Water utility

Sample: Water utility, Cape Town: report

Project: Sample: Water utility, Cape Town
Goal: Describe the project Sample: Water utility, Cape Town: run the analyses that tell the most about its data, draw every result, and write a cited report.
Run: e33b2a03-f978-4654-94e4-ffd327ff8f7b (running, 11 agent run(s))
Generated: 2026-10-18T05:36:20Z, version 1
Model cost: USD 0.0000 over 0 model call(s)

Data used

Timeline

The timeline counts 1,662 dated events in Leak and burst repairs, Customer complaints, Zone meter readings by month per month, from October 2023 to September 2026 1234. By dataset: Leak and burst repairs 950; Customer complaints 520; Zone meter readings by month 192 1. The trend is +2.5 events per month; the second half of the months has 1,208 against 454 in the first (+166.1%) 1.

Busiest months

• July 2026: 130 events 1
• August 2026: 126 events 1
• June 2026: 116 events 1

Quietest months

• January 2024: 10 events 1
• February 2024: 13 events 1
• November 2023: 14 events 1

Space time hot spots

What this analysis is. Emerging hot spots: Where hot spots are new, consecutive, intensifying, persistent, diminishing, sporadic, oscillating or historical over time 5. In ArcGIS it is Emerging Hot Spot Analysis or Create Space Time Cube 5.

Why it was run on this data. Leak and burst repairs carry dates in 'reported_at': emerging hot spot analysis finds new, intensifying and fading hot spots per month 6.

What it found. The analysis generated 1 layer saved named Emerging hot spots: Leak and burst repairs 7. Processing the Leak and burst repairs data 8 resulted in a count of 71 features 7. In total, 950 features were used during this execution 7, which took an elapsed time of 19 ms 7. The billing cost for this operation was 0.1475 7.

Findings

• Evidenced: Space time hot spots on Leak and burst repairs: Emerging hot spots: 1 layer saved: Emerging hot spots: Leak and burst repairs (71 features) 78.
• Evidenced: It reported result, count 71; result, elapsed ms 19; result, resolution 8; result, features used 950; result, time neighbors 0; billing, cost 0.1475 7.

Tool gp_space_time_hot_spots; parameters {"project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Leak and burst repairs (7e6cb18c)"}, "interval": "month", "bin_shape": "h3", "resolution": 8, "time_field": "reported_at"}

Space time hot spots

What this analysis is. Emerging hot spots: Where hot spots are new, consecutive, intensifying, persistent, diminishing, sporadic, oscillating or historical over time 5. In ArcGIS it is Emerging Hot Spot Analysis or Create Space Time Cube 5.

Why it was run on this data. Customer complaints carry dates in 'date': emerging hot spot analysis finds new, intensifying and fading hot spots per week 9.

What it found. Space time hot spots on Customer complaints: Emerging hot spots: 1 layer saved: Emerging hot spots: Customer complaints (75 features) 1011. It reported result, count 75; result, elapsed ms 15; result, resolution 8; result, features used 520; result, time neighbors 0; billing, cost 0.126 10.

Findings

• Evidenced: Space time hot spots on Customer complaints: Emerging hot spots: 1 layer saved: Emerging hot spots: Customer complaints (75 features) 1011.
• Evidenced: It reported result, count 75; result, elapsed ms 15; result, resolution 8; result, features used 520; result, time neighbors 0; billing, cost 0.126 10.

Tool gp_space_time_hot_spots; parameters {"project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Customer complaints (56e8a858)"}, "interval": "week", "bin_shape": "h3", "resolution": 8, "time_field": "date"}

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 12. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 12.

Why it was run on this data. 300 points: Getis-Ord Gi* tests whether the concentrations in Valves are statistically significant 13.

What it found. Hot spots on Valves: Hot spot analysis: 1 layer saved: Hot spot analysis: Valves (53 features) 1415. It reported result, bins 53; result, count 53; result, elapsed ms 6; result, cell size m 1,000; result, incidents used 300; result, distance band m 1,000 14.

Findings

• Evidenced: Hot spots on Valves: Hot spot analysis: 1 layer saved: Hot spot analysis: Valves (53 features) 1415.
• Evidenced: It reported result, bins 53; result, count 53; result, elapsed ms 6; result, cell size m 1,000; result, incidents used 300; result, distance band m 1,000 14.

Tool gp_hot_spots; parameters {"project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Valves (c6aecae7)"}, "aggregation": "hexagon", "cell_size_m": 1000.0, "distance_band_m": 1000.0}

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 12. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 12.

Why it was run on this data. 950 points: Getis-Ord Gi* tests whether the concentrations in Leak and burst repairs are statistically significant 16.

What it found. Hot spots on Leak and burst repairs: Hot spot analysis: 1 layer saved: Hot spot analysis: Leak and burst repairs (184 features) 817. It reported result, bins 184; result, count 184; result, elapsed ms 11; result, cell size m 500; result, incidents used 950; result, distance band m 500 17.

