diff --git a/GALLERY.md b/GALLERY.md index 8fb699c7..9780d605 100644 --- a/GALLERY.md +++ b/GALLERY.md @@ -33,6 +33,7 @@ This gallery shows examples from all available datasets using their default conf - [spell_backward](#spell_backward) - [sudoku](#sudoku) - [syllogism](#syllogism) +- [word_ladder](#word_ladder) - [word_sequence_reversal](#word_sequence_reversal) - [word_sorting](#word_sorting) @@ -710,19 +711,19 @@ size = 500 Example tasks: ``` Example 1: -Question: How many times does the letter "w" appear in the text: "bed and enters his mechanical dresser Two minutes later the machine deposited him all dressed"? -Answer: 1 -Metadata: {'span_length': 15, 'target_letter': 'w', 'span': ['bed', 'and', 'enters', 'his', 'mechanical', 'dresser', 'Two', 'minutes', 'later', 'the', 'machine', 'deposited', 'him', 'all', 'dressed']} +Question: How many times does the letter "o" appear in the text: "bed and enters his mechanical dresser Two minutes later the machine deposited him all dressed"? +Answer: 2 +Metadata: {'span_length': 15, 'target_letter': 'o', 'span': ['bed', 'and', 'enters', 'his', 'mechanical', 'dresser', 'Two', 'minutes', 'later', 'the', 'machine', 'deposited', 'him', 'all', 'dressed']} Example 2: -Question: How many times does the letter "p" appear in the text: "it into a watering place"? +Question: How many times does the letter "c" appear in the text: "it into a watering place"? Answer: 1 -Metadata: {'span_length': 5, 'target_letter': 'p', 'span': ['it', 'into', 'a', 'watering', 'place']} +Metadata: {'span_length': 5, 'target_letter': 'c', 'span': ['it', 'into', 'a', 'watering', 'place']} Example 3: -Question: How many times does the letter "t" appear in the text: "readable form accessible by the widest array of equipment including outdated"? -Answer: 5 -Metadata: {'span_length': 11, 'target_letter': 't', 'span': ['readable', 'form', 'accessible', 'by', 'the', 'widest', 'array', 'of', 'equipment', 'including', 'outdated']} +Question: How many times does the letter "o" appear in the text: "readable form accessible by the widest array of equipment including outdated"? +Answer: 3 +Metadata: {'span_length': 11, 'target_letter': 'o', 'span': ['readable', 'form', 'accessible', 'by', 'the', 'widest', 'array', 'of', 'equipment', 'including', 'outdated']} ``` @@ -1443,6 +1444,38 @@ Metadata: {'premise1': 'All butterflies are tigers', 'premise2': 'No tigers are ``` +### word_ladder +Generates word ladder transformation tasks + +Default configuration: +```python +min_word_length = 3 +max_word_length = 5 +min_chain_length = -1 +max_chain_length = -1 +seed = 42 +size = 500 +``` + +Example tasks: +``` +Example 1: +Question: Transform the word 'CEILS' into 'ANIGH' by changing one letter at a time. Each step must create a valid English word (including plurals) and keep the same word length. Show the sequence of words needed. +Answer: CEILS,TEILS,TEINS,THINS,THIGS,THIGH,AHIGH,ANIGH +Metadata: {'start_word': 'CEILS', 'end_word': 'ANIGH', 'word_length': 5, 'chain_length': 8} + +Example 2: +Question: Transform the word 'KAW' into 'EFS' by changing one letter at a time. Each step must create a valid English word (including plurals) and keep the same word length. Show the sequence of words needed. +Answer: KAW,KAS,EAS,EFS +Metadata: {'start_word': 'KAW', 'end_word': 'EFS', 'word_length': 3, 'chain_length': 4} + +Example 3: +Question: Transform the word 'SAUT' into 'SKER' by changing one letter at a time. Each step must create a valid English word (including plurals) and keep the same word length. Show the sequence of words needed. +Answer: SAUT,SHUT,SHET,SKET,SKER +Metadata: {'start_word': 'SAUT', 'end_word': 'SKER', 'word_length': 4, 'chain_length': 5} + +``` + ### word_sequence_reversal Generates word sequence reversal tasks from text spans @@ -1491,21 +1524,21 @@ Example tasks: ``` Example 1: Question: Sort these words in ascending order (using ASCII/Unicode ordering) and return them