chair.ipynb

{
  "metadata": {
    "language_info": {
      "mimetype": "text/x-python",
      "nbconvert_exporter": "python",
      "name": "python",
      "pygments_lexer": "ipython3",
      "version": "3.6.6",
      "file_extension": ".py",
      "codemirror_mode": {
        "version": 3,
        "name": "ipython"
      }
    },
    "kernelspec": {
      "name": "python36",
      "display_name": "Python 3.6",
      "language": "python"
    }
  },
  "nbformat_minor": 2,
  "nbformat": 4,
  "cells": [
    {
      "cell_type": "code",
      "source": "import requests\nimport json\nimport pandas as pd\nimport matplotlib.pyplot as plt\n\n%matplotlib inline",
      "metadata": {
        "trusted": true
      },
      "execution_count": 27,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": "keyword = \"chair\"\n\nquery = \"\"\"\n    {\n        objects(keyword: \"%s\") {\n            id\n            title\n            category\n            creation_date\n            date_made\n            description\n            maker\n            collection\n            publicAccess\n        }\n    }\n\"\"\" % keyword",
      "metadata": {
        "trusted": true
      },
      "execution_count": 28,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": "url = \"https://api.accession.io/graphql/mit-museum/developer\"\nr = requests.post(url, json={'query': query})\nprint(r.status_code)",
      "metadata": {
        "trusted": true
      },
      "execution_count": 29,
      "outputs": [
        {
          "text": "200\n",
          "name": "stdout",
          "output_type": "stream"
        }
      ]
    },
    {
      "cell_type": "code",
      "source": "json_data = r.json()\nobjects = json_data['data']['objects']\nobjects_df = pd.DataFrame(objects)",
      "metadata": {
        "trusted": true
      },
      "execution_count": 30,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": "objects_df.head()",
      "metadata": {
        "trusted": true
      },
      "execution_count": 31,
      "outputs": [
        {
          "execution_count": 31,
          "output_type": "execute_result",
          "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>category</th>\n      <th>collection</th>\n      <th>creation_date</th>\n      <th>date_made</th>\n      <th>description</th>\n      <th>id</th>\n      <th>maker</th>\n      <th>publicAccess</th>\n      <th>title</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Holography</td>\n      <td>Holography Collection</td>\n      <td>2007-06-17 16:46:11</td>\n      <td>1982</td>\n      <td>A chair in rainbow colors. The chair rotates a...</td>\n      <td>74657</td>\n      <td>Stephens, Anait</td>\n      <td>True</td>\n      <td>Chair</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Holography</td>\n      <td>Holography Collection</td>\n      <td>2007-06-17 16:46:23</td>\n      <td>1982</td>\n      <td>A chair that is tilted to the left . The chair...</td>\n      <td>74908</td>\n      <td>Stephens, Anait</td>\n      <td>True</td>\n      <td>Chair</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Holography</td>\n      <td>Holography Collection</td>\n      <td>2007-06-17 16:46:28</td>\n      <td>1982</td>\n      <td>Rainbow image of a chair that moves when the i...</td>\n      <td>74984</td>\n      <td>Stephens, Anait</td>\n      <td>True</td>\n      <td>Chair</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Holography</td>\n      <td>Holography Collection</td>\n      <td>2007-06-17 16:41:31</td>\n      <td>1984</td>\n      <td>Embossed, square foil sticker; rainbow-colored...</td>\n      <td>67908</td>\n      <td>Light Sight, Int'l; Light Impressions, Inc.</td>\n      <td>True</td>\n      <td>Beach Chair</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Holography</td>\n      <td>Holography Collection</td>\n      <td>2007-06-17 16:46:03</td>\n      <td>1982</td>\n      <td>Image of a chair. Rainbow image shows as it is...</td>\n      <td>74398</td>\n      <td>Stephens, Anait</td>\n      <td>True</td>\n      <td>Chair [test]</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "     category             collection        creation_date date_made  \\\n0  Holography  Holography Collection  2007-06-17 16:46:11      1982   \n1  Holography  Holography Collection  2007-06-17 16:46:23      1982   \n2  Holography  Holography Collection  2007-06-17 16:46:28      1982   \n3  Holography  Holography Collection  2007-06-17 16:41:31      1984   \n4  Holography  Holography Collection  2007-06-17 16:46:03      1982   \n\n                                         description     id  \\\n0  A chair in rainbow colors. The chair rotates a...  74657   \n1  A chair that is tilted to the left . The chair...  74908   \n2  Rainbow image of a chair that moves when the i...  74984   \n3  Embossed, square foil sticker; rainbow-colored...  67908   \n4  Image of a chair. Rainbow image shows as it is...  74398   \n\n                                         maker  publicAccess         title  \n0                              Stephens, Anait          True         Chair  \n1                              Stephens, Anait          True         Chair  \n2                              Stephens, Anait          True         Chair  \n3  Light Sight, Int'l; Light Impressions, Inc.          True   Beach Chair  \n4                              Stephens, Anait          True  Chair [test]  "
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": "objects_df.describe(include='all')",
      "metadata": {
        "trusted": true
      },
      "execution_count": 32,
      "outputs": [
        {
          "execution_count": 32,
          "output_type": "execute_result",