Findings

• Evidenced: Hot spots on Leak and burst repairs: Hot spot analysis: 1 layer saved: Hot spot analysis: Leak and burst repairs (184 features) 817.
• Evidenced: It reported result, bins 184; result, count 184; result, elapsed ms 11; result, cell size m 500; result, incidents used 950; result, distance band m 500 17.

Tool gp_hot_spots; parameters {"project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Leak and burst repairs (7e6cb18c)"}, "aggregation": "hexagon", "cell_size_m": 500.0, "distance_band_m": 500.0}

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 12. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 12.

Why it was run on this data. 520 points: Getis-Ord Gi* tests whether the concentrations in Customer complaints are statistically significant 18.

What it found. Hot spots on Customer complaints: Hot spot analysis: 1 layer saved: Hot spot analysis: Customer complaints (185 features) 1119. It reported result, bins 185; result, count 185; result, elapsed ms 9; result, cell size m 500; result, incidents used 520; result, distance band m 500 19.

Findings

• Evidenced: Hot spots on Customer complaints: Hot spot analysis: 1 layer saved: Hot spot analysis: Customer complaints (185 features) 1119.
• Evidenced: It reported result, bins 185; result, count 185; result, elapsed ms 9; result, cell size m 500; result, incidents used 520; result, distance band m 500 19.

Tool gp_hot_spots; parameters {"project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Customer complaints (56e8a858)"}, "aggregation": "hexagon", "cell_size_m": 500.0, "distance_band_m": 500.0}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 20. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 20.

Why it was run on this data. 300 points in Valves: a density surface shows where they concentrate 21.

What it found. Calculate density on Valves: Calculate density: 1 layer saved: Calculate density: Valves (257 features) 1522. It reported result, count 257; result, elapsed ms 9; result, bandwidth m 1,000; result, cell size m 500; result, excluded null 0; result, max density per km2 14.42 22.

Findings

• Evidenced: Calculate density on Valves: Calculate density: 1 layer saved: Calculate density: Valves (257 features) 1522.
• Evidenced: It reported result, count 257; result, elapsed ms 9; result, bandwidth m 1,000; result, cell size m 500; result, excluded null 0; result, max density per km2 14.42 22.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Valves (c6aecae7)"}, "bandwidth_m": 1000.0, "cell_size_m": 500.0}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 20. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 20.

Why it was run on this data. 950 points in Leak and burst repairs: a density surface shows where they concentrate 23.

What it found. The density calculation utilized the Leak and burst repairs data 8, resulting in 1,220 features 24. The analysis determined that the maximum density observed was 133.9 per km2 24.

Findings

• Evidenced: Calculate density on Leak and burst repairs: Calculate density: 1 layer saved: Calculate density: Leak and burst repairs (1220 features) 824.
• Evidenced: It reported result, count 1,220; result, elapsed ms 36; result, bandwidth m 500; result, cell size m 200; result, excluded null 0; result, max density per km2 133.9 24.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Leak and burst repairs (7e6cb18c)"}, "bandwidth_m": 500.0, "cell_size_m": 200.0}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 20. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 20.

Why it was run on this data. 520 points in Customer complaints: a density surface shows where they concentrate 25.

What it found. Calculate density on Customer complaints: Calculate density: 1 layer saved: Calculate density: Customer complaints (1200 features) 1126. It reported result, count 1,200; result, elapsed ms 34; result, bandwidth m 500; result, cell size m 200; result, excluded null 0; result, max density per km2 55.38 26.

Findings

• Evidenced: Calculate density on Customer complaints: Calculate density: 1 layer saved: Calculate density: Customer complaints (1200 features) 1126.
• Evidenced: It reported result, count 1,200; result, elapsed ms 34; result, bandwidth m 500; result, cell size m 200; result, excluded null 0; result, max density per km2 55.38 26.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Customer complaints (56e8a858)"}, "bandwidth_m": 500.0, "cell_size_m": 200.0}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 27. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 27.

Why it was run on this data. Count Valves inside each feature of Pressure zones by type; the counts map as a choropleth (natural breaks, sequential colors) 28.

What it found. Summarize within on Valves, Pressure zones: Summarize within: 1 layer saved: Summarize within: Pressure zones (8 features) 152930. It reported result, count 8; result, elapsed ms 1; billing, cost 0.01618; billing, list price 0.01618; billing, upstream cost 0 29.

Findings

• Evidenced: Summarize within on Valves, Pressure zones: Summarize within: 1 layer saved: Summarize within: Pressure zones (8 features) 152930.
• Evidenced: It reported result, count 8; result, elapsed ms 1; billing, cost 0.01618; billing, list price 0.01618; billing, upstream cost 0 29.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "exercised_year"}], "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Valves (c6aecae7)"}, "group_by": "type", "polygons": {"layer": "Pressure zones (a4c55d18)"}}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 27. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 27.

