Google Location History.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Plot your Google location history with matplotlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import pandas as pd, numpy as np, matplotlib.pyplot as plt\n",
    "from datetime import datetime as dt\n",
    "from mpl_toolkits.basemap import Basemap\n",
    "import warnings; warnings.simplefilter('ignore')\n",
    "%matplotlib inline\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load your history data\n",
    "Download your entire google location history as json using takeout https://takeout.google.com/settings/takeout \n",
    "\n",
    "For me it was just over 1 million points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "df_gps = pd.read_json('/home/dokeeffe/Downloads/Location History/Location History.json')\n",
    "print('There are {:,} rows in the location history dataset'.format(len(df_gps)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "df_gps.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Tidy up the data and remove what we dont need"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# parse lat, lon, and timestamp from the dict inside the locations column\n",
    "df_gps['lat'] = df_gps['locations'].map(lambda x: x['latitudeE7'])\n",
    "df_gps['lon'] = df_gps['locations'].map(lambda x: x['longitudeE7'])\n",
    "df_gps['timestamp_ms'] = df_gps['locations'].map(lambda x: x['timestampMs'])\n",
    "\n",
    "# convert lat/lon to decimalized degrees and the timestamp to date-time\n",
    "df_gps['lat'] = df_gps['lat'] / 10.**7\n",
    "df_gps['lon'] = df_gps['lon'] / 10.**7\n",
    "df_gps['timestamp_ms'] = df_gps['timestamp_ms'].astype(float) / 1000\n",
    "df_gps['datetime'] = df_gps['timestamp_ms'].map(lambda x: dt.fromtimestamp(x).strftime('%Y-%m-%d %H:%M:%S'))\n",
    "date_range = '{}-{}'.format(df_gps['datetime'].min()[:4], df_gps['datetime'].max()[:4])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# drop columns we don't need, then show a slice of the dataframe\n",
    "df_gps = df_gps.drop(labels=['locations', 'timestamp_ms'], axis=1, inplace=False)\n",
    "df_gps[1000:1005]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# define map colors\n",
    "land_color = '#f5f5f3'\n",
    "water_color = '#cdd2d4'\n",
    "coastline_color = '#f5f5f3'\n",
    "border_color = '#bbbbbb'\n",
    "meridian_color = '#f5f5f3'\n",
    "marker_fill_color = '#cc3300'\n",
    "marker_edge_color = 'None'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Plot the entire dataset on a world map"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# create the plot\n",
    "fig = plt.figure(figsize=(20, 10))\n",
    "ax = fig.add_subplot(111, axisbg='#ffffff', frame_on=False)\n",
    "ax.set_title('Google Location History, {}'.format(date_range), fontsize=24, color='#333333')\n",
    "\n",
    "# draw the basemap and its features\n",
    "m = Basemap(projection='kav7', lon_0=0, resolution='c', area_thresh=10000)\n",
    "m.drawmapboundary(color=border_color, fill_color=water_color)\n",
    "m.drawcoastlines(color=coastline_color)\n",
    "m.drawcountries(color=border_color)\n",
    "m.fillcontinents(color=land_color, lake_color=water_color)\n",
    "m.drawparallels(np.arange(-90., 120., 30.), color=meridian_color)\n",
    "m.drawmeridians(np.arange(0., 420., 60.), color=meridian_color)\n",
    "\n",
    "# project the location history points then scatter plot them\n",
    "x, y = m(df_gps['lon'].values, df_gps['lat'].values)\n",
    "m.scatter(x, y, s=9, color=marker_fill_color, edgecolor=marker_edge_color, alpha=1, zorder=3)\n",
    "\n",
    "# show the map\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Map Ireland only"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# first define a transverse mercator projection for ireland\n",
    "map_width_m = 300 * 1000\n",
    "map_height_m = 360 * 1000\n",
    "target_crs = {'datum':'WGS84',\n",
    "              'ellps':'WGS84',\n",
    "              'proj':'tmerc',\n",
    "              'lon_0':-8.2,\n",
    "              'lat_0':52.2}\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# plot the map\n",
    "fig_width = 15\n",
    "fig = plt.figure(figsize=[fig_width, fig_width * map_height_m / float(map_width_m)])\n",
    "ax = fig.add_subplot(111, axisbg='#ffffff', frame_on=False)\n",
    "ax.set_title('Ireland Location History, {}'.format(date_range), fontsize=16, color='#333333')\n",
    "\n",
    "# resolution of boundary database to use. Can be c (crude), l (low), i (intermediate), h (high), f (full) \n",
    "res = 'i'\n",
    "m = Basemap(ellps=target_crs['ellps'],\n",
    "            projection=target_crs['proj'],\n",
    "            lon_0=target_crs['lon_0'], \n",
    "            lat_0=target_crs['lat_0'],\n",
    "            width=map_width_m, \n",
    "            height=map_height_m,\n",
    "            resolution=res,\n",
    "            area_thresh=10000)\n",
    "\n",
    "m.drawcoastlines(color=coastline_color)\n",
    "m.drawcountries(color=border_color)\n",
    "m.fillcontinents(color=land_color, lake_color=water_color)\n",
    "m.drawstates(color=border_color)\n",
    "m.drawmapboundary(fill_color=water_color)\n",
    "\n",
    "x, y = m(df_gps['lon'].values, df_gps['lat'].values)\n",
    "m.scatter(x, y, s=5, color=marker_fill_color, edgecolor=marker_edge_color, alpha=0.2, zorder=3)\n",
    "plt.show();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Cork City Only"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# first define a transverse mercator projection for cork\n",
    "map_width_m = 6 * 1000\n",
    "map_height_m = 6 * 1000\n",
    "target_crs = {'datum':'WGS84',\n",
    "              'ellps':'WGS84',\n",
    "              'proj':'tmerc',\n",
    "              'lon_0':-8.470706,\n",
    "              'lat_0':51.899081}\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# plot the map\n",
    "fig_width = 15\n",
    "fig = plt.figure(figsize=[fig_width, fig_width * map_height_m / float(map_width_m)])\n",
    "ax = fig.add_subplot(111, axisbg='#ffffff', frame_on=False)\n",
    "ax.set_title('Cork city Location History, {}'.format(date_range), fontsize=16, color='#333333')\n",
    "\n",
    "# resolution of boundary database to use. Can be c (crude), l (low), i (intermediate), h (high), f (full) \n",
    "res = 'f'\n",
    "m = Basemap(ellps=target_crs['ellps'],\n",
    "            projection=target_crs['proj'],\n",
    "            lon_0=target_crs['lon_0'], \n",
    "            lat_0=target_crs['lat_0'],\n",
    "            width=map_width_m, \n",
    "            height=map_height_m,\n",
    "            resolution=res,\n",
    "            area_thresh=10000)\n",
    "\n",
    "m.drawcoastlines(color=coastline_color)\n",
    "m.drawcountries(color=border_color)\n",
    "m.fillcontinents(color=land_color, lake_color=water_color)\n",
    "m.drawstates(color=border_color)\n",
    "m.drawmapboundary(fill_color=water_color)\n",
    "\n",
    "x, y = m(df_gps['lon'].values, df_gps['lat'].values)\n",
    "m.scatter(x, y, s=5, color=marker_fill_color, edgecolor=marker_edge_color, alpha=0.3, zorder=3)\n",
    "\n",
    "# plt.savefig('images/google_location_history_cal_map.png', dpi=300, bbox_inches='tight', pad_inches=0.2)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.5.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}