Upload tokenizer.py

tokenizer.py

@@ -1,278 +1,125 @@
-"""
-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
-
+import torch
 
 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]
+    符合评估脚本要求的 Chess Tokenizer。
+    词表大小: 149 (4 special + 12 pieces + 64 from_sq + 64 to_sq + 5 suffix)
     """
-    
+
     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)
+    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]
         
-        # Load or create vocabulary
+        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)"]
+
         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._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)
+
         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."""
         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))
-    
+        """关键：支持识别带后缀的 token，让 eval 识别为 decomposed 模式"""
+        tokens = []
+        parts = text.strip().split()
+        for part in parts:
+            if part in self._vocab:
+                tokens.append(part)
+            elif len(part) >= 6: # 处理 WPe2e4 紧凑格式
+                piece, f_sq, t_sq = part[:2], part[2:4] + "_f", part[4:6] + "_t"
+                if piece in self._vocab: tokens.append(piece)
+                if f_sq in self._vocab: tokens.append(f_sq)
+                if t_sq in self._vocab: tokens.append(t_sq)
+                if len(part) > 6 and part[6:] in self.suffixes:
+                    tokens.append(part[6:])
+        return tokens
+
     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)
-    
+        """关键：去掉后缀，让 eval 的正则 [a-h][1-8] 能抓到坐标"""
+        token = self._ids_to_tokens.get(index, self.UNK_TOKEN)
+        if token in [self.PAD_TOKEN, self.BOS_TOKEN, self.EOS_TOKEN, self.UNK_TOKEN]:
+            return ""
+        return token.replace("_f", "").replace("_t", "")
+
     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.
-        """
+        """关键：在 Piece 前加空格，确保历史棋局格式正确"""
+        res = []
+        for t in tokens:
+            if not t: continue
+            # 如果是棋子 token，说明是新 move，加空格
+            if len(t) == 2 and (t.startswith('W') or t.startswith('B')):
+                res.append(" " + t)
+            else:
+                res.append(t)
+        return "".join(res).strip()
+    def _convert_token_to_id(self, token: str) -> int:
+        return self._vocab.get(token, self._vocab.get(self.UNK_TOKEN))
+
+    def decode(self, token_ids, skip_special_tokens=True, **kwargs) -> str:
+        if hasattr(token_ids, "tolist"):
+            ids = token_ids.tolist()
+        elif isinstance(token_ids, (int, torch.LongTensor, torch.IntTensor)):
+            ids = [int(token_ids)] if isinstance(token_ids, int) else token_ids.tolist()
+        else:
+            ids = token_ids
+
+        tokens = [self._convert_id_to_token(i) for i in ids]
+        return self.convert_tokens_to_string(tokens)
+
+    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> tuple:
         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",
-        )
-        
+        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)
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path, **kwargs) -> "ChessTokenizer":
+        vocab_file = os.path.join(pretrained_model_name_or_path, "vocab.json")
+        if not os.path.exists(vocab_file):
+            return cls()
+        with open(vocab_file, "r", encoding="utf-8") as f:
+            vocab = json.load(f)
+        return cls(vocab=vocab, **kwargs)