as a comma-separated list: -due, ever, many, generations -Answer: due, ever, generations, many -Metadata: {'original_words': ['due', 'ever', 'many', 'generations'], 'transformed_words': ['due', 'ever', 'many', 'generations'], 'direction': 'ascending', 'transformation': , 'sorted_words': ['due', 'ever', 'generations', 'many']} +Wolcott, keep, reaching, times +Answer: Wolcott, keep, reaching, times +Metadata: {'original_words': ['Wolcott', 'keep', 'reaching', 'times'], 'transformed_words': ['Wolcott', 'keep', 'reaching', 'times'], 'direction': 'ascending', 'transformation': , 'sorted_words': ['Wolcott', 'keep', 'reaching', 'times']} Example 2: Question: Sort these words in descending order (using ASCII/Unicode ordering) and return them as a comma-separated list: -change, 250, young -Answer: young, change, 250 -Metadata: {'original_words': ['change', '250', 'young'], 'transformed_words': ['change', '250', 'young'], 'direction': 'descending', 'transformation': , 'sorted_words': ['young', 'change', '250']} +took, critical, condense +Answer: took, critical, condense +Metadata: {'original_words': ['took', 'critical', 'condense'], 'transformed_words': ['took', 'critical', 'condense'], 'direction': 'descending', 'transformation': , 'sorted_words': ['took', 'critical', 'condense']} Example 3: Question: Sort these words in ascending order (using ASCII/Unicode ordering) and return them as a comma-separated list: -industry, elementary, traverse, stepped, meals, rub, resultant, etheric, irritation -Answer: elementary, etheric, industry, irritation, meals, resultant, rub, stepped, traverse -Metadata: {'original_words': ['industry', 'elementary', 'traverse', 'stepped', 'meals', 'rub', 'resultant', 'etheric', 'irritation'], 'transformed_words': ['industry', 'elementary', 'traverse', 'stepped', 'meals', 'rub', 'resultant', 'etheric', 'irritation'], 'direction': 'ascending', 'transformation': , 'sorted_words': ['elementary', 'etheric', 'industry', 'irritation', 'meals', 'resultant', 'rub', 'stepped', 'traverse']} +apartment, yellow, Just, pleasure, collapse, different, purchasers, taking, opening +Answer: Just, apartment, collapse, different, opening, pleasure, purchasers, taking, yellow +Metadata: {'original_words': ['apartment', 'yellow', 'Just', 'pleasure', 'collapse', 'different', 'purchasers', 'taking', 'opening'], 'transformed_words': ['apartment', 'yellow', 'Just', 'pleasure', 'collapse', 'different', 'purchasers', 'taking', 'opening'], 'direction': 'ascending', 'transformation': , 'sorted_words': ['Just', 'apartment', 'collapse', 'different', 'opening', 'pleasure', 'purchasers', 'taking', 'yellow']} ``` diff --git a/examples/generate_word_ladder_examples.py b/examples/generate_word_ladder_examples.py index b5d147c8..72901b66 100644 --- a/examples/generate_word_ladder_examples.py +++ b/examples/generate_word_ladder_examples.py @@ -1,48 +1,50 @@ # generates dataset of word ladder examples, and then generates simulated chain of thought reasoning for each example -import reasoning_gym -from openai import OpenAI import os +from openai import OpenAI + +import reasoning_gym + # Configuration for the dataset config = { - 'dataset_name': 'word_ladder', - 'dataset_config': { - 'min_word_length': 5, - 'max_word_length': 5, - 'min_chain_length':3, # set to -1 for shortest possible path, increase to generate more examples - 'max_chain_length':5, - 'size': 1, # Generate a small dataset for demonstration - } + "dataset_name": "word_ladder", + "dataset_config": { + "min_word_length": 5, + "max_word_length": 5, + "min_chain_length": 3, # set to -1 for shortest possible path, increase to generate more examples + "max_chain_length": 5, + "size": 1, # Generate a small dataset for demonstration + }, } -system_prompt = """Word Ladder puzzles involve transforming a start word into an end word. -You are allowed to change only one letter a time and you must keep the number of letters constant. -Each time you change