코드 생성

!pip install -qU autopep8 autoflake weave isort openai set-env-colab-kaggle-dotenv datasets
python
%%capture
# openai 버그를 해결하기 위한 임시 조치:
# TypeError: Client.__init__() got an unexpected keyword argument 'proxies'
# 참고: https://community.openai.com/t/error-with-openai-1-56-0-client-init-got-an-unexpected-keyword-argument-proxies/1040332/15
!pip install "httpx<0.28"
python
import ast
import os
import re
import subprocess
import tempfile
import traceback

import autopep8
import isort
from autoflake import fix_code
from datasets import load_dataset
from openai import OpenAI
from pydantic import BaseModel
from set_env import set_env

import weave
from weave import Dataset, Evaluation

set_env("WANDB_API_KEY")
set_env("OPENAI_API_KEY")
python
WEAVE_PROJECT = "codegen-cookbook-example"
weave.init(WEAVE_PROJECT)
python
client = OpenAI()
python
human_eval = load_dataset("openai_humaneval")
selected_examples = human_eval["test"][:3]

class GeneratedCode(BaseModel):
    function_signature: str
    function_args_with_docstring_within_triple_quotes: str
    code_logic: str

class FormattedGeneratedCode(BaseModel):
    full_code: str

class CodeFormatter(BaseModel):
    @weave.op()
    def lint_code(self, code: str) -> str:
        # 이스케이프된 줄바꿈 문자를 실제 줄바꿈으로 바꿉니다
        code = code.replace("\\n", "\n")

        # 사용하지 않는 임포트와 변수를 제거합니다
        code = fix_code(
            code, remove_all_unused_imports=True, remove_unused_variables=True
        )

        # 임포트를 정렬합니다
        code = isort.code(code)

        # PEP 8 포매팅을 적용합니다
        code = autopep8.fix_code(code, options={"aggressive": 2})

        return code

    @weave.op()
    def add_imports(self, code: str) -> str:
        tree = ast.parse(code)
        from_imports = {}
        global_names = set()

        for node in ast.walk(tree):
            if isinstance(node, ast.Name) and node.id not in dir(__builtins__):
                global_names.add(node.id)

        # 실제로 사용되는 typing 임포트만 추가합니다
        typing_imports = global_names.intersection(
            {"List", "Dict", "Tuple", "Set", "Optional", "Union"}
        )
        if typing_imports:
            from_imports["typing"] = typing_imports

        # 함수 내부에서 정의된 이름은 제외합니다
        function_def = next(
            node for node in tree.body if isinstance(node, ast.FunctionDef)
        )
        local_names = {arg.arg for arg in function_def.args.args}
        local_names.update(
            node.id
            for node in ast.walk(function_def)
            if isinstance(node, ast.Name) and isinstance(node.ctx, ast.Store)
        )

        global_names -= local_names
        global_names -= {"sorted"}  # 내장 함수는 제외합니다

        # import 문을 생성합니다
        import_statements = []
        for module, names in from_imports.items():
            names_str = ", ".join(sorted(names))
            import_statements.append(f"from {module} import {names_str}")

        return (
            "\n".join(import_statements) + ("\n\n" if import_statements else "") + code
        )

    @weave.op()
    def format_generated_code(
        self, generated_code: GeneratedCode
    ) -> FormattedGeneratedCode:
        # 코드 조각을 하나로 합칩니다
        full_code = f"{generated_code.function_signature}\n{generated_code.function_args_with_docstring_within_triple_quotes}\n{generated_code.code_logic}"

        # 들여쓰기를 올바르게 맞춥니다
        lines = full_code.split("\n")
        indented_lines = []
        for i, line in enumerate(lines):
            if i == 0:  # 함수 시그니처
                indented_lines.append(line)
            elif i == 1:  # 함수 인수(docstring)
                indented_lines.append("    " + line)
            else:  # 함수 본문
                indented_lines.append("    " + line)
        full_code = "\n".join(indented_lines)