Why it was run on this data. Count Valves inside each feature of Pressure zones by type; the counts map as a choropleth (natural breaks, sequential colors) 28.

What it found. Summarize within on Leak and burst repairs, Pressure zones: Summarize within: 1 layer saved: Summarize within: Pressure zones (8 features) 83031. It reported result, count 8; result, elapsed ms 2; billing, cost 0.02918; billing, list price 0.02918; billing, upstream cost 0 31.

Findings

• Evidenced: Summarize within on Leak and burst repairs, Pressure zones: Summarize within: 1 layer saved: Summarize within: Pressure zones (8 features) 83031.
• Evidenced: It reported result, count 8; result, elapsed ms 2; billing, cost 0.02918; billing, list price 0.02918; billing, upstream cost 0 31.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "water_lost_kl"}], "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Leak and burst repairs (7e6cb18c)"}, "group_by": "type", "polygons": {"layer": "Pressure zones (a4c55d18)"}}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 27. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 27.

Why it was run on this data. Count Valves inside each feature of Pressure zones by type; the counts map as a choropleth (natural breaks, sequential colors) 28.

What it found. Summarize within on Customer complaints, Pressure zones: Summarize within: 1 layer saved: Summarize within: Pressure zones (8 features) 113032. It reported result, count 8; result, elapsed ms 1; billing, cost 0.02056; billing, list price 0.02056; billing, upstream cost 0 32.

Findings

• Evidenced: Summarize within on Customer complaints, Pressure zones: Summarize within: 1 layer saved: Summarize within: Pressure zones (8 features) 113032.
• Evidenced: It reported result, count 8; result, elapsed ms 1; billing, cost 0.02056; billing, list price 0.02056; billing, upstream cost 0 32.

Tool gp_summarize_within; parameters {"stats": [], "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Customer complaints (56e8a858)"}, "group_by": "issue", "polygons": {"layer": "Pressure zones (a4c55d18)"}}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 33. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 33.

Why it was run on this data. DBSCAN finds dense groups of Valves and separates noise 34.

What it found. The analysis utilized the gp_find_point_clusters tool 35 with Valves data as the input 15. This process saved two resulting layers: Find point clusters: Valves with 300 features, and Find point clusters: cluster hulls with 11 features 35.

Findings

• Evidenced: Find point clusters on Valves: Find point clusters: 2 layers saved: Find point clusters: Valves (300 features); Find point clusters: cluster hulls (11 features) 1535.
• Evidenced: It reported result, count 300; result, noise 114; result, distance m 500; result, elapsed ms 8; result, min points 8; billing, cost 0.056 35.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Valves (c6aecae7)"}, "distance_m": 500.0, "min_points": 8}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 33. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 33.

Why it was run on this data. DBSCAN finds dense groups of Leak and burst repairs and separates noise 36.

What it found. Find point clusters on Leak and burst repairs: Find point clusters: 2 layers saved: Find point clusters: Leak and burst repairs (950 features); Find point clusters: cluster hulls (3 features) 837. It reported result, count 950; result, noise 830; result, distance m 200; result, elapsed ms 12; result, min points 20; billing, cost 0.069 37.

Findings

• Evidenced: Find point clusters on Leak and burst repairs: Find point clusters: 2 layers saved: Find point clusters: Leak and burst repairs (950 features); Find point clusters: cluster hulls (3 features) 837.
• Evidenced: It reported result, count 950; result, noise 830; result, distance m 200; result, elapsed ms 12; result, min points 20; billing, cost 0.069 37.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Leak and burst repairs (7e6cb18c)"}, "distance_m": 200.0, "min_points": 20}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 33. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 33.

Why it was run on this data. DBSCAN finds dense groups of Customer complaints and separates noise 38.

What it found. Find point clusters on Customer complaints: Find point clusters: 2 layers saved: Find point clusters: Customer complaints (520 features); Find point clusters: cluster hulls (3 features) 1139. It reported result, count 520; result, noise 196; result, distance m 500; result, elapsed ms 8; result, min points 13; billing, cost 0.0604 39.

Findings

• Evidenced: Find point clusters on Customer complaints: Find point clusters: 2 layers saved: Find point clusters: Customer complaints (520 features); Find point clusters: cluster hulls (3 features) 1139.
• Evidenced: It reported result, count 520; result, noise 196; result, distance m 500; result, elapsed ms 8; result, min points 13; billing, cost 0.0604 39.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Customer complaints (56e8a858)"}, "distance_m": 500.0, "min_points": 13}

Outliers

What this analysis is. Find outliers: Anselin local Moran’s I: HH, LL clusters and HL, LH outliers 40. In ArcGIS it is Find Outliers or Cluster and Outlier Analysis (Anselin Local Moran’s I) 40.

Why it was run on this data. Local Moran's I maps clusters and outliers of 'connections' 41.

