Transportation safety

Sample: Transportation safety, Sao Paulo: report

Project: Sample: Transportation safety, Sao Paulo
Goal: Describe the project Sample: Transportation safety, Sao Paulo: run the analyses that tell the most about its data, draw every result, and write a cited report.
Run: 35aef51a-0242-4655-8a7d-ba6fc31c344b (running, 11 agent run(s))
Generated: 2026-10-18T06:32:13Z, version 1
Model cost: USD 0.0000 over 0 model call(s)

Data used

Timeline

The timeline counts 3,910 dated events in Crashes, Traffic calming, Segment speeds by month and 1 more per month, from January 2023 to September 2026 12345. By dataset: Crashes 2,100; Segment speeds by month 1,440; Camera citations by month 300; Traffic calming 70 1. The trend is +6.63 events per month; the second half of the months has 3,688 against 126 in the first (+2827.0%) 1. 2 of the 45 months had no events 1.

Busiest months

• December 2025: 268 events 1
• January 2026: 257 events 1
• November 2025: 250 events 1

Quietest months with events

• March 2023: 1 event 1
• April 2023: 1 event 1
• May 2023: 1 event 1

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 6. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 6.

Why it was run on this data. 40 points: Getis-Ord Gi* tests whether the concentrations in Schools are statistically significant 7.

What it found. Hot spot analysis was performed using the Schools input layer 9.

Findings

• Evidenced: Hot spots on Schools: Hot spot analysis: 1 layer saved: Hot spot analysis: Schools (40 features) 89.
• Evidenced: It reported result, count 40; result, elapsed ms 3; result, excluded null 0; result, distance band m 2,000; billing, cost 0.0508; billing, list price 0.0508 8.

Tool gp_hot_spots; parameters {"field": "students", "project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Schools (cb956034)"}, "aggregation": "hexagon", "cell_size_m": 2000.0, "distance_band_m": 2000.0}

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 6. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 6.

Why it was run on this data. 2100 points: Getis-Ord Gi* tests whether the concentrations in Crashes are statistically significant 10.

What it found. Hot spots on Crashes: Hot spot analysis: 1 layer saved: Hot spot analysis: Crashes (1049 features) 1112. It reported result, bins 1,049; result, count 1,049; result, elapsed ms 64; result, cell size m 200; result, incidents used 2,100; result, distance band m 200 11.

Findings

• Evidenced: Hot spots on Crashes: Hot spot analysis: 1 layer saved: Hot spot analysis: Crashes (1049 features) 1112.
• Evidenced: It reported result, bins 1,049; result, count 1,049; result, elapsed ms 64; result, cell size m 200; result, incidents used 2,100; result, distance band m 200 11.

Tool gp_hot_spots; parameters {"project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Crashes (9501bda5)"}, "aggregation": "hexagon", "cell_size_m": 200.0, "distance_band_m": 200.0}

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 13. In ArcGIS it is Emerging Hot Spot Analysis or Create Space Time Cube 13.

Why it was run on this data. Crashes carry dates in 'occurred_at': emerging hot spot analysis finds new, intensifying and fading hot spots per month 14.

What it found. Space time hot spots on Crashes: Emerging hot spots: 1 layer saved: Emerging hot spots: Crashes (391 features) 1215. It reported result, count 391; result, elapsed ms 57; result, resolution 9; result, features used 2,100; result, time neighbors 0; billing, cost 0.205 15.

Findings

• Evidenced: Space time hot spots on Crashes: Emerging hot spots: 1 layer saved: Emerging hot spots: Crashes (391 features) 1215.
• Evidenced: It reported result, count 391; result, elapsed ms 57; result, resolution 9; result, features used 2,100; result, time neighbors 0; billing, cost 0.205 15.

Tool gp_space_time_hot_spots; parameters {"project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Crashes (9501bda5)"}, "interval": "month", "bin_shape": "h3", "resolution": 9, "time_field": "occurred_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 13. In ArcGIS it is Emerging Hot Spot Analysis or Create Space Time Cube 13.

Why it was run on this data. Traffic calming carry dates in 'date': emerging hot spot analysis finds new, intensifying and fading hot spots per month 16.

