andras/perfect-postcode
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 2 Wiki Activity Actions

Last night

Browse source
This commit is contained in:
Andras Schmelczer 2026-02-08 10:21:37 +00:00
parent 2906b01734
commit 42ee2d4c51
47 changed files with 848 additions and 478 deletions
Download patch file Download diff file Expand all files Collapse all files

25
pipeline/transform/merge.py
View file

@ -113,7 +113,12 @@ def _build_wide(
*[pl.col(c).fill_nan(None) for c in noise_cols],
)
.with_columns(
pl.max_horizontal(*noise_cols).fill_null(0).alias("noise_lden_db"),
pl.max_horizontal(*noise_cols).alias("noise_lden_db"),
)
.with_columns(
pl.col("noise_lden_db")
.fill_null(pl.col("noise_lden_db").min())
.alias("noise_lden_db"),
)
.select("postcode", "noise_lden_db")
)
@ -153,8 +158,8 @@ def _build_wide(
wide = wide.with_columns(
pl.when(pl.col("pp_property_type").is_in(["Terraced", "Semi-Detached"]))
.then(pl.col("built_form"))
.otherwise(pl.col("epc_property_type"))
.alias("epc_property_type")
.otherwise(pl.col("pp_property_type"))
.alias("property_type")
)
wide = (
@ -191,12 +196,13 @@ def _build_wide(
"Barriers to Housing and Services Score",
"lsoa21",
"oa21",
"epc_property_type",
"pp_property_type",
"built_form",
)
.rename(
{
"date_of_transfer": "Previous transaction date",
"date_of_transfer": "Date of last transaction",
"construction_age_band": "Construction age",
"is_construction_date_approximate": "Is construction date approximate",
"pp_address": "Address per Property Register",
@ -206,11 +212,11 @@ def _build_wide(
"current_energy_rating": "Current energy rating",
"potential_energy_rating": "Potential energy rating",
"total_floor_area": "Total floor area (sqm)",
"epc_property_type": "Property type",
"restaurants_2km": "Restaurants within 2km",
"groceries_2km": "Groceries within 2km",
"parks_2km": "Parks within 2km",
"public_transport_2km": "Public transport within 2km",
"property_type": "Property type",
"restaurants_2km": "Number of restaurants within 2km",
"groceries_2km": "Number of grocery shops and supermarkets within 2km",
"parks_2km": "Number of parks within 2km",
"public_transport_2km": "Number of public transport stations within 2km",
"latest_price": "Last known price",
"number_habitable_rooms": "Number of bedrooms & living rooms",
"noise_lden_db": "Noise (dB)",
@ -219,7 +225,6 @@ def _build_wide(
"max_download_speed": "Max available download speed (Mbps)",
"serious_crime_avg_yr": "Serious crime (avg/yr)",
"minor_crime_avg_yr": "Minor crime (avg/yr)",
"transaction_year": "Transaction year",
"environmental_risk": "Environmental risk",
"collapsible_deposits_risk": "Collapsible deposits risk",
"compressible_ground_risk": "Compressible ground risk",