rerun hqta and do ArcGIS steps

cal-itp · Dec 20, 2024 · 62cd4ae · 62cd4ae
1 parent 5a0218e
commit 62cd4ae
Show file tree

Hide file tree

Showing 10 changed files with 308 additions and 639 deletions.
diff --git a/high_quality_transit_areas/09_enforce_collinearity.ipynb b/high_quality_transit_areas/09_enforce_collinearity.ipynb
@@ -454,7 +454,7 @@
    },
    "outputs": [],
    "source": [
-    "feed_names_filtered = feed_names >> filter(_.name.str.contains('Sac'))\n",
+    "feed_names_filtered = feed_names >> filter(_.name.str.contains('VTA'))\n",
     "display(feed_names_filtered)\n",
     "gtfs_dataset_key = feed_names_filtered.gtfs_dataset_key.iloc[0]"
    ]
@@ -831,7 +831,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "m #  8 threshold"
+    "# m #  8 threshold"
    ]
   },
   {
@@ -1024,7 +1024,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "one_pts = hqta_points >> filter(_.agency_primary.str.contains('Valley'))"
+    "# one_pts = hqta_points >> filter(_.agency_primary.str.contains('Los Angeles County'))\n",
+    "one_pts = hqta_points >> filter(_.hqta_details != 'corridor_other_stop')"
    ]
   },
   {
@@ -1068,42 +1069,44 @@
    ]
   },
   {
-   "cell_type": "markdown",
-   "id": "4b351da3-4825-4caa-8333-33386db868f1",
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "55307463-952c-4595-98d7-a5619096aff3",
    "metadata": {},
+   "outputs": [],
    "source": [
-    "## all bus"
+    "all_bus = gpd.read_parquet(f\"{GCS_FILE_PATH}all_bus.parquet\")\n",
+    "# hqta_segments = gpd.read_parquet(f\"{GCS_FILE_PATH}hqta_segments.parquet\")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "55307463-952c-4595-98d7-a5619096aff3",
+   "id": "b9067d6c-df86-4c38-846f-c5de30828293",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# all_bus = gpd.read_parquet(f\"{GCS_FILE_PATH}all_bus.parquet\")\n",
-    "hqta_segments = gpd.read_parquet(f\"{GCS_FILE_PATH}hqta_segments.parquet\")"
+    "from sjoin_stops_to_segments import find_inconclusive_directions"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b9067d6c-df86-4c38-846f-c5de30828293",
+   "id": "4785bd05-eda6-4139-b801-951f7513d0df",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sjoin_stops_to_segments import find_inconclusive_directions"
+    "# hqta_segments = find_inconclusive_directions(hqta_segments)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4785bd05-eda6-4139-b801-951f7513d0df",
+   "id": "53421714-f669-4413-8192-b658bc5af47c",
    "metadata": {},
    "outputs": [],
    "source": [
-    "hqta_segments = find_inconclusive_directions(hqta_segments)"
+    "# hqta_segments"
    ]
   },
   {
@@ -1113,7 +1116,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# one = hqta_segments >> filter(_.schedule_gtfs_dataset_key == '70c8a8b71c815224299523bf2115924a')"
+    "one = all_bus >> filter(_.schedule_gtfs_dataset_key == 'fb467982dcc77a7f9199bebe709bb700')"
    ]
   },
   {
@@ -1123,7 +1126,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# one.geometry = one.buffer(35)"
+    "one.geometry = one.buffer(35)"
    ]
   },
   {
@@ -1136,6 +1139,16 @@
     "# one = one >> filter(_.route_id.isin(['228', '227', '062', '061', '056', '106']))"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "56688d44-b377-4b74-8a32-d7f2d2dff3db",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "one.explore(column='segment_direction')"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

diff --git a/high_quality_transit_areas/Makefile b/high_quality_transit_areas/Makefile
@@ -1,8 +1,8 @@
 hqta_data:
-	python rail_ferry_brt_stops.py
-	python create_hqta_segments.py
-	python create_aggregate_stop_frequencies.py
-	python sjoin_stops_to_segments.py
+#	python rail_ferry_brt_stops.py
+#	python create_hqta_segments.py
+#	python create_aggregate_stop_frequencies.py
+#	python sjoin_stops_to_segments.py
 	python prep_pairwise_intersections.py
 	python get_intersections.py
 	python create_bus_hqta_types.py

diff --git a/high_quality_transit_areas/logs/hqta_processing.log b/high_quality_transit_areas/logs/hqta_processing.log
@@ -128,3 +128,8 @@
 2024-12-17 15:09:48.649 | INFO     | __main__:<module>:175 - C3_create_bus_hqta_types 2024-12-11 execution time: 0:00:11.784740
 2024-12-17 15:10:23.397 | INFO     | __main__:<module>:219 - D1_assemble_hqta_points 2024-12-11 execution time: 0:00:18.075380
 2024-12-17 15:10:53.886 | INFO     | __main__:<module>:168 - D2_assemble_hqta_polygons 2024-12-11 execution time: 0:00:13.604352
+2024-12-19 14:06:19.225 | INFO     | __main__:<module>:149 - C1_prep_pairwise_intersections 2024-12-11 execution time: 0:00:04.821081
+2024-12-19 14:06:46.848 | INFO     | __main__:<module>:124 - C2_find_intersections 2024-12-11 execution time: 0:00:06.916373
+2024-12-19 14:07:17.276 | INFO     | __main__:<module>:175 - C3_create_bus_hqta_types 2024-12-11 execution time: 0:00:13.000987
+2024-12-19 14:07:53.167 | INFO     | __main__:<module>:219 - D1_assemble_hqta_points 2024-12-11 execution time: 0:00:18.462037
+2024-12-19 14:08:28.603 | INFO     | __main__:<module>:168 - D2_assemble_hqta_polygons 2024-12-11 execution time: 0:00:17.899141
diff --git a/high_quality_transit_areas/prep_pairwise_intersections.py b/high_quality_transit_areas/prep_pairwise_intersections.py
@@ -49,22 +49,27 @@ def sjoin_against_other_operators(
     """
     Spatial join of the in group vs the out group. 
     This could be the operator vs other operators, 
-    or a route vs other routes.
+    or a route vs other routes. This is currently
+    east-west vs north-south segments, which requires
+    the additional step of excluding intersections
+    resulting from the same route changing direction.
     
     Create a crosswalk / pairwise table showing these links.
     
     Compile all of them, because finding intersections is 
     computationally expensive,
     so we want to do it on fewer rows. 
     """
-    route_cols = ["hqta_segment_id", "segment_direction"]
+    route_cols = ["hqta_segment_id", "segment_direction", "route_key"]
 
     s1 = gpd.sjoin(
         in_group_df[route_cols + ["geometry"]], 
         out_group_df[route_cols  + ["geometry"]],
         how = "inner",
         predicate = "intersects"
     ).drop(columns = ["index_right", "geometry"])
+
+    s1 = s1[s1["route_key_left"] != s1["route_key_right"]]
 
     route_pairs = (
         s1.rename(