open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

rename word_reversal.py -> word_sequence_reversal.py

Browse source
This commit is contained in:
Andreas Koepf 2025-01-26 11:54:54 +01:00
parent e9ac50a6fc
commit cdf08d9d5b
5 changed files with 67 additions and 64 deletions
Download patch file Download diff file Expand all files Collapse all files

11
reasoning_gym/algorithmic/spell_backward.py
View file

@ -9,12 +9,12 @@ from ..data import read_data_file
from ..factory import ProceduralDataset, register_dataset
@dataclass
@dataclass
class SpellBackwardConfig:
"""Configuration for spelling words backward task generation"""
min_word_len: int = 3 # Minimum word length
seed: Optional[int] = None
seed: Optional[int] = None
size: int = 500 # Virtual dataset size
def validate(self) -> None:
@ -31,8 +31,9 @@ class SpellBackwardDataset(ProceduralDataset):
# Load and preprocess text
text = read_data_file("in_the_year_2889.txt")
# 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() and len(word) >= config.min_word_len]
self.words = [
word for word in re.findall(r"\b\w+\b", text) if word.isalnum() and len(word) >= config.min_word_len
]
def __getitem__(self, idx: int) -> dict:
"""Generate a single spell backward task"""