Spaces:
Sleeping
Sleeping
File size: 10,067 Bytes
4b988e0 | 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 | """Batch loaders for FalkorDB and Neo4j from staging parquet files."""
from __future__ import annotations
import os
import threading
import time
from concurrent.futures import ThreadPoolExecutor, as_completed
from pathlib import Path
from typing import Callable, Iterator
import pyarrow.parquet as pq
BASE_DIR = Path(__file__).resolve().parent.parent
DEFAULT_STAGING_DIR = BASE_DIR / "clinical_graph_staging"
CONCEPTS_FILE = "concepts.parquet"
MRREL_FILE = "mrrel_edges.parquet"
HIER_FILE = "hier_edges.parquet"
def staging_paths(staging_dir: Path | None = None) -> dict[str, Path]:
root = staging_dir or DEFAULT_STAGING_DIR
return {
"concepts": root / CONCEPTS_FILE,
"mrrel": root / MRREL_FILE,
"hier": root / HIER_FILE,
}
def require_staging(staging_dir: Path | None = None) -> dict[str, Path]:
paths = staging_paths(staging_dir)
missing = [str(p) for p in paths.values() if not p.exists()]
if missing:
raise FileNotFoundError(
"Missing staging parquet files:\n "
+ "\n ".join(missing)
+ "\nRun: uv run python3 build_clinical_graph.py --keep-staging"
)
return paths
def iter_parquet_batches(
path: Path, batch_size: int, *, max_rows: int | None = None
) -> Iterator[list[dict]]:
pf = pq.ParquetFile(path)
sent = 0
for batch in pf.iter_batches(batch_size=batch_size):
df = batch.to_pandas()
if max_rows is not None:
remaining = max_rows - sent
if remaining <= 0:
return
if len(df) > remaining:
df = df.head(remaining)
rows = df.where(df.notna(), None).to_dict(orient="records")
if not rows:
continue
sent += len(rows)
yield rows
if max_rows is not None and sent >= max_rows:
return
def _clean_str(value) -> str:
if value is None:
return ""
return str(value).strip()
def concept_rows_for_load(rows: list[dict]) -> list[dict]:
out: list[dict] = []
for row in rows:
aui = _clean_str(row.get("aui"))
if not aui:
continue
out.append(
{
"aui": aui,
"cui": _clean_str(row.get("cui")),
"tui": _clean_str(row.get("tui")),
"sab": _clean_str(row.get("sab")),
"str": _clean_str(row.get("str")),
"tty": _clean_str(row.get("tty")),
"rank": int(row["rank"]) if row.get("rank") is not None else 0,
}
)
return out
def mrrel_rows_for_load(rows: list[dict]) -> list[dict]:
out: list[dict] = []
for row in rows:
src = _clean_str(row.get("src"))
dst = _clean_str(row.get("dst"))
if not src or not dst or src == dst:
continue
out.append(
{
"src": src,
"dst": dst,
"rel": _clean_str(row.get("rel")),
"rela": _clean_str(row.get("rela")),
"sab": _clean_str(row.get("sab")),
}
)
return out
def hier_rows_for_load(rows: list[dict]) -> list[dict]:
out: list[dict] = []
for row in rows:
src = _clean_str(row.get("src"))
dst = _clean_str(row.get("dst"))
if not src or not dst or src == dst:
continue
out.append(
{
"src": src,
"dst": dst,
"sab": _clean_str(row.get("sab")),
"rela": _clean_str(row.get("rela")),
}
)
return out
def parquet_row_count(path: Path) -> int:
return pq.ParquetFile(path).metadata.num_rows
def estimate_batches(
path: Path, batch_size: int, *, max_rows: int | None = None
) -> tuple[int, int]:
"""Return (row_count, num_batches)."""
