Spaces:
Running
Running
File size: 9,267 Bytes
cb13986 |
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 |
"""
Custom Chess Tokenizer for the Chess Challenge.
This tokenizer treats each move as a single token using the extended UCI notation
from the Lichess dataset (e.g., WPe2e4, BNg8f6).
The dataset format uses:
- W/B prefix for White/Black
- Piece letter: P=Pawn, N=Knight, B=Bishop, R=Rook, Q=Queen, K=King
- Source and destination squares (e.g., e2e4)
- Special suffixes: (x)=capture, (+)=check, (+*)=checkmate, (o)/(O)=castling
"""
from __future__ import annotations
import json
import os
from pathlib import Path
from typing import Dict, List, Optional
from transformers import PreTrainedTokenizer
class ChessTokenizer(PreTrainedTokenizer):
"""
A custom tokenizer for chess moves using extended UCI notation.
This tokenizer maps each possible chess move to a unique token ID.
The vocabulary is built from the training dataset to ensure all moves
encountered during training have a corresponding token.
Example:
>>> tokenizer = ChessTokenizer()
>>> tokenizer.encode("WPe2e4 BPe7e5")
[1, 42, 87, 2] # [BOS, e2e4, e7e5, EOS]
"""
model_input_names = ["input_ids", "attention_mask"]
vocab_files_names = {"vocab_file": "vocab.json"}
# Special tokens
PAD_TOKEN = "[PAD]"
BOS_TOKEN = "[BOS]"
EOS_TOKEN = "[EOS]"
UNK_TOKEN = "[UNK]"
def __init__(
self,
vocab_file: Optional[str] = None,
vocab: Optional[Dict[str, int]] = None,
**kwargs,
):
"""
Initialize the chess tokenizer.
Args:
vocab_file: Path to a JSON file containing the vocabulary mapping.
vocab: Dictionary mapping tokens to IDs (alternative to vocab_file).
**kwargs: Additional arguments passed to PreTrainedTokenizer.
"""
# Initialize special tokens
self._pad_token = self.PAD_TOKEN
self._bos_token = self.BOS_TOKEN
self._eos_token = self.EOS_TOKEN
self._unk_token = self.UNK_TOKEN
# Remove any duplicate special-token entries passed through kwargs
# to avoid "multiple values for keyword" errors when loading from disk.
kwargs.pop("pad_token", None)
kwargs.pop("bos_token", None)
kwargs.pop("eos_token", None)
kwargs.pop("unk_token", None)
# Load or create vocabulary
if vocab is not None:
self._vocab = vocab
elif vocab_file is not None and os.path.exists(vocab_file):
with open(vocab_file, "r", encoding="utf-8") as f:
self._vocab = json.load(f)
else:
# Create a minimal vocabulary with just special tokens
# The full vocabulary should be built from the dataset
self._vocab = self._create_default_vocab()
# Create reverse mapping
self._ids_to_tokens = {v: k for k, v in self._vocab.items()}
# Call parent init AFTER setting up vocab
super().__init__(
pad_token=self._pad_token,
bos_token=self._bos_token,
eos_token=self._eos_token,
unk_token=self._unk_token,
**kwargs,
)
def _create_default_vocab(self) -> Dict[str, int]:
"""
Create a minimal default vocabulary with just special tokens.
For the full vocabulary, use `build_vocab_from_dataset()`.
This minimal vocab is just a placeholder - you should build from data.
"""
special_tokens = [self.PAD_TOKEN, self.BOS_TOKEN, self.EOS_TOKEN, self.UNK_TOKEN]
vocab = {token: idx for idx, token in enumerate(special_tokens)}
return vocab
@classmethod
def build_vocab_from_iterator(
cls,
iterator,
min_frequency: int = 1,
) -> "ChessTokenizer":
"""
Build a tokenizer vocabulary from an iterator of game strings.
Args:
iterator: An iterator yielding game strings (space-separated moves).
min_frequency: Minimum frequency for a token to be included.
Returns:
A ChessTokenizer with the built vocabulary.
