diff --git a/rt_scheduled_v_ran/02_spatial.ipynb b/rt_scheduled_v_ran/02_spatial.ipynb
new file mode 100644
index 000000000..4bdb9ebb3
--- /dev/null
+++ b/rt_scheduled_v_ran/02_spatial.ipynb
@@ -0,0 +1,7402 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c410afe6-22d7-4546-817c-fea818954108",
+   "metadata": {},
+   "source": [
+    "# Migrate to VP Usable\n",
+    "* https://github.com/cal-itp/data-analyses/issues/936\n",
+    "* cd rt_segment_speeds && pip install -r requirements.txt && cd ..\n",
+    "    * https://github.com/cal-itp/data-analyses/blob/main/Makefile#L49C2-L49C66\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8de007c5-4cdb-4285-9536-0a5f7b75b2de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import datetime\n",
+    "import dask.dataframe as dd\n",
+    "import dask_geopandas as dg\n",
+    "import dask\n",
+    "import geopandas as gpd\n",
+    "import pandas as pd\n",
+    "from scripts import vp_spatial_accuracy\n",
+    "from segment_speed_utils import helpers\n",
+    "from calitp_data_analysis.geography_utils import WGS84\n",
+    "from segment_speed_utils.project_vars import (\n",
+    "    PROJECT_CRS,\n",
+    "    SEGMENT_GCS,\n",
+    "    analysis_date,\n",
+    "    GCS_FILE_PATH,\n",
+    "    COMPILED_CACHED_VIEWS,\n",
+    "    RT_SCHED_GCS,\n",
+    "    CONFIG_PATH\n",
+    ")\n",
+    "\n",
+    "# For speeds c2\n",
+    "from typing import Literal\n",
+    "import numpy as np\n",
+    "\n",
+    "# for speeds c3\n",
+    "# also import numpy \n",
+    "from shared_utils.rt_utils import MPH_PER_MPS\n",
+    "from calitp_data_analysis import utils\n",
+    "from shared_utils import portfolio_utils, schedule_rt_utils\n",
+    "from segment_speed_utils import helpers, sched_rt_utils, wrangle_shapes, segment_calcs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c5ba79eb-2d4e-4daa-9de6-3ab657ac0a15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pd.options.display.max_columns = 100\n",
+    "pd.options.display.float_format = \"{:.2f}\".format\n",
+    "pd.set_option(\"display.max_rows\", None)\n",
+    "pd.set_option(\"display.max_colwidth\", None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "d8c8f895-8b72-413a-8ec2-72e7e0ebf29f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# calitp-analytics-data/data-analyses/rt_segment_speeds/vp_usable_2023-10-11\n",
+    "operator = 'Bay Area 511 Muni VehiclePositions'\n",
+    "gtfs_key = '7cc0cb1871dfd558f11a2885c145d144'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a3863c86-7f53-4755-8444-534a2f11e59c",
+   "metadata": {},
+   "source": [
+    "## Spatial Accuracy\n",
+    "* Based on https://github.com/cal-itp/data-analyses/blob/main/rt_scheduled_v_ran/scripts/vp_spatial_accuracy.py\n",
+    "### Grab_shape_keys_in_vp\n",
+    "#### First time reading `vp_usable`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "6bd6833a-7eb4-487a-bb3a-e445a2d1941d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def grab_shape_keys_in_vp(analysis_date: str) -> pd.DataFrame:\n",
+    "    \"\"\"\n",
+    "    Subset raw vp and find unique trip_instance_keys.\n",
+    "    Create crosswalk to link trip_instance_key to shape_array_key.\n",
+    "    \"\"\"\n",
+    "    vp_trip_df  = pd.read_parquet(f\"{SEGMENT_GCS}vp_usable_{analysis_date}\",\n",
+    "        filters = [[('gtfs_dataset_name', \"==\", operator),\n",
+    "                   ('schedule_gtfs_dataset_key', '==', gtfs_key)]],\n",
+    "        columns = ['trip_instance_key'])\n",
+    "    \n",
+    "    vp_trip_df  = vp_trip_df.drop_duplicates().reset_index(drop = True)\n",
+    "    \n",
+    "    # Make sure we have a shape geometry too\n",
+    "    # otherwise map_partitions will throw error\n",
+    "    shapes = pd.read_parquet(\n",
+    "        f\"{COMPILED_CACHED_VIEWS}routelines_{analysis_date}.parquet\",\n",
+    "        columns = [\"shape_array_key\"],\n",
+    "    ).dropna().drop_duplicates()\n",
+    "    \n",
+    "    trips_with_shape = helpers.import_scheduled_trips(\n",
+    "        analysis_date,\n",
+    "        columns = [\"trip_instance_key\", \"shape_array_key\"],\n",
+    "        get_pandas = True\n",
+    "    ).merge(\n",
+    "        shapes,\n",
+    "        on = \"shape_array_key\",\n",
+    "        how = \"inner\"\n",
+    "    ).merge(\n",
+    "        vp_trip_df,\n",
+    "        on = \"trip_instance_key\",\n",
+    "        how = \"inner\"\n",
+    "    ).drop_duplicates().dropna().reset_index(drop=True)\n",
+    "\n",
+    "    return trips_with_shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "8759e976-ea60-4604-945d-1ec9693b0495",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trips_with_shape = grab_shape_keys_in_vp(analysis_date)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "bbbc85b4-a588-4f20-9822-eb4d5b4b3723",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(9240, 2)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trips_with_shape.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "34f69e0d-68c8-4b8e-8b82-8318672d0f4d",
+   "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_instance_key</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>12de3d260e9fe09fa878cb4cdb2d6898</td>\n",
+       "      <td>749b225ca6691f77914e88577dc13e68</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>934aea5748bce830ffc2fa88dc01402a</td>\n",
+       "      <td>749b225ca6691f77914e88577dc13e68</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3d06fa8e68e4f38d3ccc7adfabb5c3d9</td>\n",
+       "      <td>f1a7410fae06937b7183f6a553707915</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>34109ad8cfeca83cd459d42c7d51d602</td>\n",
+       "      <td>f1a7410fae06937b7183f6a553707915</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>34acd907ae9d5eb5456d683d2458bbc6</td>\n",
+       "      <td>f1a7410fae06937b7183f6a553707915</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  trip_instance_key                   shape_array_key\n",
+       "0  12de3d260e9fe09fa878cb4cdb2d6898  749b225ca6691f77914e88577dc13e68\n",
+       "1  934aea5748bce830ffc2fa88dc01402a  749b225ca6691f77914e88577dc13e68\n",
+       "2  3d06fa8e68e4f38d3ccc7adfabb5c3d9  f1a7410fae06937b7183f6a553707915\n",
+       "3  34109ad8cfeca83cd459d42c7d51d602  f1a7410fae06937b7183f6a553707915\n",
+       "4  34acd907ae9d5eb5456d683d2458bbc6  f1a7410fae06937b7183f6a553707915"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trips_with_shape.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8be73ca3-7ca2-4616-9504-7defe86f3792",
+   "metadata": {},
+   "source": [
+    "### Buffer shapes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ca9923a7-914f-43ce-a840-a15d41b43aee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This is trips_with_shape_geom\n",
+    "trips_with_shape_geom =  vp_spatial_accuracy.buffer_shapes(analysis_date, \n",
+    "                                trips_with_shape,\n",
+    "                                35)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "caf4dd49-4839-475d-99ff-7765ef5fb20a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(9240, 3)"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trips_with_shape_geom.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fc115ac6-2042-4565-9ac7-bd961339f8aa",
+   "metadata": {},
+   "source": [
+    "#### Second time reading in the same file, streamline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "beaddbc2-fd11-4021-bdf0-7eea81835226",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vp = dd.read_parquet(f\"{SEGMENT_GCS}vp_usable_{analysis_date}\",\n",
+    "        filters = [[('gtfs_dataset_name', \"==\", operator),\n",
+    "                   ('schedule_gtfs_dataset_key', '==', gtfs_key)]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "6053ea36-1f85-4a1a-b10b-019f6d870986",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "trip_instance_key    9240\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vp[['trip_instance_key']].compute().nunique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "384c1e89-0b57-49dd-aaa0-69ea03e25b23",
+   "metadata": {},
+   "source": [
+    "### Full function"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "79fe772c-74db-49e7-b41d-e1daa3f23ee3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def merge_vp_with_shape_and_count(\n",
+    "    vp: dd.DataFrame,\n",
+    "    trips_with_shape_geom: gpd.GeoDataFrame\n",
+    ") -> gpd.GeoDataFrame:\n",
+    "    \"\"\"\n",
+    "    Merge vp with crosswalk and buffered shapes.\n",
+    "    Get vp count totals and vp within shape.\n",
+    "    \"\"\"\n",
+    "    vp_gdf = gpd.GeoDataFrame(\n",
+    "        vp,\n",
+    "        geometry = gpd.points_from_xy(vp.x, vp.y),\n",
+    "        crs = WGS84\n",
+    "    ).to_crs(PROJECT_CRS)\n",
+    "    \n",
+    "    vp_gdf = vp_gdf.rename(columns = {\n",
+    "    0:'gtfs_dataset_name',\n",
+    "    1: 'schedule_gtfs_dataset_key', \n",
+    "    2:'trip_id',\n",
+    "    3:'trip_instance_key',\n",
+    "    4: 'location_timestamp', \n",
+    "    5: 'location_timestamp_local',\n",
+    "    6:'x',\n",
+    "    7:'y', \n",
+    "    8:'vp_idx', \n",
+    "    9:'gtfs_dataset_key', \n",
+    "    10:'vp_dir_xnorm', \n",
+    "    11:'vp_dir_ynorm',\n",
+    "    12:'vp_primary_direction'})\n",
+    "    \n",
+    "    vp2 = pd.merge(\n",
+    "        vp_gdf,\n",
+    "        trips_with_shape_geom,\n",
+    "        on = \"trip_instance_key\",\n",
+    "        how = \"inner\"\n",
+    "    ).reset_index(drop=True)\n",
+    "    \n",
+    "    total_vp = vp_spatial_accuracy.total_vp_counts_by_trip(vp2)\n",
+    "    \n",
+    "    vp2 = vp2.assign(\n",
+    "        is_within = vp2.geometry_x.within(vp2.geometry_y)\n",
+    "    ).query('is_within==True')\n",
+    "    \n",
+    "    vps_in_shape = (vp2.groupby(\"trip_instance_key\", \n",
+    "                                observed = True, group_keys = False)\n",
+    "                    .agg({\"location_timestamp_local\": \"count\"})\n",
+    "                    .reset_index()\n",
+    "                    .rename(columns = {\"location_timestamp_local\": \"vp_in_shape\"})\n",
+    "                   )\n",
+    "        \n",
+    "    count_df = pd.merge(\n",
+    "        total_vp,\n",
+    "        vps_in_shape,\n",
+    "        on = \"trip_instance_key\",\n",
+    "        how = \"left\"\n",
+    "    )\n",
+    "    \n",
+    "    count_df = count_df.assign(\n",
+    "        vp_in_shape = count_df.vp_in_shape.fillna(0).astype(\"int32\"),\n",
+    "        total_vp = count_df.total_vp.fillna(0).astype(\"int32\")\n",
+    "    )\n",
+    "    \n",
+    "    return count_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "561287f4-8189-441c-881c-1f34fc43e7d5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "muni = merge_vp_with_shape_and_count(vp, trips_with_shape_geom)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "bcaa5da2-21a5-4c87-825a-fa2637ef9b8f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count   9240.00\n",
+       "mean     161.87\n",
+       "std       64.06\n",
+       "min        0.00\n",
+       "25%      118.00\n",
+       "50%      167.00\n",
+       "75%      207.00\n",
+       "max      481.00\n",
+       "Name: vp_in_shape, dtype: float64"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "muni.vp_in_shape.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "3504f86b-08bd-4a8d-b810-e654dd911c06",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9240"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "muni.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b03b76bf-2ce3-4400-b072-f53c9f942deb",
+   "metadata": {},
+   "source": [
+    "#### Add %?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "4b0f141c-e583-4bb2-a3a7-f059e27a66fc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count   9240.00\n",
+       "mean       0.93\n",
+       "std        0.14\n",
+       "min        0.00\n",
+       "25%        0.94\n",
+       "50%        1.00\n",
+       "75%        1.00\n",
+       "max        1.00\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "(muni.vp_in_shape/muni.total_vp).describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0a306082-dcfc-4a4a-bc3b-5ee90ae9517d",
+   "metadata": {},
+   "source": [
+    "#### Question: We are keeping rows in which 0 vps are in the shape?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "eaa02c27-eda6-47ac-ae18-827f1616d73e",
+   "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_instance_key</th>\n",
+       "      <th>total_vp</th>\n",
+       "      <th>vp_in_shape</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>167</th>\n",
+       "      <td>04ae6ea9655473bdcaf9b80d443558ae</td>\n",
+       "      <td>111</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>351</th>\n",
+       "      <td>0a1553b7a738967a422b7b8960560ded</td>\n",
+       "      <td>75</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>408</th>\n",
+       "      <td>0bc53a1063efae8a32eca4a9034d2a21</td>\n",
+       "      <td>61</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1128</th>\n",
+       "      <td>1fe28ce8669a7f946f272faf80d80ce7</td>\n",
+       "      <td>70</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1981</th>\n",
+       "      <td>37aed2e5ad125f8aede20922b38bf6b9</td>\n",
+       "      <td>78</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3022</th>\n",
+       "      <td>54e54e2839a6945b1005322398a89ae9</td>\n",
+       "      <td>132</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3127</th>\n",
+       "      <td>580684a7a6b43ce5130f60a441681713</td>\n",
+       "      <td>46</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3213</th>\n",
+       "      <td>5a82f8c02f2036db77b1979f4ae228f5</td>\n",
+       "      <td>41</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3861</th>\n",
+       "      <td>6cbdc2d321ca63df78bce01eeb06fe07</td>\n",
+       "      <td>47</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3937</th>\n",
+       "      <td>6ee4a9165f47b59cb3e10b0125dd72e8</td>\n",
+       "      <td>34</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4562</th>\n",
+       "      <td>7ff345e91303290951ef0665a57dc90e</td>\n",
+       "      <td>55</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5288</th>\n",
+       "      <td>9351c60516ef43464d962a956d1b3806</td>\n",
+       "      <td>96</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5894</th>\n",
+       "      <td>a40cc2271f048e2b72d94b051c6688cb</td>\n",
+       "      <td>120</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6119</th>\n",
+       "      <td>aa82ee2a81331cbdf044a7d5280d436a</td>\n",
+       "      <td>41</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6758</th>\n",
+       "      <td>bcb78da06a56761d2a3b8b16a3436f3d</td>\n",
+       "      <td>101</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7043</th>\n",
+       "      <td>c3fc63ec2ff7a35c0f821659075be708</td>\n",
+       "      <td>60</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7543</th>\n",
+       "      <td>d21ff3a0d37a484dc4f979d052652565</td>\n",
+       "      <td>45</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7734</th>\n",
+       "      <td>d79da0eafb4ac5188f1cd14850a6f880</td>\n",
+       "      <td>90</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8431</th>\n",
+       "      <td>ea8751445dcd6a175bd23ec5fc423d0c</td>\n",
+       "      <td>44</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8718</th>\n",
+       "      <td>f298ef83aaa934eb6577fd2ca19d4ebd</td>\n",
+       "      <td>82</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     trip_instance_key  total_vp  vp_in_shape\n",
+       "167   04ae6ea9655473bdcaf9b80d443558ae       111            0\n",
+       "351   0a1553b7a738967a422b7b8960560ded        75            0\n",
+       "408   0bc53a1063efae8a32eca4a9034d2a21        61            0\n",
+       "1128  1fe28ce8669a7f946f272faf80d80ce7        70            0\n",
+       "1981  37aed2e5ad125f8aede20922b38bf6b9        78            0\n",
+       "3022  54e54e2839a6945b1005322398a89ae9       132            0\n",
+       "3127  580684a7a6b43ce5130f60a441681713        46            0\n",
+       "3213  5a82f8c02f2036db77b1979f4ae228f5        41            0\n",
+       "3861  6cbdc2d321ca63df78bce01eeb06fe07        47            0\n",
+       "3937  6ee4a9165f47b59cb3e10b0125dd72e8        34            0\n",
+       "4562  7ff345e91303290951ef0665a57dc90e        55            0\n",
+       "5288  9351c60516ef43464d962a956d1b3806        96            0\n",
+       "5894  a40cc2271f048e2b72d94b051c6688cb       120            0\n",
+       "6119  aa82ee2a81331cbdf044a7d5280d436a        41            0\n",
+       "6758  bcb78da06a56761d2a3b8b16a3436f3d       101            0\n",
+       "7043  c3fc63ec2ff7a35c0f821659075be708        60            0\n",
+       "7543  d21ff3a0d37a484dc4f979d052652565        45            0\n",
+       "7734  d79da0eafb4ac5188f1cd14850a6f880        90            0\n",
+       "8431  ea8751445dcd6a175bd23ec5fc423d0c        44            0\n",
+       "8718  f298ef83aaa934eb6577fd2ca19d4ebd        82            0"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "muni.loc[muni.vp_in_shape == 0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "ad776dcd-700e-499e-b1c2-57c44d255153",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "trip_instance_key    9240\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vp[['trip_instance_key']].compute().nunique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "19a20f72-8a90-4823-8cc5-32f91ae1286d",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Update Completeness\n",
+    "* https://github.com/cal-itp/data-analyses/blob/main/rt_predictions/01_update_completeness.ipynb\n",
+    "\n",
+    "#### Keep only relevant `trips instance keys`?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "b2e0fa2d-089d-49a5-ab20-a8ef65925795",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Only use the trips with shapes.\n",
+    "relevant_trips = list(muni.trip_instance_key.unique())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0e0e963e-ce3a-43bd-b5eb-209af2524e0f",
+   "metadata": {},
+   "source": [
+    "#### Third time reading in `vp_usable`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "845ad61c-eab0-40c9-9e50-09c35bd50a73",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "completeness_cols = ['vp_idx',\n",
+    "      'location_timestamp_local', 'trip_instance_key',\n",
+    "      'gtfs_dataset_key']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "88b571f2-624c-47aa-a154-286902fa4a96",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vp_filtered = dd.read_parquet(f\"{SEGMENT_GCS}vp_usable_{analysis_date}\",\n",
+    "        columns = completeness_cols, \n",
+    "        filters = [[('gtfs_dataset_name', \"==\", operator),\n",
+    "                   ('schedule_gtfs_dataset_key', '==', gtfs_key),\n",
+    "                   ('trip_instance_key', 'in', relevant_trips)]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "8b1174c1-b693-40fd-94c6-16152a2a3cd7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fresh_updates = vp_filtered.sort_values(['vp_idx']).reset_index(drop = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "222d4f15-1fde-4194-b2bd-a10a50976336",
+   "metadata": {},
+   "source": [
+    "#### Question: Can't use dask for this type of groupby \n",
+    "* Also grouping only by `trip_instance_key` yields the best result..unsure if that's ok"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "add7de33-bf89-4ab1-a907-a5f6f399821e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "two_cols = ['trip_instance_key','gtfs_dataset_key']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "c9083d90-f232-4568-99f1-f92ccd98c5cc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fresh_updates_df = fresh_updates.compute()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "c9cd0c00-bdda-45c3-bb81-cc0556475501",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# fresh_updates_df = fresh_updates_df.assign(fresh = 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "201eab8e-893c-4a29-be9f-a1a81cafbbde",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\" DOES NOT WORK\\ntest_group1 = (fresh_updates_df.groupby([\\n        *two_cols, \\n         pd.Grouper(key = 'location_timestamp_local', freq = '1Min')\\n    ])\\n    .count()).reset_index() \""
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\" DOES NOT WORK\n",
+    "test_group1 = (fresh_updates_df.groupby([\n",
+    "        *two_cols, \n",
+    "         pd.Grouper(key = 'location_timestamp_local', freq = '1Min')\n",
+    "    ])\n",
+    "    .count()).reset_index() \"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "be48ea1f-b6e9-40b6-b121-2b9b744b86cb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_group2 = (fresh_updates_df.groupby([\n",
+    "        *['trip_instance_key'], \n",
+    "         pd.Grouper(key = 'location_timestamp_local', freq = '1Min')\n",
+    "    ])\n",
+    "    .count()\n",
+    "    .reset_index()\n",
+    "    .rename(columns = {'vp_idx':'number_of_pings_per_minute'})\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b9fa09c7-6406-4c72-9a61-e925fce8fa8d",
+   "metadata": {},
+   "source": [