rows = parquet_row_count(path)
if max_rows is not None:
rows = min(rows, max_rows)
batches = (rows + batch_size - 1) // batch_size if rows else 0
return rows, batches
def run_batched_load(
label: str,
path: Path,
batch_size: int,
row_mapper: Callable[[list[dict]], list[dict]],
loader: Callable[[list[dict]], None],
*,
max_rows: int | None = None,
progress_every_batches: int = 10,
) -> int:
expected_rows, expected_batches = estimate_batches(
path, batch_size, max_rows=max_rows
)
print(
f" {label}: {expected_rows:,} rows (~{expected_batches:,} batches @ {batch_size:,})",
flush=True,
)
total = 0
batch_num = 0
t0 = time.time()
last_report = t0
for raw in iter_parquet_batches(path, batch_size, max_rows=max_rows):
batch = row_mapper(raw)
if not batch:
continue
loader(batch)
total += len(batch)
batch_num += 1
now = time.time()
if (
batch_num % progress_every_batches == 0
or now - last_report >= 30
or batch_num == expected_batches
):
elapsed = now - t0
rate = total / elapsed if elapsed > 0 else 0.0
pct = 100.0 * total / expected_rows if expected_rows else 100.0
eta_s = (expected_rows - total) / rate if rate > 0 else 0
eta_m = eta_s / 60
print(
f" {label}: {total:,}/{expected_rows:,} ({pct:.1f}%) "
f"batch {batch_num}/{expected_batches} "
f"@ {rate:,.0f} rows/s, ETA ~{eta_m:.0f} min",
flush=True,
)
last_report = now
elapsed = time.time() - t0
rate = total / elapsed if elapsed > 0 else 0.0
print(
f" {label}: done {total:,} rows in {elapsed / 60:.1f} min ({rate:,.0f} rows/s)",
flush=True,
)
return total
def _partition_row_groups(path: Path, n_workers: int) -> list[list[int]]:
pf = pq.ParquetFile(path)
n = max(1, min(n_workers, pf.num_row_groups or 1))
buckets: list[list[int]] = [[] for _ in range(n)]
for i, rg in enumerate(range(pf.num_row_groups)):
buckets[i % n].append(rg)
return [b for b in buckets if b]
def _iter_row_group_batches(
path: Path,
row_group_ids: list[int],
batch_size: int,
*,
max_rows: int | None = None,
) -> Iterator[list[dict]]:
pf = pq.ParquetFile(path)
sent = 0
for rg in row_group_ids:
table = pf.read_row_group(rg)
df = table.to_pandas()
if max_rows is not None:
remaining = max_rows - sent
if remaining <= 0:
return
if len(df) > remaining:
df = df.head(remaining)
for start in range(0, len(df), batch_size):
chunk = df.iloc[start : start + batch_size]
rows = chunk.where(chunk.notna(), None).to_dict(orient="records")
if rows:
sent += len(rows)
yield rows
if max_rows is not None and sent >= max_rows:
return
def run_parallel_parquet_load(
label: str,
path: Path,
batch_size: int,
row_mapper: Callable[[list[dict]], list[dict]],
loader_factory: Callable[[], Callable[[list[dict]], None]],
*,
workers: int | None = None,
max_rows: int | None = None,
) -> int:
"""
Load parquet in parallel: one DB connection per worker, row-groups split across workers.
"""
n_workers = workers or min(8, max(1, (os.cpu_count() or 4) - 1))
expected_rows, _ = estimate_batches(path, batch_size, max_rows=max_rows)
partitions = _partition_row_groups(path, n_workers)
print(
f" {label}: {expected_rows:,} rows, {len(partitions)} workers "
f"(batch_size={batch_size:,})",
flush=True,
)
progress_lock = threading.Lock()
progress = {"rows": 0, "batches": 0}
t0 = time.time()
last_report = t0
def worker(part_id: int, row_groups: list[int]) -> int:
load_fn = loader_factory()
local = 0
try:
for raw in _iter_row_group_batches(
path, row_groups, batch_size, max_rows=max_rows
):
batch = row_mapper(raw)
if not batch:
continue
load_fn(batch)
local += len(batch)
with progress_lock:
progress["rows"] += len(batch)
progress["batches"] += 1
finally:
closer = getattr(load_fn, "close", None)
if callable(closer):
closer()
return local
total = 0
with ThreadPoolExecutor(max_workers=len(partitions)) as pool:
futures = {pool.submit(worker, i, rg): i for i, rg in enumerate(partitions)}
for fut in as_completed(futures):
total += fut.result()
now = time.time()
with progress_lock:
rows = progress["rows"]
batches = progress["batches"]
if now - last_report >= 15:
elapsed = now - t0
rate = rows / elapsed if elapsed > 0 else 0.0
pct = 100.0 * rows / expected_rows if expected_rows else 100.0
eta_m = (expected_rows - rows) / rate / 60 if rate > 0 else 0
print(
f" {label}: {rows:,}/{expected_rows:,} ({pct:.1f}%) "
f"{batches:,} batches @ {rate:,.0f} rows/s, ETA ~{eta_m:.0f} min",
flush=True,
)
last_report = now
elapsed = time.time() - t0
rate = total / elapsed if elapsed > 0 else 0.0
print(
f" {label}: done {total:,} rows in {elapsed / 60:.1f} min ({rate:,.0f} rows/s)",
flush=True,
)
return total
|