Fix data pipelines once and for all

This commit is contained in:
Andras Schmelczer 2026-06-10 21:27:32 +01:00
parent 08560476c5
commit 4012e4e047
46 changed files with 4508 additions and 855 deletions

View file

@ -180,20 +180,6 @@ pub static FEATURE_GROUPS: &[FeatureGroup] = &[
raw: false,
absolute: true,
}),
Feature::Enum(EnumFeatureConfig {
name: "Within conservation area",
order: Some(&["Yes", "No"]),
description: "Whether the postcode point falls inside a designated conservation area",
detail: "Planning Data conservation area boundaries, matched to the postcode representative point. The national dataset is a work in progress and may include duplicates or incomplete local coverage, so boundary-sensitive decisions should be checked with the local planning authority.",
source: "conservation-areas",
}),
Feature::Enum(EnumFeatureConfig {
name: "Listed building",
order: Some(&["Yes", "No"]),
description: "Whether this property appears to match a Historic England listed building entry",
detail: "Historic England National Heritage List for England listed-building points, matched conservatively to property addresses using the listed-entry name and nearby postcode candidates. Treat this as a screening signal, not a legal determination: verify any specific property on the NHLE and with the local planning authority.",
source: "listed-buildings",
}),
Feature::Numeric(FeatureConfig {
name: "Noise (dB)",
bounds: Bounds::Fixed {
@ -209,6 +195,20 @@ pub static FEATURE_GROUPS: &[FeatureGroup] = &[
raw: false,
absolute: false,
}),
Feature::Enum(EnumFeatureConfig {
name: "Within conservation area",
order: Some(&["Yes", "No"]),
description: "Whether the postcode point falls inside a designated conservation area",
detail: "Planning Data conservation area boundaries, matched to the postcode representative point. The national dataset is a work in progress and may include duplicates or incomplete local coverage, so boundary-sensitive decisions should be checked with the local planning authority.",
source: "conservation-areas",
}),
Feature::Enum(EnumFeatureConfig {
name: "Listed building",
order: Some(&["Yes", "No"]),
description: "Whether this property appears to match a Historic England listed building entry",
detail: "Historic England National Heritage List for England listed-building points, matched conservatively to property addresses using the listed-entry name and nearby postcode candidates. Treat this as a screening signal, not a legal determination: verify any specific property on the NHLE and with the local planning authority.",
source: "listed-buildings",
}),
],
},
FeatureGroup {
@ -307,89 +307,14 @@ pub static FEATURE_GROUPS: &[FeatureGroup] = &[
name: "Schools",
features: &[
Feature::Numeric(FeatureConfig {
name: "Good+ primary schools within 2km",
bounds: Bounds::Fixed {
min: 0.0,
max: 10.0,
},
step: 1.0,
description: "Primary schools rated Good or Outstanding by Ofsted within 2km",
detail: "State-funded primary schools within 2km with a current Ofsted rating of Good or Outstanding. Schools not yet inspected are excluded.",
source: "ofsted",
prefix: "",
suffix: "",
raw: false,
absolute: false,
}),
Feature::Numeric(FeatureConfig {
name: "Good+ secondary schools within 2km",
bounds: Bounds::Fixed {
min: 0.0,
max: 5.0,
},
step: 1.0,
description: "Secondary schools rated Good or Outstanding by Ofsted within 2km",
detail: "State-funded secondary schools within 2km with a current Ofsted rating of Good or Outstanding. Schools not yet inspected are excluded.",
source: "ofsted",
prefix: "",
suffix: "",
raw: false,
absolute: false,
}),
Feature::Numeric(FeatureConfig {
name: "Outstanding primary schools within 2km",
bounds: Bounds::Fixed {
min: 0.0,
max: 10.0,
},
step: 1.0,
description: "Primary schools rated Outstanding by Ofsted within 2km",
detail: "State-funded primary schools within 2km with a current Ofsted rating of Outstanding. Schools not yet inspected are excluded.",
source: "ofsted",
prefix: "",
suffix: "",
raw: false,
absolute: false,
}),
Feature::Numeric(FeatureConfig {
name: "Outstanding secondary schools within 2km",
bounds: Bounds::Fixed {
min: 0.0,
max: 5.0,
},
step: 1.0,
description: "Secondary schools rated Outstanding by Ofsted within 2km",
detail: "State-funded secondary schools within 2km with a current Ofsted rating of Outstanding. Schools not yet inspected are excluded.",
source: "ofsted",
prefix: "",
suffix: "",
raw: false,
absolute: false,
