File size: 5,843 Bytes
61449ba | 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 | from __future__ import annotations
import argparse
import json
from pathlib import Path
from typing import Any, Iterator
from .common import make_user_assistant_record, render_records, write_jsonl
ROLE_ALIASES = {
"human": "user",
"user": "user",
"assistant": "assistant",
"gpt": "assistant",
"bot": "assistant",
"system": "system",
}
def _missing_parquet_reader_error() -> ImportError:
return ImportError(
"ComplexReasoningBespoke.parquet needs a parquet reader. "
"Install one of: pyarrow, polars, or pandas with parquet support. "
"Recommended: pip install pyarrow"
)
def _iter_rows_pyarrow(path: Path, *, batch_size: int) -> Iterator[dict[str, Any]]:
import pyarrow.parquet as pq
parquet_file = pq.ParquetFile(path)
for batch in parquet_file.iter_batches(batch_size=batch_size):
for row in batch.to_pylist():
yield row
def _iter_rows_polars(path: Path) -> Iterator[dict[str, Any]]:
import polars as pl
frame = pl.read_parquet(path)
for row in frame.iter_rows(named=True):
yield row
def _iter_rows_pandas(path: Path) -> Iterator[dict[str, Any]]:
import pandas as pd
frame = pd.read_parquet(path)
for row in frame.to_dict(orient="records"):
yield row
def iter_parquet_rows(
path: str | Path,
*,
batch_size: int = 512,
) -> Iterator[dict[str, Any]]:
parquet_path = Path(path)
errors: list[Exception] = []
for loader in (_iter_rows_pyarrow, _iter_rows_polars, _iter_rows_pandas):
try:
if loader is _iter_rows_pyarrow:
yield from loader(parquet_path, batch_size=batch_size)
else:
yield from loader(parquet_path)
return
except ModuleNotFoundError as exc:
errors.append(exc)
except ImportError as exc:
errors.append(exc)
raise _missing_parquet_reader_error() from (errors[-1] if errors else None)
def _coerce_conversations(value: Any) -> list[dict[str, Any]]:
if value is None:
return []
if isinstance(value, str):
try:
value = json.loads(value)
except json.JSONDecodeError:
return []
if not isinstance(value, list):
return []
return [turn for turn in value if isinstance(turn, dict)]
def _role(turn: dict[str, Any]) -> str:
raw_role = turn.get("from", turn.get("role", ""))
return ROLE_ALIASES.get(str(raw_role).strip().lower(), str(raw_role).strip().lower())
def _content(turn: dict[str, Any]) -> str:
return str(turn.get("value", turn.get("content", ""))).strip()
def _iter_user_assistant_pairs(
conversations: list[dict[str, Any]],
*,
system_prompt: str = "",
include_system: bool = False,
) -> Iterator[tuple[str, str]]:
pending_user = ""
for turn in conversations:
role = _role(turn)
content = _content(turn)
if not content:
continue
if role == "user":
pending_user = content
continue
if role == "assistant" and pending_user:
user = pending_user
if include_system and system_prompt:
user = f"System:\n{system_prompt.strip()}\n\nUser:\n{user}"
yield user, content
pending_user = ""
def iter_records(
path: str | Path,
*,
include_system: bool = False,
include_source: bool = False,
limit: int | None = None,
batch_size: int = 512,
) -> Iterator[dict[str, str]]:
emitted = 0
parquet_path = Path(path)
for row in iter_parquet_rows(parquet_path, batch_size=batch_size):
system_prompt = str(row.get("system", "") or "")
conversations = _coerce_conversations(row.get("conversations"))
for user, assistant in _iter_user_assistant_pairs(
conversations,
system_prompt=system_prompt,
include_system=include_system,
):
record = make_user_assistant_record(
user,
assistant,
source=str(parquet_path),
include_source=include_source,
)
if record is None:
continue
yield record
emitted += 1
if limit is not None and emitted >= limit:
return
def load_records(
path: str | Path,
*,
include_system: bool = False,
include_source: bool = False,
limit: int | None = None,
batch_size: int = 512,
) -> list[dict[str, str]]:
return list(
iter_records(
path,
include_system=include_system,
include_source=include_source,
limit=limit,
batch_size=batch_size,
)
)
def main() -> None:
parser = argparse.ArgumentParser(
description="Normalize ComplexReasoningBespoke parquet to user/assistant rows."
)
parser.add_argument("input", help="Input parquet path.")
parser.add_argument("--output", help="Optional output JSONL path.")
parser.add_argument("--take", type=int, default=0, help="Print the first N rows.")
parser.add_argument("--limit", type=int, help="Stop after N emitted rows.")
parser.add_argument("--batch-size", type=int, default=512)
parser.add_argument("--include-system", action="store_true")
parser.add_argument("--include-source", action="store_true")
args = parser.parse_args()
records = load_records(
args.input,
include_system=args.include_system,
include_source=args.include_source,
limit=args.limit,
batch_size=args.batch_size,
)
if args.output:
write_jsonl(records, args.output)
if args.take:
print(render_records(records[: args.take]))
if __name__ == "__main__":
main()
|