What it found. Space time hot spots on Traffic calming: Emerging hot spots: 1 layer saved: Emerging hot spots: Traffic calming (14 features) 1718. It reported result, count 14; result, elapsed ms 4; result, resolution 7; result, features used 70; result, time neighbors 0; billing, cost 0.1035 17.

Findings

• Evidenced: Space time hot spots on Traffic calming: Emerging hot spots: 1 layer saved: Emerging hot spots: Traffic calming (14 features) 1718.
• Evidenced: It reported result, count 14; result, elapsed ms 4; result, resolution 7; result, features used 70; result, time neighbors 0; billing, cost 0.1035 17.

Tool gp_space_time_hot_spots; parameters {"project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Traffic calming (03fd1e3f)"}, "interval": "month", "bin_shape": "h3", "resolution": 7, "time_field": "date"}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 19. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 19.

Why it was run on this data. Count Schools inside each feature of Traffic districts by level; the counts map as a choropleth (natural breaks, sequential colors) 20.

What it found. Summarize within on Schools, Traffic districts: Summarize within: 1 layer saved: Summarize within: Traffic districts (12 features) 92122. It reported result, count 12; result, elapsed ms 0; billing, cost 0.01106; billing, list price 0.01106; billing, upstream cost 0 21.

Findings

• Evidenced: Summarize within on Schools, Traffic districts: Summarize within: 1 layer saved: Summarize within: Traffic districts (12 features) 92122.
• Evidenced: It reported result, count 12; result, elapsed ms 0; billing, cost 0.01106; billing, list price 0.01106; billing, upstream cost 0 21.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "students"}], "project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Schools (cb956034)"}, "group_by": "level", "polygons": {"layer": "Traffic districts (426e8d19)"}}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 19. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 19.

Why it was run on this data. Count Schools inside each feature of Traffic districts by level; the counts map as a choropleth (natural breaks, sequential colors) 20.

What it found. Summarize within on Crashes, Traffic districts: Summarize within: 1 layer saved: Summarize within: Traffic districts (12 features) 122223. It reported result, count 12; result, elapsed ms 3; billing, cost 0.05226; billing, list price 0.05226; billing, upstream cost 0 23.

Findings

• Evidenced: Summarize within on Crashes, Traffic districts: Summarize within: 1 layer saved: Summarize within: Traffic districts (12 features) 122223.
• Evidenced: It reported result, count 12; result, elapsed ms 3; billing, cost 0.05226; billing, list price 0.05226; billing, upstream cost 0 23.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "injured"}], "project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Crashes (9501bda5)"}, "group_by": "severity", "polygons": {"layer": "Traffic districts (426e8d19)"}}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 24. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 24.

Why it was run on this data. DBSCAN finds dense groups of Schools and separates noise 25.

What it found. Find point clusters on Schools: Find point clusters: 2 layers saved: Find point clusters: Schools (40 features); Find point clusters: cluster hulls (3 features) 926. It reported result, count 40; result, noise 3; result, distance m 1,000; result, elapsed ms 5; result, min points 3; billing, cost 0.0508 26.

Findings

• Evidenced: Find point clusters on Schools: Find point clusters: 2 layers saved: Find point clusters: Schools (40 features); Find point clusters: cluster hulls (3 features) 926.
• Evidenced: It reported result, count 40; result, noise 3; result, distance m 1,000; result, elapsed ms 5; result, min points 3; billing, cost 0.0508 26.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Schools (cb956034)"}, "distance_m": 1000.0, "min_points": 3}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 24. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 24.

Why it was run on this data. DBSCAN finds dense groups of Crashes and separates noise 27.

What it found. Find point clusters on Crashes: Find point clusters: 2 layers saved: Find point clusters: Crashes (2100 features); Find point clusters: cluster hulls (2 features) 1228. It reported result, count 2,100; result, noise 1,422; result, distance m 200; result, elapsed ms 32; result, min points 20; billing, cost 0.092 28.

