perfect-postcode/pipeline/run.py

45 lines
1.6 KiB
Python

"""Pipeline CLI to process property data with H3 spatial indexing."""
import polars as pl
from pipeline.sources.postcodes import save_postcodes
from pipeline.sources.property_prices import PropertyPricesSource
from pipeline.processors.h3_aggregator import save_aggregates
from pipeline.processors.journey_times_aggregator import aggregate_journey_times
def run_pipeline():
"""Run the full data processing pipeline."""
print("=" * 60)
print("Property Map Data Pipeline")
print("=" * 60)
# Step 1: Process postcodes with H3 indices
print("\n[1/4] Processing postcodes with H3 indices...")
postcodes_path = save_postcodes()
print(f" Saved: {postcodes_path}")
print("\n[2/4] Processing property prices...")
postcodes = pl.scan_parquet(postcodes_path)
property_source = PropertyPricesSource()
properties = property_source.process(postcodes)
print(" Joined property prices with postcodes")
print("\n[3/4] Aggregating at H3 resolutions...")
saved_paths = save_aggregates(properties)
for path in saved_paths:
size_mb = path.stat().st_size / (1024 * 1024)
print(f" Saved: {path.name} ({size_mb:.1f} MB)")
print("\n[4/4] Adding journey times to aggregates...")
updated_paths = aggregate_journey_times()
if updated_paths:
for path in updated_paths:
size_mb = path.stat().st_size / (1024 * 1024)
print(f" Updated: {path.name} ({size_mb:.1f} MB)")
else:
print(" Skipped (no journey time data found)")
if __name__ == "__main__":
run_pipeline()