notebooks use numbered ordering, add _utils

cal-itp · Sep 25, 2024 · e382995 · e382995
1 parent 8498292
commit e382995
Show file tree

Hide file tree

Showing 8 changed files with 43 additions and 0 deletions.
diff --git a/...ty_transit_areas/corridors-as-lines.ipynb → ...transit_areas/01_corridors-as-lines.ipynb b/...ty_transit_areas/corridors-as-lines.ipynb → ...transit_areas/01_corridors-as-lines.ipynb
diff --git a/...lity_transit_areas/hqta_green_SACOG.ipynb → ...y_transit_areas/02_hqta_green_SACOG.ipynb b/...lity_transit_areas/hqta_green_SACOG.ipynb → ...y_transit_areas/02_hqta_green_SACOG.ipynb
diff --git a/high_quality_transit_areas/hqta-map.ipynb → high_quality_transit_areas/03_hqta_map.ipynb b/high_quality_transit_areas/hqta-map.ipynb → high_quality_transit_areas/03_hqta_map.ipynb
diff --git a/...lity_transit_areas/explore-whittier.ipynb → ...y_transit_areas/04_explore_whittier.ipynb b/...lity_transit_areas/explore-whittier.ipynb → ...y_transit_areas/04_explore_whittier.ipynb
diff --git a/high_quality_transit_areas/metro_brt.ipynb → ..._quality_transit_areas/05_metro_brt.ipynb b/high_quality_transit_areas/metro_brt.ipynb → ..._quality_transit_areas/05_metro_brt.ipynb
diff --git a/high_quality_transit_areas/muni_brt.ipynb → high_quality_transit_areas/06_muni_brt.ipynb b/high_quality_transit_areas/muni_brt.ipynb → high_quality_transit_areas/06_muni_brt.ipynb
diff --git a/high_quality_transit_areas/amtrak.ipynb → high_quality_transit_areas/07_amtrak.ipynb b/high_quality_transit_areas/amtrak.ipynb → high_quality_transit_areas/07_amtrak.ipynb
diff --git a/high_quality_transit_areas/_utils.py b/high_quality_transit_areas/_utils.py
@@ -0,0 +1,43 @@
+"""
+Shared utility functions for HQTA
+"""
+import geopandas as gpd
+import intake
+import pandas as pd
+
+catalog = intake.open_catalog("catalog.yml")
+
+def add_hqta_details(row) -> str:
+    """
+    Add HQTA details of why nulls are present 
+    based on feedback from open data users.
+    """    
+    if row.hqta_type == "major_stop_bus":
+        if row.schedule_gtfs_dataset_key_primary != row.schedule_gtfs_dataset_key_secondary:
+            return "intersection_2_bus_routes_different_operators"
+        else:
+            return "intersection_2_bus_routes_same_operator"  
+
+    elif row.hqta_type == "hq_corridor_bus":
+        if row.peak_trips >= 4:
+            return "corridor_frequent_stop"
+        else:
+            return "corridor_other_stop"
+
+    elif row.hqta_type in ["major_stop_ferry", 
+                           "major_stop_brt", "major_stop_rail"]:
+        return row.hqta_type + "_single_operator"
+
+def primary_rename(df: pd.DataFrame) -> pd.DataFrame:
+    return df.rename(
+        columns = {"schedule_gtfs_dataset_key": "schedule_gtfs_dataset_key_primary"})
+
+def clip_to_ca(gdf: gpd.GeoDataFrame) -> gpd.GeoDataFrame:
+    """
+    Clip to CA boundaries. 
+    """    
+    ca = catalog.ca_boundary.read().to_crs(gdf.crs)
+
+    gdf2 = gdf.clip(ca, keep_geom_type = False).reset_index(drop=True)
+
+    return gdf2