open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Prompt tweak for code preprocessing

Browse source
This commit is contained in:
Oliver 2025-02-20 20:07:32 +00:00
parent 6fccd7ccb9
commit 4f0812464f
1 changed files with 19 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

57
notebooks/codeio/PreprocessCode.ipynb
View file

@ -33,14 +33,13 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"prompt_template = \"\"\"\n",
"You are tasked with preprocessing a raw file of Python code into a standard format. The format is made up of several components. Here is a very simple example of a raw code file:\n",
"\n",
"```python\n",
"def kg_to_pounds(weights):\n",
" return [w * 2.20462 for w in weights]\n",
"\n",
@ -52,7 +51,6 @@
"\n",
" for measurement in filter_weekly(lbs, days):\n",
" print(measurement)\n",
"```\n",
"\n",
"1. Cleaned reference code, with a main entrypoint function that takes all required arguments as parameters and returns all outputs.\n",
"\n",
@ -70,7 +68,6 @@
"\n",
"Example description:\n",
"\n",
"```plaintext\n",
"Input:\n",
" weights_kg (list of int): List of weight values in kilograms.\n",
" days (list of int): List of integers representing the number of days passed, starting from zero.\n",
@ -78,7 +75,6 @@
"Output:\n",
" return (dict): A dictionary with one key:\n",
" - weights_lb (list of int): List of filtered weight values in pounds.\n",
"```\n",
"\n",
"4. Python 3.11 code for an input generator, which randomly generates valid sets of inputs for the functions.\n",
"\n",
@ -86,24 +82,22 @@
"\n",
"Example input generator:\n",
"\n",
"```python\n",
"def input_generator():\n",
" weights = [np.random.uniform(0, 100) for _ in range(40)]\n",
" days = list(range(40))\n",
" return {{\"weights_kg\": weights, \"days\": days}}\n",
"```\n",
"\n",
"Using the guidelines and example above, preprocess the following raw code file into the standard format:\n",
"\n",
"{0}\n",
"\n",
"Output the components (reference code, query, description, input generator) in order. Separate each component with a triple newline (\\n\\n\\n).\n",
"Output the components (reference code, query, description, input generator) in order. Separate each component with a triple newline (\\n\\n\\n). Avoid code blocks and do not output any Markdown formatting.\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
@ -145,21 +139,18 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"### Reference Code\n",
"```python\n",
"def main(word1: str, word2: str) -> dict:\n",
" m, n = len(word1), len(word2)\n",
" dp = [[0] * (n + 1) for _ in range(m + 1)]\n",
"\n",
" for i in range(m + 1):\n",
" for j in range(n + 1):\n",
"def main(word1, word2):\n",
" dp = [[0 for _ in range(len(word2) + 1)] for _ in range(len(word1) + 1)]\n",
" \n",
" for i in range(len(word1) + 1):\n",
" for j in range(len(word2) + 1):\n",
" if i == 0:\n",
" dp[i][j] = j\n",
" elif j == 0:\n",
@ -171,39 +162,29 @@
" delete = dp[i - 1][j]\n",
" replace = dp[i - 1][j - 1]\n",
" dp[i][j] = 1 + min(insert, delete, replace)\n",
" \n",
" return {\"minimum_edit_distance\": dp[len(word1)][len(word2)]}\n",
"\n",
" return {\"min_edit_distance\": dp[m][n]}\n",
"```\n",
"\n",
"### Query\n",
"You are given two strings, `word1` and `word2`. Your task is to calculate the minimum number of operations required to transform `word1` into `word2`. The permitted operations are insertion, deletion, and substitution of a single character. Return the minimum number of operations needed.\n",
"You are given two strings, `word1` and `word2`. Your task is to find the minimum number of operations required to transform `word1` into `word2`. The permitted operations are insertion, deletion, and substitution of a single character. Return the minimum number of operations as an integer.\n",
"\n",
"\n",
"### Description\n",
"```plaintext\n",
"Input:\n",
" word1 (str): The first string.\n",
" word2 (str): The second string.\n",
"\n",
"Output:\n",
" return (dict): A dictionary with one key:\n",
" - min_edit_distance (int): The minimum number of operations required to transform `word1` into `word2`.\n",
"```\n",
" - minimum_edit_distance (int): The minimum number of operations required to transform `word1` into `word2`.\n",
"\n",
"### Input Generator\n",
"```python\n",
"import random\n",
"import string\n",
"\n",
"def input_generator():\n",
" def random_string(length):\n",
" letters = string.ascii_lowercase\n",
" return ''.join(random.choice(letters) for _ in range(length))\n",
"\n",
" word1 = random_string(random.randint(5, 15))\n",
" word2 = random_string(random.randint(5, 15))\n",
" import random\n",
" import string\n",
" \n",
" return {\"word1\": word1, \"word2\": word2}\n",
"```\n"
" word1 = ''.join(random.choice(string.ascii_lowercase) for _ in range(random.randint(5, 10)))\n",
" word2 = ''.join(random.choice(string.ascii_lowercase) for _ in range(random.randint(5, 10)))\n",
" return {\"word1\": word1, \"word2\": word2}\n"
]
}
],