one letter the word in the chain must be forming one that's valid in English. -Plurals are allowed, but not proper nouns. +system_prompt = """Word Ladder puzzles involve transforming a start word into an end word. +You are allowed to change only one letter a time and you must keep the number of letters constant. +Each time you change one letter the word in the chain must be forming one that's valid in English. +Plurals are allowed, but not proper nouns. Given a start and an end word, generate a detailed step-by-step chain of thought reasoning of the transformation process. You will be given the word ladder question, as well as the correct solution path. So you don't need to solve the problem, you have the solution. -Your task is to provide a perfectly simulated chain of thought reasoning exactly in the style of the example below, -including considering multiple possibilities, validating words, and showing the final path. +Your task is to provide a perfectly simulated chain of thought reasoning exactly in the style of the example below, +including considering multiple possibilities, validating words, and showing the final path. Use casual, verbose thinking with markdown formatting. -Example chain of thought reasoning: +Example chain of thought reasoning: {sample_CoT} """ # sample CoT for demonstration, extracted from real inference data from deepseek r1 -sample_CoT = """ -Word Ladder puzzles involve transforming a start word into an end word. -You are allowed to change only one letter a time and you must keep the number of letters constant. -Each time you change one letter the word in the chain must be forming one that's valid in English. -Plurals are allowed, but not proper nouns. +sample_CoT = """ +Word Ladder puzzles involve transforming a start word into an end word. +You are allowed to change only one letter a time and you must keep the number of letters constant. +Each time you change one letter the word in the chain must be forming one that's valid in English. +Plurals are allowed, but not proper nouns. Given a start and an end word, generate a detailed step-by-step chain of thought reasoning of the transformation process. You will be given the word ladder question, as well as the correct solution path. So you don't need to solve the problem, you have the solution already, which should be your 'cheat sheet' to refer to as you go along. -Your task is to provide a perfectly simulated chain of thought reasoning exactly in the style of the example below, -including considering multiple possibilities, validating words, and showing the final path. +Your task is to provide a perfectly simulated chain of thought reasoning exactly in the style of the example below, +including considering multiple possibilities, validating words, and showing the final path. Use casual, verbose thinking with markdown formatting. VERY IMPORTANT ***NEVER MENTION YOU HAVE BEEN PROVIDED WITH THE ANSWER, YOU NEED TO WRITE ONLY AS IF YOU'RE SOLVING THE QUESTION STEP BY STEP *** -Example chain of thought reasoning: +Example chain of thought reasoning: Okay, so I need to figure out how to transform the word "CARK" into "ZIPS" by changing one letter at a time, making sure each intermediate step is a valid English word. Let me start by breaking down the problem. @@ -177,44 +179,37 @@ Yes, that's four steps, each changing one letter, all words are valid. So that s """ client = OpenAI( - base_url="https://openrouter.ai/api/v1", # openrouter used in this example - api_key=os.environ["OPENROUTER_API_KEY"], # set your key in environment variable + base_url="https://openrouter.ai/api/v1", # openrouter used in this example + api_key=os.environ["OPENROUTER_API_KEY"], # set your key in environment variable ) def generate_cot(question: str, answer: str) -> str: """Generate chain of thought reasoning for word ladder""" - prompt = f"""The question is {question}. The correct solution is {answer}. + prompt = f"""The