+    "### Checks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "2b697668-d7e7-4803-a289-0fe8c2e681d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "key1 = \"38247cbee93b6f85d58bf1812ae553b9\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "c693d819-3cbc-4766-bdb2-0176a7340f55",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "key2 = \"fac53ed1db7d914cc4c1857e967344f4\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "c00f7968-5ada-4623-8881-4d7607b86e5a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "key3 = \"9e291393bf06763fb6c6fe950d6e8097\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "074357ed-2e23-45c9-913e-8e5092534627",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# test_group2.loc[test_group2.trip_instance_key == key1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "bc1bfbf4-d828-41ba-bc46-9f7bb687e123",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# fresh_updates_df.loc[fresh_updates_df.trip_instance_key == key1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "e3a6c25b-922e-4083-ba53-20193b441df3",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# test_group2.loc[test_group2.trip_instance_key == key2]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "f20ba29c-1554-4155-b3c8-56f806196939",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# fresh_updates_df.loc[fresh_updates_df.trip_instance_key == key2]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "0a1ab3be-8f3d-416e-9c18-3d2e365250c5",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# test_group2.loc[test_group2.trip_instance_key == key3]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "ec0f9c0a-0833-48e3-bf14-b00cd75aa560",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# fresh_updates_df.loc[fresh_updates_df.trip_instance_key == key3]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "5374f05c-3dfb-4e9d-a44f-1387b70c4434",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# (test_group2.fresh - test_group2.number_of_pings_per_minute).describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "c4f0f887-0bf1-4acd-9204-ce4180517fff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# test_group2.fresh.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "61617748-c555-4e88-b027-a7362cbb40f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_group2 = test_group2.assign(\n",
+    "        atleast2_trip_updates = test_group2.apply(\n",
+    "            lambda x: 1 if x[\"number_of_pings_per_minute\"] >= 2\n",
+    "            else 0, axis=1)\n",
+    "    )    \n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "f127aa0e-90f3-4946-a3c0-80c9b84aa101",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1    534886\n",
+       "0      6795\n",
+       "Name: atleast2_trip_updates, dtype: int64"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group2.atleast2_trip_updates.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ccd85839-5d29-4c0b-be92-bc6c86d3999a",
+   "metadata": {},
+   "source": [
+    "### Trip minutes is wrong\n",
+    "* Check w/ 38247cbee93b6f85d58bf1812ae553b9\n",
+    "* Began at 16:01:00, end at 17:00:000\n",
+    "* Skips having data: jumps from 4:38 to 4:54"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "079a4eb5-5708-407c-81a6-f88466e9e9df",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' DOES NOT WORK \\ntest_group2_grouped = (test_group2.groupby(two_cols)\\n           .agg({\\n               \"location_timestamp_local\": \"size\",\\n               \"atleast2_trip_updates\": \"sum\"})\\n           .reset_index()\\n          ).rename(columns = {\\n            \"location_timestamp_local\": \"trip_min_elapsed\"\\n    })\\n  '"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\" DOES NOT WORK \n",
+    "test_group2_grouped = (test_group2.groupby(two_cols)\n",
+    "           .agg({\n",
+    "               \"location_timestamp_local\": \"size\",\n",
+    "               \"atleast2_trip_updates\": \"sum\"})\n",
+    "           .reset_index()\n",
+    "          ).rename(columns = {\n",
+    "            \"location_timestamp_local\": \"trip_min_elapsed\"\n",
+    "    })\n",
+    "  \"\"\"  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "45f51f48-df0b-42ed-9f25-07534f2c2514",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# test_group2_grouped.loc[test_group2_grouped.trip_instance_key == key1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "5965a48a-dec8-444f-8f69-714c64c885ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_group2['max_time'] = test_group2.location_timestamp_local"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "d04cba0b-afd6-418a-a916-ea5fcea3f0a0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_group3 = (test_group2\n",
+    "                        .groupby(['trip_instance_key'])\n",
+    "                        .agg({'location_timestamp_local':'min','max_time':'max', \n",
+    "                             'atleast2_trip_updates':'sum'})\n",
+    "                        .reset_index()\n",
+    "                        .rename(columns = {'location_timestamp_local':'min_time'})\n",
+    "                       )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "id": "cdbcc81c-1dc4-4111-808e-c3590568d163",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_group3['trip_min_elapsed'] = (test_group3.max_time - test_group3.min_time) / pd.Timedelta(minutes=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "id": "753d1d27-8813-4cdf-bf9f-dc5193f908f7",
+   "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_instance_key</th>\n",
+       "      <th>min_time</th>\n",
+       "      <th>max_time</th>\n",
+       "      <th>atleast2_trip_updates</th>\n",
+       "      <th>trip_min_elapsed</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2002</th>\n",
+       "      <td>38247cbee93b6f85d58bf1812ae553b9</td>\n",
+       "      <td>2023-10-11 16:01:00</td>\n",
+       "      <td>2023-10-11 17:00:00</td>\n",
+       "      <td>45</td>\n",
+       "      <td>59.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     trip_instance_key            min_time  \\\n",
+       "2002  38247cbee93b6f85d58bf1812ae553b9 2023-10-11 16:01:00   \n",
+       "\n",
+       "                max_time  atleast2_trip_updates  trip_min_elapsed  \n",
+       "2002 2023-10-11 17:00:00                     45             59.00  "
+      ]
+     },
+     "execution_count": 46,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.loc[test_group3.trip_instance_key == key1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "d4e45b96-5809-49a0-840e-112efc568a8e",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# test_group2.loc[test_group2.trip_instance_key == key1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "366efe58-3194-4fd9-9b86-a4aab10cf003",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "\n",
+    "# fresh_updates_df.loc[fresh_updates_df.trip_instance_key == key1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "df84e20f-33e4-4c93-bc09-ddf2f85b5ae2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(133, 4)"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\n",
+    "fresh_updates_df.loc[fresh_updates_df.trip_instance_key == key1].shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "bf6654a0-01bf-4ae3-8158-133d9e5aeb91",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_group3 = test_group3.assign(\n",
+    "        pct_update_complete = test_group3.atleast2_trip_updates.divide(\n",
+    "            test_group3.trip_min_elapsed)\n",
+    "    ) "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "12805755-8e1c-44f1-bd4b-bf0308757367",
+   "metadata": {},
+   "source": [
+    "### Some trips experiencing pct-update-complete greater than 100%\n",
+    "* They have more rows than trip_min_elapsed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "60cfbabc-e181-4004-9e08-9ff7b80fceae",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3701"
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(test_group3.loc[test_group3.pct_update_complete > 1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "id": "6e745fec-c6c0-4f0a-b618-44a252f36b9a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9240"
+      ]
+     },
+     "execution_count": 52,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(test_group3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "a76fce93-01f6-43ec-a12b-0929883673b7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count   9240.00\n",
+       "mean       1.00\n",
+       "std        0.06\n",
+       "min        0.02\n",
+       "25%        1.00\n",
+       "50%        1.00\n",
+       "75%        1.02\n",
+       "max        1.10\n",
+       "Name: pct_update_complete, dtype: float64"
+      ]
+     },
+     "execution_count": 53,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.pct_update_complete.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "ca5b2186-0b89-47fa-8d34-437b6f26849e",
+   "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_instance_key</th>\n",
+       "      <th>min_time</th>\n",
+       "      <th>max_time</th>\n",
+       "      <th>atleast2_trip_updates</th>\n",
+       "      <th>trip_min_elapsed</th>\n",
+       "      <th>pct_update_complete</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1486</th>\n",
+       "      <td>2a9fb1144c567b98582f7dc025182ef0</td>\n",
+       "      <td>2023-10-11 10:20:00</td>\n",
+       "      <td>2023-10-11 10:30:00</td>\n",
+       "      <td>11</td>\n",
+       "      <td>10.00</td>\n",
+       "      <td>1.10</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     trip_instance_key            min_time  \\\n",
+       "1486  2a9fb1144c567b98582f7dc025182ef0 2023-10-11 10:20:00   \n",
+       "\n",
+       "                max_time  atleast2_trip_updates  trip_min_elapsed  \\\n",
+       "1486 2023-10-11 10:30:00                     11             10.00   \n",
+       "\n",
+       "      pct_update_complete  \n",
+       "1486                 1.10  "
+      ]
+     },
+     "execution_count": 54,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.loc[test_group3.pct_update_complete == 1.1].sample()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "13103a30-dd21-4390-8b97-20c2f3b314ad",
+   "metadata": {},
+   "source": [
+    "#### How many cols have larger atleast2_trip_updates compared to trip-min_elapsed (delete later)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "6862f705-501d-4285-85db-8dd758aa04c7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_group3['larger'] =test_group3.trip_min_elapsed -  test_group3.atleast2_trip_updates "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "d8659d98-012a-4b2d-9825-e605df194cad",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count   9240.00\n",
+       "mean       0.29\n",
+       "std        3.82\n",
+       "min       -1.00\n",
+       "25%       -1.00\n",
+       "50%        0.00\n",
+       "75%        0.00\n",
+       "max      105.00\n",
+       "Name: larger, dtype: float64"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.larger.describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4512571b-d486-4490-bec0-6489f1b5d0f2",
+   "metadata": {},
+   "source": [
+    "#### One trip only recorded 2+ pings per minute in 36% of its duration"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "8e633abb-5030-4f83-a70a-2214b4017048",
+   "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_instance_key</th>\n",
+       "      <th>min_time</th>\n",
+       "      <th>max_time</th>\n",
+       "      <th>atleast2_trip_updates</th>\n",
+       "      <th>trip_min_elapsed</th>\n",
+       "      <th>pct_update_complete</th>\n",
+       "      <th>larger</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>3942</th>\n",
+       "      <td>6ef4805f0104b95614b86a2b1c374d23</td>\n",
+       "      <td>2023-10-11 17:48:00</td>\n",
+       "      <td>2023-10-11 20:31:00</td>\n",
+       "      <td>58</td>\n",
+       "      <td>163.00</td>\n",
+       "      <td>0.36</td>\n",
+       "      <td>105.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     trip_instance_key            min_time  \\\n",
+       "3942  6ef4805f0104b95614b86a2b1c374d23 2023-10-11 17:48:00   \n",
+       "\n",
+       "                max_time  atleast2_trip_updates  trip_min_elapsed  \\\n",
+       "3942 2023-10-11 20:31:00                     58            163.00   \n",
+       "\n",
+       "      pct_update_complete  larger  \n",
+       "3942                 0.36  105.00  "
+      ]
+     },
+     "execution_count": 57,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.loc[test_group3.larger == 105].sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "5787a3b6-375f-4488-a536-0c543a61f780",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "176"
+      ]
+     },
+     "execution_count": 58,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(fresh_updates_df.loc[fresh_updates_df.trip_instance_key == \"6ef4805f0104b95614b86a2b1c374d23\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9360550-2b92-406e-a37e-48347fec849d",
+   "metadata": {},
+   "source": [
+    "* Minutes skipped: 6:12 to 6:18\n",
+    "* 6:19-6:26\n",
+    "* 6:28-7:33 etc etc\n",
+    "* Trip started at 5:48, ended at 8:31 "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "id": "7b94e534-8dcb-4ed7-b864-4244d93a2ac1",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# test_group2.loc[test_group2.trip_instance_key == \"6ef4805f0104b95614b86a2b1c374d23\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "id": "75d05e56-5d6d-4e02-955e-f2ab7567526a",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# fresh_updates_df.loc[fresh_updates_df.trip_instance_key == \"6ef4805f0104b95614b86a2b1c374d23\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "53cb5d9e-be40-4989-a3b6-af2131c30075",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def mask_overly_large_min(row):\n",
+    "    if row.atleast2_trip_updates > row.trip_min_elapsed:\n",
+    "        return row.trip_min_elapsed\n",
+    "    else:\n",
+    "        return row.atleast2_trip_updates"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "id": "827559b6-f997-4842-a324-4d0f169b7607",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Apply the function: if the atleast2 trip updates is larger than trip_min_elapsed, mask it\n",
+    "# Or maybe just mask the pct-update-complete? \n",
+    "test_group3[\"test_mask\"] = test_group3.apply(mask_overly_large_min, axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "id": "8d94dc4f-88c0-4817-92ae-5b8b9957ef54",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_group3 = test_group3.assign(\n",
+    "        pct_update_complete2 = test_group3.test_mask.divide(\n",
+    "            test_group3.trip_min_elapsed)\n",
+    "    ) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "id": "bc39796b-aeea-4e95-b542-23d6eb5d87b3",
+   "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_instance_key</th>\n",
+       "      <th>min_time</th>\n",
+       "      <th>max_time</th>\n",
+       "      <th>atleast2_trip_updates</th>\n",
+       "      <th>trip_min_elapsed</th>\n",
+       "      <th>pct_update_complete</th>\n",
+       "      <th>larger</th>\n",
+       "      <th>test_mask</th>\n",
+       "      <th>pct_update_complete2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1510</th>\n",
+       "      <td>2b14ada5cb9e31a2c84b2a19b22c711a</td>\n",
+       "      <td>2023-10-11 13:10:00</td>\n",
+       "      <td>2023-10-11 14:37:00</td>\n",
+       "      <td>88</td>\n",
+       "      <td>87.00</td>\n",
+       "      <td>1.01</td>\n",
+       "      <td>-1.00</td>\n",
+       "      <td>87.00</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3938</th>\n",
+       "      <td>6ee775a74150b96abf9531462c6c69e0</td>\n",
+       "      <td>2023-10-11 02:59:00</td>\n",
+       "      <td>2023-10-11 03:30:00</td>\n",
+       "      <td>32</td>\n",
+       "      <td>31.00</td>\n",
+       "      <td>1.03</td>\n",
+       "      <td>-1.00</td>\n",
+       "      <td>31.00</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     trip_instance_key            min_time  \\\n",
+       "1510  2b14ada5cb9e31a2c84b2a19b22c711a 2023-10-11 13:10:00   \n",
+       "3938  6ee775a74150b96abf9531462c6c69e0 2023-10-11 02:59:00   \n",
+       "\n",
+       "                max_time  atleast2_trip_updates  trip_min_elapsed  \\\n",
+       "1510 2023-10-11 14:37:00                     88             87.00   \n",
+       "3938 2023-10-11 03:30:00                     32             31.00   \n",
+       "\n",
+       "      pct_update_complete  larger  test_mask  pct_update_complete2  \n",
+       "1510                 1.01   -1.00      87.00                  1.00  \n",
+       "3938                 1.03   -1.00      31.00                  1.00  "
+      ]
+     },
+     "execution_count": 64,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.loc[test_group3.larger == -1].sample(2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "52c81121-29bb-41ca-bd3a-cfe2b60f7989",
+   "metadata": {},
+   "source": [
+    "#### Ex of a trip: ten minute sbut eleven rows 37622040815e89d063272bb6e37acc65\n",
+    "* The trip is ten minutes but there are eleven rows."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "id": "749f3055-f199-4905-854b-cf208c969f26",
+   "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_instance_key</th>\n",
+       "      <th>min_time</th>\n",
+       "      <th>max_time</th>\n",
+       "      <th>atleast2_trip_updates</th>\n",
+       "      <th>trip_min_elapsed</th>\n",
+       "      <th>pct_update_complete</th>\n",
+       "      <th>larger</th>\n",
+       "      <th>test_mask</th>\n",
+       "      <th>pct_update_complete2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1972</th>\n",
+       "      <td>37622040815e89d063272bb6e37acc65</td>\n",
+       "      <td>2023-10-11 05:31:00</td>\n",
+       "      <td>2023-10-11 05:41:00</td>\n",
+       "      <td>11</td>\n",
+       "      <td>10.00</td>\n",
+       "      <td>1.10</td>\n",
+       "      <td>-1.00</td>\n",
+       "      <td>10.00</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     trip_instance_key            min_time  \\\n",
+       "1972  37622040815e89d063272bb6e37acc65 2023-10-11 05:31:00   \n",
+       "\n",
+       "                max_time  atleast2_trip_updates  trip_min_elapsed  \\\n",
+       "1972 2023-10-11 05:41:00                     11             10.00   \n",
+       "\n",
+       "      pct_update_complete  larger  test_mask  pct_update_complete2  \n",
+       "1972                 1.10   -1.00      10.00                  1.00  "
+      ]
+     },
+     "execution_count": 65,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.loc[test_group3.trip_instance_key == \"37622040815e89d063272bb6e37acc65\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 174,
+   "id": "b3a1f2f3-6981-4be6-bccb-8636e4430f65",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(11, 6)"
+      ]
+     },
+     "execution_count": 174,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group2.loc[test_group2.trip_instance_key == \"37622040815e89d063272bb6e37acc65\"].shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "id": "d109f168-9183-489d-9815-f179cc26e217",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1"
+      ]
+     },
+     "execution_count": 66,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(test_group3.loc[test_group3.trip_instance_key == \"37622040815e89d063272bb6e37acc65\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "id": "714e610c-018f-406c-abc9-8c69de0ff7a5",
+   "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_instance_key</th>\n",
+       "      <th>min_time</th>\n",
+       "      <th>max_time</th>\n",
+       "      <th>atleast2_trip_updates</th>\n",
+       "      <th>trip_min_elapsed</th>\n",
+       "      <th>pct_update_complete</th>\n",
+       "      <th>larger</th>\n",
+       "      <th>test_mask</th>\n",
+       "      <th>pct_update_complete2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1972</th>\n",
+       "      <td>37622040815e89d063272bb6e37acc65</td>\n",
+       "      <td>2023-10-11 05:31:00</td>\n",
+       "      <td>2023-10-11 05:41:00</td>\n",
+       "      <td>11</td>\n",
+       "      <td>10.00</td>\n",
+       "      <td>1.10</td>\n",
+       "      <td>-1.00</td>\n",
+       "      <td>10.00</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     trip_instance_key            min_time  \\\n",
+       "1972  37622040815e89d063272bb6e37acc65 2023-10-11 05:31:00   \n",
+       "\n",
+       "                max_time  atleast2_trip_updates  trip_min_elapsed  \\\n",
+       "1972 2023-10-11 05:41:00                     11             10.00   \n",
+       "\n",
+       "      pct_update_complete  larger  test_mask  pct_update_complete2  \n",
+       "1972                 1.10   -1.00      10.00                  1.00  "
+      ]
+     },
+     "execution_count": 67,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.loc[test_group3.trip_instance_key == \"37622040815e89d063272bb6e37acc65\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b54ee94-48e6-42ed-a87f-97ba04293589",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "#### 568caf4acf76125fb5db063f8737e5a8\n",
+    "* Trip is 73 minutes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "id": "f505e963-6dd7-4624-a2a0-324ade8c04b8",
+   "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_instance_key</th>\n",
+       "      <th>min_time</th>\n",
+       "      <th>max_time</th>\n",
+       "      <th>atleast2_trip_updates</th>\n",
+       "      <th>trip_min_elapsed</th>\n",
+       "      <th>pct_update_complete</th>\n",
+       "      <th>larger</th>\n",
+       "      <th>test_mask</th>\n",
+       "      <th>pct_update_complete2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>3077</th>\n",
+       "      <td>568caf4acf76125fb5db063f8737e5a8</td>\n",
+       "      <td>2023-10-11 08:32:00</td>\n",
+       "      <td>2023-10-11 09:45:00</td>\n",
+       "      <td>74</td>\n",
+       "      <td>73.00</td>\n",
+       "      <td>1.01</td>\n",
+       "      <td>-1.00</td>\n",
+       "      <td>73.00</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     trip_instance_key            min_time  \\\n",
+       "3077  568caf4acf76125fb5db063f8737e5a8 2023-10-11 08:32:00   \n",
+       "\n",
+       "                max_time  atleast2_trip_updates  trip_min_elapsed  \\\n",
+       "3077 2023-10-11 09:45:00                     74             73.00   \n",