"""
from collections import Counter
token_counts = Counter()
for game in iterator:
moves = game.strip().split()
token_counts.update(moves)
# Filter by frequency
tokens = [
token for token, count in token_counts.items()
if count >= min_frequency
]
# Sort for reproducibility
tokens = sorted(tokens)
# Build vocabulary
special_tokens = [cls.PAD_TOKEN, cls.BOS_TOKEN, cls.EOS_TOKEN, cls.UNK_TOKEN]
vocab = {token: idx for idx, token in enumerate(special_tokens + tokens)}
return cls(vocab=vocab)
@classmethod
def build_vocab_from_dataset(
cls,
dataset_name: str = "dlouapre/lichess_2025-01_1M",
split: str = "train",
column: str = "text",
min_frequency: int = 500,
max_samples: Optional[int] = 100000,
) -> "ChessTokenizer":
"""
Build a tokenizer vocabulary from a Hugging Face dataset.
Args:
dataset_name: Name of the dataset on Hugging Face Hub.
split: Dataset split to use.
column: Column containing the game strings.
min_frequency: Minimum frequency for a token to be included (default: 500).
max_samples: Maximum number of samples to process (default: 100k).
Returns:
A ChessTokenizer with the built vocabulary.
"""
from datasets import load_dataset
dataset = load_dataset(dataset_name, split=split)
if max_samples is not None:
dataset = dataset.select(range(min(max_samples, len(dataset))))
def game_iterator():
for example in dataset:
yield example[column]
return cls.build_vocab_from_iterator(game_iterator(), min_frequency=min_frequency)
@property
def vocab_size(self) -> int:
"""Return the size of the vocabulary."""
return len(self._vocab)
def get_vocab(self) -> Dict[str, int]:
"""Return the vocabulary as a dictionary."""
return dict(self._vocab)
def _tokenize(self, text: str) -> List[str]:
"""
Tokenize a string of moves into a list of tokens.
Args:
text: A string of space-separated moves.
Returns:
List of move tokens.
"""
return text.strip().split()
def _convert_token_to_id(self, token: str) -> int:
"""Convert a token to its ID."""
return self._vocab.get(token, self._vocab.get(self.UNK_TOKEN, 0))
def _convert_id_to_token(self, index: int) -> str:
"""Convert an ID to its token."""
return self._ids_to_tokens.get(index, self.UNK_TOKEN)
def convert_tokens_to_string(self, tokens: List[str]) -> str:
"""Convert a list of tokens back to a string."""
# Filter out special tokens for cleaner output
special = {self.PAD_TOKEN, self.BOS_TOKEN, self.EOS_TOKEN, self.UNK_TOKEN}
return " ".join(t for t in tokens if t not in special)
def save_vocabulary(
self,
save_directory: str,
filename_prefix: Optional[str] = None,
) -> tuple:
"""
Save the vocabulary to a JSON file.
Args:
save_directory: Directory to save the vocabulary.
filename_prefix: Optional prefix for the filename.
Returns:
Tuple containing the path to the saved vocabulary file.
"""
if not os.path.isdir(save_directory):
os.makedirs(save_directory, exist_ok=True)
vocab_file = os.path.join(
save_directory,
(filename_prefix + "-" if filename_prefix else "") + "vocab.json",
)
with open(vocab_file, "w", encoding="utf-8") as f:
json.dump(self._vocab, f, ensure_ascii=False, indent=2)
return (vocab_file,)
def count_vocab_from_dataset(
dataset_name: str = "dlouapre/lichess_2025-01_1M",
split: str = "train",
column: str = "text",
max_samples: Optional[int] = 10000,
) -> Dict[str, int]:
"""
Count token frequencies in a dataset (useful for vocabulary analysis).
Args:
dataset_name: Name of the dataset on Hugging Face Hub.
split: Dataset split to use.
column: Column containing the game strings.
max_samples: Maximum number of samples to process.
Returns:
Dictionary mapping tokens to their frequencies.
"""
from collections import Counter
from datasets import load_dataset
dataset = load_dataset(dataset_name, split=split)
if max_samples is not None:
dataset = dataset.select(range(min(max_samples, len(dataset))))
token_counts = Counter()
for example in dataset:
moves = example[column].strip().split()
token_counts.update(moves)
return dict(token_counts)
|