wip import new "verlinkungen" #100; ToDo: run against server

.gitignore

@@ -33,7 +33,7 @@ node_modules
 
 # other things
 .env
-*.ipynb
+Untitled*.ipynb
 env.secret
 staticfiles
 media/event_error.csv

issue__100_verlinkungen.ipynb

@@ -0,0 +1,147 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "86caea5a-01df-46b0-84d7-9e4a989ddc56",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from django.core.exceptions import ObjectDoesNotExist\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "from archiv.models import Event, Person, Place\n",
+    "from archiv.import_utils import gsheet_to_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a6172706-ae6d-4076-a676-95df531b9fca",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sheet_id = \"1agkc8QZuNnZTzRNW88y6UhizidgeXCvcyqQ3OGSCfm8\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ec125df7-d53b-469d-acab-d70e4888a4a6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = gsheet_to_df(sheet_id)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d1d33ec3-6189-4fba-a5fc-c1c3850a3dd7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for g, ndf in tqdm(df.groupby(\"entity\")):\n",
+    "    ent = Person.objects.get(id=g)\n",
+    "    for i, row in ndf.iterrows():\n",
+    "        try:\n",
+    "            event = Event.objects.get(id=row[\"article\"])\n",
+    "        except ObjectDoesNotExist:\n",
+    "            print(row[\"article\"])\n",
+    "        event.person.add(ent)\n",
+    "        "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a3143d02-77d6-41d3-84fa-cf30f10ffccc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b0f0ab8a-455d-4495-b61e-19872925314b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sheet_id = \"1VV47bmUTi5GQwber7xJhHvj95XmsYI-Jrswaw1hprV4\"\n",
+    "df = gsheet_to_df(sheet_id)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "43ca3a09-2b5a-4c93-aac3-4e02a16c7554",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "04a27e79-17c2-4899-9f0e-9e1df89b0fc9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "event_does_not_exist = []\n",
+    "for g, ndf in tqdm(df.groupby(\"entity\")):\n",
+    "    ent = Place.objects.get(id=g)\n",
+    "    for i, row in ndf.iterrows():\n",
+    "        try:\n",
+    "            event = Event.objects.get(id=row[\"article\"])\n",
+    "        except ObjectDoesNotExist:\n",
+    "            event_does_not_exist.append(row[\"article\"])\n",
+    "            continue\n",
+    "        event.place.add(ent)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88102882-a127-4f60-9879-c02d5e2fd807",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len(event_does_not_exist)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6fd1e8ee-e674-4fdf-9da1-9d80524d6043",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "_"
+   ]
+  }
+ ],
+ "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": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}