+       "\n",
+       "      pct_update_complete  larger  test_mask  pct_update_complete2  \n",
+       "3077                 1.01   -1.00      73.00                  1.00  "
+      ]
+     },
+     "execution_count": 68,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.loc[test_group3.trip_instance_key == \"568caf4acf76125fb5db063f8737e5a8\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "id": "d8d800f1-e881-43f1-bd4e-699d93ba8aaf",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "74"
+      ]
+     },
+     "execution_count": 69,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(test_group2.loc[test_group2.trip_instance_key == \"568caf4acf76125fb5db063f8737e5a8\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "id": "b3a10c1f-afc5-4206-a79f-9c78b1df4854",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "221"
+      ]
+     },
+     "execution_count": 70,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(fresh_updates_df.loc[fresh_updates_df.trip_instance_key == \"568caf4acf76125fb5db063f8737e5a8\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "id": "fde7e3e4-2df8-48f3-a34a-545a5aef5f81",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9240"
+      ]
+     },
+     "execution_count": 71,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(test_group3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "id": "95a64572-3d15-4c47-ac93-1adb9c5f8d46",
+   "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_instance_key</th>\n",
+       "      <th>min_time</th>\n",
+       "      <th>max_time</th>\n",
+       "      <th>atleast2_trip_updates</th>\n",
+       "      <th>trip_min_elapsed</th>\n",
+       "      <th>pct_update_complete</th>\n",
+       "      <th>larger</th>\n",
+       "      <th>test_mask</th>\n",
+       "      <th>pct_update_complete2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>5128</th>\n",
+       "      <td>8f471c6d3f23a285b0e957db9431a89a</td>\n",
+       "      <td>2023-10-11 19:10:00</td>\n",
+       "      <td>2023-10-11 20:11:00</td>\n",
+       "      <td>61</td>\n",
+       "      <td>61.00</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>61.00</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8609</th>\n",
+       "      <td>efa2c7f74ba9cd19255dc54ec7f08ec0</td>\n",
+       "      <td>2023-10-11 13:04:00</td>\n",
+       "      <td>2023-10-11 14:05:00</td>\n",
+       "      <td>60</td>\n",
+       "      <td>61.00</td>\n",
+       "      <td>0.98</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>60.00</td>\n",
+       "      <td>0.98</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5646</th>\n",
+       "      <td>9d2e48287e1f9f7f907bc1c91a811ae3</td>\n",
+       "      <td>2023-10-11 08:38:00</td>\n",
+       "      <td>2023-10-11 09:22:00</td>\n",
+       "      <td>44</td>\n",
+       "      <td>44.00</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>44.00</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     trip_instance_key            min_time  \\\n",
+       "5128  8f471c6d3f23a285b0e957db9431a89a 2023-10-11 19:10:00   \n",
+       "8609  efa2c7f74ba9cd19255dc54ec7f08ec0 2023-10-11 13:04:00   \n",
+       "5646  9d2e48287e1f9f7f907bc1c91a811ae3 2023-10-11 08:38:00   \n",
+       "\n",
+       "                max_time  atleast2_trip_updates  trip_min_elapsed  \\\n",
+       "5128 2023-10-11 20:11:00                     61             61.00   \n",
+       "8609 2023-10-11 14:05:00                     60             61.00   \n",
+       "5646 2023-10-11 09:22:00                     44             44.00   \n",
+       "\n",
+       "      pct_update_complete  larger  test_mask  pct_update_complete2  \n",
+       "5128                 1.00    0.00      61.00                  1.00  \n",
+       "8609                 0.98    1.00      60.00                  0.98  \n",
+       "5646                 1.00    0.00      44.00                  1.00  "
+      ]
+     },
+     "execution_count": 72,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.sample(3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3b61450e-528c-4dab-9582-2bda3343e379",
+   "metadata": {},
+   "source": [
+    "## How many minutes a trip took and the average speeds?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "id": "36afb7b1-04f9-494b-a4d8-f85ddadc785b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# relevant_trips = list(test_group3.trip_instance_key.unique())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "96335b84-31a9-4887-b97f-8ebc35610220",
+   "metadata": {},
+   "source": [
+    "### C2 \n",
+    "* https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C2_triangulate_vp.py\n",
+    "* Break it apart and check it out later to undersatnd what's happening\n",
+    "* No need to `subset_usable_vp` because already filtered above."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "id": "de7fba7a-6796-4e64-884c-55d636be2c12",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def triangulate_vp(\n",
+    "    ddf: dd.DataFrame, \n",
+    "    group_cols: list = [\"trip_instance_key\"]\n",
+    ") -> np.ndarray:\n",
+    "    \"\"\"\n",
+    "    Grab a sample of vehicle positions for each trip to triangulate distance.\n",
+    "    These vp already sjoined onto the shape.\n",
+    "    Roughly pick vp at equally spaced intervals.\n",
+    "    \n",
+    "    Dask aggregation can't group and use lambda to create list of possible \n",
+    "    vp_idx.\n",
+    "    \"\"\"        \n",
+    "    grouped_ddf = ddf.groupby(group_cols, observed=True, group_keys=False)\n",
+    "\n",
+    "    min_df = (grouped_ddf\n",
+    "              .agg({\"vp_idx\": \"min\"})\n",
+    "              .rename(columns = {\"vp_idx\": \"min_vp_idx\"})\n",
+    "             )\n",
+    "\n",
+    "    max_df = (grouped_ddf\n",
+    "              .agg({\"vp_idx\": \"max\"})\n",
+    "              .rename(columns = {\"vp_idx\": \"max_vp_idx\"})\n",
+    "             )\n",
+    "    \n",
+    "    vp_range = dd.merge(\n",
+    "        min_df,\n",
+    "        max_df,\n",
+    "        left_index = True,\n",
+    "        right_index = True,\n",
+    "        how = \"inner\"\n",
+    "    )\n",
+    "\n",
+    "    vp_range = vp_range.persist()\n",
+    "    \n",
+    "    vp_range[\"range_diff\"] = vp_range.max_vp_idx - vp_range.min_vp_idx\n",
+    "    \n",
+    "    vp_range = vp_range.assign(\n",
+    "        p25_vp_idx = (vp_range.range_diff * 0.25 + vp_range.min_vp_idx\n",
+    "                     ).round(0).astype(\"int64\"),\n",
+    "        p50_vp_idx = (vp_range.range_diff * 0.5 + vp_range.min_vp_idx\n",
+    "                     ).round(0).astype(\"int64\"),\n",
+    "        p75_vp_idx = (vp_range.range_diff * 0.75 + vp_range.min_vp_idx\n",
+    "                     ).round(0).astype(\"int64\"),\n",
+    "    )\n",
+    "    \n",
+    "    vp_idx_cols = [\n",
+    "        \"min_vp_idx\", \n",
+    "        \"p25_vp_idx\",\n",
+    "        \"p50_vp_idx\", \n",
+    "        \"p75_vp_idx\",\n",
+    "        \"max_vp_idx\"\n",
+    "    ]\n",
+    "\n",
+    "    results = vp_range[vp_idx_cols].compute().to_numpy().flatten()    \n",
+    "    \n",
+    "    results = list(results)\n",
+    "    return results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "44d836be-21d3-435e-9b35-a1d9863e6257",
+   "metadata": {},
+   "source": [
+    "#### Help: which df should I use to triangulate?\n",
+    "* Trips in which 0 of the points fall into the shapes should be excluded?\n",
+    "* Using the same df as in update completeness."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "id": "659a01af-3c01-4cc3-92ea-834a96c2106a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1604702"
+      ]
+     },
+     "execution_count": 75,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(vp_filtered)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "id": "75d6fcc5-8c85-4c62-a063-62a7a73ecdc0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triangulate_muni = triangulate_vp(vp_filtered, 'trip_instance_key')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "id": "91eab6e3-4e44-4f31-829b-1dcc9b2aebf5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "list"
+      ]
+     },
+     "execution_count": 77,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(triangulate_muni)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 78,
+   "id": "8e709ae9-1c6d-4b55-ad5c-deb1d724276e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "trip_instance_key    9240\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 78,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vp_filtered[['trip_instance_key']].compute().nunique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3dac48a4-cabc-415d-822c-0162fa995efd",
+   "metadata": {},
+   "source": [
+    "#### 4th time loading `vp_usable`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 79,
+   "id": "7807ccce-416c-4f03-a92a-2296edc1d19f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vp_results = dd.read_parquet(f\"{SEGMENT_GCS}vp_usable_{analysis_date}\",\n",
+    "        columns = [\n",
+    "            \"gtfs_dataset_key\", \"trip_instance_key\",\n",
+    "            \"location_timestamp_local\",\n",
+    "            \"x\", \"y\", \"vp_idx\"],\n",
+    "        filters = [[('gtfs_dataset_name', \"==\", operator),\n",
+    "                   ('schedule_gtfs_dataset_key', '==', gtfs_key),\n",
+    "                    ('vp_idx', 'in', triangulate_muni)]]).compute()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 80,
+   "id": "d98556b6-4e16-4bce-b080-19bceadde4af",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "46198"
+      ]
+     },
+     "execution_count": 80,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(vp_results)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 81,
+   "id": "9f0282d0-c59f-4843-b23e-bb22be66404e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9240"
+      ]
+     },
+     "execution_count": 81,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vp_results.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 82,
+   "id": "bbcab824-28a9-4fb3-828a-471b83966b39",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>location_timestamp_local</th>\n",
+       "      <th>x</th>\n",
+       "      <th>y</th>\n",
+       "      <th>vp_idx</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>11825575</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>d28f5a7bf8faf0aa6de5c4cf02c7c106</td>\n",
+       "      <td>2023-10-11 17:06:59</td>\n",
+       "      <td>-122.48</td>\n",
+       "      <td>37.73</td>\n",
+       "      <td>11825575</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                          gtfs_dataset_key                 trip_instance_key  \\\n",
+       "11825575  c0e3039da063db95ebabd3fe4ee611a4  d28f5a7bf8faf0aa6de5c4cf02c7c106   \n",
+       "\n",
+       "         location_timestamp_local       x     y    vp_idx  \n",
+       "11825575      2023-10-11 17:06:59 -122.48 37.73  11825575  "
+      ]
+     },
+     "execution_count": 82,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vp_results.sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "id": "63c04621-ad68-4e3d-9cec-133dbf0aa3b0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def merge_rt_scheduled_trips(\n",
+    "    rt_trips: dd.DataFrame,\n",
+    "    analysis_date: str,\n",
+    "    group_cols: list = [\"trip_instance_key\"]) -> dd.DataFrame:\n",
+    "    \"\"\"\n",
+    "    Merge RT trips (vehicle positions) to scheduled trips \n",
+    "    to get the shape_array_key.\n",
+    "    Don't pull other scheduled trip columns now, wait until\n",
+    "    after aggregation is done.\n",
+    "    \"\"\"\n",
+    "    trips = helpers.import_scheduled_trips(\n",
+    "        analysis_date,\n",
+    "        columns = group_cols + [\"shape_array_key\"],\n",
+    "        get_pandas = True\n",
+    "    )\n",
+    "        \n",
+    "    df = dd.merge(\n",
+    "        rt_trips,\n",
+    "        trips,\n",
+    "        on = group_cols,\n",
+    "        how = \"left\",\n",
+    "    )\n",
+    "    \n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 84,
+   "id": "866b83cc-c0d9-4fc5-b794-f995e8b760de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C2_triangulate_vp.py#L170-L180\n",
+    "vp_with_sched = (\n",
+    "        merge_rt_scheduled_trips(\n",
+    "            vp_results, \n",
+    "            analysis_date, \n",
+    "            group_cols = [\"trip_instance_key\"]\n",
+    "        ).sort_values(\"vp_idx\")\n",
+    "        .reset_index(drop=True)\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 85,
+   "id": "8b6f6495-aa13-4452-a2c9-bf8c1f7f49fd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "pandas.core.frame.DataFrame"
+      ]
+     },
+     "execution_count": 85,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(vp_with_sched)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 86,
+   "id": "a7b261ec-41b8-4f87-998d-a4b5fafc7ec2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check triangualte worked \n",
+    "triangulate_check = vp_with_sched.groupby(['trip_instance_key']).agg({'location_timestamp_local':'nunique'}).reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "id": "bd19bfd5-48d1-4722-a67c-56069bf89e35",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "5    9239\n",
+       "3       1\n",
+       "Name: location_timestamp_local, dtype: int64"
+      ]
+     },
+     "execution_count": 89,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "triangulate_check.location_timestamp_local.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 87,
+   "id": "24d761ba-cc50-406e-9538-e6f2f8705b75",
+   "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_instance_key</th>\n",
+       "      <th>location_timestamp_local</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>6824</th>\n",
+       "      <td>be7a580802c3ec183904cac37e6c0afd</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     trip_instance_key  location_timestamp_local\n",
+       "6824  be7a580802c3ec183904cac37e6c0afd                         3"
+      ]
+     },
+     "execution_count": 87,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "triangulate_check.loc[triangulate_check.location_timestamp_local == 3]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 88,
+   "id": "6e24fb38-f641-418d-99cc-c1b7aaf0e4a1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count   9240.00\n",
+       "mean       5.00\n",
+       "std        0.02\n",
+       "min        3.00\n",
+       "25%        5.00\n",
+       "50%        5.00\n",
+       "75%        5.00\n",
+       "max        5.00\n",
+       "Name: location_timestamp_local, dtype: float64"
+      ]
+     },
+     "execution_count": 88,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "triangulate_check.location_timestamp_local.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 176,
+   "id": "546417f6-e033-43e5-ba70-fdc392697561",
+   "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>vp_idx</th>\n",
+       "      <th>location_timestamp_local</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>gtfs_dataset_key</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>12506123</th>\n",
+       "      <td>12506123</td>\n",
+       "      <td>2023-10-11 16:13:08</td>\n",
+       "      <td>be7a580802c3ec183904cac37e6c0afd</td>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12506124</th>\n",
+       "      <td>12506124</td>\n",
+       "      <td>2023-10-11 17:01:19</td>\n",
+       "      <td>be7a580802c3ec183904cac37e6c0afd</td>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12506125</th>\n",
+       "      <td>12506125</td>\n",
+       "      <td>2023-10-11 17:01:35</td>\n",
+       "      <td>be7a580802c3ec183904cac37e6c0afd</td>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            vp_idx location_timestamp_local                 trip_instance_key  \\\n",
+       "12506123  12506123      2023-10-11 16:13:08  be7a580802c3ec183904cac37e6c0afd   \n",
+       "12506124  12506124      2023-10-11 17:01:19  be7a580802c3ec183904cac37e6c0afd   \n",
+       "12506125  12506125      2023-10-11 17:01:35  be7a580802c3ec183904cac37e6c0afd   \n",
+       "\n",
+       "                          gtfs_dataset_key  \n",
+       "12506123  c0e3039da063db95ebabd3fe4ee611a4  \n",
+       "12506124  c0e3039da063db95ebabd3fe4ee611a4  \n",
+       "12506125  c0e3039da063db95ebabd3fe4ee611a4  "
+      ]
+     },
+     "execution_count": 176,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vp_filtered.loc[vp_filtered.trip_instance_key == \"be7a580802c3ec183904cac37e6c0afd\"].compute()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "687e9c19-daf3-4384-942a-947728bb0680",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "### C3\n",
+    "* https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C3_trip_route_speed.py"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 91,
+   "id": "78c974a0-51f8-42a0-b256-1d8f7c22482e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C3_trip_route_speed.py#L262-L265\n",
+    "vp_c3 = gpd.GeoDataFrame(\n",
+    "        vp_with_sched,\n",
+    "        geometry = gpd.points_from_xy(vp_with_sched.x, vp_with_sched.y, crs=WGS84)\n",
+    "    ).to_crs(PROJECT_CRS).drop(columns = [\"x\", \"y\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 92,
+   "id": "410e5f12-24fc-443b-adb5-e05f9e12ba2a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9240"
+      ]
+     },
+     "execution_count": 92,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vp_c3.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 93,
+   "id": "23c64d78-3c7f-4b58-9ccd-18159d9e1a4e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "shapes_list = vp_c3.shape_array_key.unique().tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 94,
+   "id": "b3bd3c05-7c1d-44e8-afe3-a28a7c6e6190",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "shapes = helpers.import_scheduled_shapes(\n",
+    "        analysis_date,\n",
+    "        columns = [\"shape_array_key\",\"geometry\"],\n",
+    "        filters = [[(\"shape_array_key\", \"in\", shapes_list)]],\n",
+    "        get_pandas = True,\n",
+    "        crs = PROJECT_CRS\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 95,
+   "id": "cbcf928d-c9ec-46e9-9685-48ca5efe8359",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(255, 2)"
+      ]
+     },
+     "execution_count": 95,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "shapes.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 96,
+   "id": "255037a4-079e-4586-beba-0c170f4c6fcb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "geopandas.geodataframe.GeoDataFrame"
+      ]
+     },
+     "execution_count": 96,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(shapes)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 97,
+   "id": "47bbe61e-e014-48c3-b85f-1dea06d5e56e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# shapes.explore('shape_array_key')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 98,
+   "id": "27c8fff8-f8a7-4906-a3f4-7faac4969bde",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C3_trip_route_speed.py#L280-L287\n",
+    "c3_m1 = pd.merge(\n",
+    "        vp_c3,\n",
+    "        shapes,\n",
+    "        on = \"shape_array_key\",\n",
+    "        how = \"inner\"\n",
+    "    ).rename(columns = {\"geometry_x\": \"vp_geometry\", \n",
+    "                        \"geometry_y\": \"shape_geometry\"}\n",
+    "            ).set_geometry(\"vp_geometry\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 99,
+   "id": "7430576e-c571-45de-afb9-500c21336808",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C3_trip_route_speed.py#L290-L293\n",
+    "shape_meters_geoseries = wrangle_shapes.project_point_geom_onto_linestring(\n",
+    "        c3_m1,\n",
+    "        \"shape_geometry\",\n",
+    "        \"vp_geometry\",\n",
+    "    )\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 100,
+   "id": "6631d594-78d7-494a-8bd2-86d2b0c19b1f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "c3_m1[\"shape_meters\"] = shape_meters_geoseries"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9c6f493b-53dd-4ef6-95ad-445a0562d633",
+   "metadata": {},
+   "source": [
+    "#### distance_and_seconds_elapsed\n",
+    "* Breaking apart to understand\n",
+    "* https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C3_trip_route_speed.py#L290-L293"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 101,
+   "id": "50260f4c-91b2-4e89-afbb-a1dc12594d4d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dist_col = \"shape_meters\"\n",
+    "time_col = \"location_timestamp_local\"\n",
+    "group_cols = [\"gtfs_dataset_key\", \"trip_instance_key\"]\n",
+    "sort_cols = group_cols + [\"vp_idx\"]\n",
+    " "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 102,
+   "id": "af0b69f8-5c48-433b-a732-958d12eb2e82",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "geopandas.geodataframe.GeoDataFrame"
+      ]
+     },
+     "execution_count": 102,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(c3_m1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 103,
+   "id": "34e03a27-05bc-49fb-b285-1c9df094fc27",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "c3_m1 = c3_m1.assign(\n",
+    "        prior_dist = (c3_m1.sort_values(sort_cols)\n",
+    "                      .groupby(group_cols, \n",
+    "                               observed=True, group_keys=False)\n",
+    "                      [dist_col]\n",
+    "                      .apply(lambda x: x.shift(1))\n",
+    "                     ),\n",
+    "        prior_time = (c3_m1.sort_values(sort_cols)\n",
+    "                      .groupby(group_cols, \n",
+    "                               observed=True, group_keys=False)\n",
+    "                      [time_col]\n",
+    "                      .apply(lambda x: x.shift(1))\n",