Findings

• Evidenced: Find point clusters on Crashes: Find point clusters: 2 layers saved: Find point clusters: Crashes (2100 features); Find point clusters: cluster hulls (2 features) 1228.
• Evidenced: It reported result, count 2,100; result, noise 1,422; result, distance m 200; result, elapsed ms 32; result, min points 20; billing, cost 0.092 28.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Crashes (9501bda5)"}, "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 24. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 24.

Why it was run on this data. DBSCAN finds dense groups of Pedestrian crossings and separates noise 29.

What it found. Find point clusters on Pedestrian crossings: Find point clusters: 2 layers saved: Find point clusters: Pedestrian crossings (200 features); Find point clusters: cluster hulls (11 features) 3031. It reported result, count 200; result, noise 53; result, distance m 500; result, elapsed ms 6; result, min points 5; billing, cost 0.054 30.

Findings

• Evidenced: Find point clusters on Pedestrian crossings: Find point clusters: 2 layers saved: Find point clusters: Pedestrian crossings (200 features); Find point clusters: cluster hulls (11 features) 3031.
• Evidenced: It reported result, count 200; result, noise 53; result, distance m 500; result, elapsed ms 6; result, min points 5; billing, cost 0.054 30.

A model draft was discarded because a sentence did not cite a source of this section.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Pedestrian crossings (5a5fc524)"}, "distance_m": 500.0, "min_points": 5}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 32. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 32.

Why it was run on this data. 40 points in Schools: a density surface shows where they concentrate 33.

What it found. Calculate density on Schools: Calculate density: 1 layer saved: Calculate density: Schools (80 features) 934. It reported result, count 80; result, elapsed ms 4; result, bandwidth m 2,000; result, cell size m 1,000; result, excluded null 0; result, max density per km2 1,488 34.

Findings

• Evidenced: Calculate density on Schools: Calculate density: 1 layer saved: Calculate density: Schools (80 features) 934.
• Evidenced: It reported result, count 80; result, elapsed ms 4; result, bandwidth m 2,000; result, cell size m 1,000; result, excluded null 0; result, max density per km2 1,488 34.

A model draft was discarded because a sentence did not cite a source of this section.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Schools (cb956034)"}, "bandwidth_m": 2000.0, "cell_size_m": 1000.0, "weight_field": "students"}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 32. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 32.

Why it was run on this data. 2100 points in Crashes: a density surface shows where they concentrate 35.

What it found. The density calculation used the Crashes layer as input 12. The tool successfully processed the data, yielding 4,112 features 36.

Findings

• Evidenced: Calculate density on Crashes: Calculate density: 1 layer saved: Calculate density: Crashes (4112 features) 1236.
• Evidenced: It reported result, count 4,112; result, elapsed ms 110; result, bandwidth m 200; result, cell size m 100; result, excluded null 0; result, max density per km2 816.6 36.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Crashes (9501bda5)"}, "bandwidth_m": 200.0, "cell_size_m": 100.0}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 32. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 32.

Why it was run on this data. 200 points in Pedestrian crossings: a density surface shows where they concentrate 37.

What it found. The calculation of density was performed on the Pedestrian crossings layer 31 using the gp_calculate_density function 38. This process yielded a count of 251 features 38, with an elapsed time of 7 milliseconds 38. The resulting density calculation reported a maximum density per km2 of 9.062 38.

Findings

• Evidenced: Calculate density on Pedestrian crossings: Calculate density: 1 layer saved: Calculate density: Pedestrian crossings (251 features) 3138.
• Evidenced: It reported result, count 251; result, elapsed ms 7; result, bandwidth m 1,000; result, cell size m 500; result, excluded null 0; result, max density per km2 9.062 38.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Pedestrian crossings (5a5fc524)"}, "bandwidth_m": 1000.0, "cell_size_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 6. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 6.

Why it was run on this data. 200 points: Getis-Ord Gi* tests whether the concentrations in Pedestrian crossings are statistically significant 39.

What it found. Hot spots on Pedestrian crossings: Hot spot analysis: 1 layer saved: Hot spot analysis: Pedestrian crossings (54 features) 3140. It reported result, bins 54; result, count 54; result, elapsed ms 5; result, cell size m 1,000; result, incidents used 200; result, distance band m 1,000 40.

