christianV/Craze-Data-check
1
0
Fork 0
mirror of https://github.com/christianvidalwolf-prog/Craze-Data-check.git synced 2026-08-03 17:05:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix: tighten near-duplicate detection to <1 cm absolute difference per axis

Browse Source 
Replaces percentage-based threshold (15%) with strict absolute tolerance:
two dimension groups are flagged only if all three sorted dimensions
differ by less than 1 cm. Targets likely data entry typos.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Christian Vidal Wolf
2026-04-07 10:56:58 +02:00
co-authored by Claude Sonnet 4.6
parent 9753958761
commit d48e2cb0ff
1 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/components/DimensionsView.tsx
+10 -10
View File
@@ -110,14 +110,14 @@ export function DimensionsView({ data, headers, onEdit, onSaveRow, onCaptureStat
}, [groups, showOnlyInconsistent]);
const nearDuplicateClusters = useMemo((): NearDuplicateCluster[] => {
// Two groups are "similar" if every sorted dimension pair differs by ≤15%
// Two groups are "similar" if every sorted dimension pair differs by < 1 cm absolute
// (keys are already sorted ascending, e.g. "15x20x29")
const THRESHOLD = 0.15;
const MAX_DIFF_CM = 1;
const maxRelativeDiff = (keyA: string, keyB: string): number => {
const maxAbsDiff = (keyA: string, keyB: string): number => {
const a = keyA.split('x').map(Number);
const b = keyB.split('x').map(Number);
return Math.max(...a.map((v, i) => Math.abs(v - b[i]) / Math.max(v, b[i], 0.001)));
return Math.max(...a.map((v, i) => Math.abs(v - b[i])));
};
const validGroups = groups.filter(g => g.volume > 0);
@@ -135,8 +135,8 @@ export function DimensionsView({ data, headers, onEdit, onSaveRow, onCaptureStat
const b = validGroups[j];
if (assignedKeys.has(b.key)) continue;
// b must be similar to every group already in the cluster
const isSimilar = cluster.every(g => maxRelativeDiff(g.key, b.key) <= THRESHOLD);
// b must be within 1 cm on every axis of every group already in the cluster
const isSimilar = cluster.every(g => maxAbsDiff(g.key, b.key) < MAX_DIFF_CM);
if (isSimilar) {
cluster.push(b);
assignedKeys.add(b.key);
@@ -145,11 +145,11 @@ export function DimensionsView({ data, headers, onEdit, onSaveRow, onCaptureStat
if (cluster.length >= 2) {
const volumes = cluster.map(g => g.volume);
// Max dimension-wise diff across all pairs in the cluster
// Max absolute diff (cm) across all pairs in the cluster
let maxDiffPct = 0;
for (let x = 0; x < cluster.length; x++) {
for (let y = x + 1; y < cluster.length; y++) {
maxDiffPct = Math.max(maxDiffPct, maxRelativeDiff(cluster[x].key, cluster[y].key) * 100);
maxDiffPct = Math.max(maxDiffPct, maxAbsDiff(cluster[x].key, cluster[y].key));
}
}
clusters.push({ groups: cluster, volumes, maxDiffPct });
@@ -254,7 +254,7 @@ export function DimensionsView({ data, headers, onEdit, onSaveRow, onCaptureStat
<Link2 className="w-4 h-4 text-violet-400" />
<span className="text-sm font-semibold text-violet-300">Possible data entry errors</span>
<span className="text-xs text-slate-500 bg-slate-900 px-2 py-0.5 rounded-full border border-slate-700">
{nearDuplicateClusters.length} cluster{nearDuplicateClusters.length !== 1 ? 's' : ''} with similar dimensions (≤15% per axis)
{nearDuplicateClusters.length} cluster{nearDuplicateClusters.length !== 1 ? 's' : ''} with dimensions differing &lt;1 cm per axis
</span>
</div>
{nearDuplicateClusters.map((cluster, ci) => (
@@ -276,7 +276,7 @@ export function DimensionsView({ data, headers, onEdit, onSaveRow, onCaptureStat
</span>
))}
<span className="text-xs text-violet-400/70">
— max axis diff {cluster.maxDiffPct.toFixed(1)}%
— max diff {cluster.maxDiffPct.toFixed(1)} cm
</span>
</div>
</button>