fix: fix osm2pgsql categories, remove unused parameter, increase parallellity in transit, update readme

2026-03-06 13:46:44 +01:00 · 2026-03-06 13:46:44 +01:00 · f067472fd5
commit f067472fd5
parent fe6e59f427
4 changed files with 80 additions and 22 deletions
--- a/README.md
+++ b/README.md
@ -15,9 +15,12 @@ Next.js App Server
  ├── PostgreSQL + PostGIS (POIs, grid points, precomputed scores)
  └── Valkey (API response cache, BullMQ queues)

+BullMQ Worker (download queue, concurrency 1)
+  └── download-pbf      → streams OSM PBF from Geofabrik (serialised to avoid
+                          redundant parallel downloads; idempotent if file exists)
+
 BullMQ Worker (pipeline queue, concurrency 8)
  ├── refresh-city      → orchestrates full ingest via FlowProducer
-  ├── download-pbf      → streams OSM PBF from Geofabrik
  ├── extract-pois      → osmium filter + osm2pgsql flex → raw_pois
  ├── generate-grid     → PostGIS 200 m hex grid → grid_points
  ├── compute-scores    → two-phase orchestrator (see Scoring below)
@ -108,13 +111,73 @@ docker compose up postgres valkey -d

 ## Category Definitions

-| Category | OSM Sources |
-|----------|-------------|
-| Service & Trade | supermarkets, shops, restaurants, pharmacies, banks, cafés |
-| Transport | bus stops, metro, tram, train stations, bike share, car share |
-| Work & School | offices, coworking, schools, kindergartens, universities |
-| Culture & Community | libraries, hospitals, clinics, museums, theatres, community centres |
-| Recreation | parks, playgrounds, sports centres, gyms, green spaces |
+Five categories cover everyday destinations. All categories are scored at the same threshold (5, 10, 15, 20, or 30 minutes — user-selectable). The **universal weight** column shows how strongly a subcategory contributes to its parent category score in the Universal profile (range 0–1); other profiles override specific values — see the Profiles table below.
+
+### Service & Trade
+
+| OSM tag(s) | Subcategory | Universal weight |
+|---|---|:---:|
+| `shop=supermarket`, `shop=wholesale` | `supermarket` | 1.0 |
+| `shop=convenience` | `convenience` | 0.65 |
+| `amenity=pharmacy`, `shop=pharmacy` | `pharmacy` | 1.0 |
+| `amenity=restaurant`, `amenity=fast_food` | `restaurant` | 0.55 |
+| `amenity=cafe`, `shop=bakery` | `cafe` | 0.4 |
+| `amenity=bank` | `bank` | 0.35 |
+| `amenity=post_office` | `post_office` | 0.4 |
+| `shop=greengrocer`, `shop=butcher`, `amenity=marketplace`, `shop=department_store`, `shop=mall` | `market` | 0.4 |
+| `shop=laundry`, `shop=dry_cleaning` | `laundry` | 0.3 |
+| `amenity=atm` | `atm` | 0.2 |
+
+### Transport
+
+| OSM tag(s) | Subcategory | Universal weight |
+|---|---|:---:|
+| `railway=station`, `railway=halt` | `train_station` | 1.0 |
+| `railway=subway_entrance`, `railway=subway_station` | `metro` | 1.0 |
+| `railway=tram_stop` | `tram_stop` | 0.75 |
+| `highway=bus_stop`, `amenity=bus_station` | `bus_stop` | 0.55 |
+| `amenity=ferry_terminal` | `ferry` | 0.5 |
+| `amenity=bicycle_rental` | `bike_share` | 0.5 |
+| `amenity=car_sharing` | `car_share` | 0.5 |
+
+**Excluded:** `public_transport=stop_position` and `public_transport=platform` — these duplicate `highway=bus_stop` / `railway=tram_stop` nodes at the exact same location and would double-count stops in scoring.
+
+### Work & School
+
+| OSM tag(s) | Subcategory | Universal weight |
+|---|---|:---:|
+| `amenity=kindergarten`, `amenity=childcare` | `kindergarten` | 0.75 |
+| `amenity=school` | `school` | 0.7 |
+| `office=coworking` | `coworking` | 0.55 |
+| `amenity=university`, `amenity=college` | `university` | 0.55 |
+| `amenity=driving_school` | `driving_school` | 0.2 |
+
+**Excluded:** `office=company`, `office=government`, `landuse=commercial`, `landuse=office` — ubiquitous in every urban block; they always win the "nearest POI" race in the detail view, masking meaningful destinations. Government buildings are captured via `amenity=townhall` / `amenity=police` in Culture & Community instead.
+
+### Culture & Community
+
+| OSM tag(s) | Subcategory | Universal weight |
+|---|---|:---:|
+| `amenity=hospital` | `hospital` | 1.0 |
+| `amenity=clinic`, `amenity=doctors` | `clinic` | 0.8 |
+| `amenity=library` | `library` | 0.7 |
+| `amenity=community_centre`, `leisure=arts_centre` | `community_center` | 0.6 |
+| `amenity=social_facility` | `social_services` | 0.6 |
+| `amenity=theatre`, `amenity=cinema` | `theatre` | 0.5 |
+| `tourism=museum` | `museum` | 0.4 |
+| `amenity=townhall`, `amenity=police` | `government` | 0.4 |
+| `amenity=place_of_worship` | `place_of_worship` | 0.25 |
+
+### Recreation
+
+| OSM tag(s) | Subcategory | Universal weight |
+|---|---|:---:|
+| `leisure=park`, `leisure=garden` | `park` | 1.0 |
+| `leisure=playground` | `playground` | 0.85 |
+| `leisure=sports_centre`, `leisure=pitch` | `sports_facility` | 0.65 |
+| `leisure=fitness_centre` | `gym` | 0.65 |
+| `leisure=nature_reserve`, `leisure=golf_course`, `landuse=recreation_ground`, `landuse=grass`, `landuse=meadow`, `landuse=forest` | `green_space` | 0.6 |
+| `leisure=swimming_pool`, `amenity=swimming_pool` | `swimming_pool` | 0.55 |