Findings

• Evidenced: Hot spots on Pedestrian crossings: Hot spot analysis: 1 layer saved: Hot spot analysis: Pedestrian crossings (54 features) 3140.
• Evidenced: It reported result, bins 54; result, count 54; result, elapsed ms 5; result, cell size m 1,000; result, incidents used 200; result, distance band m 1,000 40.

Tool gp_hot_spots; parameters {"project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Pedestrian crossings (5a5fc524)"}, "aggregation": "hexagon", "cell_size_m": 1000.0, "distance_band_m": 1000.0}

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 41. In ArcGIS it is Repeat and Near Repeat Classification or Near Repeat Calculator 41.

Why it was run on this data. Near repeat analysis tests whether Crashes close in space also follow each other within 30 days 42.

What it found. Near repeat on Crashes: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Crashes (2100 features) 1243. It reported result, days 30; result, count 2,100; result, chains 190; result, distance m 100; result, elapsed ms 41; result, pairs linked 506 43.

Findings

• Evidenced: Near repeat on Crashes: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Crashes (2100 features) 1243.
• Evidenced: It reported result, days 30; result, count 2,100; result, chains 190; result, distance m 100; result, elapsed ms 41; result, pairs linked 506 43.

Tool gp_near_repeat; parameters {"days": 30, "project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Crashes (9501bda5)"}, "distance_m": 100.0, "time_field": "occurred_at"}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 19. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 19.

Why it was run on this data. Count Pedestrian crossings inside each feature of Traffic districts by type; the counts map as a choropleth (natural breaks, sequential colors) 44.

What it found. The analysis used Pedestrian crossings 31 and Traffic districts 22 as inputs for the geoprocessing summary 45. The gp_summarize_within tool reported a result count of 12 45.

Findings

• Evidenced: Summarize within on Pedestrian crossings, Traffic districts: Summarize within: 1 layer saved: Summarize within: Traffic districts (12 features) 223145.
• Evidenced: It reported result, count 12; result, elapsed ms 1; billing, cost 0.01424; billing, list price 0.01424; billing, upstream cost 0 45.

Tool gp_summarize_within; parameters {"stats": [], "project": "220702b2-1327-4244-9cff-74cf9d501f98", "features": {"layer": "Pedestrian crossings (5a5fc524)"}, "group_by": "type", "polygons": {"layer": "Traffic districts (426e8d19)"}}

Maps and charts

The run also made 18 map image(s) 464748495051525354555657585960616263 and 25 chart(s) 64656667686970717273747576777879808182838485868788.

