Update tokenizer.py

tokenizer.py

@@ -1,55 +1,184 @@
+"""
+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
-import re
+from pathlib import Path
 from typing import Dict, List, Optional
+
 from transformers import PreTrainedTokenizer
-import torch
+
 
 class ChessTokenizer(PreTrainedTokenizer):
     """
-    vocab size: 4 special + 12 pieces + 64 from_sq + 64 to_sq + 5 suffix + 4 promotions (qrbn)
+    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):
-        special_tokens = [self.PAD_TOKEN, self.BOS_TOKEN, self.EOS_TOKEN, self.UNK_TOKEN]
+    
+    def __init__(
+        self,
+        vocab_file: Optional[str] = None,
+        vocab: Optional[Dict[str, int]] = None,
+        **kwargs,
+    ):
+        """
+        Initialize the chess tokenizer.
         
-        self.colors_pieces = [f'{c}{p}' for c in ['W','B'] for p in ['P','N','B','R','Q','K']]
-        self.squares = [f'{f}{r}' for r in '12345678' for f in 'abcdefgh']
-        self.suffixes = ["(x)", "(+)", "(+*)", "(o)", "(O)"]
-        self.promotions = ["q", "r", "b", "n"]  # promotion Token
+        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:
-            self._vocab = {t: i for i, t in enumerate(special_tokens)}
-            for cp in self.colors_pieces: self._vocab[cp] = len(self._vocab)
-            for sq in self.squares: self._vocab[f"{sq}_f"] = len(self._vocab)
-            for sq in self.squares: self._vocab[f"{sq}_t"] = len(self._vocab)
-            for suf in self.suffixes: self._vocab[suf] = len(self._vocab)
-            for promo in self.promotions: self._vocab[promo] = len(self._vocab)
-
+            # 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,
+            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."""