Sccp lpp 2024a

rt_delay/rt_analysis/rt_filter_map_plot.py

@@ -720,7 +720,7 @@ def quick_map_corridor(self):
             selector = select(_.geometry, _.total_speed_delay, _.total_schedule_delay)
         else:
             selector = select(_.geometry, _.total_speed_delay)
-        gdf = (self.corridor >> selector).iloc[:1,:]
+        gdf = (self.corridor >> selector).dissolve()
         m = pd.concat([mappable_stops, gdf]).explore(tiles = "CartoDB positron")
         return m
 
@@ -814,8 +814,9 @@ def corridor_metrics(self, sccp = False):
                               >> mutate(new_avg_trips_hr = ((_.n_trips + _.trips_added) / _.span_hours) / 2)
                               # create avg per direction by div 2
                           )
-        both_metrics_df['length_miles'] = (self.corridor.distance_meters / METERS_PER_MILE).iloc[0]
-        both_metrics_df['distance_meters'] = self.corridor.distance_meters
+        if 'distance_meters' in self.corridor.columns:
+            both_metrics_df['length_miles'] = (self.corridor.distance_meters / METERS_PER_MILE).iloc[0]
+            both_metrics_df['distance_meters'] = self.corridor.distance_meters
         both_metrics_df['target_mph'] = self.transit_priority_target_mph
         # both_metrics_df.length_miles = both_metrics_df.length_miles.fillna(value=gdf.length_miles.iloc[0])
         gdf = gpd.GeoDataFrame(both_metrics_df, geometry=self.corridor.geometry, crs=self.corridor.crs)

rt_delay/rt_analysis/sccp_tools.py

@@ -19,15 +19,14 @@ def sccp_average_metrics(itp_id: int, date_range: np.arange, corridor: gpd.GeoDa
     schedule_metrics = []
     speed_metrics = []
     for date in date_range:
-        date = date.astype(dt.date)
         try:
             rt_day = rt_filter_map_plot.from_gcs(itp_id, date)
             rt_day.add_corridor(corridor)
             if filter_dict:
                 rt_day.set_filter(**filter_dict)
-            metrics = rt_day.corridor_metrics()
-            schedule_metrics += [metrics['schedule_metric_minutes']]
-            speed_metrics += [metrics['speed_metric_minutes']]
+            metrics = rt_day.corridor_metrics(sccp=True)
+            schedule_metrics += [metrics['schedule_delay_minutes'].sum()]
+            speed_metrics += [metrics['speed_delay_minutes'].sum()]
             print(f'complete for date: {date}')
         except Exception as e:
             print(f'failed for date: {date}')