What the map shows. The map, titled "Emerging hot spots: Traffic calming," displays spatial analysis results across multiple hexagonal zones. According to the map's legend, every area is categorized under the "No pattern detected" status for this emerging hot spot analysis. The map does not display any visible clusters, gradients, or outliers of high or low traffic calming activity. The uniform 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. 180 rows id 9a0c9c08-6710-43e7-925b-a5575fc6ff05
2. 2Dataset: Crashes. vector, 2100 rows id 4c514909-5014-41d8-b00c-114927c21aa8
3. 3Dataset: Traffic calming. vector, 70 rows id a3bcfa4c-92bd-4d42-84a1-8fa68b0ed82e
4. 4Dataset: Segment speeds by month. table, 1440 rows id d8e69dfa-1f0d-4b89-a415-acb37422c879
5. 5Dataset: Camera citations by month. table, 300 rows id 6dd2a5a7-473b-47ef-87b8-127a0fa9fe0d
6. 6Catalog: 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
7. 7Plan: Hot spots of Schools (the Start plan's candidate c_6820fa8048aa). 40 points: Getis-Ord Gi* tests whether the concentrations in Schools are statistically significant. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_6820fa8048aa
8. 8Tool result: gp_hot_spots, step 0. Hot spot analysis: 1 layer saved: Hot spot analysis: Schools (40 features). id b665fc95-b641-4093-9d22-956737a8fbfd:0
9. 9Layer: Schools. 40 features id cb956034-2d9c-4a8b-b395-a35fdb983208
10. 10Plan: Hot spots of Crashes (the Start plan's candidate c_770e814da3da). 2100 points: Getis-Ord Gi* tests whether the concentrations in Crashes are statistically significant. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_770e814da3da
11. 11Tool result: gp_hot_spots, step 1. Hot spot analysis: 1 layer saved: Hot spot analysis: Crashes (1049 features). id b665fc95-b641-4093-9d22-956737a8fbfd:1
12. 12Layer: Crashes. 2,100 features id 9501bda5-835f-47e8-b486-e5fa594533df
13. 13Catalog: 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
14. 14Plan: Space time hot spots of Crashes (the Start plan's candidate c_94b04cf53208). Crashes carry dates in 'occurred_at': emerging hot spot analysis finds new, intensifying and fading hot spots per month. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_94b04cf53208
15. 15Tool result: gp_space_time_hot_spots, step 0. Emerging hot spots: 1 layer saved: Emerging hot spots: Crashes (391 features). id a02448cc-b477-4a6c-8ae7-3ac23d189640:0
16. 16Plan: Space time hot spots of Traffic calming (the Start plan's candidate c_b32d5bad7a33). Traffic calming carry dates in 'date': emerging hot spot analysis finds new, intensifying and fading hot spots per month. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_b32d5bad7a33
17. 17Tool result: gp_space_time_hot_spots, step 1. Emerging hot spots: 1 layer saved: Emerging hot spots: Traffic calming (14 features). id a02448cc-b477-4a6c-8ae7-3ac23d189640:1
18. 18Layer: Traffic calming. 70 features id 03fd1e3f-918a-4f9a-8ab9-945371297dc6
19. 19Catalog: 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
20. 20Plan: Schools per feature of Traffic districts (the Start plan's candidate c_8a3ffc7a90b1). Count Schools inside each feature of Traffic districts by level; the counts map as a choropleth (natural breaks, sequential colors). id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_8a3ffc7a90b1
21. 21Tool result: gp_summarize_within, step 0. Summarize within: 1 layer saved: Summarize within: Traffic districts (12 features). id 8387f3d4-ed0c-4186-a3ac-98f72f10cd75:0
22. 22Layer: Traffic districts. 12 features id 426e8d19-80fb-4cf4-9a7a-1e47e48d31cc
23. 23Tool result: gp_summarize_within, step 1. Summarize within: 1 layer saved: Summarize within: Traffic districts (12 features). id 8387f3d4-ed0c-4186-a3ac-98f72f10cd75:1