What it found. Outliers on Pressure zones: Find outliers: 1 layer saved: Find outliers: Pressure zones (8 features) 3042. It reported result, count 8; result, elapsed ms 3; result, permutations 199; result, excluded null 0; result, distance band m 2,338; billing, cost 0.05024 42.

Findings

• Evidenced: Outliers on Pressure zones: Find outliers: 1 layer saved: Find outliers: Pressure zones (8 features) 3042.
• Evidenced: It reported result, count 8; result, elapsed ms 3; result, permutations 199; result, excluded null 0; result, distance band m 2,338; billing, cost 0.05024 42.

Tool gp_outliers; parameters {"field": "connections", "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Pressure zones (a4c55d18)"}, "aggregation": "hexagon"}

Spatial autocorrelation

What this analysis is. Spatial autocorrelation: Global Moran’s I: is the pattern clustered, dispersed or random 43. In ArcGIS it is Spatial Autocorrelation (Global Moran’s I) 43.

Why it was run on this data. Global Moran's I says whether similar values of 'connections' sit next to each other 44.

What it found. The gp_spatial_autocorrelation tool was executed using Pressure zones as input 30, 45.

Findings

• Evidenced: Spatial autocorrelation on Pressure zones: Spatial autocorrelation: done; no map output 3045.
• Evidenced: It reported result, n 8; result, p value 0.3743; result, z score -0.8884; result, morans i -0.3913; result, variance 0.07821; result, elapsed ms 1 45.

Tool gp_spatial_autocorrelation; parameters {"field": "connections", "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Pressure zones (a4c55d18)"}}

Near repeat

What this analysis is. Repeat and near repeat classification: Classify incidents as originators, repeats (same place) or near repeats within a distance and time window, with a Knox test table 46. In ArcGIS it is Repeat and Near Repeat Classification or Near Repeat Calculator 46.

Why it was run on this data. Near repeat analysis tests whether Leak and burst repairs close in space also follow each other within 30 days 47.

What it found. Near repeat on Leak and burst repairs: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Leak and burst repairs (950 features) 848. It reported result, days 30; result, count 950; result, chains 114; result, distance m 200; result, elapsed ms 20; result, pairs linked 246 48.

Findings

• Evidenced: Near repeat on Leak and burst repairs: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Leak and burst repairs (950 features) 848.
• Evidenced: It reported result, days 30; result, count 950; result, chains 114; result, distance m 200; result, elapsed ms 20; result, pairs linked 246 48.

Tool gp_near_repeat; parameters {"days": 30, "project": "0f6d1895-598a-4c17-a195-fc538533c4a3", "features": {"layer": "Leak and burst repairs (7e6cb18c)"}, "distance_m": 200.0, "time_field": "reported_at"}

Maps and charts

The run also made 20 map image(s) 4950515253545556575859606162636465666768 and 27 chart(s) 697071727374757677787980818283848586878889909192939495.

What the map shows. The map displays emerging hot spots concerning leak and burst repairs, utilizing a classification of 'Sporadic hot spot' and 'No pattern detected.' A noticeable cluster of sporadic hot spots, indicated by the lighter orange coloring, is visible in the central-to-upper portion of the mapped area. In contrast, the majority of the tiles surrounding this central region are colored gray, corresponding to an absence of detected pattern. Overall, the analysis shows a localized concentration of repairs activity surrounded by areas where no significant spatial pattern was detected. 49

Inferred: read from the image by gemma4:e4b, not evidence.

Changes since the last run

This is the first report of this project.

