aggregating candidate info

impact_evaluation/eda_delay_analysis.ipynb

@@ -0,0 +1,88 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import data\n",
+    "\n",
+    "candidates_rt = pd.read_csv('../data/temproary_data/candidate_roundTrip_route.csv')\n",
+    "candidates_rt['round_trip_route_IATA'] = candidates_rt['round_trip_route_IATA'].apply(eval)\n",
+    "roundTrips = pd.read_csv('../data/temproary_data/round_trip_flights.csv')\n",
+    "airports_info = pd.read_csv('../data/cleaned_data/Airport_Codes.csv')\n",
+    "tickets_info = pd.read_csv('../data/cleaned_data/Tickets.csv')\n",
+    "\n",
+    "tickets_info = tickets_info.assign(\n",
+    "        sorted_route=tickets_info.apply(\n",
+    "            lambda x: tuple(\n",
+    "                sorted([x[\"ORIGIN_AIRPORT_IATA_CODE\"], x[\"DEST_AIRPORT_IATA_CODE\"]])\n",
+    "            ),\n",
+    "            axis=1,\n",
+    "        )\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# gather relevent data\n",
+    "\n",
+    "airports_can = {i for pair in candidates_rt['round_trip_route_IATA'].values for i in pair}\n",
+    "\n",
+    "candidate_roundTrips = roundTrips[roundTrips['round_trip_route_IATA'].isin(candidates_rt['round_trip_route_IATA'])]\n",
+    "candidate_airports = airports_info[airports_info['AIRPORT_IATA_CODE'].apply(lambda x: x in airports_can)]\n",
+    "candidate_tickets = tickets_info[tickets_info['sorted_route'].isin(candidates_rt['round_trip_route_IATA'])]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Delay analysis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "tongConsultinInc",
+   "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": "3.8.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}