+    "                     )   \n",
+    "    )\n",
+    "  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "id": "ffbc94d1-090f-4a54-ac85-d5b155660ca8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# distance should be positive, but sometimes it's not, \n",
+    "# so use absolute value\n",
+    "c3_m1 = c3_m1.assign(\n",
+    "        change_meters = abs(c3_m1[dist_col] - c3_m1.prior_dist),\n",
+    "        change_sec = (c3_m1[time_col] - c3_m1.prior_time).divide(\n",
+    "                       np.timedelta64(1, 's'))\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "id": "a274e442-2a65-4c84-a5ba-dc35d068771c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "one_trip = c3_m1.loc[c3_m1.trip_instance_key == \"ec2ef3dc047b844d7abf2d035728e202\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "id": "2700eca7-ce6e-4c9d-92d4-7331fee5ffc3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "28840               NaT\n",
+       "28841   0 days 00:05:21\n",
+       "28842   0 days 00:05:21\n",
+       "28843   0 days 00:05:06\n",
+       "28844   0 days 00:05:21\n",
+       "dtype: timedelta64[ns]"
+      ]
+     },
+     "execution_count": 106,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "(one_trip[time_col] - one_trip.prior_time).head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 107,
+   "id": "47e620ba-672a-4baf-bfbd-90ec5b7c6865",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>location_timestamp_local</th>\n",
+       "      <th>vp_idx</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>vp_geometry</th>\n",
+       "      <th>shape_meters</th>\n",
+       "      <th>prior_dist</th>\n",
+       "      <th>prior_time</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>28840</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>ec2ef3dc047b844d7abf2d035728e202</td>\n",
+       "      <td>2023-10-11 21:21:08</td>\n",
+       "      <td>12415722</td>\n",
+       "      <td>652d492c9725307ab5f725bb616ee4a0</td>\n",
+       "      <td>POINT (-212402.440 -28559.730)</td>\n",
+       "      <td>161.50</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28841</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>ec2ef3dc047b844d7abf2d035728e202</td>\n",
+       "      <td>2023-10-11 21:26:29</td>\n",
+       "      <td>12415738</td>\n",
+       "      <td>652d492c9725307ab5f725bb616ee4a0</td>\n",
+       "      <td>POINT (-212088.927 -27551.761)</td>\n",
+       "      <td>1454.71</td>\n",
+       "      <td>161.50</td>\n",
+       "      <td>2023-10-11 21:21:08</td>\n",
+       "      <td>1293.21</td>\n",
+       "      <td>321.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28842</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>ec2ef3dc047b844d7abf2d035728e202</td>\n",
+       "      <td>2023-10-11 21:31:50</td>\n",
+       "      <td>12415754</td>\n",
+       "      <td>652d492c9725307ab5f725bb616ee4a0</td>\n",
+       "      <td>POINT (-212560.266 -26634.904)</td>\n",
+       "      <td>2819.51</td>\n",
+       "      <td>1454.71</td>\n",
+       "      <td>2023-10-11 21:26:29</td>\n",
+       "      <td>1364.80</td>\n",
+       "      <td>321.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28843</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>ec2ef3dc047b844d7abf2d035728e202</td>\n",
+       "      <td>2023-10-11 21:36:56</td>\n",
+       "      <td>12415769</td>\n",
+       "      <td>652d492c9725307ab5f725bb616ee4a0</td>\n",
+       "      <td>POINT (-212711.278 -26637.392)</td>\n",
+       "      <td>2970.41</td>\n",
+       "      <td>2819.51</td>\n",
+       "      <td>2023-10-11 21:31:50</td>\n",
+       "      <td>150.90</td>\n",
+       "      <td>306.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28844</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>ec2ef3dc047b844d7abf2d035728e202</td>\n",
+       "      <td>2023-10-11 21:42:17</td>\n",
+       "      <td>12415785</td>\n",
+       "      <td>652d492c9725307ab5f725bb616ee4a0</td>\n",
+       "      <td>POINT (-212752.276 -26640.128)</td>\n",
+       "      <td>3016.19</td>\n",
+       "      <td>2970.41</td>\n",
+       "      <td>2023-10-11 21:36:56</td>\n",
+       "      <td>45.78</td>\n",
+       "      <td>321.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       gtfs_dataset_key                 trip_instance_key  \\\n",
+       "28840  c0e3039da063db95ebabd3fe4ee611a4  ec2ef3dc047b844d7abf2d035728e202   \n",
+       "28841  c0e3039da063db95ebabd3fe4ee611a4  ec2ef3dc047b844d7abf2d035728e202   \n",
+       "28842  c0e3039da063db95ebabd3fe4ee611a4  ec2ef3dc047b844d7abf2d035728e202   \n",
+       "28843  c0e3039da063db95ebabd3fe4ee611a4  ec2ef3dc047b844d7abf2d035728e202   \n",
+       "28844  c0e3039da063db95ebabd3fe4ee611a4  ec2ef3dc047b844d7abf2d035728e202   \n",
+       "\n",
+       "      location_timestamp_local    vp_idx                   shape_array_key  \\\n",
+       "28840      2023-10-11 21:21:08  12415722  652d492c9725307ab5f725bb616ee4a0   \n",
+       "28841      2023-10-11 21:26:29  12415738  652d492c9725307ab5f725bb616ee4a0   \n",
+       "28842      2023-10-11 21:31:50  12415754  652d492c9725307ab5f725bb616ee4a0   \n",
+       "28843      2023-10-11 21:36:56  12415769  652d492c9725307ab5f725bb616ee4a0   \n",
+       "28844      2023-10-11 21:42:17  12415785  652d492c9725307ab5f725bb616ee4a0   \n",
+       "\n",
+       "                          vp_geometry  shape_meters  prior_dist  \\\n",
+       "28840  POINT (-212402.440 -28559.730)        161.50         NaN   \n",
+       "28841  POINT (-212088.927 -27551.761)       1454.71      161.50   \n",
+       "28842  POINT (-212560.266 -26634.904)       2819.51     1454.71   \n",
+       "28843  POINT (-212711.278 -26637.392)       2970.41     2819.51   \n",
+       "28844  POINT (-212752.276 -26640.128)       3016.19     2970.41   \n",
+       "\n",
+       "               prior_time  change_meters  change_sec  \n",
+       "28840                 NaT            NaN         NaN  \n",
+       "28841 2023-10-11 21:21:08        1293.21      321.00  \n",
+       "28842 2023-10-11 21:26:29        1364.80      321.00  \n",
+       "28843 2023-10-11 21:31:50         150.90      306.00  \n",
+       "28844 2023-10-11 21:36:56          45.78      321.00  "
+      ]
+     },
+     "execution_count": 107,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "one_trip.drop(columns = ['shape_geometry'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 108,
+   "id": "da8c879f-b7d5-40d5-95ea-540a68dfc9f3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Test with one trip\n",
+    "one_trip2 = (one_trip.groupby(group_cols, \n",
+    "                     observed=True, group_keys=False)\n",
+    "           .agg({\"change_meters\": \"sum\", \n",
+    "                 \"change_sec\": \"sum\"})\n",
+    "           .reset_index()\n",
+    "          )\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 109,
+   "id": "91e1e3cd-3ddd-4f0d-ac4c-9d79bb136828",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>ec2ef3dc047b844d7abf2d035728e202</td>\n",
+       "      <td>2854.69</td>\n",
+       "      <td>1269.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   gtfs_dataset_key                 trip_instance_key  \\\n",
+       "0  c0e3039da063db95ebabd3fe4ee611a4  ec2ef3dc047b844d7abf2d035728e202   \n",
+       "\n",
+       "   change_meters  change_sec  \n",
+       "0        2854.69     1269.00  "
+      ]
+     },
+     "execution_count": 109,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "one_trip2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 110,
+   "id": "a501338c-5c10-4872-81e0-483ef8f44171",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "2.237"
+      ]
+     },
+     "execution_count": 110,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "MPH_PER_MPS"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 111,
+   "id": "7e67e8b6-0d28-4222-9fd4-8cb85eec9a1f",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "      <th>speed_mph</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>ec2ef3dc047b844d7abf2d035728e202</td>\n",
+       "      <td>2854.69</td>\n",
+       "      <td>1269.00</td>\n",
+       "      <td>5.03</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   gtfs_dataset_key                 trip_instance_key  \\\n",
+       "0  c0e3039da063db95ebabd3fe4ee611a4  ec2ef3dc047b844d7abf2d035728e202   \n",
+       "\n",
+       "   change_meters  change_sec  speed_mph  \n",
+       "0        2854.69     1269.00       5.03  "
+      ]
+     },
+     "execution_count": 111,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "one_trip2.assign(\n",
+    "        speed_mph = (one_trip2.change_meters.divide(one_trip2.change_sec) * \n",
+    "                     MPH_PER_MPS)\n",
+    "    )\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 112,
+   "id": "e687d2c6-51ee-481b-bc23-3540a5b6d09b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "c3_m2 = (c3_m1.groupby(group_cols, \n",
+    "                     observed=True, group_keys=False)\n",
+    "           .agg({\"change_meters\": \"sum\", \n",
+    "                 \"change_sec\": \"sum\"})\n",
+    "           .reset_index()\n",
+    "          )\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 113,
+   "id": "2d5dec48-a014-4c64-ac73-cd0a867b12fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "c3_m2 = c3_m2.assign(\n",
+    "        speed_mph = (c3_m2.change_meters.divide(c3_m1.change_sec) * \n",
+    "                     MPH_PER_MPS)\n",
+    "    )\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 114,
+   "id": "00560062-5a81-4035-baad-e59c631166e4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count   7392.00\n",
+       "mean      29.82\n",
+       "std       21.56\n",
+       "min        0.00\n",
+       "25%       17.66\n",
+       "50%       25.23\n",
+       "75%       35.86\n",
+       "max      340.24\n",
+       "Name: speed_mph, dtype: float64"
+      ]
+     },
+     "execution_count": 114,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m2.speed_mph.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 115,
+   "id": "dac3c329-0602-4391-a6cb-5eb66d5fa656",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# muni.loc[muni.vp_in_shape == 0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "54c52ae9-03a7-4986-a62f-21ee53e89630",
+   "metadata": {},
+   "source": [
+    "#### See why a trip would have speed_mph of 0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 116,
+   "id": "93e5d405-bd05-4108-89ac-83ffbaef40d9",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>location_timestamp_local</th>\n",
+       "      <th>vp_idx</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>vp_geometry</th>\n",
+       "      <th>shape_meters</th>\n",
+       "      <th>prior_dist</th>\n",
+       "      <th>prior_time</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>35703</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>04ae6ea9655473bdcaf9b80d443558ae</td>\n",
+       "      <td>2023-10-11 18:34:47</td>\n",
+       "      <td>12628774</td>\n",
+       "      <td>f82328b9817126227af1aa52033d8847</td>\n",
+       "      <td>POINT (-212105.135 -21893.355)</td>\n",
+       "      <td>1411.65</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35704</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>04ae6ea9655473bdcaf9b80d443558ae</td>\n",
+       "      <td>2023-10-11 18:44:18</td>\n",
+       "      <td>12628802</td>\n",
+       "      <td>f82328b9817126227af1aa52033d8847</td>\n",
+       "      <td>POINT (-212100.059 -21901.268)</td>\n",
+       "      <td>1411.65</td>\n",
+       "      <td>1411.65</td>\n",
+       "      <td>2023-10-11 18:34:47</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>571.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35705</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>04ae6ea9655473bdcaf9b80d443558ae</td>\n",
+       "      <td>2023-10-11 18:53:17</td>\n",
+       "      <td>12628829</td>\n",
+       "      <td>f82328b9817126227af1aa52033d8847</td>\n",
+       "      <td>POINT (-212100.087 -21902.380)</td>\n",
+       "      <td>1411.65</td>\n",
+       "      <td>1411.65</td>\n",
+       "      <td>2023-10-11 18:44:18</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>539.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35706</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>04ae6ea9655473bdcaf9b80d443558ae</td>\n",
+       "      <td>2023-10-11 19:02:17</td>\n",
+       "      <td>12628856</td>\n",
+       "      <td>f82328b9817126227af1aa52033d8847</td>\n",
+       "      <td>POINT (-212100.228 -21907.936)</td>\n",
+       "      <td>1411.65</td>\n",
+       "      <td>1411.65</td>\n",
+       "      <td>2023-10-11 18:53:17</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>540.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35707</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>04ae6ea9655473bdcaf9b80d443558ae</td>\n",
+       "      <td>2023-10-11 19:11:31</td>\n",
+       "      <td>12628884</td>\n",
+       "      <td>f82328b9817126227af1aa52033d8847</td>\n",
+       "      <td>POINT (-212098.611 -21913.537)</td>\n",
+       "      <td>1411.65</td>\n",
+       "      <td>1411.65</td>\n",
+       "      <td>2023-10-11 19:02:17</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>554.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       gtfs_dataset_key                 trip_instance_key  \\\n",
+       "35703  c0e3039da063db95ebabd3fe4ee611a4  04ae6ea9655473bdcaf9b80d443558ae   \n",
+       "35704  c0e3039da063db95ebabd3fe4ee611a4  04ae6ea9655473bdcaf9b80d443558ae   \n",
+       "35705  c0e3039da063db95ebabd3fe4ee611a4  04ae6ea9655473bdcaf9b80d443558ae   \n",
+       "35706  c0e3039da063db95ebabd3fe4ee611a4  04ae6ea9655473bdcaf9b80d443558ae   \n",
+       "35707  c0e3039da063db95ebabd3fe4ee611a4  04ae6ea9655473bdcaf9b80d443558ae   \n",
+       "\n",
+       "      location_timestamp_local    vp_idx                   shape_array_key  \\\n",
+       "35703      2023-10-11 18:34:47  12628774  f82328b9817126227af1aa52033d8847   \n",
+       "35704      2023-10-11 18:44:18  12628802  f82328b9817126227af1aa52033d8847   \n",
+       "35705      2023-10-11 18:53:17  12628829  f82328b9817126227af1aa52033d8847   \n",
+       "35706      2023-10-11 19:02:17  12628856  f82328b9817126227af1aa52033d8847   \n",
+       "35707      2023-10-11 19:11:31  12628884  f82328b9817126227af1aa52033d8847   \n",
+       "\n",
+       "                          vp_geometry  shape_meters  prior_dist  \\\n",
+       "35703  POINT (-212105.135 -21893.355)       1411.65         NaN   \n",
+       "35704  POINT (-212100.059 -21901.268)       1411.65     1411.65   \n",
+       "35705  POINT (-212100.087 -21902.380)       1411.65     1411.65   \n",
+       "35706  POINT (-212100.228 -21907.936)       1411.65     1411.65   \n",
+       "35707  POINT (-212098.611 -21913.537)       1411.65     1411.65   \n",
+       "\n",
+       "               prior_time  change_meters  change_sec  \n",
+       "35703                 NaT            NaN         NaN  \n",
+       "35704 2023-10-11 18:34:47           0.00      571.00  \n",
+       "35705 2023-10-11 18:44:18           0.00      539.00  \n",
+       "35706 2023-10-11 18:53:17           0.00      540.00  \n",
+       "35707 2023-10-11 19:02:17           0.00      554.00  "
+      ]
+     },
+     "execution_count": 116,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m1.loc[c3_m1.trip_instance_key == \"04ae6ea9655473bdcaf9b80d443558ae\"].drop(columns = ['shape_geometry'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 209,
+   "id": "a303aab1-a574-4dbb-9a62-fff52cbd3070",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 9240 entries, 0 to 9239\n",
+      "Data columns (total 5 columns):\n",
+      " #   Column             Non-Null Count  Dtype   \n",
+      "---  ------             --------------  -----   \n",
+      " 0   gtfs_dataset_key   9240 non-null   category\n",
+      " 1   trip_instance_key  9240 non-null   object  \n",
+      " 2   change_meters      9240 non-null   float64 \n",
+      " 3   change_sec         9240 non-null   float64 \n",
+      " 4   speed_mph          7392 non-null   float64 \n",
+      "dtypes: category(1), float64(3), object(1)\n",
+      "memory usage: 298.0+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "c3_m2.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 117,
+   "id": "91db6999-f3f8-4001-bdda-4ad59abeeef7",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "      <th>speed_mph</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>167</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>04ae6ea9655473bdcaf9b80d443558ae</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2204.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>863</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>183990ffbd08d7d7df0308b35227a058</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1530.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1128</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>1fe28ce8669a7f946f272faf80d80ce7</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1379.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2854</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>5056febd44cda31254459111e1fc79d0</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>875.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3213</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>5a82f8c02f2036db77b1979f4ae228f5</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>803.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3232</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>5b07e2bf68a16c54d798ef4028e02026</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1004.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3937</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>6ee4a9165f47b59cb3e10b0125dd72e8</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>649.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4562</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>7ff345e91303290951ef0665a57dc90e</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1403.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6758</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>bcb78da06a56761d2a3b8b16a3436f3d</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2000.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7043</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>c3fc63ec2ff7a35c0f821659075be708</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1173.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7239</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>c992295be425ff2d17de0f0f29bec301</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>877.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7543</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>d21ff3a0d37a484dc4f979d052652565</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>873.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8431</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>ea8751445dcd6a175bd23ec5fc423d0c</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>866.00</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      gtfs_dataset_key                 trip_instance_key  \\\n",
+       "167   c0e3039da063db95ebabd3fe4ee611a4  04ae6ea9655473bdcaf9b80d443558ae   \n",
+       "863   c0e3039da063db95ebabd3fe4ee611a4  183990ffbd08d7d7df0308b35227a058   \n",
+       "1128  c0e3039da063db95ebabd3fe4ee611a4  1fe28ce8669a7f946f272faf80d80ce7   \n",
+       "2854  c0e3039da063db95ebabd3fe4ee611a4  5056febd44cda31254459111e1fc79d0   \n",
+       "3213  c0e3039da063db95ebabd3fe4ee611a4  5a82f8c02f2036db77b1979f4ae228f5   \n",
+       "3232  c0e3039da063db95ebabd3fe4ee611a4  5b07e2bf68a16c54d798ef4028e02026   \n",
+       "3937  c0e3039da063db95ebabd3fe4ee611a4  6ee4a9165f47b59cb3e10b0125dd72e8   \n",
+       "4562  c0e3039da063db95ebabd3fe4ee611a4  7ff345e91303290951ef0665a57dc90e   \n",
+       "6758  c0e3039da063db95ebabd3fe4ee611a4  bcb78da06a56761d2a3b8b16a3436f3d   \n",
+       "7043  c0e3039da063db95ebabd3fe4ee611a4  c3fc63ec2ff7a35c0f821659075be708   \n",
+       "7239  c0e3039da063db95ebabd3fe4ee611a4  c992295be425ff2d17de0f0f29bec301   \n",
+       "7543  c0e3039da063db95ebabd3fe4ee611a4  d21ff3a0d37a484dc4f979d052652565   \n",
+       "8431  c0e3039da063db95ebabd3fe4ee611a4  ea8751445dcd6a175bd23ec5fc423d0c   \n",
+       "\n",
+       "      change_meters  change_sec  speed_mph  \n",
+       "167            0.00     2204.00       0.00  \n",
+       "863            0.00     1530.00       0.00  \n",
+       "1128           0.00     1379.00       0.00  \n",
+       "2854           0.00      875.00       0.00  \n",
+       "3213           0.00      803.00       0.00  \n",
+       "3232           0.00     1004.00       0.00  \n",
+       "3937           0.00      649.00       0.00  \n",
+       "4562           0.00     1403.00       0.00  \n",
+       "6758           0.00     2000.00       0.00  \n",
+       "7043           0.00     1173.00       0.00  \n",
+       "7239           0.00      877.00       0.00  \n",
+       "7543           0.00      873.00       0.00  \n",
+       "8431           0.00      866.00       0.00  "
+      ]
+     },
+     "execution_count": 117,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m2.loc[c3_m2.speed_mph == 0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "328178ff-9e1e-48b6-9580-ae6b557f0987",
+   "metadata": {},
+   "source": [
+    "#### add_scheduled_trip_columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 118,
+   "id": "e465113c-2bc5-4792-bd10-822184882fe6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Attach scheduled trip columns, like route, direction, time_of_day\n",
+    "group_cols = [\"trip_instance_key\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 119,