 ## Scoring

@ -174,13 +237,13 @@ Each profile carries two sets of weights:
 - **Category weights** (used as slider presets in the UI, range 0–2): how much relative importance each of the 5 categories receives in the composite score.
 - **Subcategory weights** (baked into precomputed scores, range 0–1): how strongly a specific subcategory contributes to its parent category score.

-| Profile | Emoji | Category emphasis | Notable subcategory boosts |
-|---------|-------|-------------------|---------------------------|
-| Universal | ⚖️ | All equal (1.0) | Balanced baseline |
-| Young Family | 👨‍👩‍👧 | Work & School 1.5×, Recreation 1.4×, Service 1.2× | school, kindergarten, playground, clinic all → 1.0 |
-| Senior | 🧓 | Culture & Community 1.5×, Service 1.4×, Transport 1.1× | hospital, clinic, pharmacy, social services → 1.0; school → 0.05 |
-| Young Professional | 💼 | Transport 1.5×, Recreation 1.1× | metro, train → 1.0; gym 0.9; coworking 0.85; school → 0.1 |
-| Student | 🎓 | Work & School 1.5×, Transport 1.4×, Culture 1.2× | university, library → 1.0; bike share 0.85; school → 0.05 |
+| Profile | Emoji | Category weights | Notable subcategory overrides (vs. Universal) |
+|---------|-------|------------------|------------------------------------------------|
+| Universal | ⚖️ | All 1.0 | Baseline — see tables above for all weights |
+| Young Family | 👨‍👩‍👧 | Work & School 1.5, Recreation 1.4, Service 1.2, Culture 0.9, Transport 1.0 | school → 1.0, kindergarten → 1.0, playground → 1.0, clinic → 1.0, park → 1.0; gym → 0.5, university → 0.2, driving\_school → (inherits 0.2) |
+| Senior | 🧓 | Culture & Community 1.5, Service 1.4, Transport 1.1, Recreation 1.0, Work & School 0.3 | hospital → 1.0, clinic → 1.0, pharmacy → 1.0, social\_services → 0.9, bus\_stop → 0.75, tram\_stop → 0.8, metro → 0.8; school → 0.05, kindergarten → 0.05, university → 0.15 |
+| Young Professional | 💼 | Transport 1.5, Recreation 1.1, Service 1.0, Culture 0.9, Work & School 0.7 | metro → 1.0, train\_station → 1.0, tram\_stop → 0.85, bike\_share → 0.7; gym → 0.9, restaurant → 0.75, coworking → 0.85; school → 0.1, kindergarten → 0.05 |
+| Student | 🎓 | Work & School 1.5, Transport 1.4, Culture & Community 1.2, Service 0.9, Recreation 0.8 | university → 1.0, library → 1.0, coworking → 0.9, bike\_share → 0.85, cafe → 0.9, metro → 1.0, train\_station → 0.9; school → 0.05, kindergarten → 0.05 |

