This commit is contained in:
Andras Schmelczer 2026-06-02 20:14:32 +01:00
parent fbfebc651c
commit aab85fe32e
33 changed files with 2016 additions and 283 deletions

View file

@ -116,9 +116,9 @@ MAP_ASSETS_DEPS := pipeline/download/map_assets.py pipeline/transform/transform_
generate-postcode-boundaries generate-travel-times enrich-actual-listings
prepare: $(PRICES_STAMP) download-places tiles satellite-tiles overlay-tiles property-border-tiles generate-postcode-boundaries download-map-assets generate-travel-times | $(POSTCODES_PQ) $(PROPERTIES_PQ) $(PRICE_INDEX)
$(VALIDATE_OUTPUTS) --parquet $(POSTCODES_PQ) --parquet $(PROPERTIES_PQ) --parquet $(PRICE_INDEX) --postcode-boundary-match "$(POSTCODES_PQ)::$(PC_BOUNDARIES)" --postcode-features $(POSTCODES_PQ) --properties-subset "$(PROPERTIES_PQ)::$(POSTCODES_PQ)" --price-index $(PRICE_INDEX)
$(VALIDATE_OUTPUTS) --parquet $(POSTCODES_PQ) --parquet $(PROPERTIES_PQ) --parquet $(PRICE_INDEX) --postcode-boundary-match "$(POSTCODES_PQ)::$(PC_BOUNDARIES)" --postcode-features $(POSTCODES_PQ) --postcode-universe "$(ARCGIS)::$(POSTCODES_PQ)" --properties-subset "$(PROPERTIES_PQ)::$(POSTCODES_PQ)" --price-index $(PRICE_INDEX)
merge: $(MERGE_STAMP) | $(POSTCODES_PQ) $(PROPERTIES_PQ)
$(VALIDATE_OUTPUTS) --parquet $(POSTCODES_PQ) --parquet $(PROPERTIES_PQ) --postcode-features $(POSTCODES_PQ) --properties-subset "$(PROPERTIES_PQ)::$(POSTCODES_PQ)"
$(VALIDATE_OUTPUTS) --parquet $(POSTCODES_PQ) --parquet $(PROPERTIES_PQ) --postcode-features $(POSTCODES_PQ) --postcode-universe "$(ARCGIS)::$(POSTCODES_PQ)" --properties-subset "$(PROPERTIES_PQ)::$(POSTCODES_PQ)"
enrich-actual-listings: $(ACTUAL_LISTINGS_ENRICHED)
tiles: $(TILES) $(SATELLITE_TILES) $(SATELLITE_HIGHRES_TILES)
satellite-tiles: $(SATELLITE_TILES)
@ -413,13 +413,13 @@ $(MERGE_STAMP): $(EPC_PP) $(ARCGIS) $(IOD) $(POI_PROXIMITY) \
--tree-density-postcodes $(TREE_DENSITY_PC) \
--output-postcodes $(POSTCODES_PQ) \
--output-properties $(PROPERTIES_PQ)
$(VALIDATE_OUTPUTS) --parquet $(POSTCODES_PQ) --parquet $(PROPERTIES_PQ) --postcode-features $(POSTCODES_PQ) --properties-subset "$(PROPERTIES_PQ)::$(POSTCODES_PQ)"
$(VALIDATE_OUTPUTS) --parquet $(POSTCODES_PQ) --parquet $(PROPERTIES_PQ) --postcode-features $(POSTCODES_PQ) --postcode-universe "$(ARCGIS)::$(POSTCODES_PQ)" --properties-subset "$(PROPERTIES_PQ)::$(POSTCODES_PQ)"
@touch $@
# ── Price estimation (post-merge) ───────────────────────────────────────────
$(POSTCODES_PQ) $(PROPERTIES_PQ) &: $(MERGE_STAMP)
$(VALIDATE_OUTPUTS) --parquet $(POSTCODES_PQ) --parquet $(PROPERTIES_PQ) --postcode-features $(POSTCODES_PQ) --properties-subset "$(PROPERTIES_PQ)::$(POSTCODES_PQ)"
$(VALIDATE_OUTPUTS) --parquet $(POSTCODES_PQ) --parquet $(PROPERTIES_PQ) --postcode-features $(POSTCODES_PQ) --postcode-universe "$(ARCGIS)::$(POSTCODES_PQ)" --properties-subset "$(PROPERTIES_PQ)::$(POSTCODES_PQ)"
$(PRICE_INDEX): $(MERGE_STAMP) $(PRICE_INDEX_DEPS) | $(PROPERTIES_PQ) $(POSTCODES_PQ)
uv run python -m pipeline.transform.price_estimation.index --input $(PROPERTIES_PQ) --postcodes $(POSTCODES_PQ) --output $@
@ -428,7 +428,7 @@ $(PRICE_INDEX): $(MERGE_STAMP) $(PRICE_INDEX_DEPS) | $(PROPERTIES_PQ) $(POSTCODE
$(PRICES_STAMP): $(MERGE_STAMP) $(PRICE_INDEX) $(PRICE_ESTIMATE_DEPS) | $(PROPERTIES_PQ) $(POSTCODES_PQ)
@rm -f $@
uv run python -m pipeline.transform.price_estimation.estimate --properties $(PROPERTIES_PQ) --postcodes $(POSTCODES_PQ) --index $(PRICE_INDEX)
$(VALIDATE_OUTPUTS) --parquet $(PROPERTIES_PQ) --parquet $(POSTCODES_PQ) --parquet $(PRICE_INDEX) --postcode-features $(POSTCODES_PQ) --properties-subset "$(PROPERTIES_PQ)::$(POSTCODES_PQ)" --price-index $(PRICE_INDEX)
$(VALIDATE_OUTPUTS) --parquet $(PROPERTIES_PQ) --parquet $(POSTCODES_PQ) --parquet $(PRICE_INDEX) --postcode-features $(POSTCODES_PQ) --postcode-universe "$(ARCGIS)::$(POSTCODES_PQ)" --properties-subset "$(PROPERTIES_PQ)::$(POSTCODES_PQ)" --price-index $(PRICE_INDEX)
@touch $@
$(ACTUAL_LISTINGS_ENRICHED): $(ACTUAL_LISTINGS_RAW) $(EPC) \