+   "id": "25b7221d-725c-4f9a-9728-497e6b46464f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "keep_cols = [\n",
+    "        \"gtfs_dataset_key\",\n",
+    "        \"direction_id\", \n",
+    "        \"route_id\", \"route_short_name\", \"route_long_name\", \"route_desc\",\n",
+    "    ] + group_cols"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 120,
+   "id": "ab221f62-4c2b-4700-8612-0b491432c36f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "crosswalk = helpers.import_scheduled_trips(\n",
+    "        analysis_date, \n",
+    "        columns = keep_cols, \n",
+    "        get_pandas = True\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 121,
+   "id": "29ddf9da-454a-40d6-bc2c-ab2b74504cbe",
+   "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>schedule_gtfs_dataset_key</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>route_short_name</th>\n",
+       "      <th>route_long_name</th>\n",
+       "      <th>route_desc</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1770249a5a2e770ca90628434d4934b1</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>3402</td>\n",
+       "      <td>Route 11</td>\n",
+       "      <td>Route 11</td>\n",
+       "      <td>PACIFIC VIEW MALL via TELEPHONE RD</td>\n",
+       "      <td>1b3cc71bbb3c3166e8c5540ca26a97ba</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1770249a5a2e770ca90628434d4934b1</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>3402</td>\n",
+       "      <td>Route 11</td>\n",
+       "      <td>Route 11</td>\n",
+       "      <td>PACIFIC VIEW MALL via TELEPHONE RD</td>\n",
+       "      <td>f780ba65965e61d394635fd80fc81232</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          schedule_gtfs_dataset_key  direction_id route_id route_short_name  \\\n",
+       "0  1770249a5a2e770ca90628434d4934b1          1.00     3402         Route 11   \n",
+       "1  1770249a5a2e770ca90628434d4934b1          1.00     3402         Route 11   \n",
+       "\n",
+       "  route_long_name                          route_desc  \\\n",
+       "0        Route 11  PACIFIC VIEW MALL via TELEPHONE RD   \n",
+       "1        Route 11  PACIFIC VIEW MALL via TELEPHONE RD   \n",
+       "\n",
+       "                  trip_instance_key  \n",
+       "0  1b3cc71bbb3c3166e8c5540ca26a97ba  \n",
+       "1  f780ba65965e61d394635fd80fc81232  "
+      ]
+     },
+     "execution_count": 121,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "crosswalk.head(2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 122,
+   "id": "774e182c-9157-47e3-9c95-160a331353c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "common_shape = sched_rt_utils.most_common_shape_by_route_direction(analysis_date)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 123,
+   "id": "e83a2e56-3fe7-400f-8a67-9bad9989a5dc",
+   "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>schedule_gtfs_dataset_key</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>common_shape_id</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>014d0998350083249a9eb310635548c2</td>\n",
+       "      <td>10866826</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>10866826:1</td>\n",
+       "      <td>80d84c820ca200c0b3d1791185c72b56</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>014d0998350083249a9eb310635548c2</td>\n",
+       "      <td>10866849</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>10866849:1</td>\n",
+       "      <td>99faaf65ccc65b3ec0e6704765b60195</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          schedule_gtfs_dataset_key  route_id  direction_id common_shape_id  \\\n",
+       "0  014d0998350083249a9eb310635548c2  10866826          1.00      10866826:1   \n",
+       "1  014d0998350083249a9eb310635548c2  10866849          1.00      10866849:1   \n",
+       "\n",
+       "                    shape_array_key  \n",
+       "0  80d84c820ca200c0b3d1791185c72b56  \n",
+       "1  99faaf65ccc65b3ec0e6704765b60195  "
+      ]
+     },
+     "execution_count": 123,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "common_shape.head(2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 124,
+   "id": "ada2f87d-85c4-4999-926e-7dbb0cc57b90",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "crosswalk2 = pd.merge(\n",
+    "        crosswalk,\n",
+    "        common_shape,\n",
+    "        on = [\"schedule_gtfs_dataset_key\", \"route_id\", \"direction_id\"],\n",
+    "        how = \"inner\"\n",
+    "    ).astype({\"direction_id\": \"Int64\"})\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 125,
+   "id": "c473c35b-ac7c-4839-81eb-3b31ec25ca38",
+   "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>schedule_gtfs_dataset_key</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>route_short_name</th>\n",
+       "      <th>route_long_name</th>\n",
+       "      <th>route_desc</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>common_shape_id</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>84626</th>\n",
+       "      <td>3c275e5acf8974e1afd765bd3011424c</td>\n",
+       "      <td>1</td>\n",
+       "      <td>59</td>\n",
+       "      <td>HD</td>\n",
+       "      <td>Hospital: Direct</td>\n",
+       "      <td>None</td>\n",
+       "      <td>966a69a34ccc9b82dc65ae82346a12e4</td>\n",
+       "      <td>59:2</td>\n",
+       "      <td>b47002305320d71375303e2de926642a</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "              schedule_gtfs_dataset_key  direction_id route_id  \\\n",
+       "84626  3c275e5acf8974e1afd765bd3011424c             1       59   \n",
+       "\n",
+       "      route_short_name   route_long_name route_desc  \\\n",
+       "84626               HD  Hospital: Direct       None   \n",
+       "\n",
+       "                      trip_instance_key common_shape_id  \\\n",
+       "84626  966a69a34ccc9b82dc65ae82346a12e4            59:2   \n",
+       "\n",
+       "                        shape_array_key  \n",
+       "84626  b47002305320d71375303e2de926642a  "
+      ]
+     },
+     "execution_count": 125,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "crosswalk2.sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 126,
+   "id": "866defff-f203-4f25-a150-aea22333c7f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "time_of_day = sched_rt_utils.get_trip_time_buckets(analysis_date)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 127,
+   "id": "d52698d8-7021-4766-92b2-dd6674928944",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((101973, 5), 101973)"
+      ]
+     },
+     "execution_count": 127,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "time_of_day.shape, time_of_day.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 128,
+   "id": "bc2161ba-d506-41a6-8517-63891af5f8e9",
+   "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_instance_key</th>\n",
+       "      <th>service_hours</th>\n",
+       "      <th>trip_first_departure_datetime_pacific</th>\n",
+       "      <th>time_of_day</th>\n",
+       "      <th>service_minutes</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1b3cc71bbb3c3166e8c5540ca26a97ba</td>\n",
+       "      <td>0.60</td>\n",
+       "      <td>2023-10-11 10:40:00</td>\n",
+       "      <td>Midday</td>\n",
+       "      <td>36.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>f780ba65965e61d394635fd80fc81232</td>\n",
+       "      <td>0.55</td>\n",
+       "      <td>2023-10-11 17:40:00</td>\n",
+       "      <td>PM Peak</td>\n",
+       "      <td>33.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  trip_instance_key  service_hours  \\\n",
+       "0  1b3cc71bbb3c3166e8c5540ca26a97ba           0.60   \n",
+       "1  f780ba65965e61d394635fd80fc81232           0.55   \n",
+       "\n",
+       "  trip_first_departure_datetime_pacific time_of_day  service_minutes  \n",
+       "0                   2023-10-11 10:40:00      Midday            36.00  \n",
+       "1                   2023-10-11 17:40:00     PM Peak            33.00  "
+      ]
+     },
+     "execution_count": 128,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "time_of_day.head(2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 129,
+   "id": "834ce86a-8735-4d06-9be9-ef96d2fbbec0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "crosswalk2 = portfolio_utils.add_route_name(\n",
+    "        crosswalk2\n",
+    "    ).drop(columns = [\"route_short_name\", \"route_long_name\", \"route_desc\"])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 130,
+   "id": "226915d5-2dce-45af-aeae-0d6f32f36f1e",
+   "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>schedule_gtfs_dataset_key</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>common_shape_id</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>route_name_used</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1770249a5a2e770ca90628434d4934b1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3402</td>\n",
+       "      <td>1b3cc71bbb3c3166e8c5540ca26a97ba</td>\n",
+       "      <td>8254</td>\n",
+       "      <td>a669792e07a16b260139c6950011b759</td>\n",
+       "      <td>PACIFIC VIEW MALL via TELEPHONE RD</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1770249a5a2e770ca90628434d4934b1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3402</td>\n",
+       "      <td>f780ba65965e61d394635fd80fc81232</td>\n",
+       "      <td>8254</td>\n",
+       "      <td>a669792e07a16b260139c6950011b759</td>\n",
+       "      <td>PACIFIC VIEW MALL via TELEPHONE RD</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          schedule_gtfs_dataset_key  direction_id route_id  \\\n",
+       "0  1770249a5a2e770ca90628434d4934b1             1     3402   \n",
+       "1  1770249a5a2e770ca90628434d4934b1             1     3402   \n",
+       "\n",
+       "                  trip_instance_key common_shape_id  \\\n",
+       "0  1b3cc71bbb3c3166e8c5540ca26a97ba            8254   \n",
+       "1  f780ba65965e61d394635fd80fc81232            8254   \n",
+       "\n",
+       "                    shape_array_key                     route_name_used  \n",
+       "0  a669792e07a16b260139c6950011b759  PACIFIC VIEW MALL via TELEPHONE RD  \n",
+       "1  a669792e07a16b260139c6950011b759  PACIFIC VIEW MALL via TELEPHONE RD  "
+      ]
+     },
+     "execution_count": 130,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "crosswalk2.head(2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 131,
+   "id": "03971a5f-a151-43bf-a417-2d7be7a1d37b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "pandas.core.frame.DataFrame"
+      ]
+     },
+     "execution_count": 131,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(c3_m2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 132,
+   "id": "0163454e-5e0c-41d5-895d-8e0a6985ff29",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C3_trip_route_speed.py#L116-L124\n",
+    "c3_m3 = dd.merge(\n",
+    "        c3_m2,\n",
+    "        crosswalk2,\n",
+    "        on = group_cols,\n",
+    "        how = \"left\",\n",
+    "    ).merge(\n",
+    "        time_of_day,\n",
+    "        on = group_cols,\n",
+    "        how = \"left\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 133,
+   "id": "39bd5b37-d195-4dc1-85d4-e1c54b298248",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "pandas.core.frame.DataFrame"
+      ]
+     },
+     "execution_count": 133,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(c3_m3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 134,
+   "id": "49e475a8-530d-4b12-9c9d-1741b0fc39dd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['gtfs_dataset_key', 'trip_instance_key', 'change_meters', 'change_sec',\n",
+       "       'speed_mph', 'schedule_gtfs_dataset_key', 'direction_id', 'route_id',\n",
+       "       'common_shape_id', 'shape_array_key', 'route_name_used',\n",
+       "       'service_hours', 'trip_first_departure_datetime_pacific', 'time_of_day',\n",
+       "       'service_minutes'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 134,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m3.columns"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7d40ef54-9b9e-40ea-9651-1a00a36d8105",
+   "metadata": {},
+   "source": [
+    "#### avg_route_speeds_by_time_of_day"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 135,
+   "id": "3e325d57-160f-40b5-8a7c-0692173e8874",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C3_trip_route_speed.py#L166\n",
+    "def drop_extremely_low_and_high_speeds(\n",
+    "    df: pd.DataFrame, \n",
+    "    speed_range: tuple\n",
+    ") -> pd.DataFrame:\n",
+    "    \"\"\"\n",
+    "    Descriptives show the 5th percentile is around 5 mph, \n",
+    "    and 95th percentile is around 25 mph.\n",
+    "    \n",
+    "    There are some weird calculations for <3 mph, and even\n",
+    "    some negative values, so let's exclude those...maybe\n",
+    "    the vp is not traveling across the entirety of the shape.\n",
+    "    \n",
+    "    Exclude unusually high speeds, over 70 mph.\n",
+    "    \"\"\"\n",
+    "    low, high = speed_range\n",
+    "    \n",
+    "    df2 = df[(df.speed_mph >= low) & \n",
+    "             (df.speed_mph <= high)\n",
+    "            ].reset_index(drop=True)\n",
+    "    \n",
+    "    return df2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 136,
+   "id": "f5c8dc5d-61cd-4883-a089-000ca1e11d76",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "c3_m3 = drop_extremely_low_and_high_speeds(c3_m3, speed_range = (3, 70))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 178,
+   "id": "983a896a-e40b-4c46-93a9-78643c7e1e69",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((6993, 15), (46198, 12), (9240, 5))"
+      ]
+     },
+     "execution_count": 178,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m3.shape, c3_m1.shape, c3_m2.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 138,
+   "id": "a9be0c3a-f224-40f4-b807-bb7fc387e344",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "6993"
+      ]
+     },
+     "execution_count": 138,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m3.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 139,
+   "id": "33dbfa67-8bef-457c-b415-c5826e41601c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9240"
+      ]
+     },
+     "execution_count": 139,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m1.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 177,
+   "id": "52ae9db4-6e23-4c8b-b421-cba1c583b31f",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "      <th>speed_mph</th>\n",
+       "      <th>schedule_gtfs_dataset_key</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>common_shape_id</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>route_name_used</th>\n",
+       "      <th>service_hours</th>\n",
+       "      <th>trip_first_departure_datetime_pacific</th>\n",
+       "      <th>time_of_day</th>\n",
+       "      <th>service_minutes</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "Empty DataFrame\n",
+       "Columns: [gtfs_dataset_key, trip_instance_key, change_meters, change_sec, speed_mph, schedule_gtfs_dataset_key, direction_id, route_id, common_shape_id, shape_array_key, route_name_used, service_hours, trip_first_departure_datetime_pacific, time_of_day, service_minutes]\n",
+       "Index: []"
+      ]
+     },
+     "execution_count": 177,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m3.loc[c3_m3.trip_instance_key == \"04ae6ea9655473bdcaf9b80d443558ae\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b00d1985-6f8d-47da-9164-422fc6b515d0",
+   "metadata": {},
+   "source": [
+    "#### Question: Is this common to have 25% of trips dropped?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 140,
+   "id": "8ffc55df-73e0-412e-b428-018184b5efff",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.7568181818181818"
+      ]
+     },
+     "execution_count": 140,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "6993/9240"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 141,
+   "id": "626c4e6c-fc59-4bb0-91bb-007887d3e75b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "group_cols = [\n",
+    "            \"gtfs_dataset_key\", \"time_of_day\",\n",
+    "            \"route_id\", \"direction_id\",\n",
+    "            \"route_name_used\",\n",
+    "            \"common_shape_id\", \"shape_array_key\"\n",
+    "        ]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 142,
+   "id": "c2d6e858-4d63-4ffc-baea-d8a5ab32987a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# test with one route\n",
+    "one_route = c3_m3.loc[c3_m3.route_id == \"14R\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 143,
+   "id": "a6a2c843-022e-4e4e-bd1c-eace7dd25d59",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((193, 15), 193)"
+      ]
+     },
+     "execution_count": 143,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "one_route.shape, one_route.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 144,
+   "id": "c8bc46f0-bcd3-4aaa-8c6c-5e38b0fe7210",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "      <th>speed_mph</th>\n",
+       "      <th>schedule_gtfs_dataset_key</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>common_shape_id</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>route_name_used</th>\n",
+       "      <th>service_hours</th>\n",
+       "      <th>trip_first_departure_datetime_pacific</th>\n",
+       "      <th>time_of_day</th>\n",
+       "      <th>service_minutes</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>73</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>0317ba64ff87ddd8b3dd626368a341a8</td>\n",
+       "      <td>13487.57</td>\n",
+       "      <td>5379.00</td>\n",
+       "      <td>40.83</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>1</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>0.90</td>\n",
+       "      <td>2023-10-11 18:25:00</td>\n",
+       "      <td>PM Peak</td>\n",
+       "      <td>54.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>144</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>059a49f356f6b8bdb7f12458dafc68e4</td>\n",
+       "      <td>20787.34</td>\n",
+       "      <td>5069.00</td>\n",
+       "      <td>59.09</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>1</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>0.75</td>\n",
+       "      <td>2023-10-11 08:30:00</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>45.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>173</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>06dc64f00c021e66d0c7bd52df8fed9c</td>\n",
+       "      <td>12924.90</td>\n",
+       "      <td>2594.00</td>\n",
+       "      <td>32.27</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>0</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>11403</td>\n",
+       "      <td>453493134b4598d0dbdddb92e825ae24</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>0.85</td>\n",
+       "      <td>2023-10-11 19:36:00</td>\n",
+       "      <td>PM Peak</td>\n",
+       "      <td>51.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>202</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>07ab77edf2b69295d643794e3cd497af</td>\n",
+       "      <td>13682.26</td>\n",
+       "      <td>4427.00</td>\n",
+       "      <td>32.49</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>1</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>0.77</td>\n",
+       "      <td>2023-10-11 05:58:00</td>\n",
+       "      <td>Early AM</td>\n",
+       "      <td>46.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>230</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>08adb7403f95343c6c9579cb137c8c15</td>\n",
+       "      <td>13624.98</td>\n",
+       "      <td>5094.00</td>\n",
+       "      <td>33.46</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>1</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>0.90</td>\n",
+       "      <td>2023-10-11 12:49:00</td>\n",
+       "      <td>Midday</td>\n",
+       "      <td>54.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     gtfs_dataset_key                 trip_instance_key  \\\n",
+       "73   c0e3039da063db95ebabd3fe4ee611a4  0317ba64ff87ddd8b3dd626368a341a8   \n",
+       "144  c0e3039da063db95ebabd3fe4ee611a4  059a49f356f6b8bdb7f12458dafc68e4   \n",
+       "173  c0e3039da063db95ebabd3fe4ee611a4  06dc64f00c021e66d0c7bd52df8fed9c   \n",
+       "202  c0e3039da063db95ebabd3fe4ee611a4  07ab77edf2b69295d643794e3cd497af   \n",
+       "230  c0e3039da063db95ebabd3fe4ee611a4  08adb7403f95343c6c9579cb137c8c15   \n",
+       "\n",
+       "     change_meters  change_sec  speed_mph         schedule_gtfs_dataset_key  \\\n",
+       "73        13487.57     5379.00      40.83  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "144       20787.34     5069.00      59.09  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "173       12924.90     2594.00      32.27  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "202       13682.26     4427.00      32.49  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "230       13624.98     5094.00      33.46  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "\n",
+       "     direction_id route_id common_shape_id                   shape_array_key  \\\n",
+       "73              1      14R           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "144             1      14R           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "173             0      14R           11403  453493134b4598d0dbdddb92e825ae24   \n",
+       "202             1      14R           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "230             1      14R           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "\n",
+       "    route_name_used  service_hours trip_first_departure_datetime_pacific  \\\n",
+       "73   5am-10pm daily           0.90                   2023-10-11 18:25:00   \n",
