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

Update data

Browse source
This commit is contained in:
Andras Schmelczer 2026-05-14 08:17:10 +01:00
parent a4103b0896
commit 273d7a83ee
15 changed files with 716 additions and 316 deletions
Download patch file Download diff file Expand all files Collapse all files

6
pipeline/transform/price_estimation/utils.py
View file

@ -19,7 +19,7 @@ TERRACE_TYPES = [
"Terraced",
]
FLAT_TYPES = ["Flats/Maisonettes"]
TYPE_GROUPS = ["Detached", "Semi-Detached", "Terraced", "Flats", "Bungalow"]
TYPE_GROUPS = ["Detached", "Semi-Detached", "Terraced", "Flats"]
SHRINKAGE_K = 50
@ -30,8 +30,6 @@ def type_group_expr():
.then(pl.lit("Terraced"))
.when(pl.col("Property type").is_in(FLAT_TYPES))
.then(pl.lit("Flats"))
.when(pl.col("Property type") == "Bungalow")
.then(pl.lit("Bungalow"))
.when(pl.col("Property type").is_in(["Detached", "Semi-Detached"]))
.then(pl.col("Property type"))
.otherwise(pl.lit(None))
@ -61,7 +59,7 @@ def hierarchy_keys(sector: str) -> tuple[str, str]:
return district, area
NON_REF_TYPES = ["Terraced", "Semi-Detached", "Flats", "Bungalow"]
NON_REF_TYPES = ["Terraced", "Semi-Detached", "Flats"]
def build_hedonic_features(df: pl.DataFrame) -> np.ndarray: