crimes_by_hour.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Seattle 2014 Crime Reports - Hour Analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We're looking at the [crime data collected in 2014 in Seattle, WA](https://github.com/uwescience/datasci_course_materials/blob/master/assignment6/seattle_incidents_summer_2014.csv?raw=true). \n",
    "An interesting visualization might be to plot crimes by hour.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import datetime\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "webpath = \"https://raw.githubusercontent.com/uwescience/datasci_course_materials/master/assignment6/\"\n",
    "dtype={'Date Reported': datetime, 'Occurred Date or Date Range Start': datetime,'Occurred Date Range End': datetime}\n",
    "c = pd.read_csv(webpath+'seattle_incidents_summer_2014.csv', index_col=0, parse_dates=True, low_memory=False )\n",
    "c[\"Occurred Date or Date Range Start\"] = pd.to_datetime(c[\"Occurred Date or Date Range Start\"])\n",
    "c.set_index(\"Occurred Date or Date Range Start\", inplace=True)\n",
    "c['h'] = c.index.hour\n",
    "    \n",
    "fig = plt.figure()\n",
    "ax = plt.subplot(111)\n",
    "\n",
    "grp_agg = c.groupby('h').size()\n",
    "grp_agg.plot(x='h',label='count').set_title('Crime Rate Hours')\n",
    "\n",
    "ax.set_xlabel(\"hour of day\")\n",
    "ax.set_ylabel(\"count\")\n",
    "plt.legend(loc='best',bbox_to_anchor=(1.1, 1.05))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First conclusion we can draw is that the probability of crime occuring in Seattle in 2014 was lowest at 5am. Are criminals nocturnal? By breaking down this plot into crime types, can we infer anymore from the data? Below, we see that Car Prowl's are common in Seattle, WA and are most frequent in the late evening and early mornings. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig = plt.figure()\n",
    "ax = plt.subplot(111)\n",
    "\n",
    "for key, grp in c.groupby('Summarized Offense Description'):\n",
    "    grp_agg = grp.groupby('h').size()\n",
    "    grp_agg.plot(x='h',label='{k}'.format(k=key)).set_title('Crime Rate Hours')\n",
    "\n",
    "ax.set_xlabel(\"hour of day\")\n",
    "ax.set_ylabel(\"count\")\n",
    "plt.legend(loc='best',bbox_to_anchor=(1.1, 1.05))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Moreover, Car Prowls peak between the hours of 8pm and 1am (the ones reported, at least. See below). "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig = plt.figure()\n",
    "ax = plt.subplot(111)\n",
    "\n",
    "for key, grp in c.groupby('Summarized Offense Description'):\n",
    "    if 'car prowl' in key.lower():\n",
    "        grp_agg = grp.groupby('h').size()\n",
    "        grp_agg.plot(x='h',label='{k}'.format(k=key)).set_title('Crime Rate Hours')\n",
    "\n",
    "ax.set_xlabel(\"hour of day\")\n",
    "ax.set_ylabel(\"count\")\n",
    "plt.legend(loc='best',bbox_to_anchor=(1.1, 1.05))\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2.0
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}