 ### Composite score

--- a/infra/osm2pgsql.lua
+++ b/infra/osm2pgsql.lua
@ -99,6 +99,7 @@ local tag_map = {
        swimming_pool   = { 'recreation', 'swimming_pool' },
        garden          = { 'recreation', 'park' },
        nature_reserve  = { 'recreation', 'green_space' },
+        golf_course     = { 'recreation', 'green_space' },
        pitch           = { 'recreation', 'sports_facility' },
        arts_centre     = { 'culture_community', 'community_center' },
    },
--- a/shared/src/osm-tags.ts
+++ b/shared/src/osm-tags.ts
@ -22,7 +22,6 @@ export interface CategoryDefinition {
  id: CategoryId;
  label: string;
  defaultWeight: number;
-  defaultThresholdMinutes: number;
  color: string;
  tags: TagFilter[];
 }
@ -32,7 +31,6 @@ export const CATEGORIES: CategoryDefinition[] = [
    id: "service_trade",
    label: "Service & Trade",
    defaultWeight: 0.2,
-    defaultThresholdMinutes: 10,
    color: "#e63946",
    tags: [
      {
@ -70,7 +68,6 @@ export const CATEGORIES: CategoryDefinition[] = [
    id: "transport",
    label: "Transport",
    defaultWeight: 0.2,
-    defaultThresholdMinutes: 8,
    color: "#457b9d",
    tags: [
      { key: "highway", values: ["bus_stop"] },
@ -92,7 +89,6 @@ export const CATEGORIES: CategoryDefinition[] = [
    id: "work_school",
    label: "Work & School",
    defaultWeight: 0.2,
-    defaultThresholdMinutes: 20,
    color: "#2a9d8f",
    tags: [
      { key: "office", values: ["coworking"] },
@ -113,7 +109,6 @@ export const CATEGORIES: CategoryDefinition[] = [
    id: "culture_community",
    label: "Culture & Community",
    defaultWeight: 0.2,
-    defaultThresholdMinutes: 15,
    color: "#e9c46a",
    tags: [
      {
@ -140,7 +135,6 @@ export const CATEGORIES: CategoryDefinition[] = [
    id: "recreation",
    label: "Recreation",
    defaultWeight: 0.2,
-    defaultThresholdMinutes: 10,
    color: "#06d6a0",
    tags: [
      {
--- a/worker/src/jobs/compute-transit.ts
+++ b/worker/src/jobs/compute-transit.ts
@ -30,7 +30,7 @@ export type ComputeTransitData = {
 };

 /** Grid points processed per concurrent Valhalla isochrone call. */
-const BATCH_CONCURRENCY = 4;
+const BATCH_CONCURRENCY = 8;
 /** Rows per INSERT. */
 const INSERT_CHUNK = 2000;