          "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>category</th>\n      <th>collection</th>\n      <th>creation_date</th>\n      <th>date_made</th>\n      <th>description</th>\n      <th>id</th>\n      <th>maker</th>\n      <th>publicAccess</th>\n      <th>title</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>count</th>\n      <td>45</td>\n      <td>40</td>\n      <td>45</td>\n      <td>36</td>\n      <td>42</td>\n      <td>45.000000</td>\n      <td>34</td>\n      <td>45</td>\n      <td>45</td>\n    </tr>\n    <tr>\n      <th>unique</th>\n      <td>5</td>\n      <td>9</td>\n      <td>40</td>\n      <td>23</td>\n      <td>38</td>\n      <td>NaN</td>\n      <td>16</td>\n      <td>1</td>\n      <td>36</td>\n    </tr>\n    <tr>\n      <th>top</th>\n      <td>Science &amp; Technology</td>\n      <td>Harold E. Edgerton Collection</td>\n      <td>2007-06-17 16:40:56</td>\n      <td>1982</td>\n      <td>(MS)</td>\n      <td>NaN</td>\n      <td>Edgerton, Harold Eugene</td>\n      <td>True</td>\n      <td>Chair</td>\n    </tr>\n    <tr>\n      <th>freq</th>\n      <td>16</td>\n      <td>15</td>\n      <td>3</td>\n      <td>4</td>\n      <td>3</td>\n      <td>NaN</td>\n      <td>10</td>\n      <td>45</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>96654.266667</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>34946.271354</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>min</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>42562.000000</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>71321.000000</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>50%</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>88615.000000</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>101202.000000</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>max</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>176484.000000</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "                    category                     collection  \\\ncount                     45                             40   \nunique                     5                              9   \ntop     Science & Technology  Harold E. Edgerton Collection   \nfreq                      16                             15   \nmean                     NaN                            NaN   \nstd                      NaN                            NaN   \nmin                      NaN                            NaN   \n25%                      NaN                            NaN   \n50%                      NaN                            NaN   \n75%                      NaN                            NaN   \nmax                      NaN                            NaN   \n\n              creation_date date_made description             id  \\\ncount                    45        36          42      45.000000   \nunique                   40        23          38            NaN   \ntop     2007-06-17 16:40:56      1982        (MS)            NaN   \nfreq                      3         4           3            NaN   \nmean                    NaN       NaN         NaN   96654.266667   \nstd                     NaN       NaN         NaN   34946.271354   \nmin                     NaN       NaN         NaN   42562.000000   \n25%                     NaN       NaN         NaN   71321.000000   \n50%                     NaN       NaN         NaN   88615.000000   \n75%                     NaN       NaN         NaN  101202.000000   \nmax                     NaN       NaN         NaN  176484.000000   \n\n                          maker publicAccess  title  \ncount                        34           45     45  \nunique                       16            1     36  \ntop     Edgerton, Harold Eugene         True  Chair  \nfreq                         10           45      3  \nmean                        NaN          NaN    NaN  \nstd                         NaN          NaN    NaN  \nmin                         NaN          NaN    NaN  \n25%                         NaN          NaN    NaN  \n50%                         NaN          NaN    NaN  \n75%                         NaN          NaN    NaN  \nmax                         NaN          NaN    NaN  "
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": "objects_df.isnull().sum()",
      "metadata": {
        "trusted": true
      },
      "execution_count": 33,
      "outputs": [
        {
          "execution_count": 33,
          "output_type": "execute_result",
          "data": {
            "text/plain": "category          0\ncollection        5\ncreation_date     0\ndate_made         9\ndescription       3\nid                0\nmaker            11\npublicAccess      0\ntitle             0\ndtype: int64"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": "pd.value_counts(objects_df['category']).plot.bar()",
      "metadata": {
        "trusted": true
      },
      "execution_count": 34,
      "outputs": [
        {
          "execution_count": 34,
          "output_type": "execute_result",
          "data": {
            "text/plain": "<matplotlib.axes._subplots.AxesSubplot at 0x7f5e57d9b160>"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": "<Figure size 432x288 with 1 Axes>"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": "pd.value_counts(objects_df['collection']).plot.bar()",
      "metadata": {
        "trusted": true
      },
      "execution_count": 35,
      "outputs": [
        {
          "execution_count": 35,
          "output_type": "execute_result",
          "data": {
            "text/plain": "<matplotlib.axes._subplots.AxesSubplot at 0x7f5e578f2e10>"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": "<Figure size 432x288 with 1 Axes>"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": "",
      "metadata": {},
      "execution_count": null,
      "outputs": []
    }
  ]
}