Source code for langchain.evaluation.parsing.json_distance
import json
from typing import Any, Callable, Optional, Union
from langchain_core.utils.json import parse_json_markdown
from langchain.evaluation.schema import StringEvaluator
[docs]class JsonEditDistanceEvaluator(StringEvaluator):
"""一个计算JSON字符串之间编辑距离的评估器。
该评估器在解析并将两个JSON字符串转换为规范格式(即,空格和键的顺序被规范化)之后,计算两个JSON字符串之间的标准化Damerau-Levenshtein距离。它可以通过替代距离和规范化函数进行定制。
参数:
string_distance(可选[Callable[[str, str], float]]):计算两个字符串之间距离的可调用函数。
如果未提供,则将使用`rapidfuzz`包中的Damerau-Levenshtein距离。
canonicalize(可选[Callable[[Any], Any]]):将解析的JSON对象转换为其规范字符串形式的可调用函数。
如果未提供,默认行为是使用排序后的键和没有额外空格序列化JSON。
**kwargs(Any):额外的关键字参数。
属性:
_string_distance(Callable[[str, str], float]):内部距离计算函数。
_canonicalize(Callable[[Any], Any]):内部规范化函数。
示例:
>>> evaluator = JsonEditDistanceEvaluator()
>>> result = evaluator.evaluate_strings(prediction='{"a": 1, "b": 2}', reference='{"a": 1, "b": 3}')
>>> assert result["score"] is not None
引发:
ImportError:如果未安装`rapidfuzz`并且未提供替代的`string_distance`函数。""" # noqa: E501
[docs] def __init__(
self,
string_distance: Optional[Callable[[str, str], float]] = None,
canonicalize: Optional[Callable[[Any], Any]] = None,
**kwargs: Any,
) -> None:
super().__init__()
if string_distance is not None:
self._string_distance = string_distance
else:
try:
from rapidfuzz import distance as rfd
except ImportError:
raise ImportError(
"The default string_distance operator for the "
" JsonEditDistanceEvaluator requires installation of "
"the rapidfuzz package. "
"Please install it with `pip install rapidfuzz`."
)
self._string_distance = rfd.DamerauLevenshtein.normalized_distance
if canonicalize is not None:
self._canonicalize = canonicalize
else:
self._canonicalize = lambda x: json.dumps(
x,
separators=(",", ":"),
sort_keys=True, # eliminate whitespace
)
@property
def requires_input(self) -> bool:
return False
@property
def requires_reference(self) -> bool:
return True
@property
def evaluation_name(self) -> str:
return "json_edit_distance"
def _parse_json(self, node: Any) -> Union[dict, list, None, float, bool, int, str]:
if isinstance(node, str):
return parse_json_markdown(node)
return node
def _evaluate_strings(
self,
prediction: str,
input: Optional[str] = None,
reference: Optional[str] = None,
**kwargs: Any,
) -> dict:
parsed = self._canonicalize(self._parse_json(prediction))
label = self._canonicalize(self._parse_json(reference))
distance = self._string_distance(parsed, label)
return {"score": distance}