open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-27 17:23:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: Inherit WordReversalDataset from ProceduralDataset

Browse source
This commit is contained in:
Andreas Koepf (aider) 2025-01-24 11:16:15 +01:00
parent 981ff73ed7
commit 190c2aafa4
1 changed files with 4 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

21
reasoning_gym/algorithmic/word_reversal.py
View file

@ -5,7 +5,8 @@ from dataclasses import dataclass
from random import Random from random import Random
from typing import List, Optional from typing import List, Optional
from reasoning_gym.data import read_data_file from ..data import read_data_file
from ..dataset import ProceduralDataset
@dataclass @dataclass
@ -23,33 +24,19 @@ class WordReversalConfig:
assert self.max_words >= self.min_words, "max_words must be >= min_words" assert self.max_words >= self.min_words, "max_words must be >= min_words"
class WordReversalDataset: class WordReversalDataset(ProceduralDataset):
"""Generates word reversal tasks from text spans""" """Generates word reversal tasks from text spans"""
def __init__(self, config: WordReversalConfig): def __init__(self, config: WordReversalConfig):
self.config = config self.config = config
self.config.validate() self.config.validate()
self.seed = config.seed if config.seed is not None else Random().randint(0, 2**32) super().__init__(seed=config.seed, size=config.size)
# Load and preprocess text # Load and preprocess text
text = read_data_file("in_the_year_2889.txt") text = read_data_file("in_the_year_2889.txt")
# Extract words and clean them to contain only alphanumeric characters # Extract words and clean them to contain only alphanumeric characters
self.words = [word for word in re.findall(r"\b\w+\b", text) if word.isalnum()] self.words = [word for word in re.findall(r"\b\w+\b", text) if word.isalnum()]
def __len__(self) -> int:
return self.config.size
def __iter__(self):
self._current_idx = 0
return self
def __next__(self):
if self._current_idx >= self.config.size:
raise StopIteration
item = self[self._current_idx]
self._current_idx += 1
return item
def __getitem__(self, idx: int) -> dict: def __getitem__(self, idx: int) -> dict:
"""Generate a single word reversal task""" """Generate a single word reversal task"""
rng = Random(self.seed + idx) rng = Random(self.seed + idx)