Sources

1. 1Rendering: Chart: Timeline: events per month by dataset. 108 rows id 94a93c16-67b9-41a4-8ed2-808fbbf2754f
2. 2Dataset: Leak and burst repairs. vector, 950 rows id 3f198310-8d97-42f8-b03b-813a838bc233
3. 3Dataset: Customer complaints. vector, 520 rows id 57e4c410-eab9-4da0-8287-b2acf2ce16ca
4. 4Dataset: Zone meter readings by month. table, 192 rows id 56bef21a-7861-4acc-b024-b65a14052a40
5. 5Catalog: Emerging hot spots (operation catalog, gp_space_time_hot_spots). Where hot spots are new, consecutive, intensifying, persistent, diminishing, sporadic, oscillating or historical over time. ArcGIS: Emerging Hot Spot Analysis, Create Space Time Cube. id gp_space_time_hot_spots
6. 6Plan: Space time hot spots of Leak and burst repairs (the Start plan's candidate c_6d3c49125c9a). Leak and burst repairs carry dates in 'reported_at': emerging hot spot analysis finds new, intensifying and fading hot spots per month. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_6d3c49125c9a
7. 7Tool result: gp_space_time_hot_spots, step 0. Emerging hot spots: 1 layer saved: Emerging hot spots: Leak and burst repairs (71 features). id 8c251b5b-c068-49c2-83e1-3ea333425a96:0
8. 8Layer: Leak and burst repairs. 950 features id 7e6cb18c-a956-4aa0-b060-b927e53b2106
9. 9Plan: Space time hot spots of Customer complaints (the Start plan's candidate c_8348225de6d1). Customer complaints carry dates in 'date': emerging hot spot analysis finds new, intensifying and fading hot spots per week. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_8348225de6d1
10. 10Tool result: gp_space_time_hot_spots, step 1. Emerging hot spots: 1 layer saved: Emerging hot spots: Customer complaints (75 features). id 8c251b5b-c068-49c2-83e1-3ea333425a96:1
11. 11Layer: Customer complaints. 520 features id 56e8a858-22c0-49f4-ad9c-220e4d9d9989
12. 12Catalog: Hot spot analysis (operation catalog, gp_hot_spots). Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins. ArcGIS: Find Hot Spots, Hot Spot Analysis (Getis-Ord Gi*). QGIS: qgis:hotspot (plugin). id gp_hot_spots
13. 13Plan: Hot spots of Valves (the Start plan's candidate c_73fb2acb1b6a). 300 points: Getis-Ord Gi* tests whether the concentrations in Valves are statistically significant. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_73fb2acb1b6a
14. 14Tool result: gp_hot_spots, step 0. Hot spot analysis: 1 layer saved: Hot spot analysis: Valves (53 features). id 5758135c-54d5-4daf-a6ef-b217938623cb:0
15. 15Layer: Valves. 300 features id c6aecae7-984d-4e15-9197-a69b622b052f
16. 16Plan: Hot spots of Leak and burst repairs (the Start plan's candidate c_580c09db1123). 950 points: Getis-Ord Gi* tests whether the concentrations in Leak and burst repairs are statistically significant. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_580c09db1123
17. 17Tool result: gp_hot_spots, step 1. Hot spot analysis: 1 layer saved: Hot spot analysis: Leak and burst repairs (184 features). id 5758135c-54d5-4daf-a6ef-b217938623cb:1
18. 18Plan: Hot spots of Customer complaints (the Start plan's candidate c_00d8b144d9af). 520 points: Getis-Ord Gi* tests whether the concentrations in Customer complaints are statistically significant. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_00d8b144d9af
19. 19Tool result: gp_hot_spots, step 2. Hot spot analysis: 1 layer saved: Hot spot analysis: Customer complaints (185 features). id 5758135c-54d5-4daf-a6ef-b217938623cb:2
20. 20Catalog: Calculate density (operation catalog, gp_calculate_density). Kernel density per square kilometer on a grid. ArcGIS: Calculate Density, Kernel Density. QGIS: native:heatmapkerneldensityestimation. id gp_calculate_density
21. 21Plan: Kernel density of Valves (the Start plan's candidate c_d636e5cd662d). 300 points in Valves: a density surface shows where they concentrate. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_d636e5cd662d
22. 22Tool result: gp_calculate_density, step 0. Calculate density: 1 layer saved: Calculate density: Valves (257 features). id 15ea63ce-83f8-46f4-930b-a1531b369666:0
23. 23Plan: Kernel density of Leak and burst repairs (the Start plan's candidate c_ab36517e4e0c). 950 points in Leak and burst repairs: a density surface shows where they concentrate. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_ab36517e4e0c
