notebook which closes #58 added [skip ci]

wikidata_wiki__to_wikidata_entity.ipynb

@@ -0,0 +1,76 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from apis_core.apis_metainfo.models import Uri"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cols = [\"id\", \"uri\", \"domain\", \"entity__id\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = Uri.objects.filter(uri__icontains=\"/Q\").exclude(uri__icontains=\"pedia\").values_list(*cols)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.DataFrame(data, columns=cols)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for ent, ndf in df.groupby(\"entity__id\"):\n",
+    "    if len(ndf) > 1:\n",
+    "        for i, row in ndf.iterrows():\n",
+    "            if \"org/wiki\" in row[\"uri\"]:\n",
+    "                uri_obj = Uri.objects.get(id=row[\"id\"])\n",
+    "                uri_obj.delete()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Django Shell-Plus",
+   "language": "python",
+   "name": "django_extensions"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}