Use OSM data for geocoding in all boroughs

.github/workflows/e2etest.yml

@@ -13,16 +13,16 @@ jobs:
         tar -xzf geocache.tgz
     - name: Run geocoder
       run: |
-        PYTHONPATH=. poetry run oldnyc/geocode/geocode.py --ids_filter test/random200-ids.txt --images_ndjson data/images.ndjson --output_format id-location.txt --geocode > >(tee test/random200-geocoded.txt) 2> >(tee test/random200.logs.txt >&2)
+        PYTHONPATH=. poetry run oldnyc/geocode/geocode.py --ids_filter test/random200-ids.txt --output_format id-location.txt --geocode --no-progress-bar > >(tee test/random200-geocoded.txt) 2> >(tee test/random200.logs.txt >&2)
         # See https://stackoverflow.com/a/692407/388951 for the stdout/stderr redirection
     - name: Generate intersections
       run: |
         export PYTHONPATH=.
-        poetry run python oldnyc/geocode/osm/generate_intersections.py > data/intersections.csv
+        poetry run python oldnyc/geocode/osm/generate_intersections.py
     - name: Generate truth data
       run: |
         export PYTHONPATH=.
-        poetry run oldnyc/geocode/geocode.py --images_ndjson data/images.ndjson --output_format geojson --ids_filter data/geocode/random500-ids.txt  --geocode > /tmp/images.geojson
+        poetry run oldnyc/geocode/geocode.py --output_format geojson --ids_filter data/geocode/random500-ids.txt  --geocode > /tmp/images.geojson
         poetry run oldnyc/geocode/truth/make_localturk_csv.py data/geocode/random500-ids.txt /tmp/images.geojson data/geocode/random500.csv
         # We don't actually care about the diff on this file, just that make_localturk_csv.py doesn't error out.
         git checkout data/geocode/random500.csv
@@ -32,7 +32,7 @@ jobs:
     - name: Check performance on truth data
       run: |
         export PYTHONPATH=.
-        poetry run oldnyc/geocode/geocode.py --ids_filter data/geocode/truth-ids.txt --images_ndjson data/images.ndjson --output_format geojson --geocode > /tmp/actual.geojson
+        poetry run oldnyc/geocode/geocode.py --ids_filter data/geocode/truth-ids.txt --output_format geojson --geocode --no-progress-bar > /tmp/actual.geojson
         poetry run oldnyc/geocode/calculate_metrics.py --stats_only --truth_data data/geocode/truth.geojson --computed_data /tmp/actual.geojson > test/geocode-performance.txt
     - name: Check for diffs
       run: |
@@ -84,7 +84,7 @@ jobs:
       run: |
         export PYTHONPATH=.
         tar -xzf geocache.tgz
-        poetry run oldnyc/geocode/geocode.py --images_ndjson data/images.ndjson --lat_lon_map data/lat-lon-map.txt --output_format lat-lon-to-ids.json --geocode > data/lat-lon-to-ids.json 2> >(tee >( sed -n '/Finalizing/,$p' > test/geocoding-stats.txt) >&2)
+        poetry run oldnyc/geocode/geocode.py --lat_lon_map data/lat-lon-map.txt --output_format lat-lon-to-ids.json --geocode --no-progress-bar > data/lat-lon-to-ids.json 2> >(tee >( sed -n '/Finalizing/,$p' > test/geocoding-stats.txt) >&2)
     - name: Generate static site
       run: |
         export PYTHONPATH=.

data/README.md

@@ -23,6 +23,8 @@ TODO:
 
 ## Repro instructions
 
+If there are no instructions for a file here, check `e2etest.yml`.
+
 ### osm-roads.json
 
 Run `data/nyc-named-roads.overpass-query.txt` through the Overpass API. This will produce a big JSON file that needs to be filtered. You can do this with: