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

Tonight

Browse source
This commit is contained in:
Andras Schmelczer 2026-05-06 22:40:46 +01:00
parent 28323f145e
commit 94f9c0d594
76 changed files with 3238 additions and 1230 deletions
Download patch file Download diff file Expand all files Collapse all files

54
pipeline/transform/transform_poi.py
View file

@ -1086,12 +1086,56 @@ GROCERY_RETAILER_DISPLAY_NAMES: dict[str, str] = {
}
GROCERY_FASCIA_ICON_NAMES: dict[str, str] = {
"Aldi Local": "Aldi",
"Asda Express": "Asda Express",
"Asda Living": "Asda Living",
"Asda PFS": "Asda PFS",
"Cooltrader": "Heron Foods",
"Cook": "COOK",
"Eurospar": "Spar",
"Eurospar PFS": "Spar",
"Heron": "Heron Foods",
"Little Waitrose": "Little Waitrose",
"Little Waitrose Shell": "Little Waitrose",
"Marks and Spencer": "M&S",
"Marks and Spencer BP": "M&S Food",
"Marks and Spencer Clothing": "M&S Clothing",
"Marks and Spencer Food To Go": "M&S Food",
"Marks and Spencer Food Outlet": "M&S Outlet",
"Marks and Spencer Foodhall": "M&S Food",
"Marks and Spencer Hospital": "M&S Hospital",
"Marks and Spencer MSA": "M&S MSA",
"Marks and Spencer Outlet": "M&S Outlet",
"Marks and Spencer Simply Food": "M&S Food",
"Marks and Spencer Travel SF": "M&S Food",
"Morrisons Daily": "Morrisons Daily",
"Morrisons Select": "Morrisons",
"Sainsburys": "Sainsbury's",
"Sainsburys Local": "Sainsbury's Local",
"Spar PFS": "Spar",
"Tesco Express": "Tesco Express",
"Tesco Express Esso": "Tesco Express",
"Tesco Extra": "Tesco Extra",
"The Co-operative Food": "Co-op",
"The Co-operative Food PFS": "Co-op",
"The Food Warehouse": "The Food Warehouse",
"Waitrose MSA": "Waitrose",
}
def normalize_grocery_retailer(retailer: str | None) -> str:
if retailer is None:
return ""
return GROCERY_RETAILER_DISPLAY_NAMES.get(retailer, retailer)
def normalize_grocery_icon_category(fascia: str | None, retailer: str | None) -> str:
if fascia:
return GROCERY_FASCIA_ICON_NAMES.get(fascia, normalize_grocery_retailer(fascia))
return normalize_grocery_retailer(retailer)
def transform_grocery_retail_points(
grocery_df: pl.DataFrame,
boundary_path: Path | None = None,
@ -1133,9 +1177,15 @@ def transform_grocery_retail_points(
pl.col("retailer")
.map_elements(normalize_grocery_retailer, return_dtype=pl.String)
.alias("category"),
pl.struct(["fascia", "retailer"])
.map_elements(
lambda row: normalize_grocery_icon_category(row["fascia"], row["retailer"]),
return_dtype=pl.String,
)
.alias("icon_category"),
pl.lit("Groceries").alias("group"),
pl.lit("🛒").alias("emoji"),
).select("id", "name", "category", "group", "lat", "lng", "emoji")
).select("id", "name", "category", "icon_category", "group", "lat", "lng", "emoji")
def transform(
@ -1189,6 +1239,7 @@ def transform(
lf = lf.with_columns(
pl.col("category").replace_strict(group_mapping).alias("group"),
pl.col("category").replace_strict(name_mapping).alias("category"),
pl.col("category").replace_strict(name_mapping).alias("icon_category"),
pl.col("category").replace_strict(emoji_mapping).alias("emoji"),
)
@ -1203,6 +1254,7 @@ def transform(
naptan = naptan_df.lazy().with_columns(
pl.col("category").replace_strict(NAPTAN_EMOJIS).alias("emoji"),
pl.lit("Public Transport").alias("group"),
pl.col("category").alias("icon_category"),
)
frames = [lf, naptan]