24. 24Catalog: 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
25. 25Plan: Cluster points of Schools (the Start plan's candidate c_a5ebd65960a7). DBSCAN finds dense groups of Schools and separates noise. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_a5ebd65960a7
26. 26Tool result: gp_find_point_clusters, step 0. Find point clusters: 2 layers saved: Find point clusters: Schools (40 features); Find point clusters: cluster hulls (3 features). id 54de2fc4-ad0a-412e-bf5d-e9653a15671f:0
27. 27Plan: Cluster points of Crashes (the Start plan's candidate c_2c9942f1fafe). DBSCAN finds dense groups of Crashes and separates noise. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_2c9942f1fafe
28. 28Tool result: gp_find_point_clusters, step 1. Find point clusters: 2 layers saved: Find point clusters: Crashes (2100 features); Find point clusters: cluster hulls (2 features). id 54de2fc4-ad0a-412e-bf5d-e9653a15671f:1
29. 29Plan: Cluster points of Pedestrian crossings (the Start plan's candidate c_c18fe860314d). DBSCAN finds dense groups of Pedestrian crossings and separates noise. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_c18fe860314d
30. 30Tool result: gp_find_point_clusters, step 2. Find point clusters: 2 layers saved: Find point clusters: Pedestrian crossings (200 features); Find point clusters: cluster hulls (11 features). id 54de2fc4-ad0a-412e-bf5d-e9653a15671f:2
31. 31Layer: Pedestrian crossings. 200 features id 5a5fc524-5914-46f0-b637-120d3de1b01c
32. 32Catalog: 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
33. 33Plan: Kernel density of Schools (the Start plan's candidate c_25e52236511e). 40 points in Schools: a density surface shows where they concentrate. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_25e52236511e
34. 34Tool result: gp_calculate_density, step 0. Calculate density: 1 layer saved: Calculate density: Schools (80 features). id 002fb5f9-1af6-402f-b464-49edd32e3044:0
35. 35Plan: Kernel density of Crashes (the Start plan's candidate c_bfc2a7ecf90c). 2100 points in Crashes: a density surface shows where they concentrate. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_bfc2a7ecf90c
36. 36Tool result: gp_calculate_density, step 1. Calculate density: 1 layer saved: Calculate density: Crashes (4112 features). id 002fb5f9-1af6-402f-b464-49edd32e3044:1
37. 37Plan: Kernel density of Pedestrian crossings (the Start plan's candidate c_9b962a31a776). 200 points in Pedestrian crossings: a density surface shows where they concentrate. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_9b962a31a776
38. 38Tool result: gp_calculate_density, step 2. Calculate density: 1 layer saved: Calculate density: Pedestrian crossings (251 features). id 002fb5f9-1af6-402f-b464-49edd32e3044:2
39. 39Plan: Hot spots of Pedestrian crossings (the Start plan's candidate c_6f2484f162ad). 200 points: Getis-Ord Gi* tests whether the concentrations in Pedestrian crossings are statistically significant. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_6f2484f162ad
40. 40Tool result: gp_hot_spots, step 0. Hot spot analysis: 1 layer saved: Hot spot analysis: Pedestrian crossings (54 features). id 20671da3-3c9f-4bfc-ab63-45789559bbaa:0
41. 41Catalog: 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
42. 42Plan: Near repeat of Crashes (the Start plan's candidate c_f79962c58bba). Near repeat analysis tests whether Crashes close in space also follow each other within 30 days. id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_f79962c58bba
43. 43Tool result: gp_near_repeat, step 0. Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Crashes (2100 features). id 9871ee2f-25cc-4833-b2ad-49666fe06c44:0
