111 lines
4.0 KiB
JavaScript
111 lines
4.0 KiB
JavaScript
// metric_presenter.js — 统一维护指标语义(高分好 / 低分好)、颜色阈值与简要说明。
|
||
|
||
(function attachMetricPresenter(globalObj) {
|
||
const METRIC_META = {
|
||
faithfulness: {
|
||
direction: "higher_better",
|
||
description: "回答是否被检索内容直接支持,越高越可靠。",
|
||
},
|
||
answer_relevancy: {
|
||
direction: "higher_better",
|
||
description: "回答与问题是否紧密相关,越高越切题。",
|
||
},
|
||
context_recall: {
|
||
direction: "higher_better",
|
||
description: "检索片段覆盖标准答案关键信息的程度,越高越完整。",
|
||
},
|
||
context_precision: {
|
||
direction: "higher_better",
|
||
description: "检索片段中有效信息的占比,越高越精准。",
|
||
},
|
||
noise_sensitivity: {
|
||
direction: "lower_better",
|
||
description: "对噪声上下文的敏感程度,越低说明抗干扰能力越强。",
|
||
},
|
||
factual_correctness: {
|
||
direction: "higher_better",
|
||
description: "回答与标准答案在事实层面的吻合程度,越高越准确。",
|
||
},
|
||
semantic_similarity: {
|
||
direction: "higher_better",
|
||
description: "回答与标准答案在语义上的相似程度,越高越接近。",
|
||
},
|
||
};
|
||
|
||
function isLowerBetter(metricName) {
|
||
return METRIC_META[metricName]?.direction === "lower_better";
|
||
}
|
||
|
||
function scoreClass(metricName, value) {
|
||
if (value === null || value === undefined || Number.isNaN(Number(value))) return "na";
|
||
const numeric = Number(value);
|
||
if (isLowerBetter(metricName)) {
|
||
if (numeric <= 0.15) return "good";
|
||
if (numeric <= 0.35) return "warn";
|
||
return "bad";
|
||
}
|
||
if (numeric >= 0.85) return "good";
|
||
if (numeric >= 0.65) return "warn";
|
||
return "bad";
|
||
}
|
||
|
||
function describeMetric(metricName) {
|
||
return METRIC_META[metricName]?.description || "该指标用于衡量当前问答样本的评估表现。";
|
||
}
|
||
|
||
function binColor(metricName, lower) {
|
||
const numeric = Number(lower);
|
||
if (isLowerBetter(metricName)) {
|
||
if (numeric < 0.2) return "#16a34a";
|
||
if (numeric < 0.4) return "#84cc16";
|
||
if (numeric < 0.6) return "#eab308";
|
||
if (numeric < 0.8) return "#f97316";
|
||
return "#dc2626";
|
||
}
|
||
if (numeric >= 0.8) return "#16a34a";
|
||
if (numeric >= 0.6) return "#84cc16";
|
||
if (numeric >= 0.4) return "#eab308";
|
||
if (numeric >= 0.2) return "#f97316";
|
||
return "#dc2626";
|
||
}
|
||
|
||
// 计算某指标本次相对上一次的涨跌信息,方向语义随指标而定
|
||
// (noise_sensitivity 越低越好:下降=改善)。
|
||
function deltaInfo(metricName, current, previous) {
|
||
const isNum = (v) => v !== null && v !== undefined && !Number.isNaN(Number(v));
|
||
if (!isNum(current) || !isNum(previous)) {
|
||
return { hasData: false, delta: null, improved: null, arrow: "", magnitude: "", cls: "delta-flat" };
|
||
}
|
||
const delta = Number(current) - Number(previous);
|
||
const rounded = Math.round(delta * 10000) / 10000;
|
||
const arrow = rounded > 0 ? "▲" : rounded < 0 ? "▼" : "→";
|
||
const magnitude = Math.abs(rounded).toFixed(2);
|
||
const improved = isLowerBetter(metricName) ? rounded < 0 : rounded > 0;
|
||
const cls = rounded === 0 ? "delta-flat" : improved ? "delta-good" : "delta-bad";
|
||
return { hasData: true, delta: rounded, improved, arrow, magnitude, cls };
|
||
}
|
||
|
||
// 返回指标的"达标阈值"(柱状图对比用,方向感知)。
|
||
// higher-better 指标:0.85;lower-better (noise_sensitivity):0.15。
|
||
function passThreshold(metricName) {
|
||
return isLowerBetter(metricName) ? 0.15 : 0.85;
|
||
}
|
||
|
||
// 判断某指标的值是否达标。
|
||
function meetsTarget(metricName, value) {
|
||
if (value === null || value === undefined || Number.isNaN(Number(value))) return false;
|
||
const v = Number(value);
|
||
return isLowerBetter(metricName) ? v <= passThreshold(metricName) : v >= passThreshold(metricName);
|
||
}
|
||
|
||
globalObj.MetricPresenter = {
|
||
scoreClass,
|
||
describeMetric,
|
||
binColor,
|
||
isLowerBetter,
|
||
deltaInfo,
|
||
passThreshold,
|
||
meetsTarget,
|
||
};
|
||
})(window);
|