24. 24Tool result: gp_calculate_density, step 1. Calculate density: 1 layer saved: Calculate density: Leak and burst repairs (1220 features). id 15ea63ce-83f8-46f4-930b-a1531b369666:1
25. 25Plan: Kernel density of Customer complaints (the Start plan's candidate c_be075c3460ae). 520 points in Customer complaints: a density surface shows where they concentrate. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_be075c3460ae
26. 26Tool result: gp_calculate_density, step 2. Calculate density: 1 layer saved: Calculate density: Customer complaints (1200 features). id 15ea63ce-83f8-46f4-930b-a1531b369666:2
27. 27Catalog: Summarize within (operation catalog, gp_summarize_within). Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons. ArcGIS: Summarize Within, Aggregate Points. QGIS: native:countpointsinpolygon, native:sumlinelengths. id gp_summarize_within
28. 28Plan: Valves per feature of Pressure zones (the Start plan's candidate c_5c2b4f19804e). Count Valves inside each feature of Pressure zones by type; the counts map as a choropleth (natural breaks, sequential colors). id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_5c2b4f19804e
29. 29Tool result: gp_summarize_within, step 0. Summarize within: 1 layer saved: Summarize within: Pressure zones (8 features). id 7fbce9f6-226d-43c9-b187-49e18e2f3a63:0
30. 30Layer: Pressure zones. 8 features id a4c55d18-97e0-4d48-82c0-0a14b5ad5659
31. 31Tool result: gp_summarize_within, step 1. Summarize within: 1 layer saved: Summarize within: Pressure zones (8 features). id 7fbce9f6-226d-43c9-b187-49e18e2f3a63:1
32. 32Tool result: gp_summarize_within, step 2. Summarize within: 1 layer saved: Summarize within: Pressure zones (8 features). id 7fbce9f6-226d-43c9-b187-49e18e2f3a63:2
33. 33Catalog: Find point clusters (operation catalog, gp_find_point_clusters). Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise. ArcGIS: Find Point Clusters, Density-based Clustering. QGIS: native:dbscanclustering, native:stdbscanclustering. id gp_find_point_clusters
34. 34Plan: Cluster points of Valves (the Start plan's candidate c_5a8770e11140). DBSCAN finds dense groups of Valves and separates noise. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_5a8770e11140
35. 35Tool result: gp_find_point_clusters, step 0. Find point clusters: 2 layers saved: Find point clusters: Valves (300 features); Find point clusters: cluster hulls (11 features). id d14409c4-ceb7-40bf-8118-b4f183221686:0
36. 36Plan: Cluster points of Leak and burst repairs (the Start plan's candidate c_fcbb370f7b11). DBSCAN finds dense groups of Leak and burst repairs and separates noise. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_fcbb370f7b11
37. 37Tool result: gp_find_point_clusters, step 1. Find point clusters: 2 layers saved: Find point clusters: Leak and burst repairs (950 features); Find point clusters: cluster hulls (3 features). id d14409c4-ceb7-40bf-8118-b4f183221686:1
38. 38Plan: Cluster points of Customer complaints (the Start plan's candidate c_ffd68e523286). DBSCAN finds dense groups of Customer complaints and separates noise. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_ffd68e523286
39. 39Tool result: gp_find_point_clusters, step 2. Find point clusters: 2 layers saved: Find point clusters: Customer complaints (520 features); Find point clusters: cluster hulls (3 features). id d14409c4-ceb7-40bf-8118-b4f183221686:2
40. 40Catalog: Find outliers (operation catalog, gp_outliers). Anselin local Moran’s I: HH, LL clusters and HL, LH outliers. ArcGIS: Find Outliers, Cluster and Outlier Analysis (Anselin Local Moran’s I). id gp_outliers
41. 41Plan: Local morans i of Pressure zones (the Start plan's candidate c_d6bf59d0b92b). Local Moran's I maps clusters and outliers of 'connections'. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_d6bf59d0b92b
42. 42Tool result: gp_outliers, step 0. Find outliers: 1 layer saved: Find outliers: Pressure zones (8 features). id d51ffd20-8b3f-40ae-b231-4aaceda6ee41:0
43. 43Catalog: Spatial autocorrelation (operation catalog, gp_spatial_autocorrelation). Global Moran’s I: is the pattern clustered, dispersed or random. ArcGIS: Spatial Autocorrelation (Global Moran’s I). id gp_spatial_autocorrelation
44. 44Plan: Global morans i of Pressure zones (the Start plan's candidate c_6ddd928b3a6c). Global Moran's I says whether similar values of 'connections' sit next to each other. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_6ddd928b3a6c