}),
Feature::Numeric(FeatureConfig {
name: "Good+ primary schools within 5km",
bounds: Bounds::Fixed {
min: 0.0,
max: 30.0,
},
step: 1.0,
description: "Primary schools rated Good or Outstanding by Ofsted within 5km",
detail: "State-funded primary schools within 5km with a current Ofsted rating of Good or Outstanding. Schools not yet inspected are excluded.",
source: "ofsted",
prefix: "",
suffix: "",
raw: false,
absolute: false,
}),
Feature::Numeric(FeatureConfig {
name: "Good+ secondary schools within 5km",
name: "Good+ primary school catchments",
bounds: Bounds::Fixed {
min: 0.0,
max: 15.0,
},
step: 1.0,
description: "Secondary schools rated Good or Outstanding by Ofsted within 5km",
detail: "State-funded secondary schools within 5km with a current Ofsted rating of Good or Outstanding. Schools not yet inspected are excluded.",
description: "Primary schools rated Good or Outstanding whose modelled catchment area covers this postcode",
detail: "How many state-funded primary schools with a current Ofsted rating of Good or Outstanding draw their pupils from an area covering this postcode. Catchment radii are modelled by simulating England's distance-based admissions (each school's places against the local child population, Census 2021) and calibrated against published 'last distance offered' figures; they are estimates, not official admission areas. Schools not yet inspected are excluded.",
source: "ofsted",
prefix: "",
suffix: "",
@ -397,14 +322,14 @@ pub static FEATURE_GROUPS: &[FeatureGroup] = &[
absolute: false,
}),
Feature::Numeric(FeatureConfig {
name: "Outstanding primary schools within 5km",
name: "Good+ secondary school catchments",
bounds: Bounds::Fixed {
min: 0.0,
max: 30.0,
max: 11.0,
},
step: 1.0,
description: "Primary schools rated Outstanding by Ofsted within 5km",
detail: "State-funded primary schools within 5km with a current Ofsted rating of Outstanding. Schools not yet inspected are excluded.",
description: "Secondary schools rated Good or Outstanding whose modelled catchment area covers this postcode",
detail: "How many state-funded secondary schools with a current Ofsted rating of Good or Outstanding draw their pupils from an area covering this postcode. Catchment radii are modelled by simulating England's distance-based admissions (each school's places against the local child population, Census 2021) and calibrated against published 'last distance offered' figures; they are estimates, not official admission areas. Schools not yet inspected are excluded.",
source: "ofsted",
prefix: "",
suffix: "",
@ -412,14 +337,29 @@ pub static FEATURE_GROUPS: &[FeatureGroup] = &[
absolute: false,
}),
Feature::Numeric(FeatureConfig {
name: "Outstanding secondary schools within 5km",
name: "Outstanding primary school catchments",
bounds: Bounds::Fixed {
min: 0.0,
max: 15.0,
max: 8.0,
},
step: 1.0,
description: "Secondary schools rated Outstanding by Ofsted within 5km",
detail: "State-funded secondary schools within 5km with a current Ofsted rating of Outstanding. Schools not yet inspected are excluded.",
description: "Primary schools rated Outstanding whose modelled catchment area covers this postcode",
detail: "How many state-funded primary schools with a current Ofsted rating of Outstanding draw their pupils from an area covering this postcode. Catchment radii are modelled by simulating England's distance-based admissions (each school's places against the local child population, Census 2021) and calibrated against published 'last distance offered' figures; they are estimates, not official admission areas. Schools not yet inspected are excluded.",
source: "ofsted",
prefix: "",
suffix: "",
raw: false,
absolute: false,
}),
Feature::Numeric(FeatureConfig {
name: "Outstanding secondary school catchments",
bounds: Bounds::Fixed {
min: 0.0,
max: 4.0,
},
step: 1.0,
description: "Secondary schools rated Outstanding whose modelled catchment area covers this postcode",
detail: "How many state-funded secondary schools with a current Ofsted rating of Outstanding draw their pupils from an area covering this postcode. Catchment radii are modelled by simulating England's distance-based admissions (each school's places against the local child population, Census 2021) and calibrated against published 'last distance offered' figures; they are estimates, not official admission areas. Schools not yet inspected are excluded.",
source: "ofsted",
prefix: "",
suffix: "",