File size: 3,635 Bytes
3a464db | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | import evaluate as hf_evaluate
import re
from datasets import Dataset
import ast
# Hugging Face code_eval
try:
pass_at_k = hf_evaluate.load("code_eval")
except Exception as e:
raise e
def process_docs(dataset: Dataset) -> Dataset:
def _process_doc(doc):
doc["text"] = doc["prompt"]
doc["test_list_str"] = "\n".join(doc["test"])
return doc
return dataset.map(_process_doc)
def pass_at_1(references, predictions):
processed_predictions = []
for pred in predictions:
pred_after_step1 = humaneval_postprocess(pred)
pred_after_step2 = _process_answer(pred_after_step1)
processed_predictions.append(pred_after_step2)
results = pass_at_k.compute(
references=list(references),
predictions=[processed_predictions],
k=[1],
)
return results[0]["pass@1"]
def humaneval_postprocess(text: str) -> str:
blocks = re.findall(r'```(?:python)?\n(.*?)\n```', text, re.DOTALL)
if blocks:
return blocks[0].strip()
return text.strip()
# def _process_answer(text: str) -> str:
# patterns = [
# r"'(.*)'\s*$$DONE$$",
# r"$$BEGIN$$\s*'(.*)'\s*$$DONE$$",
# r"BEGIN\s*'(.*)'\s*$$DONE$$",
# r"$$BEGIN$$\s*'(.*)'\s*DONE",
# r"BEGIN\s*'(.*)'\s*DONE",
# r"$$BEGIN$$\s*'(.*)\s*$$DONE$$",
# r"BEGIN\s*'(.*)\s*$$DONE$$",
# r"$$BEGIN$$\s*'(.*)\s*DONE",
# r"BEGIN\s*'(.*)\s*DONE",
# r'$$BEGIN$$\s*(.*)\s*$$DONE$$',
# r'BEGIN\s*(.*)\s*$$DONE$$',
# r'$$BEGIN$$\s*(.*)\s*DONE',
# r'BEGIN\s*(.*)\s*DONE',
# r'```python\s*(.*)\s*```',
# r'```\s*(.*)\s*```',
# r'```python\s*(.*)\s*$',
# r'```\s*(.*)\s*$',
# r'(.*)\s*```.*',
# r"\[BEGIN\]\s*'(.*)",
# r'\[BEGIN\](.*)',
# ]
# for p in patterns:
# match = re.search(p, text, re.DOTALL)
# if match:
# text = match.group(1)
# break
# text = text.split('```')[0]
# text = re.split(r"'?\s*\$\$?DONE\$\$?", text)[0]
# text = text.replace('\\_', '_')
# text = text.strip()
# return text
def _process_answer(text: str) -> str:
patterns = [
r"'(.*)'\s*$$DONE$$",
r"$$BEGIN$$\s*'(.*)'\s*$$DONE$$",
r"BEGIN\s*'(.*)'\s*$$DONE$$",
r"$$BEGIN$$\s*'(.*)'\s*DONE",
r"BEGIN\s*'(.*)'\s*DONE",
r"$$BEGIN$$\s*'(.*)\s*$$DONE$$",
r"BEGIN\s*'(.*)\s*$$DONE$$",
r"$$BEGIN$$\s*'(.*)\s*DONE",
r"BEGIN\s*'(.*)\s*DONE",
r'$$BEGIN$$\s*(.*)\s*$$DONE$$',
r'BEGIN\s*(.*)\s*$$DONE$$',
r'$$BEGIN$$\s*(.*)\s*DONE',
r'BEGIN\s*(.*)\s*DONE',
r'```python\s*(.*)\s*```',
r'```\s*(.*)\s*```',
r'```python\s*(.*)\s*$',
r'```\s*(.*)\s*$',
r'(.*)\s*```.*',
r"\[BEGIN\]\s*'(.*)",
r'\[BEGIN\](.*)',
]
for p in patterns:
match = re.search(p, text, re.DOTALL)
if match:
text = match.group(1)
break
text = text.split('```')[0]
text = re.split(r"'?\s*\$\$?DONE\$\$?", text)[0]
text = text.replace('\\_', '_')
text = text.strip()
try:
tree = ast.parse(text)
filtered_nodes = [
node for node in tree.body
if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef, ast.ClassDef, ast.Import, ast.ImportFrom))
]
if filtered_nodes:
import astor
text = "\n\n".join([ast.unparse(node) for node in filtered_nodes])
except Exception:
pass
return text.strip()
|