45. 45Tool result: gp_spatial_autocorrelation, step 1. Spatial autocorrelation: done; no map output. id d51ffd20-8b3f-40ae-b231-4aaceda6ee41:1
46. 46Catalog: Repeat and near repeat classification (operation catalog, gp_near_repeat). Classify incidents as originators, repeats (same place) or near repeats within a distance and time window, with a Knox test table. ArcGIS: Repeat and Near Repeat Classification, Near Repeat Calculator. id gp_near_repeat
47. 47Plan: Near repeat of Leak and burst repairs (the Start plan's candidate c_31a838496880). Near repeat analysis tests whether Leak and burst repairs close in space also follow each other within 30 days. id 4f377cd3-7339-41df-845b-392c7e4b6b94:c_31a838496880
48. 48Tool result: gp_near_repeat, step 0. Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Leak and burst repairs (950 features). id 49d484f0-691d-49a8-9795-a8bae9950aef:0
49. 49Rendering: Map: Emerging hot spots: Leak and burst repairs id 3f3bb028-17f1-44d1-9de6-44fc0a9fc721
50. 50Rendering: Map: Emerging hot spots: Customer complaints id 9509ddaa-4c98-4096-9c90-32c7d0128ded
51. 51Rendering: Map: Hot spot analysis: Valves id d9873c2c-3566-4d27-8fb1-3136201c8204
52. 52Rendering: Map: Hot spot analysis: Leak and burst repairs id cdaff975-dab2-424f-adfa-2274328ed591
53. 53Rendering: Map: Hot spot analysis: Customer complaints id a6899e22-c5e5-420f-b266-3bc1126baba6
54. 54Rendering: Map: Calculate density: Valves id ceb559c1-f678-4874-aea2-b7d563cf1fef
55. 55Rendering: Map: Calculate density: Leak and burst repairs id 8c99a9da-4d30-49f5-a977-12f556499841
56. 56Rendering: Map: Calculate density: Customer complaints id b9ce5771-f68b-494b-ae0f-5e0d4969f781
57. 57Rendering: Map: Summarize within: Pressure zones id fd78fee3-ac8d-4b2b-b5ed-f7f57f068c3f
58. 58Rendering: Map: Summarize within: Pressure zones id e6e4e8f2-04db-41fd-9da6-5906d1ba4b30
59. 59Rendering: Map: Summarize within: Pressure zones id a4dbb3eb-6f59-462f-b3a9-d07bb0313663
60. 60Rendering: Map: Find point clusters: Valves id db8344db-3a76-4085-aeb4-dd38135e8607
61. 61Rendering: Map: Find point clusters: cluster hulls id 49a3caba-0eac-49c0-a96c-a416fb8cffcc
62. 62Rendering: Map: Find point clusters: Leak and burst repairs id 2ad72120-f06f-49cc-bcfe-1d1f0f3704d0
63. 63Rendering: Map: Find point clusters: cluster hulls id 1a6807c6-9e63-44e0-b47a-9cfd06d92860
64. 64Rendering: Map: Find point clusters: Customer complaints id 6cdef5e4-9d12-42ff-9772-03d4ae9d2a31
65. 65Rendering: Map: Find point clusters: cluster hulls id 0a4f53e6-e3e8-4a99-86a4-49c237e7d264
66. 66Rendering: Map: Pressure zones by connections id a91f1b3f-c237-43d7-ba64-33ecbd256f0a
67. 67Rendering: Map: Find outliers: Pressure zones id 44cdd90e-0c9c-4cf3-93b9-7b1f48c5e306
68. 68Rendering: Map: Repeat and near repeat classification: Leak and burst repairs id 5f3c5bb5-4c59-4d70-a046-4429e3906db9
69. 69Rendering: Chart: Water mains over time (install_year). 13 rows id 02627da8-8e62-4e80-9719-72a7e2f55e57
70. 70Rendering: Chart: Leak and burst repairs over time (reported_at). 144 rows id c494397c-b48a-49fb-afa7-7a5504c99947
71. 71Rendering: Chart: Valves over time (exercised_year). 10 rows id dcd28c89-a9a3-4182-881a-28e358a8b5a7
72. 72Rendering: Chart: Fire hydrants over time (last_test_year). 9 rows id 9501bf0d-1118-4646-9011-1d6607707f6d
73. 73Rendering: Chart: Customer complaints over time (date). 212 rows id 7b3d1156-e7a8-493d-9083-daeb182a4c85
74. 74Rendering: Chart: Zone meter readings by month over time (month). 24 rows id 2ab22dd9-e4bb-48ba-8c04-bc7babef5d0b
75. 75Rendering: Chart: Pipe replacement plan over time (planned_year). 9 rows id 177c5fda-dc15-4abc-a44e-4ee15d594e8b
76. 76Rendering: Chart: Emerging hot spots: Leak and burst repairs. 8 rows id 595a0dc9-9c95-4ae1-b0ca-4e5d14d12396
77. 77Rendering: Chart: Emerging hot spots: Customer complaints. 8 rows id 49549103-57d2-486d-8bd4-4431013cb1b3
78. 78Rendering: Chart: Hot spot analysis: Valves. 10 rows id 5e1fa7b3-4f72-4f37-b847-44ccfd91b8d8
79. 79Rendering: Chart: Hot spot analysis: Leak and burst repairs. 13 rows id 4cefd833-0e50-4578-9d0a-70931ac2bf5a
80. 80Rendering: Chart: Hot spot analysis: Customer complaints. 11 rows id 86d35ebf-41a8-48e6-b171-41a261df419b
81. 81Rendering: Chart: Calculate density: Valves. 10 rows id 27f5c03d-412f-4e4d-822d-a1df30a1c49a
