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

.

Browse source
This commit is contained in:
Andras Schmelczer 2026-07-03 18:28:56 +01:00
parent 909e241907
commit 1ee796b282
29 changed files with 250 additions and 126 deletions
Download patch file Download diff file Expand all files Collapse all files

4
pipeline/download/rental_prices.py
View file

@ -35,7 +35,7 @@ def _data_rows(df: pl.DataFrame) -> pl.DataFrame:
The preamble length varies (title, optional "This worksheet contains..."
note, then the header row starting with "Time period"), so locate the
header by content instead of counting rows — a fixed slice leaves the
header by content instead of counting rows: a fixed slice leaves the
header in the data whenever ONS adds or removes a note line.
"""
header_marker = (
@ -78,7 +78,7 @@ def _latest_rents_long(df: pl.DataFrame) -> pl.DataFrame:
print(f"LAs in latest month: {df.height}")
# Melt to long format: one row per area x bedroom count.
# PIPR has no Studio category — one-bed rent used as proxy for bedrooms=0.
# PIPR has no Studio category: one-bed rent used as proxy for bedrooms=0.
frames = []
for col, bedrooms in [
("rent_1bed", 0), # Studio (proxy)