sccp/0_sccp_refactor_scratchpad.ipynb

@@ -0,0 +1,335 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "d528f399-cf33-459e-b5dc-92e0b4ae389a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import geopandas as gpd\n",
+    "from siuba import *\n",
+    "import shared_utils\n",
+    "\n",
+    "from calitp_data_analysis import get_fs\n",
+    "from segment_speed_utils import helpers, time_series_utils, gtfs_schedule_wrangling\n",
+    "from segment_speed_utils.project_vars import SCHED_GCS, SEGMENT_GCS, GTFS_DATA_DICT, analysis_date"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "6cd318e5-5c4e-4249-b158-232f4d940770",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "catalog = shared_utils.catalog_utils.get_catalog('gtfs_analytics_data')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6e86c1a8-d3de-4fc6-9478-c03133b6745c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'dir': '${gcs_paths.SEGMENT_GCS}', 'stage1': '${speeds_tables.vp_dwell}', 'stage2': 'nearest/nearest_vp_shape_segments', 'stage2b': 'nearest/nearest2_vp_shape_segments', 'stage3': 'stop_arrivals', 'stage4': 'speeds_stop_segments', 'trip_stop_cols': ['trip_instance_key', 'stop_sequence'], 'shape_stop_cols': ['shape_array_key', 'shape_id', 'stop_sequence'], 'stop_pair_cols': ['stop_pair', 'stop_pair_name'], 'route_dir_cols': ['route_id', 'direction_id'], 'shape_stop_single_segment': 'rollup_singleday/speeds_shape_stop_segments', 'route_dir_single_segment': 'rollup_singleday/speeds_route_dir_segments', 'route_dir_multi_segment': 'rollup_multiday/speeds_route_dir_segments', 'segments_file': 'segment_options/shape_stop_segments', 'max_speed': '${speed_vars.max_speed}'}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "catalog.stop_segments"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "f766b50a-c70d-4681-992c-d7f8979ada69",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'2024-10-16'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "analysis_date"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a5dbe9fc-5997-4232-ae4b-980dd5dff349",
+   "metadata": {},
+   "source": [
+    "## wait, isn't 'rt_stop_times' what I need?\n",
+    "\n",
+    "* I basically need the same data Amanda's using for bunching, except I do also care about schedule"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "74a301dc-4455-430a-8209-79ed5d431026",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'dir': '${gcs_paths.SEGMENT_GCS}', 'stage1': '${speeds_tables.vp_dwell}', 'stage2': 'nearest/nearest_vp_rt_stop_times', 'stage2b': 'nearest/nearest2_vp_rt_stop_times', 'stage3': 'rt_stop_times/stop_arrivals', 'stage4': 'rt_stop_times/speeds', 'trip_stop_cols': ['trip_instance_key', 'stop_sequence'], 'shape_stop_cols': ['shape_array_key', 'shape_id', 'stop_sequence'], 'stop_pair_cols': ['stop_pair', 'stop_pair_name'], 'route_dir_cols': ['route_id', 'direction_id'], 'segments_file': 'segment_options/stop_segments', 'trip_speeds_single_summary': 'rollup_singleday/speeds_trip', 'route_dir_single_summary': 'rollup_singleday/speeds_route_dir', 'route_dir_multi_summary': 'rollup_multiday/speeds_route_dir', 'min_trip_minutes': '${speed_vars.time_min_cutoff}', 'max_trip_minutes': 180, 'max_speed': '${speed_vars.max_speed}', 'min_meters_elapsed': 1609}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "catalog.rt_stop_times"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4c8f882f-a60f-4007-9062-6c998088d808",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'dir': '${gcs_paths.RT_SCHED_GCS}', 'stop_times_direction': 'stop_times_direction', 'sched_trip_metrics': 'schedule_trip/schedule_trip_metrics', 'sched_route_direction_metrics': 'schedule_route_dir/schedule_route_direction_metrics', 'vp_trip_metrics': 'vp_trip/trip_metrics', 'vp_route_direction_metrics': 'vp_route_dir/route_direction_metrics', 'vp_operator_metrics': 'vp_operator/operator_metrics', 'sched_stop_metrics': 'schedule_stop/schedule_stop_metrics', 'schedule_rt_stop_times': 'schedule_rt_stop_times', 'early_trip_minutes': -5, 'late_trip_minutes': 5}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "catalog.rt_vs_schedule_tables"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "294b8f67-1486-48e9-8fe9-015b009d8e53",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path = f'{catalog.schedule_downloads.dir}{catalog.schedule_downloads.trips}_{analysis_date}.parquet'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "508d38d4-086c-43e6-8044-6ded0882e105",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'gs://calitp-analytics-data/data-analyses/rt_delay/compiled_cached_views/trips_2024-10-16.parquet'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "path"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "dc3543ea-2544-4917-887e-9de4441fb460",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trips = pd.read_parquet(path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "7c8ec6df-fd29-4a16-a063-7e03af3dd9d7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path = f'{catalog.rt_vs_schedule_tables.dir}{catalog.rt_vs_schedule_tables.schedule_rt_stop_times}_{analysis_date}.parquet'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "9d95c8be-a1d7-4b9f-814f-57f295d3d1df",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "schedule_rt = pd.read_parquet(path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "a5a84ce0-3ae4-41c7-a8fb-82caea7aa268",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>trip_id</th>\n",
+       "      <th>stop_id</th>\n",
+       "      <th>stop_sequence</th>\n",
+       "      <th>scheduled_arrival_sec</th>\n",
+       "      <th>schedule_gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>rt_arrival_sec</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>t_5912118_b_83127_tn_0</td>\n",
+       "      <td>7728100</td>\n",
+       "      <td>5</td>\n",
+       "      <td>25426.0</td>\n",
+       "      <td>09e16227fc42c4fe90204a9d11581034</td>\n",
+       "      <td>893cb960f2ca78f823bd67adee30eaa3</td>\n",
+       "      <td>25434</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>t_5912118_b_83127_tn_0</td>\n",
+       "      <td>7728400</td>\n",
+       "      <td>8</td>\n",
+       "      <td>25559.0</td>\n",
+       "      <td>09e16227fc42c4fe90204a9d11581034</td>\n",
+       "      <td>893cb960f2ca78f823bd67adee30eaa3</td>\n",
+       "      <td>25594</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>t_5912118_b_83127_tn_0</td>\n",
+       "      <td>7728900</td>\n",
+       "      <td>12</td>\n",
+       "      <td>25768.0</td>\n",
+       "      <td>09e16227fc42c4fe90204a9d11581034</td>\n",
+       "      <td>893cb960f2ca78f823bd67adee30eaa3</td>\n",
+       "      <td>25751</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  trip_id  stop_id  stop_sequence  scheduled_arrival_sec  \\\n",
+       "0  t_5912118_b_83127_tn_0  7728100              5                25426.0   \n",
+       "1  t_5912118_b_83127_tn_0  7728400              8                25559.0   \n",
+       "2  t_5912118_b_83127_tn_0  7728900             12                25768.0   \n",
+       "\n",
+       "          schedule_gtfs_dataset_key                 trip_instance_key  \\\n",
+       "0  09e16227fc42c4fe90204a9d11581034  893cb960f2ca78f823bd67adee30eaa3   \n",
+       "1  09e16227fc42c4fe90204a9d11581034  893cb960f2ca78f823bd67adee30eaa3   \n",
+       "2  09e16227fc42c4fe90204a9d11581034  893cb960f2ca78f823bd67adee30eaa3   \n",
+       "\n",
+       "   rt_arrival_sec  \n",
+       "0           25434  \n",
+       "1           25594  \n",
+       "2           25751  "
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "schedule_rt >> head(3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "158d8fe4-4640-4ae9-84aa-e4b8391f6bdf",
+   "metadata": {},
+   "source": [
+    "Good, but we don't have distance (and thus speed) available..."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0ef4a641-283b-4b68-bce7-8e3d9beb51c9",
+   "metadata": {},
+   "source": [
+    "get from cut segments?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ceba93c9-accd-4da7-b77c-6c0a7786cb01",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version_major": 2,
+    "version_minor": 0
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

sccp/corridors_sccp_lpp/2024/beaumont_map.geojson

@@ -0,0 +1 @@
+{"type":"FeatureCollection","features":[{"type":"Feature","properties":{},"geometry":{"coordinates":[[[-116.99044694002112,33.926399060021296],[-116.99044694002112,33.92403782209635],[-116.98813434742624,33.92403782209635],[-116.98813434742624,33.926399060021296],[-116.99044694002112,33.926399060021296]]],"type":"Polygon"}}]}