44. 44Plan: Pedestrian crossings per feature of Traffic districts (the Start plan's candidate c_c09d00b8db7e). Count Pedestrian crossings inside each feature of Traffic districts by type; the counts map as a choropleth (natural breaks, sequential colors). id b084b0e6-acd2-4d38-bfd7-32a3ffa79c90:c_c09d00b8db7e
45. 45Tool result: gp_summarize_within, step 0. Summarize within: 1 layer saved: Summarize within: Traffic districts (12 features). id 1ff731de-fa54-412a-90f2-45eb74c9277e:0
46. 46Rendering: Map: Hot spot analysis: Schools id adeafe66-bb7e-41b6-a50a-d645d50e3878
47. 47Rendering: Map: Hot spot analysis: Crashes id 233e2091-e0f2-486b-9e97-493528e7345f
48. 48Rendering: Map: Emerging hot spots: Crashes id fbc0e5a3-a877-4a33-bf17-9ad55699796c
49. 49Rendering: Map: Emerging hot spots: Traffic calming id a1894195-d446-4aa2-9f8e-d0c822d7fa9e
50. 50Rendering: Map: Summarize within: Traffic districts id 30ea9d3d-11ed-4c02-a9da-973b648cdda5
51. 51Rendering: Map: Summarize within: Traffic districts id 59917dcd-4eac-4bbc-9094-fa048d8e0a8b
52. 52Rendering: Map: Find point clusters: Schools id b9530209-8153-4b70-81e4-d13d4126e118
53. 53Rendering: Map: Find point clusters: cluster hulls id 330923f5-621d-43f6-9f98-83b237722c00
54. 54Rendering: Map: Find point clusters: Crashes id e8b0af6b-ab8d-4188-83ae-a83a5a7c76b3
55. 55Rendering: Map: Find point clusters: cluster hulls id e5080803-3fc0-47b7-95f7-4829eb6d3859
56. 56Rendering: Map: Find point clusters: Pedestrian crossings id 5f216382-62b6-4351-86ff-4e5ae0af8125
57. 57Rendering: Map: Find point clusters: cluster hulls id 58f6c7d6-f814-4b9e-a8c9-4dd6d9ef95d1
58. 58Rendering: Map: Calculate density: Schools id f2b01dad-ebee-465f-9e27-d62097f4c268
59. 59Rendering: Map: Calculate density: Crashes id 64a4981a-c955-42e7-b34b-254a98f25520
60. 60Rendering: Map: Calculate density: Pedestrian crossings id 2756e5bb-abe5-4473-b915-78f831d3d5a4
61. 61Rendering: Map: Hot spot analysis: Pedestrian crossings id 8f0a76db-4777-4ab7-9a9a-930da7a08925
62. 62Rendering: Map: Repeat and near repeat classification: Crashes id 02ed79bd-4bdf-4842-93fe-2e184455d945
63. 63Rendering: Map: Summarize within: Traffic districts id 6dfdb515-5e14-402d-871f-0ffa294530f7
64. 64Rendering: Chart: Crashes over time (occurred_at). 96 rows id 8cda2c81-bd3a-4553-9c58-295ed795aff2
65. 65Rendering: Chart: Speed cameras over time (installed_year). 1 rows id 7edbd055-674b-4ee4-97e5-347a866c2947
66. 66Rendering: Chart: Traffic calming over time (date). 168 rows id 2d958f28-45c2-4b7a-87ed-c8ab49911031
67. 67Rendering: Chart: Segment speeds by month over time (month). 49 rows id b7432eea-2c3a-477a-a1e8-2d36cd655803
68. 68Rendering: Chart: Camera citations by month over time (month). 49 rows id 969fa530-28ba-4dd0-a75b-69aa84b54678
69. 69Rendering: Chart: Hot spot analysis: Schools. 10 rows id 461534e0-1147-4c68-b696-ce72af84c87e
70. 70Rendering: Chart: Hot spot analysis: Crashes. 17 rows id e0c0fd5a-fbcd-48a4-b737-5ec55e00e9b6
71. 71Rendering: Chart: Emerging hot spots: Crashes. 10 rows id 733c92a3-ffad-470a-a9c0-f4d673d42289
72. 72Rendering: Chart: Emerging hot spots: Traffic calming. 5 rows id 10c55d47-29c7-4734-a9fe-0a0b7975fbb8
73. 73Rendering: Chart: Summarize within: Traffic districts. 5 rows id d2a4a3dc-7d76-4a0e-b041-b334e994f076
74. 74Rendering: Chart: Summarize within: Traffic districts. 5 rows id 897d00dc-b8b3-4e8d-9d2a-a66ba81fa3a8
75. 75Rendering: Chart: Find point clusters: Schools. 4 rows id 423c158c-d88d-476c-b3d7-399c0645179a
76. 76Rendering: Chart: Find point clusters: cluster hulls. 3 rows id b7ed2b2a-82e2-47a7-b9fd-40ba7637b0fb
77. 77Rendering: Chart: Find point clusters: Crashes. 3 rows id 7ea99118-9ea1-4440-a6b8-2787d996b886
78. 78Rendering: Chart: Find point clusters: cluster hulls. 2 rows id 1f581a53-06c3-4e15-b1d5-c6d8810d5069
