utils.py

import re
from typing import Union

import evaluate as hf_evaluate


try:
    compute_ = hf_evaluate.load("code_eval")
    test_cases = ["assert add(2, 3)==5"]
    candidates = [["def add(a,b): return a*b"]]
    results = compute_.compute(references=test_cases, predictions=candidates, k=[1])
except Exception as e:
    raise e


def pass_at_k(references: list[str], predictions: list[list[str]], k: list[int] = None):
    global compute_
    assert k is not None
    if isinstance(k, int):
        k = [k]
    res = compute_.compute(
        references=references,
        predictions=predictions,
        k=k,
    )
    return res[0]


def extract_python_block(text: str) -> str:
    if not text.startswith("```"):
        text = "```python\n" + text + "\n```"
    # capture only fences whose language tag is 'python'
    pattern = re.compile(r"```python\n([\s\S]*?)\n?```", re.IGNORECASE)
    m = pattern.search(text)
    return "from __future__ import annotations\n" + m.group(1) if m else ""


def extract_code_blocks(text: str) -> str:
    # Pattern to match ```...``` blocks
    ignore_annotations = "from __future__ import annotations\n"
    pattern = r"```(?:\w+)?\n?(.*?)\n?```"
    # (+ ```) as we add the opening "```python" to the gen_prefix
    matches = re.findall(pattern, r"```" + text, re.DOTALL)
    # if no matches, try to match ```...``` blocks (after removing the language)
    if not matches:
        text_without_lang = re.sub(r"```python", "```", text)
        matches = re.findall(pattern, text_without_lang, re.DOTALL)
    if not matches:
        return ignore_annotations + text
    else:
        return ignore_annotations + matches[0]


def build_predictions(resps: list[list[str]], docs: list[dict]) -> list[list[str]]:
    return [[extract_code_blocks(r) for r in resp] for resp in resps]


def list_fewshot_samples():
    return [
        {
            "task_id": 2,
            "text": "Write a function to find the similar elements from the given two tuple lists.",
            "code": "def similar_elements(test_tup1, test_tup2):\r\n  res = tuple(set(test_tup1) & set(test_tup2))\r\n  return (res) ",
            "test_list": [
                "assert similar_elements((3, 4, 5, 6),(5, 7, 4, 10)) == (4, 5)",
                "assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4)",
                "assert similar_elements((11, 12, 14, 13),(17, 15, 14, 13)) == (13, 14)",
            ],
            "is_fewshot": True,
        },
        {
            "task_id": 3,
            "text": "Write a python function to identify non-prime numbers.",
            "code": "import math\r\ndef is_not_prime(n):\r\n    result = False\r\n    for i in range(2,int(math.sqrt(n)) + 1):\r\n        if n % i == 0:\r\n            result = True\r\n    return result",
            "test_list": [
                "assert is_not_prime(2) == False",
                "assert is_not_prime(10) == True",
                "assert is_not_prime(35) == True",
            ],
            "is_fewshot": True,
        },
        {
            "task_id": 4,
            "text": "Write a function to find the largest integers from a given list of numbers using heap queue algorithm.",
            "code": "import heapq as hq\r\ndef heap_queue_largest(nums,n):\r\n  largest_nums = hq.nlargest(n, nums)\r\n  return largest_nums",
            "test_list": [
                "assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],3)==[85, 75, 65] ",
                "assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] ",
                "assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],5)==[85, 75, 65, 58, 35]",
            ],
            "is_fewshot": True,
        },
    ]