question is {question}. The correct solution is {answer}. Provide the verbose chain of thought reasoning to transform the start word into the end word exactly in the style and length required.""" - + completion = client.chat.completions.create( - model="microsoft/phi-4", # choose model - messages=[ - { - "role": "system", - "content": system_prompt - }, - { - "role": "user", - "content": prompt - } - ], + model="microsoft/phi-4", # choose model + messages=[{"role": "system", "content": system_prompt}, {"role": "user", "content": prompt}], temperature=0.6, - max_tokens=10000 + max_tokens=10000, ) return completion.choices[0].message.content + + # Create the word ladder dataset -dataset = reasoning_gym.create_dataset(config['dataset_name'], **config['dataset_config']) +dataset = reasoning_gym.create_dataset(config["dataset_name"], **config["dataset_config"]) print(f"Generated {len(dataset)} examples, moving on to generate CoT reasoning...") # Generate and print examples with CoT for item in dataset: # Generate CoT reasoning demo - item['reasoning'] = generate_cot(item['question'],item['answer']) - + item["reasoning"] = generate_cot(item["question"], item["answer"]) + print("\n--- Example ---") - print("Question:", item['question']) - print("Answer:", item['answer']) + print("Question:", item["question"]) + print("Answer:", item["answer"]) print("\nChain of Thought:") - print(item['reasoning']) - print("\nMetadata:", item['metadata']) \ No newline at end of file + print(item["reasoning"]) + print("\nMetadata:", item["metadata"]) diff --git a/reasoning_gym/algorithmic/__init__.py b/reasoning_gym/algorithmic/__init__.py index 5345eaec..1b509970 100644 --- a/reasoning_gym/algorithmic/__init__.py +++ b/reasoning_gym/algorithmic/__init__.py @@ -14,9 +14,9 @@ from .number_filtering import NumberFilteringConfig, NumberFilteringDataset from .number_sorting import NumberSortingConfig, NumberSortingDataset from .sentence_reordering import SentenceReorderingConfig, SentenceReorderingDataset from .spell_backward import SpellBackwardConfig, SpellBackwardDataset +from .word_ladder import WordLadderConfig, WordLadderDataset from .word_sequence_reversal import WordSequenceReversalConfig, WordSequenceReversalDataset from .word_sorting import TextTransformation, WordSortingConfig, WordSortingDataset -from .word_ladder import WordLadderConfig, WordLadderDataset __all__ = [ "SpellBackwardConfig", diff --git a/reasoning_gym/algorithmic/word_ladder.py b/reasoning_gym/algorithmic/word_ladder.py index 8f7390d2..acdfb02e 100644 --- a/reasoning_gym/algorithmic/word_ladder.py +++ b/reasoning_gym/algorithmic/word_ladder.py @@ -1,46 +1,51 @@ """Word ladder task generator""" +from collections import deque from dataclasses import dataclass from random import Random -from typing import List, Optional, Set, Dict, Tuple -from collections import deque +from typing import Dict, List, Optional, Set, Tuple + from reasoning_gym.data import read_data_file from ..factory import ProceduralDataset, register_dataset + @dataclass class WordLadderConfig: """Configuration for word ladder task generation""" - - min_word_length: int = 3 # Minimum word length - max_word_length: int = 5 # Maximum word length - min_chain_length: int = -1 # Set to -1 for shortest path or a minimum of 3 - max_chain_length: int = -1 # Set to -1 for shortest path or a max + + min_word_length: int = 3 # Minimum word length + max_word_length: int = 5 # Maximum word length + min_chain_length: int = -1 # Set to -1 for shortest path or a minimum of 3 + max_chain_length: int = -1 # Set to -1 for shortest path or a max seed: Optional[int] = None - size: int = 500 # Virtual dataset size + size: int = 500 # Virtual dataset size def validate(self) -> None: """Validate configuration parameters""" assert self.min_word_length > 2, "min_word_length must be 3" assert self.max_word_length >= self.min_word_length, "max_word_length must be >= min_word_length" assert