fix clustering in sf

clouds/snowflake/libraries/javascript/libs/clustering.js

@@ -1,7 +1,35 @@
 import { featureCollection, feature, clustersKmeans } from '@turf/turf';
 
+function prioritizeDistinctSort(arr) {
+    const uniqueValues = [];
+    const duplicatedValues = [];
+
+    // Split the array into unique and duplicated values
+    const countMap = {};
+    for (const item of arr) {
+        if (countMap[item] === undefined) {
+            countMap[item] = 1;
+            uniqueValues.push(item);
+        } else {
+            countMap[item]++;
+            duplicatedValues.push(item);
+        }
+    }
+
+    // Sort unique values alphabetically
+    uniqueValues.sort();
+
+    // Sort duplicated values alphabetically
+    duplicatedValues.sort();
+
+    // Concatenate unique and duplicated values
+    const result = [...uniqueValues, ...duplicatedValues];
+    return result;
+}
+
 export default {
     featureCollection,
     feature,
-    clustersKmeans
+    clustersKmeans,
+    prioritizeDistinctSort
 };

clouds/snowflake/libraries/javascript/test/clustering.test.js

@@ -4,4 +4,5 @@ test('clustering library defined', () => {
     expect(clusteringLib.featureCollection).toBeDefined();
     expect(clusteringLib.feature).toBeDefined();
     expect(clusteringLib.clustersKmeans).toBeDefined();
+    expect(clusteringLib.prioritizeDistinctSort).toBeDefined();
 });

clouds/snowflake/modules/sql/clustering/ST_CLUSTERKMEANS.sql

@@ -17,8 +17,7 @@ AS $$
     const options = {};
     options.numberOfClusters = Number(NUMBEROFCLUSTERS);
     options.mutate = true;
-    GEOJSONS = Array.from(new Set(GEOJSONS));
-    const featuresCollection = clusteringLib.featureCollection(GEOJSONS.map(x => clusteringLib.feature(JSON.parse(x))));
+    const featuresCollection = clusteringLib.featureCollection(clusteringLib.prioritizeDistinctSort(GEOJSONS).map(x => clusteringLib.feature(JSON.parse(x))));
     clusteringLib.clustersKmeans(featuresCollection, options);
     const cluster = [];
     featuresCollection.features.forEach(function(item, index, array) {