79. 79Rendering: Chart: Find point clusters: Pedestrian crossings. 12 rows id 734ca768-921a-4688-b5a3-91e547b8132f
80. 80Rendering: Chart: Find point clusters: cluster hulls. 11 rows id 644e98c9-2e62-4e6c-88cc-2bac7654aca8
81. 81Rendering: Chart: Calculate density: Schools. 8 rows id 5185f166-2557-47d4-95a0-e09a9b9dffa6
82. 82Rendering: Chart: Calculate density: Crashes. 14 rows id d1d3088c-9c82-4847-9ad2-937f125a2774
83. 83Rendering: Chart: Calculate density: Pedestrian crossings. 9 rows id 2be0343e-08ed-45f8-b191-db1ac61f21d2
84. 84Rendering: Chart: Hot spot analysis: Pedestrian crossings. 9 rows id 04bdc4d9-e0fe-477a-8403-b2f2881d948a
85. 85Rendering: Chart: Repeat and near repeat classification: Crashes. 144 rows id 533c2ef2-04e7-4ec6-9dda-091526d4b60e
86. 86Rendering: Chart: Summarize within: Traffic districts. 5 rows id f50135c9-a379-4056-b401-ddd84d655807
87. 87Rendering: Chart: Repeat and near repeat classification: Crashes over time. 144 rows id aa71a552-c3d9-4aee-a82e-f6857fbc92a9
88. 88Rendering: Chart: Find point clusters: Crashes over time. 144 rows id 1d507cb3-0287-4a28-9492-374091139b83
89. 89Dataset: Road segments. vector, 900 rows id a1c0c341-b0b4-4540-8666-cc898710a5a2
90. 90Dataset: Traffic districts. vector, 12 rows id 4ddf9694-9e59-443e-9e26-b99d63650843
91. 91Dataset: Speed cameras. vector, 25 rows id d0346d0a-3495-47e2-bbaa-9bdebea63dae
92. 92Dataset: Schools. vector, 40 rows id 47516658-bc03-4d11-a9a3-83d7b85272e7
93. 93Dataset: Bus stops. vector, 120 rows id b69ec834-01b9-40fe-b4d7-048918f3ff66
94. 94Dataset: Pedestrian crossings. vector, 200 rows id 9904012c-b65c-4579-bb44-535cd45f66ca
95. 95Dataset: Vision Zero corridor review. document, ? rows id cef3f8f3-9628-4f98-b173-947dda8f30f3
96. 96Record: Sample: Transportation safety, Sao Paulo id 220702b2-1327-4244-9cff-74cf9d501f98
97. 97Layer: Hot spot analysis: Schools. 40 features id e24a725d-1226-4c6c-ac79-ddb0e0634c6c
98. 98Layer: Hot spot analysis: Crashes. 1,049 features id becfaca3-5eea-4150-9c71-4a8a51769984
99. 99Layer: Emerging hot spots: Crashes. 391 features id 9df86500-c0e4-4e6a-b523-dc729593eaa4
100. 100Layer: Emerging hot spots: Traffic calming. 14 features id fd2099dc-7aac-4041-8f85-bb99a6553671
101. 101Layer: Summarize within: Traffic districts. 12 features id 7dd3dbff-8946-47c0-9f8c-365a3f16b57f
102. 102Layer: Summarize within: Traffic districts. 12 features id ab0320a0-7ff1-4268-8628-c5d500503744
103. 103Layer: Find point clusters: Schools. 40 features id 62d9b779-75eb-44b3-af8e-6b11cb59257b
104. 104Layer: Find point clusters: cluster hulls. 3 features id 9a336160-b53a-41a1-bdce-2ce51cd5a9fe
105. 105Layer: Find point clusters: Crashes. 2,100 features id a3b9de76-4c1e-4b60-b686-346672b601ef
106. 106Layer: Find point clusters: cluster hulls. 2 features id fb76f8c2-f8d9-4e00-9560-bec71fbe6696
107. 107Layer: Find point clusters: Pedestrian crossings. 200 features id 177f4978-c15d-4e75-b5c7-7a917152e219
108. 108Layer: Find point clusters: cluster hulls. 11 features id 42bb9ca8-0db1-4b9d-8ed3-e7c9337230cf
109. 109Layer: Calculate density: Schools. 80 features id 41390c5d-5081-4052-9d4c-9ba56bf9b6f5
110. 110Layer: Calculate density: Crashes. 4,112 features id b719c8e4-0a00-46f8-a1ac-dba4d26a9fcb
111. 111Layer: Calculate density: Pedestrian crossings. 251 features id 59d27925-1f02-4b09-86f4-ada68a81d6fe
112. 112Layer: Hot spot analysis: Pedestrian crossings. 54 features id a4ed9f7b-d1d3-42f8-a3e7-e16c31bbc302
113. 113Layer: Repeat and near repeat classification: Crashes. 2,100 features id 983941e1-9046-42e6-a142-4a34d1f16e13
114. 114Layer: Summarize within: Traffic districts. 12 features id 611b1b4c-39d3-405a-976d-57aca77ac14e