Glen.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from collections import defaultdict\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "class AirlineAggregator:\n",
    "    \n",
    "    def __init__(self, filepath):\n",
    "        self.filepath = filepath\n",
    "        self.cols = ['CARRIER_DELAY', 'WEATHER_DELAY', 'NAS_DELAY', \n",
    "            'SECURITY_DELAY', 'LATE_AIRCRAFT_DELAY']\n",
    "        self.df = pd.read_csv(self.filepath)\n",
    "        self.df = self.df.fillna(0)\n",
    "\n",
    "    @property\n",
    "    def airline_conditions_dict(self):\n",
    "        \"\"\"  \n",
    "            create a dictionary whose keys are the airlines\n",
    "            and whose values are a list of dictionaries by delay type\n",
    "        \"\"\"\n",
    "        airline_conditions = defaultdict(list)\n",
    "        ### CAREFUL - note the use of sample to speed up compute\n",
    "        for index, row in self.df.sample(n=20000).iterrows():\n",
    "            airline = row.AIRLINE\n",
    "            values = [ {col:getattr(row, col)} for col in self.cols]\n",
    "            airline_conditions[airline].append(values)\n",
    "        return airline_conditions\n",
    "            \n",
    "    def compute_metrics(self, airline_key, delay_type, aggregation_type):\n",
    "        \"\"\"\n",
    "            the compute_metrics method takes an airline, delay type\n",
    "            and aggregation type, then computes the required metrics\n",
    "        \"\"\"\n",
    "        rows = self.airline_conditions_dict.get(airline_key)\n",
    "        rows = [x[0].get(delay_type) for x in rows]\n",
    "    \n",
    "        if aggregation_type == 'sum':\n",
    "            return sum(rows)\n",
    "        elif aggregation_type == 'mean':\n",
    "            return np.mean([x for x in rows if x > 0]) # avoid the zero skewing the mean\n",
    "        elif aggregation_type == 'count':\n",
    "            return np.count_nonzero(rows)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = AirlineAggregator('/Users/jeff/Downloads/Jan2018.csv') # Initialize an object with the filapath"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "226"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a.compute_metrics('AA', 'CARRIER_DELAY', 'count') # flights having that delay"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "8885.0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a.compute_metrics('AA', 'CARRIER_DELAY', 'sum') # mins delayed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "42.767441860465119"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a.compute_metrics('AA', 'CARRIER_DELAY', 'mean') # avg delayed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[[{'CARRIER_DELAY': 0.0},\n",
       "  {'WEATHER_DELAY': 0.0},\n",
       "  {'NAS_DELAY': 0.0},\n",
       "  {'SECURITY_DELAY': 0.0},\n",
       "  {'LATE_AIRCRAFT_DELAY': 0.0}],\n",
       " [{'CARRIER_DELAY': 45.0},\n",
       "  {'WEATHER_DELAY': 12.0},\n",
       "  {'NAS_DELAY': 0.0},\n",
       "  {'SECURITY_DELAY': 0.0},\n",
       "  {'LATE_AIRCRAFT_DELAY': 118.0}],\n",
       " [{'CARRIER_DELAY': 0.0},\n",
       "  {'WEATHER_DELAY': 0.0},\n",
       "  {'NAS_DELAY': 0.0},\n",
       "  {'SECURITY_DELAY': 0.0},\n",
       "  {'LATE_AIRCRAFT_DELAY': 0.0}],\n",
       " [{'CARRIER_DELAY': 27.0},\n",
       "  {'WEATHER_DELAY': 0.0},\n",
       "  {'NAS_DELAY': 0.0},\n",
       "  {'SECURITY_DELAY': 0.0},\n",
       "  {'LATE_AIRCRAFT_DELAY': 0.0}],\n",
       " [{'CARRIER_DELAY': 0.0},\n",
       "  {'WEATHER_DELAY': 0.0},\n",
       "  {'NAS_DELAY': 0.0},\n",
       "  {'SECURITY_DELAY': 0.0},\n",
       "  {'LATE_AIRCRAFT_DELAY': 0.0}]]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a.airline_conditions_dict['AA'][:5] # access to the raw data for arbitrary computation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}