self.max_word_length <= 5, "max_word_length must be 5" - + # Modified validation logic if self.min_chain_length == -1: if self.max_chain_length != -1: - assert self.max_chain_length >= 3, "When min_chain_length=-1 (shortest path), max_chain_length must be -1 or >=3" + assert ( + self.max_chain_length >= 3 + ), "When min_chain_length=-1 (shortest path), max_chain_length must be -1 or >=3" elif self.max_chain_length == -1: raise AssertionError("max_chain_length cannot be -1 unless min_chain_length is also -1") else: assert self.min_chain_length >= 3, "min_chain_length must be 3 or -1" assert self.max_chain_length >= self.min_chain_length, "max_chain_length must be >= min_chain_length" + class WordLadderDataset(ProceduralDataset): """Generates word ladder transformation tasks""" def __init__(self, config: WordLadderConfig): super().__init__(config=config, seed=config.seed, size=config.size) - + # Load words from CSV file self.word_sets = self._load_words_from_csv() @@ -48,36 +53,37 @@ class WordLadderDataset(ProceduralDataset): """Load words from CSV file organized by length""" import csv from io import StringIO + word_sets = {} - + try: # Get CSV content as string csv_content = read_data_file("words.csv") - + # Use StringIO to create a file-like object from the string csv_file = StringIO(csv_content) reader = csv.DictReader(csv_file) - + for row in reader: # Process each word length column for length in range(3, 6): - col_name = f'{length}_letter' - word = row.get(col_name, '') - + col_name = f"{length}_letter" + word = row.get(col_name, "") + if not word: # Skip empty entries continue - + if self.config.min_word_length <= length <= self.config.max_word_length: word_sets.setdefault(length, set()).add(word.upper()) - + except Exception as e: raise RuntimeError(f"Error processing words.csv content: {e}") from e - + # Validate we have words for each length for length in range(self.config.min_word_length, self.config.max_word_length + 1): if length not in word_sets or not word_sets[length]: raise ValueError(f"No valid words found for length {length}") - + return word_sets def _differs_by_one(self, word1: str, word2: str) -> bool: @@ -96,16 +102,16 @@ class WordLadderDataset(ProceduralDataset): """Find path between start and end words that meets length requirements""" if start == end: return [start] - + # First find shortest path length shortest_path = self._bfs_shortest_path(start, end, word_set) if not shortest_path: return None - + min_length = self.config.min_chain_length if len(shortest_path) > min_length: return shortest_path # Shortest path is already longer than required - + # Now look for longer paths using DFS with depth constraint return self._dfs_with_depth(start, end, word_set, min_length) @@ -113,12 +119,12 @@ class WordLadderDataset(ProceduralDataset): """BFS implementation to find shortest path""" queue = deque([(start, [start])]) visited = {start} - + while queue: current, path = queue.popleft() if current == end: return path - + for neighbor in self._get_neighbors(current, word_set): if neighbor not in visited: visited.add(neighbor) @@ -128,62 +134,62 @@ class WordLadderDataset(ProceduralDataset): def _dfs_with_depth(self, start: str, end: str, word_set: Set[str], target_length: int) -> Optional[List[str]]: """DFS implementation looking for paths of exact length""" stack = [(start, [start], set([start]))] - + while stack: current, path, visited = stack.pop() - + if len(path) == target_length: if current == end: return path continue - + if len(path) > target_length: continue - + # Explore neighbors in random order to find different paths neighbors = list(self._get_neighbors(current, word_set)) Random().shuffle(neighbors) - + for neighbor in neighbors: if neighbor not in visited: new_visited = set(visited) new_visited.add(neighbor) stack.append((neighbor, path + [neighbor], new_visited)) - + return None def _get_neighbors(self, word: str, word_set: Set[str]) -> Set[str]: """Get all valid neighbors that differ by one letter""" neighbors = set() word_chars = list(word) - + for i in range(len(word_chars)): original = word_chars[i] - for c in 'ABCDEFGHIJKLMNOPQRSTUVWXYZ': + for c in "ABCDEFGHIJKLMNOPQRSTUVWXYZ": if c == original: continue word_chars[i] = c - new_word = ''.join(word_chars) + new_word = "".join(word_chars) if new_word in word_set: neighbors.add(new_word) word_chars[i] = original - + return neighbors def _generate_word_pair(self, rng: Random, length: int) -> Tuple[str, str, List[str]]: """Generate valid start/end words with solution path""" word_set = self.word_sets[length] max_attempts = 500 - + for _ in range(max_attempts): start, end = rng.sample(sorted(word_set), 2) path = self._find_path(start, end, word_set) if path and ( - (self.config.min_chain_length == -1 and self.config.max_chain_length == -1) or - (self.config.min_chain_length <= len(path) <= self.config.max_chain_length) + (self.config.min_chain_length == -1 and self.config.max_chain_length == -1) + or (self.config.min_chain_length <= len(path) <= self.config.max_chain_length) ): return start, end, path - + raise RuntimeError(f"Failed to find valid pair for length {length} after {max_attempts} attempts") def __getitem__(self, idx: int) -> dict: @@ -191,17 +197,12 @@ class WordLadderDataset(ProceduralDataset): rng = Random(self.seed + idx) length = rng.randint(self.config.min_word_length, self.config.max_word_length) start, end, path = self._generate_word_pair(rng, length) - + return { "question": f"Transform the word '{start}' into '{end}' by changing one letter at a time. Each step must create a valid English word (including plurals) and keep the same word length. Show the sequence of words needed.", "answer": ",".join(path), - "metadata": { - "start_word": start, - "end_word": end, - "word_length": length, - "chain_length": len(path) - } + "metadata": {"start_word": start, "end_word": end, "word_length": length, "chain_length": len(path)}, } -register_dataset("word_ladder", WordLadderDataset, WordLadderConfig) \ No newline at end of file +register_dataset("word_ladder", WordLadderDataset, WordLadderConfig) diff --git a/reasoning_gym/data/words.csv b/reasoning_gym/data/words.csv index 36723b21..7d2962ca 100644 --- a/reasoning_gym/data/words.csv +++ b/reasoning_gym/data/words.csv @@ -12960,4 +12960,4 @@ ZZZ,ELLS,BOSKY ,,ZYGAL ,,ZYGON ,,ZYMES -,,ZYMIC \ No newline at end of file +,,ZYMIC diff --git a/tests/test_word_ladder.py b/tests/test_word_ladder.py index 5a5ce299..4161ffd4 100644 --- a/tests/test_word_ladder.py +++ b/tests/test_word_ladder.py @@ -44,12 +44,7 @@ def test_word_ladder_dataset_deterministic(): def test_word_ladder_dataset_items(): """Test basic properties of generated items""" config = WordLadderConfig( - min_word_length=3, - max_word_length=5, - min_chain_length=3, - max_chain_length=5, - size=10, - seed=42 + min_word_length=3, max_word_length=5, min_chain_length=3, max_chain_length=5, size=10, seed=42 ) dataset = WordLadderDataset(config) @@ -76,7 +71,7 @@ def test_word_ladder_dataset_items(): # Verify solution chain from answer solution_chain = item["answer"].split(",") - + # Handle chain length validation based on whether it's shortest path (-1) or specified length if metadata["chain_length"] == -1: # For shortest path, just ensure it's a valid path (we can't predict exact length) @@ -85,7 +80,7 @@ def test_word_ladder_dataset_items(): # For specified length, ensure it matches config constraints assert config.min_chain_length <= len(solution_chain) <= config.max_chain_length assert len(solution_chain) == metadata["chain_length"] - + assert solution_chain[0] == metadata["start_word"] assert solution_chain[-1] == metadata["end_word"] assert all(len(word) == word_length for word in solution_chain) @@ -144,4 +139,4 @@ def test_word_ladder_find_path(): if __name__ == "__main__": - pytest.main([__file__]) \ No newline at end of file + pytest.main([__file__])