82. 82Rendering: Chart: Calculate density: Leak and burst repairs. 12 rows id 4666369b-bfa5-4f04-901c-ec29c5b49d6c
83. 83Rendering: Chart: Calculate density: Customer complaints. 12 rows id aa86d4c3-c625-4f70-a661-51f8126e6af8
84. 84Rendering: Chart: Summarize within: Pressure zones. 5 rows id 0d45df48-f878-4529-8914-7b9c943ea003
85. 85Rendering: Chart: Summarize within: Pressure zones. 5 rows id 502ad046-ea5a-4ca6-9f48-484b32739196
86. 86Rendering: Chart: Summarize within: Pressure zones. 5 rows id 949001f2-9fc6-4ae2-909c-4b238ba0916e
87. 87Rendering: Chart: Find point clusters: Valves. 12 rows id 868093f7-066c-469b-baa7-f20941a2f40e
88. 88Rendering: Chart: Find point clusters: cluster hulls. 11 rows id 84119cbe-b098-4105-bce7-8ddc860ad22d
89. 89Rendering: Chart: Find point clusters: Leak and burst repairs. 4 rows id 1b45df1b-a05d-4531-ae0d-49c2224a2551
90. 90Rendering: Chart: Find point clusters: cluster hulls. 3 rows id 5a127efb-1998-463d-8956-bee898322fc9
91. 91Rendering: Chart: Find point clusters: Customer complaints. 4 rows id ae5b32b2-383a-4be8-bf14-6c6f8449b0b1
92. 92Rendering: Chart: Find point clusters: cluster hulls. 3 rows id 2b12b071-0f4d-46c7-abc8-69c6b190d0d6
93. 93Rendering: Chart: Repeat and near repeat classification: Leak and burst repairs over time. 144 rows id 3fc856ce-5d0d-407f-ad64-e3c0cc964288
94. 94Rendering: Chart: Find point clusters: Customer complaints over time. 212 rows id 1e06545d-de8b-4037-b0da-2de0f7f334fe
95. 95Rendering: Chart: Find point clusters: Leak and burst repairs over time. 144 rows id b893e1bc-7a5d-4622-8b2d-a1fc99d79142
96. 96Dataset: Pressure zones. vector, 8 rows id 8e552b2b-0ef5-4c0c-821c-708e0de62375
97. 97Dataset: Water mains. vector, 2130 rows id b6d4651b-de72-426b-b18e-081f92a20090
98. 98Dataset: Reservoirs. vector, 4 rows id a4ba7898-6adb-4a62-b4b3-2baa51710fd7
99. 99Dataset: Valves. vector, 300 rows id 2f9d6af4-8dbc-4919-9c2e-358009680d94
100. 100Dataset: Fire hydrants. vector, 250 rows id 5c702260-a660-41d8-8aac-adc95c8d4329
101. 101Dataset: Pipe replacement plan. table, 220 rows id c062d67a-c643-4dbc-bddd-b13a8c563a9e
102. 102Dataset: Non-revenue water briefing. document, ? rows id 0a3aab36-0977-4c51-a725-7886eccfb7f7
103. 103Record: Sample: Water utility, Cape Town id 0f6d1895-598a-4c17-a195-fc538533c4a3
104. 104Layer: Emerging hot spots: Leak and burst repairs. 71 features id fcb15038-1ce5-4dfe-bef3-37f0d0710660
105. 105Layer: Emerging hot spots: Customer complaints. 75 features id 6cd4cdee-eaed-4536-97a3-8cfcfcea991a
106. 106Layer: Hot spot analysis: Valves. 53 features id e6e46379-bab5-4be3-b731-f573fbaeaa2b
107. 107Layer: Hot spot analysis: Leak and burst repairs. 184 features id 1b8c7972-3a5f-43cb-9c04-79be94f68fa2
108. 108Layer: Hot spot analysis: Customer complaints. 185 features id cc6c04aa-9769-4c55-bffd-23f14fc19e22
109. 109Layer: Calculate density: Valves. 257 features id 7c69e54b-2611-4108-a8f1-7edbf9681ff2
110. 110Layer: Calculate density: Leak and burst repairs. 1,220 features id 10a45b3b-e980-47be-9cf9-6b191e7fa957
111. 111Layer: Calculate density: Customer complaints. 1,200 features id 36b7f8be-2e78-4f25-add1-4c5b63fade60
112. 112Layer: Summarize within: Pressure zones. 8 features id e1b22dd3-e0d4-4c9f-a4dd-6460b011a8f0
113. 113Layer: Summarize within: Pressure zones. 8 features id 2c26882f-372c-4dd1-9856-1556ecf83503
114. 114Layer: Summarize within: Pressure zones. 8 features id 8d6f5fe5-afba-45d0-8676-09532976c3ba
115. 115Layer: Find point clusters: Valves. 300 features id 4058852d-d252-42dd-b715-c4555264de96
116. 116Layer: Find point clusters: cluster hulls. 11 features id 01ccf49b-1072-42db-8660-3b6bfa50a885
117. 117Layer: Find point clusters: Leak and burst repairs. 950 features id 2ace68cb-dd6a-44c4-9784-ec90079bfd14
118. 118Layer: Find point clusters: cluster hulls. 3 features id cee4dd63-1a39-434b-86a5-dbfe42ae6477
119. 119Layer: Find point clusters: Customer complaints. 520 features id 7c106e45-1ddc-48c3-bc26-ae9c11c94028
120. 120Layer: Find point clusters: cluster hulls. 3 features id 5dfd2c79-c5e3-4675-8539-b2fa77d08d7a
121. 121Layer: Find outliers: Pressure zones. 8 features id e61c7a42-8b9f-473a-8310-bc15178693a5
122. 122Layer: Repeat and near repeat classification: Leak and burst repairs. 950 features id 9bbadc15-5868-46e4-9005-946ec8a2298c