        # 코드에 린트를 적용합니다
        full_code = self.lint_code(full_code)

        # 임포트를 추가합니다
        cleaned_code = self.add_imports(full_code)

        return FormattedGeneratedCode(full_code=cleaned_code)

class CodeGenerationPipeline(weave.Model):
    model_name: str
    formatter: CodeFormatter

    def __init__(
        self, model_name: str = "gpt-4o", formatter: CodeFormatter | None = None
    ):
        if formatter is None:
            formatter = CodeFormatter()
        super().__init__(model_name=model_name, formatter=formatter)
        self.model_name = model_name
        self.formatter = formatter

    @weave.op()
    async def predict(self, prompt: str):
        generated_code = self.generate_code(prompt)
        formatted_generated_code = self.formatter.format_generated_code(generated_code)

        return formatted_generated_code.full_code

    @weave.op()
    def generate_code(self, prompt: str) -> GeneratedCode:
        completion = client.beta.chat.completions.parse(
            model=self.model_name,
            messages=[
                {
                    "role": "system",
                    "content": "You are an expert Python code generator.",
                },
                {"role": "user", "content": prompt},
            ],
            response_format=GeneratedCode,
        )
        message = completion.choices[0].message
        if message.parsed:
            return message.parsed
        else:
            raise ValueError(message.refusal)

CODE_TEMPLATE = """
{model_output}

{test}

if __name__ == "__main__":
    check({entry_point})
"""
python
@weave.op()
async def score_humaneval_test(test: str, entry_point: str, output: str):
    generated_code = output

    # 테스트 문자열에서 테스트 케이스 추출
    test_cases = re.findall(r"assert.*", test)
    test_cases_str = "\n            ".join(test_cases)

    # 전체 소스 코드 생성
    full_code = CODE_TEMPLATE.format(
        model_output=generated_code,
        test=test,
        test_cases=test_cases_str,
        entry_point=entry_point,
    )

    # 코드를 저장할 임시 파일 생성
    with tempfile.NamedTemporaryFile(delete=False, suffix=".py") as tmp_file:
        # 생성된 코드를 임시 파일에 기록
        tmp_file.write(full_code.encode())
        tmp_file_path = tmp_file.name

    try:
        # timeout을 설정하고 임시 Python 파일을 하위 프로세스로 실행
        result = subprocess.run(
            ["python", tmp_file_path],
            capture_output=True,
            text=True,
            timeout=10,  # timeout 10초
        )

        print(result)

        if result.returncode == 0:
            return {"correct": True}
        else:
            return {"correct": False, "error": result.stderr, "output": result.stdout}
    except subprocess.TimeoutExpired:
        return {"correct": False, "error": "TimeoutExpired"}
    except Exception as e:
        return {"correct": False, "error": traceback.format_exc()}
    finally:
        # 실행이 끝나면 임시 파일을 반드시 삭제
        os.remove(tmp_file_path)

formatted_selected_examples = [
    {
        "task_id": task_id,
        "prompt": prompt,
        "canonical_solution": solution,
        "test": test,
        "entry_point": entry_point,
    }
    for task_id, prompt, solution, test, entry_point in zip(
        selected_examples["task_id"],
        selected_examples["prompt"],
        selected_examples["canonical_solution"],
        selected_examples["test"],
        selected_examples["entry_point"],
    )
]
python
prompt_dataset = Dataset(
    name="humaneval_code_gen_example",
    rows=[
        {
            "prompt": example["prompt"],
            "test": example["test"],
            "entry_point": example["entry_point"],
        }
        for example in formatted_selected_examples
    ],
)
weave.publish(prompt_dataset)
python
EVAL_RUN = True
python
for model_name in ["gpt-4o-2024-08-06"]:
    pipeline = CodeGenerationPipeline(model_name=model_name)
    if not EVAL_RUN:
        dataset = prompt_dataset.rows[2]
        result = await pipeline.predict(dataset["prompt"])
        score_result = await score_humaneval_test(
            dataset["test"], dataset["entry_point"], result["generated_code"].full_code
        )
    else:
        evaluation = Evaluation(
            name="minimal_code_gen_evaluation",
            dataset=prompt_dataset,
            scorers=[score_humaneval_test],
        )
        results = await evaluation.evaluate(pipeline)