_expansion=args.expansion == "on"
)
else:
matrix = _query_index_matrix(
query_expansion=args.expansion == "on",
popularity=args.popularity,
)
engine = MenuSearchEngine.get_instance(args.app_version)
original_embed = engine.embedder.embed_text
embedding_cache: dict[str, list] = {}
def cached_embed(text: str) -> list:
if text not in embedding_cache:
embedding_cache[text] = original_embed(text)
return embedding_cache[text]
engine.embedder.embed_text = cached_embed
reports = []
baseline_ranks: list[int | None] | None = None
for config in matrix:
_apply(config)
ranks = []
predictions = []
by_source: dict[str, list[int | None]] = {}
for item in rows:
hits = engine.search(
item["query"],
top_n=5,
threshold=0.0,
use_hyde=False,
use_reranker=False,
)
predicted = [hit.get("menu_id", "") for hit in hits]
rank = _rank(predicted, _answers(item))
ranks.append(rank)
by_source.setdefault(
str(item.get("source") or "unknown"), []
).append(rank)
predictions.append(
{
"query": item["query"],
"source": str(item.get("source") or "unknown"),
"expected_ids": sorted(_answers(item)),
"predicted_ids": predicted,
"rank": rank,
}
)
if baseline_ranks is None:
baseline_ranks = ranks
improved_top3 = sum(
(before is None or before > 3)
and after is not None
and after <= 3
for before, after in zip(baseline_ranks, ranks)
)
regressed_top3 = sum(
before is not None
and before <= 3
and (after is None or after > 3)
for before, after in zip(baseline_ranks, ranks)
)
report = {
"config": config,
"metrics": _metrics(ranks),
"metrics_by_source": {
source: _metrics(source_ranks)
for source, source_ranks in sorted(by_source.items())
},
"top3_improved_vs_control": improved_top3,
"top3_regressed_vs_control": regressed_top3,
"predictions": predictions,
}
reports.append(report)
metrics = report["metrics"]
print(
f"{config['name']}: Acc@1={metrics['acc1']:.1%} "
f"Acc@3={metrics['acc3']:.1%} Acc@5={metrics['acc5']:.1%} "
f"MRR@5={metrics['mrr5']:.3f} "
f"Top3 +{improved_top3}/-{regressed_top3}"
)
for source, source_metrics in report["metrics_by_source"].items():
print(
f" {source}: Acc@1={source_metrics['acc1']:.1%} "
f"Acc@3={source_metrics['acc3']:.1%} "
f"Acc@5={source_metrics['acc5']:.1%}"
)
output = args.output or (
DATA_DIR
/ "experiments"
/ f"ranking_{args.matrix}_{args.app_version.replace('.', '_')}.json"
)
output.parent.mkdir(parents=True, exist_ok=True)
output.write_text(
json.dumps(
{
"created_at": datetime.now(timezone.utc).isoformat(),
"app_version": args.app_version,
"eval_path": str(args.eval_path),
"rows": len(rows),
"reports": reports,
},
ensure_ascii=False,
indent=2,
)
+ "\n",
encoding="utf-8",
)
print(f"output: {output}")
if __name__ == "__main__":
main()
|