perfect-postcode/pipeline/processors/h3_aggregator.py

42 lines
1.3 KiB
Python

from pathlib import Path
import polars as pl
from pipeline.config import AGGREGATES_DIR, H3_RESOLUTIONS
def aggregate(df: pl.LazyFrame, resolution: int) -> pl.LazyFrame:
"""Aggregate property data by H3 cell and year."""
h3_col = f"h3_res{resolution}"
return (
df.group_by(h3_col, "year")
.agg(
pl.len().alias("count"),
pl.col("price").mean().alias("avg_price"),
pl.col("price").median().alias("median_price"),
pl.col("price").min().alias("min_price"),
pl.col("price").max().alias("max_price"),
)
.rename({h3_col: "h3"})
)
def aggregate_all(df: pl.LazyFrame) -> dict[int, pl.LazyFrame]:
"""Aggregate at all H3 resolutions."""
return {res: aggregate(df, res) for res in H3_RESOLUTIONS}
def save_aggregates(df: pl.LazyFrame, output_dir: Path | None = None) -> list[Path]:
"""Aggregate and save at all H3 resolutions."""
output_dir = output_dir or AGGREGATES_DIR
output_dir.mkdir(parents=True, exist_ok=True)
saved_paths = []
aggregates = aggregate_all(df)
for res, agg_df in aggregates.items():
output_path = output_dir / f"res{res}.parquet"
agg_df.collect().write_parquet(output_path)
saved_paths.append(output_path)
return saved_paths