Kulturnav Entititer

salgo60 · Jun 30, 2020 · 9f5988a · 9f5988a
1 parent 9e06cdb
commit 9f5988a
Show file tree

Hide file tree

Showing 4 changed files with 108 additions and 39 deletions.
diff --git a/.ipynb_checkpoints/Riksdagens ledamöter-checkpoint.ipynb b/.ipynb_checkpoints/Riksdagens ledamöter-checkpoint.ipynb
@@ -14,8 +14,8 @@
     "* Wikipedia [WikiProject_Sweden/Swedish_Riksdag_documents](https://www.wikidata.org/wiki/Wikidata:WikiProject_Sweden/Swedish_Riksdag_documents)\n",
     "\n",
     "\n",
-    "* intressent_id = Wikidata Property P1214 \n",
-    "* sourceid = Wikidata Property P8388 \n"
+    "* intressent_id = Wikidata Property [P1214](https://www.wikidata.org/wiki/Property:P1214) \n",
+    "* sourceid = Wikidata Property [P8388](https://www.wikidata.org/wiki/Property:P8388) \n"
    ]
   },
   {

diff --git a/Kulturnav - Entity.ipynb b/Kulturnav - Entity.ipynb
@@ -4,34 +4,50 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Kulturnav - Entity"
+    "## Kulturnav - Entity  \n",
+    "* [This Notebook](https://github.com/salgo60/open-data-examples/blob/master/Kulturnav%20-%20Entity.ipynb)\n",
+    "* [API](https://kulturnav.org/info/api)\n",
+    "* [blogpost](https://minancestry.blogspot.com/2020/06/draft-kulturnav.html)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "82ca4700ec744398afc3c76ceb62ab64",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, max=25000.0), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "************************"
+      "\n"
      ]
     }
    ],
    "source": [
     "import urllib3, json\n",
-    "import pandas as pd \n",
+    "import pandas as pd  \n",
+    "from tqdm.notebook import trange  \n",
     "http = urllib3.PoolManager() \n",
     "pd.set_option(\"display.max.columns\", None) \n",
     "urlbase = \"https://kulturnav.org/api/search/entityType:Entity?start=\" \n",
     "\n",
     "dftot = pd.DataFrame()\n",
-    "for i in range(1,500000,20):\n",
+    "for i in trange(1,500000,20):\n",
     "    url = urlbase + str(i)\n",
-    "    if ((i-1) % 10000) == 0:\n",
-    "       print('*', end='', flush=True)\n",
     "    r = http.request('GET', url)\n",
     "    try:\n",
     "        data = json.loads(r.data)\n",
@@ -42,32 +58,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "<class 'pandas.core.frame.DataFrame'>\n",
-      "Int64Index: 100000 entries, 0 to 19\n",
+      "Int64Index: 500000 entries, 0 to 19\n",
       "Data columns (total 14 columns):\n",
-      "uuid                   100000 non-null object\n",
-      "entityType             100000 non-null object\n",
-      "acl                    100000 non-null object\n",
-      "currentVersion         100000 non-null bool\n",
-      "createdAt              100000 non-null object\n",
-      "createdBy              100000 non-null object\n",
-      "updatedAt              60000 non-null object\n",
-      "updatedBy              60000 non-null object\n",
-      "savedSource            85000 non-null object\n",
-      "inline                 100000 non-null bool\n",
-      "caption                100000 non-null object\n",
-      "properties             100000 non-null object\n",
-      "entityTypeName         100000 non-null object\n",
-      "entityTypeHierarchy    100000 non-null object\n",
+      "uuid                   500000 non-null object\n",
+      "entityType             500000 non-null object\n",
+      "acl                    500000 non-null object\n",
+      "currentVersion         500000 non-null bool\n",
+      "createdAt              500000 non-null object\n",
+      "createdBy              500000 non-null object\n",
+      "updatedAt              300000 non-null object\n",
+      "updatedBy              300000 non-null object\n",
+      "savedSource            425000 non-null object\n",
+      "inline                 500000 non-null bool\n",
+      "caption                500000 non-null object\n",
+      "properties             500000 non-null object\n",
+      "entityTypeName         500000 non-null object\n",
+      "entityTypeHierarchy    500000 non-null object\n",
       "dtypes: bool(2), object(12)\n",
-      "memory usage: 10.1+ MB\n"
+      "memory usage: 50.5+ MB\n"
      ]
     }
    ],
@@ -77,7 +93,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -131,7 +147,7 @@
        "      <td>SCRIPT: extractDrafts</td>\n",
        "      <td>False</td>\n",
        "      <td>{}</td>\n",
-       "      <td>{'dataset.primaryLanguage': [{'uuid': '734bae0...</td>\n",
+       "      <td>{'dataset.primaryLanguage': [{'uuid': '63c88b1...</td>\n",
        "      <td>{'nn': 'Organisasjon', 'no': 'Organisasjon', '...</td>\n",
        "      <td>[Agent, Organization]</td>\n",
        "    </tr>\n",
@@ -307,7 +323,7 @@
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>100000 rows × 14 columns</p>\n",
+       "<p>500000 rows × 14 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -377,7 +393,7 @@
        "19            INTERACTIVE   False  {'sv': '__DIMU_STAGING (KulturIT AS)'}   \n",
        "\n",
        "                                           properties  \\\n",
-       "0   {'dataset.primaryLanguage': [{'uuid': '734bae0...   \n",
+       "0   {'dataset.primaryLanguage': [{'uuid': '63c88b1...   \n",
        "1   {'entity.dataset': [{'uuid': 'deecb7d7-8a3f-46...   \n",
        "2   {'dataset.privateAcl': [{'uuid': '855a7e66-e66...   \n",
        "3   {'entity.dataset': [{'uuid': '59978ea2-2dc8-47...   \n",
@@ -402,10 +418,10 @@
        "18  {'nn': 'Mappe', 'no': 'Mappe', 'sv': 'Mapp', '...        [Dataset, List]  \n",
        "19  {'nn': 'Mappe', 'no': 'Mappe', 'sv': 'Mapp', '...        [Dataset, List]  \n",
        "\n",
-       "[100000 rows x 14 columns]"
+       "[500000 rows x 14 columns]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -416,19 +432,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "List            80000\n",
-       "Person          15000\n",
-       "Organization     5000\n",
+       "List            400000\n",
+       "Person           75000\n",
+       "Organization     25000\n",
        "Name: entityType, dtype: int64"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -437,6 +453,47 @@
     "dftot.entityType.value_counts()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "SyntaxError",
+     "evalue": "invalid syntax (<ipython-input-12-9f5d15fb5bbd>, line 1)",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;36m  File \u001b[0;32m\"<ipython-input-12-9f5d15fb5bbd>\"\u001b[0;36m, line \u001b[0;32m1\u001b[0m\n\u001b[0;31m    personE = dftot[dftot[\"entityType\"]=\"Person\"]\u001b[0m\n\u001b[0m                                       ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
+     ]
+    }
+   ],
+   "source": [
+    "personE = dftot[dftot[\"entityType\"]=\"Person\"] "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1800x360 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "%matplotlib inline  \n",
+    "import matplotlib.pyplot as plt  \n",
+    "plot2 = dftot.entityType.value_counts().plot.pie(y='counts', figsize=(25, 5)) \n",
+    "plt.show()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,