+       "144  5am-10pm daily           0.75                   2023-10-11 08:30:00   \n",
+       "173  5am-10pm daily           0.85                   2023-10-11 19:36:00   \n",
+       "202  5am-10pm daily           0.77                   2023-10-11 05:58:00   \n",
+       "230  5am-10pm daily           0.90                   2023-10-11 12:49:00   \n",
+       "\n",
+       "    time_of_day  service_minutes  \n",
+       "73      PM Peak            54.00  \n",
+       "144     AM Peak            45.00  \n",
+       "173     PM Peak            51.00  \n",
+       "202    Early AM            46.00  \n",
+       "230      Midday            54.00  "
+      ]
+     },
+     "execution_count": 144,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "one_route.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 145,
+   "id": "8ef2f776-d9f0-4ca9-a9f5-b384040f2f05",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['gtfs_dataset_key',\n",
+       " 'time_of_day',\n",
+       " 'route_id',\n",
+       " 'direction_id',\n",
+       " 'route_name_used',\n",
+       " 'common_shape_id',\n",
+       " 'shape_array_key']"
+      ]
+     },
+     "execution_count": 145,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "group_cols"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aa8cf621-b772-44d4-97e5-c11c738adfb0",
+   "metadata": {},
+   "source": [
+    "#### One route test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 146,
+   "id": "10f541bc-1e94-4878-bb1e-2ae88ece99ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "one_route2 = (one_route.groupby(group_cols, \n",
+    "                       observed = True, group_keys = False)\n",
+    "           .agg({\n",
+    "               \"speed_mph\": \"mean\",\n",
+    "               \"service_minutes\": \"mean\",\n",
+    "               \"change_sec\": \"mean\",\n",
+    "               \"trip_instance_key\": \"count\"\n",
+    "           }).reset_index()\n",
+    "          )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 147,
+   "id": "3eac1991-7a9c-4a05-84f2-0769529609da",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(10, 11)"
+      ]
+     },
+     "execution_count": 147,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "one_route2.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 148,
+   "id": "58647959-a118-403d-97bc-c1abb35d61b5",
+   "metadata": {
+    "tags": []
+   },
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>time_of_day</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>route_name_used</th>\n",
+       "      <th>common_shape_id</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>speed_mph</th>\n",
+       "      <th>service_minutes</th>\n",
+       "      <th>change_sec</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11403</td>\n",
+       "      <td>453493134b4598d0dbdddb92e825ae24</td>\n",
+       "      <td>29.38</td>\n",
+       "      <td>43.19</td>\n",
+       "      <td>3139.44</td>\n",
+       "      <td>16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>39.80</td>\n",
+       "      <td>50.36</td>\n",
+       "      <td>4804.36</td>\n",
+       "      <td>22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Early AM</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11403</td>\n",
+       "      <td>453493134b4598d0dbdddb92e825ae24</td>\n",
+       "      <td>37.89</td>\n",
+       "      <td>42.00</td>\n",
+       "      <td>3555.80</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Early AM</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>34.42</td>\n",
+       "      <td>44.45</td>\n",
+       "      <td>4602.45</td>\n",
+       "      <td>11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Evening</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11403</td>\n",
+       "      <td>453493134b4598d0dbdddb92e825ae24</td>\n",
+       "      <td>33.69</td>\n",
+       "      <td>51.00</td>\n",
+       "      <td>3014.44</td>\n",
+       "      <td>9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Evening</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>32.25</td>\n",
+       "      <td>53.00</td>\n",
+       "      <td>5149.00</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Midday</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11403</td>\n",
+       "      <td>453493134b4598d0dbdddb92e825ae24</td>\n",
+       "      <td>32.46</td>\n",
+       "      <td>46.94</td>\n",
+       "      <td>3371.86</td>\n",
+       "      <td>35</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Midday</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>31.30</td>\n",
+       "      <td>50.61</td>\n",
+       "      <td>4478.18</td>\n",
+       "      <td>33</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>PM Peak</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11403</td>\n",
+       "      <td>453493134b4598d0dbdddb92e825ae24</td>\n",
+       "      <td>38.41</td>\n",
+       "      <td>49.78</td>\n",
+       "      <td>3893.81</td>\n",
+       "      <td>36</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>PM Peak</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>31.35</td>\n",
+       "      <td>53.71</td>\n",
+       "      <td>4823.19</td>\n",
+       "      <td>21</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   gtfs_dataset_key time_of_day route_id  direction_id  \\\n",
+       "0  c0e3039da063db95ebabd3fe4ee611a4     AM Peak      14R             0   \n",
+       "1  c0e3039da063db95ebabd3fe4ee611a4     AM Peak      14R             1   \n",
+       "2  c0e3039da063db95ebabd3fe4ee611a4    Early AM      14R             0   \n",
+       "3  c0e3039da063db95ebabd3fe4ee611a4    Early AM      14R             1   \n",
+       "4  c0e3039da063db95ebabd3fe4ee611a4     Evening      14R             0   \n",
+       "5  c0e3039da063db95ebabd3fe4ee611a4     Evening      14R             1   \n",
+       "6  c0e3039da063db95ebabd3fe4ee611a4      Midday      14R             0   \n",
+       "7  c0e3039da063db95ebabd3fe4ee611a4      Midday      14R             1   \n",
+       "8  c0e3039da063db95ebabd3fe4ee611a4     PM Peak      14R             0   \n",
+       "9  c0e3039da063db95ebabd3fe4ee611a4     PM Peak      14R             1   \n",
+       "\n",
+       "  route_name_used common_shape_id                   shape_array_key  \\\n",
+       "0  5am-10pm daily           11403  453493134b4598d0dbdddb92e825ae24   \n",
+       "1  5am-10pm daily           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "2  5am-10pm daily           11403  453493134b4598d0dbdddb92e825ae24   \n",
+       "3  5am-10pm daily           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "4  5am-10pm daily           11403  453493134b4598d0dbdddb92e825ae24   \n",
+       "5  5am-10pm daily           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "6  5am-10pm daily           11403  453493134b4598d0dbdddb92e825ae24   \n",
+       "7  5am-10pm daily           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "8  5am-10pm daily           11403  453493134b4598d0dbdddb92e825ae24   \n",
+       "9  5am-10pm daily           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "\n",
+       "   speed_mph  service_minutes  change_sec  trip_instance_key  \n",
+       "0      29.38            43.19     3139.44                 16  \n",
+       "1      39.80            50.36     4804.36                 22  \n",
+       "2      37.89            42.00     3555.80                  5  \n",
+       "3      34.42            44.45     4602.45                 11  \n",
+       "4      33.69            51.00     3014.44                  9  \n",
+       "5      32.25            53.00     5149.00                  5  \n",
+       "6      32.46            46.94     3371.86                 35  \n",
+       "7      31.30            50.61     4478.18                 33  \n",
+       "8      38.41            49.78     3893.81                 36  \n",
+       "9      31.35            53.71     4823.19                 21  "
+      ]
+     },
+     "execution_count": 148,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "one_route2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 149,
+   "id": "7514d742-2076-487c-84a6-235a6ac65ef4",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>time_of_day</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>route_name</th>\n",
+       "      <th>common_shape_id</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>speed_mph</th>\n",
+       "      <th>avg_sched_trip_min</th>\n",
+       "      <th>n_trips</th>\n",
+       "      <th>avg_rt_trip_min</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11403</td>\n",
+       "      <td>453493134b4598d0dbdddb92e825ae24</td>\n",
+       "      <td>29.40</td>\n",
+       "      <td>43.20</td>\n",
+       "      <td>16</td>\n",
+       "      <td>52.30</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>39.80</td>\n",
+       "      <td>50.40</td>\n",
+       "      <td>22</td>\n",
+       "      <td>80.10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Early AM</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11403</td>\n",
+       "      <td>453493134b4598d0dbdddb92e825ae24</td>\n",
+       "      <td>37.90</td>\n",
+       "      <td>42.00</td>\n",
+       "      <td>5</td>\n",
+       "      <td>59.30</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Early AM</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>34.40</td>\n",
+       "      <td>44.50</td>\n",
+       "      <td>11</td>\n",
+       "      <td>76.70</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Evening</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11403</td>\n",
+       "      <td>453493134b4598d0dbdddb92e825ae24</td>\n",
+       "      <td>33.70</td>\n",
+       "      <td>51.00</td>\n",
+       "      <td>9</td>\n",
+       "      <td>50.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Evening</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>32.30</td>\n",
+       "      <td>53.00</td>\n",
+       "      <td>5</td>\n",
+       "      <td>85.80</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Midday</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11403</td>\n",
+       "      <td>453493134b4598d0dbdddb92e825ae24</td>\n",
+       "      <td>32.50</td>\n",
+       "      <td>46.90</td>\n",
+       "      <td>35</td>\n",
+       "      <td>56.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>Midday</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>31.30</td>\n",
+       "      <td>50.60</td>\n",
+       "      <td>33</td>\n",
+       "      <td>74.60</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>PM Peak</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11403</td>\n",
+       "      <td>453493134b4598d0dbdddb92e825ae24</td>\n",
+       "      <td>38.40</td>\n",
+       "      <td>49.80</td>\n",
+       "      <td>36</td>\n",
+       "      <td>64.90</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>PM Peak</td>\n",
+       "      <td>14R</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>11452</td>\n",
+       "      <td>defb027e7468735f91300a9851f3e1d7</td>\n",
+       "      <td>31.40</td>\n",
+       "      <td>53.70</td>\n",
+       "      <td>21</td>\n",
+       "      <td>80.40</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   gtfs_dataset_key time_of_day route_id  direction_id  \\\n",
+       "0  c0e3039da063db95ebabd3fe4ee611a4     AM Peak      14R             0   \n",
+       "1  c0e3039da063db95ebabd3fe4ee611a4     AM Peak      14R             1   \n",
+       "2  c0e3039da063db95ebabd3fe4ee611a4    Early AM      14R             0   \n",
+       "3  c0e3039da063db95ebabd3fe4ee611a4    Early AM      14R             1   \n",
+       "4  c0e3039da063db95ebabd3fe4ee611a4     Evening      14R             0   \n",
+       "5  c0e3039da063db95ebabd3fe4ee611a4     Evening      14R             1   \n",
+       "6  c0e3039da063db95ebabd3fe4ee611a4      Midday      14R             0   \n",
+       "7  c0e3039da063db95ebabd3fe4ee611a4      Midday      14R             1   \n",
+       "8  c0e3039da063db95ebabd3fe4ee611a4     PM Peak      14R             0   \n",
+       "9  c0e3039da063db95ebabd3fe4ee611a4     PM Peak      14R             1   \n",
+       "\n",
+       "       route_name common_shape_id                   shape_array_key  \\\n",
+       "0  5am-10pm daily           11403  453493134b4598d0dbdddb92e825ae24   \n",
+       "1  5am-10pm daily           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "2  5am-10pm daily           11403  453493134b4598d0dbdddb92e825ae24   \n",
+       "3  5am-10pm daily           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "4  5am-10pm daily           11403  453493134b4598d0dbdddb92e825ae24   \n",
+       "5  5am-10pm daily           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "6  5am-10pm daily           11403  453493134b4598d0dbdddb92e825ae24   \n",
+       "7  5am-10pm daily           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "8  5am-10pm daily           11403  453493134b4598d0dbdddb92e825ae24   \n",
+       "9  5am-10pm daily           11452  defb027e7468735f91300a9851f3e1d7   \n",
+       "\n",
+       "   speed_mph  avg_sched_trip_min  n_trips  avg_rt_trip_min  \n",
+       "0      29.40               43.20       16            52.30  \n",
+       "1      39.80               50.40       22            80.10  \n",
+       "2      37.90               42.00        5            59.30  \n",
+       "3      34.40               44.50       11            76.70  \n",
+       "4      33.70               51.00        9            50.20  \n",
+       "5      32.30               53.00        5            85.80  \n",
+       "6      32.50               46.90       35            56.20  \n",
+       "7      31.30               50.60       33            74.60  \n",
+       "8      38.40               49.80       36            64.90  \n",
+       "9      31.40               53.70       21            80.40  "
+      ]
+     },
+     "execution_count": 149,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "one_route2.assign(\n",
+    "        avg_rt_trip_min = one_route2.change_sec.divide(60).round(1),\n",
+    "        service_minutes = one_route2.service_minutes.round(1),\n",
+    "        speed_mph = one_route2.speed_mph.round(1),\n",
+    "    ).rename(columns = {\n",
+    "        \"service_minutes\": \"avg_sched_trip_min\",\n",
+    "        \"trip_instance_key\": \"n_trips\",\n",
+    "        \"route_name_used\": \"route_name\",\n",
+    "    }).drop(columns = \"change_sec\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 150,
+   "id": "9279c8f2-ea9b-4476-b8e0-717774396fd2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C3_trip_route_speed.py#L168-L177\n",
+    "c3_m4 = (c3_m3.groupby(group_cols, \n",
+    "                       observed = True, group_keys = False)\n",
+    "           .agg({\n",
+    "               \"speed_mph\": \"mean\",\n",
+    "               \"service_minutes\": \"mean\",\n",
+    "               \"change_sec\": \"mean\",\n",
+    "               \"trip_instance_key\": \"count\"\n",
+    "           }).reset_index()\n",
+    "          )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 151,
+   "id": "d4440381-13fe-45c0-86a5-e0c3423c037f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C3_trip_route_speed.py#L178-L188\n",
+    "c3_m4 = c3_m4.assign(\n",
+    "        avg_rt_trip_min = c3_m4.change_sec.divide(60).round(1),\n",
+    "        service_minutes = c3_m4.service_minutes.round(1),\n",
+    "        speed_mph = c3_m4.speed_mph.round(1),\n",
+    "    ).rename(columns = {\n",
+    "        \"service_minutes\": \"avg_sched_trip_min\",\n",
+    "        \"trip_instance_key\": \"n_trips\",\n",
+    "        \"route_name_used\": \"route_name\",\n",
+    "    }).drop(columns = \"change_sec\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2c70074a-c4d4-4b73-a43f-7516f9ac9bdf",
+   "metadata": {},
+   "source": [
+    "#### Checks"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d9186189-d512-48c6-b1eb-8253561df44d",
+   "metadata": {},
+   "source": [
+    "##### Shape 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 152,
+   "id": "d1b02f96-e561-4b68-87da-cc2c6838ec1d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "shape_array_1 = \"0055ea6cd09cc68606d37851a6c91366\"\n",
+    "shape1_time = \"AM Peak\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 153,
+   "id": "3d9a7c26-3dd1-4589-8412-f0b763da274c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def check_shapes(shape_array, time_of_day):\n",
+    "    display(c3_m4.loc[(c3_m4.shape_array_key == shape_array) & (c3_m4.time_of_day == time_of_day)])\n",
+    "    display(c3_m3.loc[(c3_m3.shape_array_key == shape_array) & (c3_m3.time_of_day == time_of_day)])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 154,
+   "id": "fdacca64-50e2-4160-92bd-cda2e279d887",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>time_of_day</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>route_name</th>\n",
+       "      <th>common_shape_id</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>speed_mph</th>\n",
+       "      <th>avg_sched_trip_min</th>\n",
+       "      <th>n_trips</th>\n",
+       "      <th>avg_rt_trip_min</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>69</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>55</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>260</td>\n",
+       "      <td>0055ea6cd09cc68606d37851a6c91366</td>\n",
+       "      <td>10.10</td>\n",
+       "      <td>16.00</td>\n",
+       "      <td>4</td>\n",
+       "      <td>31.70</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                    gtfs_dataset_key time_of_day route_id  direction_id  \\\n",
+       "69  c0e3039da063db95ebabd3fe4ee611a4     AM Peak       55             0   \n",
+       "\n",
+       "        route_name common_shape_id                   shape_array_key  \\\n",
+       "69  5am-10pm daily             260  0055ea6cd09cc68606d37851a6c91366   \n",
+       "\n",
+       "    speed_mph  avg_sched_trip_min  n_trips  avg_rt_trip_min  \n",
+       "69      10.10               16.00        4            31.70  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "      <th>speed_mph</th>\n",
+       "      <th>schedule_gtfs_dataset_key</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>common_shape_id</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>route_name_used</th>\n",
+       "      <th>service_hours</th>\n",
+       "      <th>trip_first_departure_datetime_pacific</th>\n",
+       "      <th>time_of_day</th>\n",
+       "      <th>service_minutes</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>4963</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>b68e89ab04e684839d2cde80be127219</td>\n",
+       "      <td>3832.26</td>\n",
+       "      <td>2365.00</td>\n",
+       "      <td>6.52</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>0</td>\n",
+       "      <td>55</td>\n",
+       "      <td>260</td>\n",
+       "      <td>0055ea6cd09cc68606d37851a6c91366</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>0.27</td>\n",
+       "      <td>2023-10-11 07:59:00</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>16.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5783</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>d32ca8727a4d9c0ee126664507d42c08</td>\n",
+       "      <td>3856.82</td>\n",
+       "      <td>2255.00</td>\n",
+       "      <td>6.99</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>0</td>\n",
+       "      <td>55</td>\n",
+       "      <td>260</td>\n",
+       "      <td>0055ea6cd09cc68606d37851a6c91366</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>0.27</td>\n",
+       "      <td>2023-10-11 09:20:00</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>16.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6308</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>e59e81c33cab600d4009318f354fbf9a</td>\n",
+       "      <td>1662.33</td>\n",
+       "      <td>881.00</td>\n",
+       "      <td>3.59</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>0</td>\n",
+       "      <td>55</td>\n",
+       "      <td>260</td>\n",
+       "      <td>0055ea6cd09cc68606d37851a6c91366</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>0.27</td>\n",
+       "      <td>2023-10-11 08:20:00</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>16.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6559</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>ef66bcc7ebab13dc4cd4e2b0c6085ee7</td>\n",
+       "      <td>3843.80</td>\n",
+       "      <td>2099.00</td>\n",
+       "      <td>23.18</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>0</td>\n",
+       "      <td>55</td>\n",
+       "      <td>260</td>\n",
+       "      <td>0055ea6cd09cc68606d37851a6c91366</td>\n",
+       "      <td>5am-10pm daily</td>\n",
+       "      <td>0.27</td>\n",
+       "      <td>2023-10-11 09:41:00</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>16.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      gtfs_dataset_key                 trip_instance_key  \\\n",
+       "4963  c0e3039da063db95ebabd3fe4ee611a4  b68e89ab04e684839d2cde80be127219   \n",
+       "5783  c0e3039da063db95ebabd3fe4ee611a4  d32ca8727a4d9c0ee126664507d42c08   \n",
+       "6308  c0e3039da063db95ebabd3fe4ee611a4  e59e81c33cab600d4009318f354fbf9a   \n",
+       "6559  c0e3039da063db95ebabd3fe4ee611a4  ef66bcc7ebab13dc4cd4e2b0c6085ee7   \n",
+       "\n",
+       "      change_meters  change_sec  speed_mph         schedule_gtfs_dataset_key  \\\n",
+       "4963        3832.26     2365.00       6.52  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "5783        3856.82     2255.00       6.99  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "6308        1662.33      881.00       3.59  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "6559        3843.80     2099.00      23.18  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "\n",
