{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Exploring the face data\n",
    "\n",
    "This notebook plays around with the [data](faces_per_image.csv) generated by running the facial detection script [over the whole Tribune collection](Finding-all-the-faces-in-the-Tribune-collection.ipynb)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import altair as alt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('faces_per_image.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>faces</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>60364.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3.821433</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>6.661479</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>4.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>174.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              faces\n",
       "count  60364.000000\n",
       "mean       3.821433\n",
       "std        6.661479\n",
       "min        0.000000\n",
       "25%        1.000000\n",
       "50%        2.000000\n",
       "75%        4.000000\n",
       "max      174.000000"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>faces</th>\n",
       "      <th>image</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>20402</th>\n",
       "      <td>174</td>\n",
       "      <td>FL4470426.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28301</th>\n",
       "      <td>117</td>\n",
       "      <td>FL4494940.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34768</th>\n",
       "      <td>145</td>\n",
       "      <td>FL4517063.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36351</th>\n",
       "      <td>111</td>\n",
       "      <td>FL4522209.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36353</th>\n",
       "      <td>105</td>\n",
       "      <td>FL4522212.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37843</th>\n",
       "      <td>109</td>\n",
       "      <td>FL4526927.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49708</th>\n",
       "      <td>127</td>\n",
       "      <td>FL4564048.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50428</th>\n",
       "      <td>104</td>\n",
       "      <td>FL4566376.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53969</th>\n",
       "      <td>132</td>\n",
       "      <td>FL4577551.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54041</th>\n",
       "      <td>110</td>\n",
       "      <td>FL4577772.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54044</th>\n",
       "      <td>144</td>\n",
       "      <td>FL4577775.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54062</th>\n",
       "      <td>112</td>\n",
       "      <td>FL4577793.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54172</th>\n",
       "      <td>126</td>\n",
       "      <td>FL4578163.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54173</th>\n",
       "      <td>111</td>\n",
       "      <td>FL4578164.jpg</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       faces          image\n",
       "20402    174  FL4470426.jpg\n",
       "28301    117  FL4494940.jpg\n",
       "34768    145  FL4517063.jpg\n",
       "36351    111  FL4522209.jpg\n",
       "36353    105  FL4522212.jpg\n",
       "37843    109  FL4526927.jpg\n",
       "49708    127  FL4564048.jpg\n",
       "50428    104  FL4566376.jpg\n",
       "53969    132  FL4577551.jpg\n",
       "54041    110  FL4577772.jpg\n",
       "54044    144  FL4577775.jpg\n",
       "54062    112  FL4577793.jpg\n",
       "54172    126  FL4578163.jpg\n",
       "54173    111  FL4578164.jpg"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# More than 100 faces!?\n",
    "\n",
    "df.loc[df['faces'] > 100]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<div id=\"altair-viz-54b218d932c84780a8448bb713f71a55\"></div>\n",
       "<script type=\"text/javascript\">\n",
       "  (function(spec, embedOpt){\n",
       "    let outputDiv = document.currentScript.previousElementSibling;\n",
       "    if (outputDiv.id !== \"altair-viz-54b218d932c84780a8448bb713f71a55\") {\n",
       "      outputDiv = document.getElementById(\"altair-viz-54b218d932c84780a8448bb713f71a55\");\n",
       "    }\n",
       "    const paths = {\n",
       "      \"vega\": \"https://cdn.jsdelivr.net/npm//vega@5?noext\",\n",
       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm//vega-lib?noext\",\n",
       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm//vega-lite@4.8.1?noext\",\n",
       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm//vega-embed@6?noext\",\n",
       "    };\n",
       "\n",
       "    function loadScript(lib) {\n",
       "      return new Promise(function(resolve, reject) {\n",
       "        var s = document.createElement('script');\n",
       "        s.src = paths[lib];\n",
       "        s.async = true;\n",
       "        s.onload = () => resolve(paths[lib]);\n",
       "        s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
       "        document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
       "      });\n",
       "    }\n",
       "\n",
       "    function showError(err) {\n",
       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
       "      throw err;\n",
       "    }\n",
       "\n",
       "    function displayChart(vegaEmbed) {\n",
       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
       "    }\n",
       "\n",
       "    if(typeof define === \"function\" && define.amd) {\n",
       "      requirejs.config({paths});\n",
       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
       "    } else if (typeof vegaEmbed === \"function\") {\n",
       "      displayChart(vegaEmbed);\n",
       "    } else {\n",
       "      loadScript(\"vega\")\n",
       "        .then(() => loadScript(\"vega-lite\"))\n",
       "        .then(() => loadScript(\"vega-embed\"))\n",
       "        .catch(showError)\n",
       "        .then(() => displayChart(vegaEmbed));\n",
       "    }\n",
       "  })({\"config\": {\"view\": {\"continuousWidth\": 400, \"continuousHeight\": 300}}, \"data\": {\"url\": \"altair-data-0e5575df802f24b7201c08688cd2eea2.json\", \"format\": {\"type\": \"json\"}}, \"mark\": \"bar\", \"encoding\": {\"x\": {\"type\": \"quantitative\", \"bin\": {\"maxbins\": 100}, \"field\": \"faces\"}, \"y\": {\"type\": \"quantitative\", \"aggregate\": \"count\"}}, \"$schema\": \"https://vega.github.io/schema/vega-lite/v4.8.1.json\"}, {\"mode\": \"vega-lite\"});\n",
       "</script>"
      ],
      "text/plain": [
       "alt.Chart(...)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "alt.data_transformers.enable('json')\n",
    "alt.Chart(df).mark_bar().encode(\n",
    "    x=alt.X('faces:Q', bin=alt.BinParams(maxbins=100)),\n",
    "    y='count():Q'\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "230677"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['faces'].sum()"
   ]
  },
  {
   "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}