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

lmao

Browse source
This commit is contained in:
Andras Schmelczer 2026-02-15 22:39:49 +00:00
parent 03445188ea
commit 524580eb25
102 changed files with 36625 additions and 1295 deletions
Download patch file Download diff file Expand all files Collapse all files

7
pipeline/transform/join_epc_pp.py
View file

@ -7,6 +7,7 @@ from ..utils import fuzzy_join_on_postcode
pl.Config.set_tbl_cols(-1)
RATING_RANK = {"A": 1, "B": 2, "C": 3, "D": 4, "E": 5, "F": 6, "G": 7}
MIN_PRICE = 50_000
def main():
@ -117,7 +118,9 @@ def main():
.collect()
)
event_counts = events["renovation_history"].explode().struct.field("event").value_counts()
event_counts = (
events["renovation_history"].explode().struct.field("event").value_counts()
)
print(f"Renovation events: {events.height} properties with events")
print(event_counts)
@ -159,6 +162,7 @@ def main():
"old_new",
)
.filter(pl.col("pp_property_type") != "Other")
.filter(pl.col("price") >= MIN_PRICE)
.with_columns(
pl.concat_str(
[pl.col("saon"), pl.col("paon"), pl.col("street")],
@ -171,6 +175,7 @@ def main():
.agg(
pl.struct(
pl.col("date_of_transfer").dt.year().alias("year"),
pl.col("date_of_transfer").dt.month().cast(pl.UInt8).alias("month"),
"price",
).alias("historical_prices"),
pl.col("pp_property_type").last(),