+       "      direction_id route_id common_shape_id                   shape_array_key  \\\n",
+       "4963             0       55             260  0055ea6cd09cc68606d37851a6c91366   \n",
+       "5783             0       55             260  0055ea6cd09cc68606d37851a6c91366   \n",
+       "6308             0       55             260  0055ea6cd09cc68606d37851a6c91366   \n",
+       "6559             0       55             260  0055ea6cd09cc68606d37851a6c91366   \n",
+       "\n",
+       "     route_name_used  service_hours trip_first_departure_datetime_pacific  \\\n",
+       "4963  5am-10pm daily           0.27                   2023-10-11 07:59:00   \n",
+       "5783  5am-10pm daily           0.27                   2023-10-11 09:20:00   \n",
+       "6308  5am-10pm daily           0.27                   2023-10-11 08:20:00   \n",
+       "6559  5am-10pm daily           0.27                   2023-10-11 09:41:00   \n",
+       "\n",
+       "     time_of_day  service_minutes  \n",
+       "4963     AM Peak            16.00  \n",
+       "5783     AM Peak            16.00  \n",
+       "6308     AM Peak            16.00  \n",
+       "6559     AM Peak            16.00  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "check_shapes(shape_array_1, shape1_time)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 155,
+   "id": "327155b2-c46d-4d89-be06-58f5f2f324cc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "31.666666666666668"
+      ]
+     },
+     "execution_count": 155,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "(2365+2255+881+2099)/4/60"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "07b4ca28-3a71-424c-b742-9b47bc4176db",
+   "metadata": {},
+   "source": [
+    "##### Shape 2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 156,
+   "id": "e391d24c-0def-4475-b570-dcb4c0fdb82d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "shape_key2 = \"e52c291259f04c198a0c1f245ec26be9\"\n",
+    "time2 = \"AM Peak\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 157,
+   "id": "f0513f75-7ade-4eb5-a5cf-95e7cb647ab8",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>time_of_day</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>route_name</th>\n",
+       "      <th>common_shape_id</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>speed_mph</th>\n",
+       "      <th>avg_sched_trip_min</th>\n",
+       "      <th>n_trips</th>\n",
+       "      <th>avg_rt_trip_min</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>65</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>52</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Weekdays 6am-10pm Weekends 8am-10pm</td>\n",
+       "      <td>5200</td>\n",
+       "      <td>e52c291259f04c198a0c1f245ec26be9</td>\n",
+       "      <td>15.90</td>\n",
+       "      <td>26.00</td>\n",
+       "      <td>6</td>\n",
+       "      <td>47.50</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                    gtfs_dataset_key time_of_day route_id  direction_id  \\\n",
+       "65  c0e3039da063db95ebabd3fe4ee611a4     AM Peak       52             0   \n",
+       "\n",
+       "                             route_name common_shape_id  \\\n",
+       "65  Weekdays 6am-10pm Weekends 8am-10pm            5200   \n",
+       "\n",
+       "                     shape_array_key  speed_mph  avg_sched_trip_min  n_trips  \\\n",
+       "65  e52c291259f04c198a0c1f245ec26be9      15.90               26.00        6   \n",
+       "\n",
+       "    avg_rt_trip_min  \n",
+       "65            47.50  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "      <th>speed_mph</th>\n",
+       "      <th>schedule_gtfs_dataset_key</th>\n",
+       "      <th>direction_id</th>\n",
+       "      <th>route_id</th>\n",
+       "      <th>common_shape_id</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>route_name_used</th>\n",
+       "      <th>service_hours</th>\n",
+       "      <th>trip_first_departure_datetime_pacific</th>\n",
+       "      <th>time_of_day</th>\n",
+       "      <th>service_minutes</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>57</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>027ffc2ecdce130df8e8b2f2d81b17d6</td>\n",
+       "      <td>6505.34</td>\n",
+       "      <td>2703.00</td>\n",
+       "      <td>18.19</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>0</td>\n",
+       "      <td>52</td>\n",
+       "      <td>5200</td>\n",
+       "      <td>e52c291259f04c198a0c1f245ec26be9</td>\n",
+       "      <td>Weekdays 6am-10pm Weekends 8am-10pm</td>\n",
+       "      <td>0.40</td>\n",
+       "      <td>2023-10-11 09:34:00</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>24.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>91</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>03b5bb249b7188cc3935b355ad008a82</td>\n",
+       "      <td>6625.95</td>\n",
+       "      <td>2548.00</td>\n",
+       "      <td>18.46</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>0</td>\n",
+       "      <td>52</td>\n",
+       "      <td>5200</td>\n",
+       "      <td>e52c291259f04c198a0c1f245ec26be9</td>\n",
+       "      <td>Weekdays 6am-10pm Weekends 8am-10pm</td>\n",
+       "      <td>0.48</td>\n",
+       "      <td>2023-10-11 07:56:00</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>29.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2101</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>50848f3ca9a5b8db9149cf4d4c0ce008</td>\n",
+       "      <td>6660.49</td>\n",
+       "      <td>3261.00</td>\n",
+       "      <td>12.02</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>0</td>\n",
+       "      <td>52</td>\n",
+       "      <td>5200</td>\n",
+       "      <td>e52c291259f04c198a0c1f245ec26be9</td>\n",
+       "      <td>Weekdays 6am-10pm Weekends 8am-10pm</td>\n",
+       "      <td>0.42</td>\n",
+       "      <td>2023-10-11 08:34:00</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>25.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4013</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>94f8ca1587768bca12471d4dfd63cace</td>\n",
+       "      <td>6786.87</td>\n",
+       "      <td>2735.00</td>\n",
+       "      <td>14.68</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>0</td>\n",
+       "      <td>52</td>\n",
+       "      <td>5200</td>\n",
+       "      <td>e52c291259f04c198a0c1f245ec26be9</td>\n",
+       "      <td>Weekdays 6am-10pm Weekends 8am-10pm</td>\n",
+       "      <td>0.42</td>\n",
+       "      <td>2023-10-11 08:54:00</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>25.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4699</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>acf1b602311569dd97867a45b5c16e4c</td>\n",
+       "      <td>9837.34</td>\n",
+       "      <td>3691.00</td>\n",
+       "      <td>17.80</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>0</td>\n",
+       "      <td>52</td>\n",
+       "      <td>5200</td>\n",
+       "      <td>e52c291259f04c198a0c1f245ec26be9</td>\n",
+       "      <td>Weekdays 6am-10pm Weekends 8am-10pm</td>\n",
+       "      <td>0.48</td>\n",
+       "      <td>2023-10-11 08:15:00</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>29.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6700</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>f5058b9f8fe6df4e55644a6cc0896faf</td>\n",
+       "      <td>6657.79</td>\n",
+       "      <td>2162.00</td>\n",
+       "      <td>14.39</td>\n",
+       "      <td>7cc0cb1871dfd558f11a2885c145d144</td>\n",
+       "      <td>0</td>\n",
+       "      <td>52</td>\n",
+       "      <td>5200</td>\n",
+       "      <td>e52c291259f04c198a0c1f245ec26be9</td>\n",
+       "      <td>Weekdays 6am-10pm Weekends 8am-10pm</td>\n",
+       "      <td>0.40</td>\n",
+       "      <td>2023-10-11 09:55:00</td>\n",
+       "      <td>AM Peak</td>\n",
+       "      <td>24.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      gtfs_dataset_key                 trip_instance_key  \\\n",
+       "57    c0e3039da063db95ebabd3fe4ee611a4  027ffc2ecdce130df8e8b2f2d81b17d6   \n",
+       "91    c0e3039da063db95ebabd3fe4ee611a4  03b5bb249b7188cc3935b355ad008a82   \n",
+       "2101  c0e3039da063db95ebabd3fe4ee611a4  50848f3ca9a5b8db9149cf4d4c0ce008   \n",
+       "4013  c0e3039da063db95ebabd3fe4ee611a4  94f8ca1587768bca12471d4dfd63cace   \n",
+       "4699  c0e3039da063db95ebabd3fe4ee611a4  acf1b602311569dd97867a45b5c16e4c   \n",
+       "6700  c0e3039da063db95ebabd3fe4ee611a4  f5058b9f8fe6df4e55644a6cc0896faf   \n",
+       "\n",
+       "      change_meters  change_sec  speed_mph         schedule_gtfs_dataset_key  \\\n",
+       "57          6505.34     2703.00      18.19  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "91          6625.95     2548.00      18.46  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "2101        6660.49     3261.00      12.02  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "4013        6786.87     2735.00      14.68  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "4699        9837.34     3691.00      17.80  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "6700        6657.79     2162.00      14.39  7cc0cb1871dfd558f11a2885c145d144   \n",
+       "\n",
+       "      direction_id route_id common_shape_id                   shape_array_key  \\\n",
+       "57               0       52            5200  e52c291259f04c198a0c1f245ec26be9   \n",
+       "91               0       52            5200  e52c291259f04c198a0c1f245ec26be9   \n",
+       "2101             0       52            5200  e52c291259f04c198a0c1f245ec26be9   \n",
+       "4013             0       52            5200  e52c291259f04c198a0c1f245ec26be9   \n",
+       "4699             0       52            5200  e52c291259f04c198a0c1f245ec26be9   \n",
+       "6700             0       52            5200  e52c291259f04c198a0c1f245ec26be9   \n",
+       "\n",
+       "                          route_name_used  service_hours  \\\n",
+       "57    Weekdays 6am-10pm Weekends 8am-10pm           0.40   \n",
+       "91    Weekdays 6am-10pm Weekends 8am-10pm           0.48   \n",
+       "2101  Weekdays 6am-10pm Weekends 8am-10pm           0.42   \n",
+       "4013  Weekdays 6am-10pm Weekends 8am-10pm           0.42   \n",
+       "4699  Weekdays 6am-10pm Weekends 8am-10pm           0.48   \n",
+       "6700  Weekdays 6am-10pm Weekends 8am-10pm           0.40   \n",
+       "\n",
+       "     trip_first_departure_datetime_pacific time_of_day  service_minutes  \n",
+       "57                     2023-10-11 09:34:00     AM Peak            24.00  \n",
+       "91                     2023-10-11 07:56:00     AM Peak            29.00  \n",
+       "2101                   2023-10-11 08:34:00     AM Peak            25.00  \n",
+       "4013                   2023-10-11 08:54:00     AM Peak            25.00  \n",
+       "4699                   2023-10-11 08:15:00     AM Peak            29.00  \n",
+       "6700                   2023-10-11 09:55:00     AM Peak            24.00  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "check_shapes(shape_key2, time2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "69d4639b-a9e9-44d0-8398-3aca1a0a11ff",
+   "metadata": {},
+   "source": [
+    "## Outer Join\n",
+    "#### Question: how to connect back to trip instance key?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 183,
+   "id": "41d4e8fd-33fa-4dfc-aa12-98c8abe16240",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "pandas.core.frame.DataFrame"
+      ]
+     },
+     "execution_count": 183,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Spatial Accuracy\n",
+    "type(muni)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 184,
+   "id": "dfb2e9c8-67d3-4a4d-b64a-eebac0f35bac",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['trip_instance_key', 'total_vp', 'vp_in_shape'], dtype='object')"
+      ]
+     },
+     "execution_count": 184,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "muni.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 185,
+   "id": "6b2780f0-a359-4fb1-9082-2c7d40ba42df",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9240"
+      ]
+     },
+     "execution_count": 185,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "muni.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 186,
+   "id": "05adc5b0-2a0b-4860-af3d-bda2349bff99",
+   "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_instance_key</th>\n",
+       "      <th>total_vp</th>\n",
+       "      <th>vp_in_shape</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>00068c2e2316950af50ffaa9584c7a46</td>\n",
+       "      <td>126</td>\n",
+       "      <td>126</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>000c62b70d9438b7951457a74a4c89b2</td>\n",
+       "      <td>152</td>\n",
+       "      <td>140</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0010126e10a24f22fb36018ed0f79572</td>\n",
+       "      <td>413</td>\n",
+       "      <td>315</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0013822d90020aa52bae3dab73d15fd0</td>\n",
+       "      <td>205</td>\n",
+       "      <td>205</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>001a66b1633388f4fe9eea5acf374481</td>\n",
+       "      <td>227</td>\n",
+       "      <td>227</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  trip_instance_key  total_vp  vp_in_shape\n",
+       "0  00068c2e2316950af50ffaa9584c7a46       126          126\n",
+       "1  000c62b70d9438b7951457a74a4c89b2       152          140\n",
+       "2  0010126e10a24f22fb36018ed0f79572       413          315\n",
+       "3  0013822d90020aa52bae3dab73d15fd0       205          205\n",
+       "4  001a66b1633388f4fe9eea5acf374481       227          227"
+      ]
+     },
+     "execution_count": 186,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "muni.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 187,
+   "id": "fd016ce7-c607-41c4-8fe3-fd5835a8abc2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['trip_instance_key', 'min_time', 'max_time', 'atleast2_trip_updates',\n",
+       "       'trip_min_elapsed', 'pct_update_complete', 'larger', 'test_mask',\n",
+       "       'pct_update_complete2'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 187,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Update Completeness\n",
+    "test_group3.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 188,
+   "id": "09b39eab-5919-4b96-a127-a9e4ce4f86aa",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9240"
+      ]
+     },
+     "execution_count": 188,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 189,
+   "id": "96940334-7067-4f0f-aa6b-564ad1a6848d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_group3 = test_group3.drop(columns = ['min_time','max_time','trip_min_elapsed', 'pct_update_complete','larger','test_mask'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 190,
+   "id": "130b01f7-02a6-49b3-8f87-d76ebbf53a8f",
+   "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_instance_key</th>\n",
+       "      <th>atleast2_trip_updates</th>\n",
+       "      <th>pct_update_complete2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>00068c2e2316950af50ffaa9584c7a46</td>\n",
+       "      <td>42</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>000c62b70d9438b7951457a74a4c89b2</td>\n",
+       "      <td>50</td>\n",
+       "      <td>0.98</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0010126e10a24f22fb36018ed0f79572</td>\n",
+       "      <td>138</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0013822d90020aa52bae3dab73d15fd0</td>\n",
+       "      <td>68</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>001a66b1633388f4fe9eea5acf374481</td>\n",
+       "      <td>76</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  trip_instance_key  atleast2_trip_updates  \\\n",
+       "0  00068c2e2316950af50ffaa9584c7a46                     42   \n",
+       "1  000c62b70d9438b7951457a74a4c89b2                     50   \n",
+       "2  0010126e10a24f22fb36018ed0f79572                    138   \n",
+       "3  0013822d90020aa52bae3dab73d15fd0                     68   \n",
+       "4  001a66b1633388f4fe9eea5acf374481                     76   \n",
+       "\n",
+       "   pct_update_complete2  \n",
+       "0                  1.00  \n",
+       "1                  0.98  \n",
+       "2                  1.00  \n",
+       "3                  1.00  \n",
+       "4                  1.00  "
+      ]
+     },
+     "execution_count": 190,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_group3.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 191,
+   "id": "a24dbf3a-e060-49b1-982b-2a583c98286a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "outer_merge1 = pd.merge(test_group3, muni, \n",
+    "                        on = \"trip_instance_key\",\n",
+    "                        how = \"outer\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 192,
+   "id": "320cb842-c935-4c40-b7c9-6396c820da68",
+   "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_instance_key</th>\n",
+       "      <th>atleast2_trip_updates</th>\n",
+       "      <th>pct_update_complete2</th>\n",
+       "      <th>total_vp</th>\n",
+       "      <th>vp_in_shape</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>3202</th>\n",
+       "      <td>5a26483ef38d216c42696681ee376614</td>\n",
+       "      <td>71</td>\n",
+       "      <td>0.95</td>\n",
+       "      <td>217</td>\n",
+       "      <td>183</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     trip_instance_key  atleast2_trip_updates  \\\n",
+       "3202  5a26483ef38d216c42696681ee376614                     71   \n",
+       "\n",
+       "      pct_update_complete2  total_vp  vp_in_shape  \n",
+       "3202                  0.95       217          183  "
+      ]
+     },
+     "execution_count": 192,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "outer_merge1.sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 202,
+   "id": "44c12eae-0c78-4d50-9a48-42cbd7c2521f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9240"
+      ]
+     },
+     "execution_count": 202,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "outer_merge1.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 193,
+   "id": "f75301c2-96bd-487e-9c10-176777fc4f8c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['gtfs_dataset_key', 'trip_instance_key', 'change_meters', 'change_sec',\n",
+       "       'speed_mph', 'schedule_gtfs_dataset_key', 'direction_id', 'route_id',\n",
+       "       'common_shape_id', 'shape_array_key', 'route_name_used',\n",
+       "       'service_hours', 'trip_first_departure_datetime_pacific', 'time_of_day',\n",
+       "       'service_minutes'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 193,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m3.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 194,
+   "id": "2ee51b82-169c-449b-a507-103c9a839dbf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Averages\n",
+    "crosswalk_back_to_trips = c3_m3[['shape_array_key','gtfs_dataset_key','time_of_day','trip_instance_key']].drop_duplicates().reset_index(drop = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 195,
+   "id": "7d5ddf3f-4cc8-43af-9575-c90bece499fb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "6993"
+      ]
+     },
+     "execution_count": 195,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "crosswalk_back_to_trips.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 196,
+   "id": "5d3a24fd-362f-4a62-9fcf-c7f03b2770f3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "outer_merge2 = pd.merge(outer_merge1, crosswalk_back_to_trips, \n",
+    "                        on = \"trip_instance_key\",\n",
+    "                        how = \"outer\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 197,
+   "id": "2d6b71df-80e9-4fbd-8ac2-e1f55ba04929",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['trip_instance_key', 'atleast2_trip_updates', 'pct_update_complete2',\n",
+       "       'total_vp', 'vp_in_shape', 'shape_array_key', 'gtfs_dataset_key',\n",
+       "       'time_of_day'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 197,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "outer_merge2.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 198,
+   "id": "6030cb7f-5655-4132-b214-4259e5d5090e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['gtfs_dataset_key', 'time_of_day', 'route_id', 'direction_id',\n",
+       "       'route_name', 'common_shape_id', 'shape_array_key', 'speed_mph',\n",
+       "       'avg_sched_trip_min', 'n_trips', 'avg_rt_trip_min'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 198,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m4.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 199,
+   "id": "c8bea8f0-ea00-4e1d-9783-398f277e768c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "outer_merge3 = pd.merge(outer_merge2, c3_m4, \n",
+    "                        on = [\"gtfs_dataset_key\", \"shape_array_key\", \"time_of_day\"],\n",
+    "                        how = \"outer\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fe34ed54-badd-45ed-8ee2-f18a51207b3c",
+   "metadata": {},
+   "source": [
+    "#### Question: even if we drop the speeds, we should still have the shape_array_key and whatnot?\n",
+    "* How come some of the rows have no speeds?? What went wrong?\n",
+    "* 519cc26f9599677993f8d8cd269eb3cc should have a speed?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 206,
+   "id": "e3883628-9629-45ef-9a29-d5f4e60215c2",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "      <th>speed_mph</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2900</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>519cc26f9599677993f8d8cd269eb3cc</td>\n",
+       "      <td>11329.47</td>\n",
+       "      <td>2960.00</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      gtfs_dataset_key                 trip_instance_key  \\\n",
+       "2900  c0e3039da063db95ebabd3fe4ee611a4  519cc26f9599677993f8d8cd269eb3cc   \n",
+       "\n",
+       "      change_meters  change_sec  speed_mph  \n",
+       "2900       11329.47     2960.00        NaN  "
+      ]
+     },
+     "execution_count": 206,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m2.loc[c3_m2.trip_instance_key == \"519cc26f9599677993f8d8cd269eb3cc\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 208,
+   "id": "363d9f9e-a299-4e70-8e80-ce608b74bd18",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>location_timestamp_local</th>\n",
+       "      <th>vp_idx</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>vp_geometry</th>\n",
+       "      <th>shape_meters</th>\n",
+       "      <th>prior_dist</th>\n",
+       "      <th>prior_time</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>15100</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>519cc26f9599677993f8d8cd269eb3cc</td>\n",
+       "      <td>2023-10-11 20:02:59</td>\n",
+       "      <td>11958556</td>\n",
+       "      <td>15955f0486291f4d897d69cc2e2db08d</td>\n",
+       "      <td>POINT (-208310.474 -19578.210)</td>\n",
+       "      <td>146.29</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15101</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>519cc26f9599677993f8d8cd269eb3cc</td>\n",
+       "      <td>2023-10-11 20:15:16</td>\n",
+       "      <td>11958593</td>\n",
+       "      <td>15955f0486291f4d897d69cc2e2db08d</td>\n",
+       "      <td>POINT (-208720.144 -18849.817)</td>\n",
+       "      <td>4400.58</td>\n",
+       "      <td>146.29</td>\n",
+       "      <td>2023-10-11 20:02:59</td>\n",
+       "      <td>4254.30</td>\n",
+       "      <td>737.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15102</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>519cc26f9599677993f8d8cd269eb3cc</td>\n",
+       "      <td>2023-10-11 20:27:31</td>\n",
+       "      <td>11958630</td>\n",
+       "      <td>15955f0486291f4d897d69cc2e2db08d</td>\n",
+       "      <td>POINT (-210732.513 -22505.869)</td>\n",
+       "      <td>11426.63</td>\n",
+       "      <td>4400.58</td>\n",
+       "      <td>2023-10-11 20:15:16</td>\n",
+       "      <td>7026.05</td>\n",
+       "      <td>735.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15103</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>519cc26f9599677993f8d8cd269eb3cc</td>\n",
+       "      <td>2023-10-11 20:39:48</td>\n",
+       "      <td>11958667</td>\n",
+       "      <td>15955f0486291f4d897d69cc2e2db08d</td>\n",
+       "      <td>POINT (-210720.177 -22491.169)</td>\n",
+       "      <td>11445.89</td>\n",
+       "      <td>11426.63</td>\n",
+       "      <td>2023-10-11 20:27:31</td>\n",
+       "      <td>19.26</td>\n",
+       "      <td>737.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15104</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>519cc26f9599677993f8d8cd269eb3cc</td>\n",
+       "      <td>2023-10-11 20:52:19</td>\n",
+       "      <td>11958704</td>\n",
+       "      <td>15955f0486291f4d897d69cc2e2db08d</td>\n",
+       "      <td>POINT (-210647.181 -22436.301)</td>\n",
+       "      <td>11475.76</td>\n",
+       "      <td>11445.89</td>\n",
+       "      <td>2023-10-11 20:39:48</td>\n",
+       "      <td>29.86</td>\n",
+       "      <td>751.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       gtfs_dataset_key                 trip_instance_key  \\\n",
+       "15100  c0e3039da063db95ebabd3fe4ee611a4  519cc26f9599677993f8d8cd269eb3cc   \n",
+       "15101  c0e3039da063db95ebabd3fe4ee611a4  519cc26f9599677993f8d8cd269eb3cc   \n",
+       "15102  c0e3039da063db95ebabd3fe4ee611a4  519cc26f9599677993f8d8cd269eb3cc   \n",
+       "15103  c0e3039da063db95ebabd3fe4ee611a4  519cc26f9599677993f8d8cd269eb3cc   \n",
+       "15104  c0e3039da063db95ebabd3fe4ee611a4  519cc26f9599677993f8d8cd269eb3cc   \n",
+       "\n",
+       "      location_timestamp_local    vp_idx                   shape_array_key  \\\n",
+       "15100      2023-10-11 20:02:59  11958556  15955f0486291f4d897d69cc2e2db08d   \n",
+       "15101      2023-10-11 20:15:16  11958593  15955f0486291f4d897d69cc2e2db08d   \n",
+       "15102      2023-10-11 20:27:31  11958630  15955f0486291f4d897d69cc2e2db08d   \n",
+       "15103      2023-10-11 20:39:48  11958667  15955f0486291f4d897d69cc2e2db08d   \n",
+       "15104      2023-10-11 20:52:19  11958704  15955f0486291f4d897d69cc2e2db08d   \n",
+       "\n",
+       "                          vp_geometry  shape_meters  prior_dist  \\\n",
+       "15100  POINT (-208310.474 -19578.210)        146.29         NaN   \n",
+       "15101  POINT (-208720.144 -18849.817)       4400.58      146.29   \n",
+       "15102  POINT (-210732.513 -22505.869)      11426.63     4400.58   \n",
+       "15103  POINT (-210720.177 -22491.169)      11445.89    11426.63   \n",
+       "15104  POINT (-210647.181 -22436.301)      11475.76    11445.89   \n",
+       "\n",
+       "               prior_time  change_meters  change_sec  \n",
+       "15100                 NaT            NaN         NaN  \n",
+       "15101 2023-10-11 20:02:59        4254.30      737.00  \n",
+       "15102 2023-10-11 20:15:16        7026.05      735.00  \n",
+       "15103 2023-10-11 20:27:31          19.26      737.00  \n",
+       "15104 2023-10-11 20:39:48          29.86      751.00  "
+      ]
+     },
+     "execution_count": 208,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m1.loc[c3_m1.trip_instance_key == \"519cc26f9599677993f8d8cd269eb3cc\"].drop(columns = ['shape_geometry'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "596112c3-1cc8-434e-97b5-12f1dc2864c7",
+   "metadata": {},
+   "source": [
+    "#### check w/ another trip"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 215,
+   "id": "b254128f-6388-4315-b99d-0616c973f3a1",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "      <th>speed_mph</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>5290</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>9359a381c89e52b7bc78bb4942e4b077</td>\n",
+       "      <td>4872.66</td>\n",
+       "      <td>5109.00</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      gtfs_dataset_key                 trip_instance_key  \\\n",
+       "5290  c0e3039da063db95ebabd3fe4ee611a4  9359a381c89e52b7bc78bb4942e4b077   \n",
+       "\n",
+       "      change_meters  change_sec  speed_mph  \n",
+       "5290        4872.66     5109.00        NaN  "
+      ]
+     },
+     "execution_count": 215,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m2.loc[c3_m2.trip_instance_key == \"9359a381c89e52b7bc78bb4942e4b077\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 216,
+   "id": "e38be645-43bf-4f7a-9a08-108fdfe76f7c",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>location_timestamp_local</th>\n",
+       "      <th>vp_idx</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>vp_geometry</th>\n",
+       "      <th>shape_meters</th>\n",
+       "      <th>prior_dist</th>\n",
+       "      <th>prior_time</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2105</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>9359a381c89e52b7bc78bb4942e4b077</td>\n",
+       "      <td>2023-10-11 07:22:58</td>\n",
+       "      <td>11475833</td>\n",
+       "      <td>6b99e6706ef5d2fb8e8518256a3c00c4</td>\n",
+       "      <td>POINT (-215158.815 -23030.763)</td>\n",
+       "      <td>357.86</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2106</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>9359a381c89e52b7bc78bb4942e4b077</td>\n",
+       "      <td>2023-10-11 07:44:17</td>\n",
+       "      <td>11475897</td>\n",
+       "      <td>6b99e6706ef5d2fb8e8518256a3c00c4</td>\n",
+       "      <td>POINT (-215158.815 -23030.763)</td>\n",
+       "      <td>357.86</td>\n",
+       "      <td>357.86</td>\n",
+       "      <td>2023-10-11 07:22:58</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1279.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2107</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>9359a381c89e52b7bc78bb4942e4b077</td>\n",
+       "      <td>2023-10-11 08:05:37</td>\n",
+       "      <td>11475961</td>\n",
+       "      <td>6b99e6706ef5d2fb8e8518256a3c00c4</td>\n",
+       "      <td>POINT (-213850.819 -22835.343)</td>\n",
+       "      <td>1645.28</td>\n",
+       "      <td>357.86</td>\n",
+       "      <td>2023-10-11 07:44:17</td>\n",
+       "      <td>1287.42</td>\n",
+       "      <td>1280.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2108</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>9359a381c89e52b7bc78bb4942e4b077</td>\n",
+       "      <td>2023-10-11 08:27:00</td>\n",
+       "      <td>11476025</td>\n",
+       "      <td>6b99e6706ef5d2fb8e8518256a3c00c4</td>\n",
+       "      <td>POINT (-210713.785 -22130.479)</td>\n",
+       "      <td>5150.33</td>\n",
+       "      <td>1645.28</td>\n",
+       "      <td>2023-10-11 08:05:37</td>\n",
+       "      <td>3505.05</td>\n",
+       "      <td>1283.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2109</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>9359a381c89e52b7bc78bb4942e4b077</td>\n",
+       "      <td>2023-10-11 08:48:07</td>\n",
+       "      <td>11476089</td>\n",
+       "      <td>6b99e6706ef5d2fb8e8518256a3c00c4</td>\n",
+       "      <td>POINT (-210637.615 -22057.788)</td>\n",
+       "      <td>5230.53</td>\n",
+       "      <td>5150.33</td>\n",
+       "      <td>2023-10-11 08:27:00</td>\n",
+       "      <td>80.19</td>\n",
+       "      <td>1267.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      gtfs_dataset_key                 trip_instance_key  \\\n",
+       "2105  c0e3039da063db95ebabd3fe4ee611a4  9359a381c89e52b7bc78bb4942e4b077   \n",
+       "2106  c0e3039da063db95ebabd3fe4ee611a4  9359a381c89e52b7bc78bb4942e4b077   \n",
+       "2107  c0e3039da063db95ebabd3fe4ee611a4  9359a381c89e52b7bc78bb4942e4b077   \n",
+       "2108  c0e3039da063db95ebabd3fe4ee611a4  9359a381c89e52b7bc78bb4942e4b077   \n",
+       "2109  c0e3039da063db95ebabd3fe4ee611a4  9359a381c89e52b7bc78bb4942e4b077   \n",
+       "\n",
+       "     location_timestamp_local    vp_idx                   shape_array_key  \\\n",
+       "2105      2023-10-11 07:22:58  11475833  6b99e6706ef5d2fb8e8518256a3c00c4   \n",
+       "2106      2023-10-11 07:44:17  11475897  6b99e6706ef5d2fb8e8518256a3c00c4   \n",
+       "2107      2023-10-11 08:05:37  11475961  6b99e6706ef5d2fb8e8518256a3c00c4   \n",
+       "2108      2023-10-11 08:27:00  11476025  6b99e6706ef5d2fb8e8518256a3c00c4   \n",
+       "2109      2023-10-11 08:48:07  11476089  6b99e6706ef5d2fb8e8518256a3c00c4   \n",
+       "\n",
+       "                         vp_geometry  shape_meters  prior_dist  \\\n",
+       "2105  POINT (-215158.815 -23030.763)        357.86         NaN   \n",
+       "2106  POINT (-215158.815 -23030.763)        357.86      357.86   \n",
+       "2107  POINT (-213850.819 -22835.343)       1645.28      357.86   \n",
+       "2108  POINT (-210713.785 -22130.479)       5150.33     1645.28   \n",
+       "2109  POINT (-210637.615 -22057.788)       5230.53     5150.33   \n",
+       "\n",
+       "              prior_time  change_meters  change_sec  \n",
+       "2105                 NaT            NaN         NaN  \n",
+       "2106 2023-10-11 07:22:58           0.00     1279.00  \n",
+       "2107 2023-10-11 07:44:17        1287.42     1280.00  \n",
+       "2108 2023-10-11 08:05:37        3505.05     1283.00  \n",
+       "2109 2023-10-11 08:27:00          80.19     1267.00  "
+      ]
+     },
+     "execution_count": 216,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m1.loc[c3_m1.trip_instance_key == \"9359a381c89e52b7bc78bb4942e4b077\"].drop(columns = ['shape_geometry'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fa73bd7b-9cd5-42d1-a5b2-38cf252ab5f6",
+   "metadata": {},
+   "source": [
+    "#### Check a trip with speed mph"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 217,
+   "id": "326763e6-75d3-4891-af7d-690b5ce1781d",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "      <th>speed_mph</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>6889</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>bfe892c83789ea8fb7cf2bfbf8c3704a</td>\n",
+       "      <td>6745.28</td>\n",
+       "      <td>2668.00</td>\n",
+       "      <td>12.51</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      gtfs_dataset_key                 trip_instance_key  \\\n",
+       "6889  c0e3039da063db95ebabd3fe4ee611a4  bfe892c83789ea8fb7cf2bfbf8c3704a   \n",
+       "\n",
+       "      change_meters  change_sec  speed_mph  \n",
+       "6889        6745.28     2668.00      12.51  "
+      ]
+     },
+     "execution_count": 217,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m2.loc[~c3_m2.speed_mph.isna()].sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 218,
+   "id": "f711e45d-98f8-40ed-a599-658669fd21d6",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "      <th>speed_mph</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>6889</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>bfe892c83789ea8fb7cf2bfbf8c3704a</td>\n",
+       "      <td>6745.28</td>\n",
+       "      <td>2668.00</td>\n",
+       "      <td>12.51</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      gtfs_dataset_key                 trip_instance_key  \\\n",
+       "6889  c0e3039da063db95ebabd3fe4ee611a4  bfe892c83789ea8fb7cf2bfbf8c3704a   \n",
+       "\n",
+       "      change_meters  change_sec  speed_mph  \n",
+       "6889        6745.28     2668.00      12.51  "
+      ]
+     },
+     "execution_count": 218,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m2.loc[c3_m2.trip_instance_key == \"bfe892c83789ea8fb7cf2bfbf8c3704a\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 219,
+   "id": "36ad980e-d8fa-4a61-aac7-ecc688701625",
+   "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>gtfs_dataset_key</th>\n",
+       "      <th>trip_instance_key</th>\n",
+       "      <th>location_timestamp_local</th>\n",
+       "      <th>vp_idx</th>\n",
+       "      <th>shape_array_key</th>\n",
+       "      <th>vp_geometry</th>\n",
+       "      <th>shape_meters</th>\n",
+       "      <th>prior_dist</th>\n",
+       "      <th>prior_time</th>\n",
+       "      <th>change_meters</th>\n",
+       "      <th>change_sec</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>23620</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>bfe892c83789ea8fb7cf2bfbf8c3704a</td>\n",
+       "      <td>2023-10-11 07:27:20</td>\n",
+       "      <td>12268908</td>\n",
+       "      <td>3493166801a9913231925d9a167b2182</td>\n",
+       "      <td>POINT (-210495.407 -23811.592)</td>\n",
+       "      <td>331.68</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23621</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>bfe892c83789ea8fb7cf2bfbf8c3704a</td>\n",
+       "      <td>2023-10-11 07:38:37</td>\n",
+       "      <td>12268942</td>\n",
+       "      <td>3493166801a9913231925d9a167b2182</td>\n",
+       "      <td>POINT (-210542.304 -23633.930)</td>\n",
+       "      <td>570.97</td>\n",
+       "      <td>331.68</td>\n",
+       "      <td>2023-10-11 07:27:20</td>\n",
+       "      <td>239.29</td>\n",
+       "      <td>677.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23622</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>bfe892c83789ea8fb7cf2bfbf8c3704a</td>\n",
+       "      <td>2023-10-11 07:49:25</td>\n",
+       "      <td>12268975</td>\n",
+       "      <td>3493166801a9913231925d9a167b2182</td>\n",
+       "      <td>POINT (-211724.216 -22030.923)</td>\n",
+       "      <td>2816.80</td>\n",
+       "      <td>570.97</td>\n",
+       "      <td>2023-10-11 07:38:37</td>\n",
+       "      <td>2245.82</td>\n",
+       "      <td>648.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23623</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>bfe892c83789ea8fb7cf2bfbf8c3704a</td>\n",
+       "      <td>2023-10-11 08:00:28</td>\n",
+       "      <td>12269008</td>\n",
+       "      <td>3493166801a9913231925d9a167b2182</td>\n",
+       "      <td>POINT (-213012.221 -21465.442)</td>\n",
+       "      <td>4744.72</td>\n",
+       "      <td>2816.80</td>\n",
+       "      <td>2023-10-11 07:49:25</td>\n",
+       "      <td>1927.92</td>\n",
+       "      <td>663.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23624</th>\n",
+       "      <td>c0e3039da063db95ebabd3fe4ee611a4</td>\n",
+       "      <td>bfe892c83789ea8fb7cf2bfbf8c3704a</td>\n",
+       "      <td>2023-10-11 08:11:48</td>\n",
+       "      <td>12269042</td>\n",
+       "      <td>3493166801a9913231925d9a167b2182</td>\n",
+       "      <td>POINT (-215142.435 -21544.168)</td>\n",
+       "      <td>7076.96</td>\n",
+       "      <td>4744.72</td>\n",
+       "      <td>2023-10-11 08:00:28</td>\n",
+       "      <td>2332.24</td>\n",
+       "      <td>680.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       gtfs_dataset_key                 trip_instance_key  \\\n",
+       "23620  c0e3039da063db95ebabd3fe4ee611a4  bfe892c83789ea8fb7cf2bfbf8c3704a   \n",
+       "23621  c0e3039da063db95ebabd3fe4ee611a4  bfe892c83789ea8fb7cf2bfbf8c3704a   \n",
+       "23622  c0e3039da063db95ebabd3fe4ee611a4  bfe892c83789ea8fb7cf2bfbf8c3704a   \n",
+       "23623  c0e3039da063db95ebabd3fe4ee611a4  bfe892c83789ea8fb7cf2bfbf8c3704a   \n",
+       "23624  c0e3039da063db95ebabd3fe4ee611a4  bfe892c83789ea8fb7cf2bfbf8c3704a   \n",
+       "\n",
+       "      location_timestamp_local    vp_idx                   shape_array_key  \\\n",
+       "23620      2023-10-11 07:27:20  12268908  3493166801a9913231925d9a167b2182   \n",
+       "23621      2023-10-11 07:38:37  12268942  3493166801a9913231925d9a167b2182   \n",
+       "23622      2023-10-11 07:49:25  12268975  3493166801a9913231925d9a167b2182   \n",
+       "23623      2023-10-11 08:00:28  12269008  3493166801a9913231925d9a167b2182   \n",
+       "23624      2023-10-11 08:11:48  12269042  3493166801a9913231925d9a167b2182   \n",
+       "\n",
+       "                          vp_geometry  shape_meters  prior_dist  \\\n",
+       "23620  POINT (-210495.407 -23811.592)        331.68         NaN   \n",
+       "23621  POINT (-210542.304 -23633.930)        570.97      331.68   \n",
+       "23622  POINT (-211724.216 -22030.923)       2816.80      570.97   \n",
+       "23623  POINT (-213012.221 -21465.442)       4744.72     2816.80   \n",
+       "23624  POINT (-215142.435 -21544.168)       7076.96     4744.72   \n",
+       "\n",
+       "               prior_time  change_meters  change_sec  \n",
+       "23620                 NaT            NaN         NaN  \n",
+       "23621 2023-10-11 07:27:20         239.29      677.00  \n",
+       "23622 2023-10-11 07:38:37        2245.82      648.00  \n",
+       "23623 2023-10-11 07:49:25        1927.92      663.00  \n",
+       "23624 2023-10-11 08:00:28        2332.24      680.00  "
+      ]
+     },
+     "execution_count": 219,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "c3_m1.loc[c3_m1.trip_instance_key == \"bfe892c83789ea8fb7cf2bfbf8c3704a\"].drop(columns = ['shape_geometry'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 203,
+   "id": "cecd7b7d-cbb9-4ae9-859b-56c82b47f1b3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9240"
+      ]
+     },
+     "execution_count": 203,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "outer_merge3.trip_instance_key.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 204,
+   "id": "81efe638-1c2c-41d0-a681-38cd310b0f51",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "Int64Index: 9240 entries, 0 to 9239\n",
+      "Data columns (total 16 columns):\n",
+      " #   Column                 Non-Null Count  Dtype   \n",
+      "---  ------                 --------------  -----   \n",
+      " 0   trip_instance_key      9240 non-null   object  \n",
+      " 1   atleast2_trip_updates  9240 non-null   int64   \n",
+      " 2   pct_update_complete2   9240 non-null   float64 \n",
+      " 3   total_vp               9240 non-null   int32   \n",
+      " 4   vp_in_shape            9240 non-null   int32   \n",
+      " 5   shape_array_key        6993 non-null   object  \n",
+      " 6   gtfs_dataset_key       6993 non-null   category\n",
+      " 7   time_of_day            6993 non-null   object  \n",
+      " 8   route_id               6993 non-null   object  \n",
+      " 9   direction_id           6993 non-null   Int64   \n",
+      " 10  route_name             6993 non-null   object  \n",
+      " 11  common_shape_id        6993 non-null   object  \n",
+      " 12  speed_mph              6993 non-null   float64 \n",
+      " 13  avg_sched_trip_min     6993 non-null   float64 \n",
+      " 14  n_trips                6993 non-null   float64 \n",
+      " 15  avg_rt_trip_min        6993 non-null   float64 \n",
+      "dtypes: Int64(1), category(1), float64(5), int32(2), int64(1), object(6)\n",
+      "memory usage: 1.1+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "outer_merge3.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 201,
+   "id": "ca82385c-2138-4ffa-9263-da69926f727c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# check_shapes(\"dfd50ed85c60540a1f9b9c2d1afa93ff\", \"Evening\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "381e9cf3-9dbf-4432-869d-f39d28927a7d",
+   "metadata": {},
+   "source": [
+    "## Final cleaning\n",
+    "* How come you export it twice? \n",
+    "* https://github.com/cal-itp/data-analyses/blob/metrics_rt/rt_segment_speeds/scripts/C3_trip_route_speed.py#L178-L188"
+   ]
+  }
+ ],
+ "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"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}