tokenizer.py

"""
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
from pathlib import Path
from typing import Dict, Iterable, List, Optional

from transformers.tokenization_utils 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 | Path] = None,
        vocab: Dict[str, int] = {},
        **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)

        if vocab and vocab_file:
            raise ValueError("Provide either vocab or vocab_file, not both.")

        vocab_file = Path(vocab_file) if vocab_file is not None else None

        self._vocab = (
            vocab
            or (
                json.loads(vocab_file.read_text())
                if vocab_file is not None and vocab_file.exists() and vocab_file.is_file()
                else {}
            )
            or 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: Iterable[str],
        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))))

        return cls.build_vocab_from_iterator(
            (example[column] for example in dataset), 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, **kwargs) -> 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 | Path,
        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.
        """
        save_directory = Path(save_directory)
        if not save_directory.is_dir():
            save_directory.mkdir(parents=True, exist_ok=True)

        filename = self.vocab_files_names["vocab_file"]
        filename_prefix = f"{filename_prefix}-{filename}" if filename_prefix else filename
        vocab_file = save_directory / filename

        vocab_file.write_text(json.dumps(self._vocab, indent=2), encoding="utf-8")
        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)