Add files via upload

deutsche-nationalbibliothek · Sep 3, 2024 · 0e0ea07 · 0e0ea07
1 parent 4f9fbb3
commit 0e0ea07
Show file tree

Hide file tree

Showing 3 changed files with 667 additions and 0 deletions.
diff --git a/workshops/2024_Digital_History_Halle/02_Autoren_extrahieren.ipynb b/workshops/2024_Digital_History_Halle/02_Autoren_extrahieren.ipynb
@@ -0,0 +1,127 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "56184c51-b4cd-4009-b53c-40f73bb4e14a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "22cfe659-cb0d-42c4-830f-d10deb947f4e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"Studentenbewegung.csv\", encoding=\"utf-8\")\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "49e471cb-3e2f-46ae-8b44-3707b8dd5d79",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.drop(['titel', 'rela'], axis=1)\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3b37bdbf-cf0f-4ebe-a1f3-3d0406a411dc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df[df['author'] != 'unknown']\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "54b7dbc7-4bb0-42b2-b642-c97dcbf6b3fe",
+   "metadata": {},
+   "source": [
+    "### Bereinigen: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d2b544f6-c1d9-4391-8fe5-12815a31a09d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.loc[:, 'gnd_modified'] = df['gnd'].str.split(';').str.get(0)\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "83716027-df06-4469-a03e-b40905f937b0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.drop(['gnd'], axis=1)\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "66378256-9230-44b8-9243-026c7ca5e171",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "count_unknown = (df['gnd_modified'] == 'unknown').sum()\n",
+    "print(\"Einträge in gnd_modified mit value 'unknown': \", count_unknown)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b37202ea-4067-483f-bd93-41f4d6dc43a3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv(\"authors.csv\", encoding=\"utf-8\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ffad82ee-3945-4a99-a11b-b36f127500df",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/workshops/2024_Digital_History_Halle/04_Kartendarstellung.ipynb b/workshops/2024_Digital_History_Halle/04_Kartendarstellung.ipynb
@@ -0,0 +1,180 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a0a353f0-04f8-4d56-8285-5ce440aa88fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from geopy.geocoders import Nominatim\n",
+    "from geopy.exc import GeocoderTimedOut\n",
+    "import plotly.express as px"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "85fd2f76-4a65-4310-a82f-d1e0b6168748",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"authors-csv.csv\", encoding=\"utf-8\")\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bd119b8f-ff17-4055-8a0d-9c1b571c3b38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialisieren des Geolocators: \n",
+    "geolocator = Nominatim(user_agent=\"geoapiExercises\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ce67491f-88de-44ae-8ebb-62707b78a477",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Funktion, um Longitude und Latitude zu ermitteln:\n",
+    "def get_lat_long(place):\n",
+    "    try:\n",
+    "        location = geolocator.geocode(place)\n",
+    "        if location:\n",
+    "            return location.latitude, location.longitude\n",
+    "        else:\n",
+    "            return None, None\n",
+    "    except GeocoderTimedOut:\n",
+    "        return None, None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ec029f1f-20d2-4bd9-86ab-91aee865fe1c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Funktion auf der Spalte \"place\" ausführen, um neue Spalten \"lat\" und \"long\" zu ergänzen: \n",
+    "df[['lat', 'long']] = df['place'].apply(lambda x: pd.Series(get_lat_long(x)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "880d0dd3-7164-4091-985b-dca67334ec3e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8dcbaa61-c183-4f97-a0fd-168e5871ec9d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.dropna(subset=['lat', 'long'])\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1c122059-d170-4c5c-9134-317c684d30b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Gruppieren bei \"place\" und zählen der Vorkommen der einzelnen Orte:\n",
+    "place_counts = df.groupby('place').size().reset_index(name='count')\n",
+    "place_counts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3952f9a7-8d8c-45bd-ac7a-eb6239ef51af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Zusammenführen der Zählungen mit dem ursprünglichen Dataframe in einem neuen Dataframe \"df_with_counts\":\n",
+    "df_with_counts = df.merge(place_counts, on='place')\n",
+    "df_with_counts"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0d8647d3-ac4c-4bd4-aa44-1829e2707484",
+   "metadata": {},
+   "source": [
+    "### Kartenvisualisierung erstellen:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "64e8cadd-be66-4dff-a9f6-206b02b5a963",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Karte erstellen:\n",
+    "fig = px.scatter_mapbox(df_with_counts, \n",
+    "                        lat=\"lat\", \n",
+    "                        lon=\"long\", \n",
+    "                        hover_name=\"place\", \n",
+    "                        hover_data=[\"count\"],\n",
+    "                        size=\"count\",\n",
+    "                        color=\"count\",\n",
+    "                        zoom=4,\n",
+    "                        height=600)\n",
+    "\n",
+    "# Update des Layouts\n",
+    "fig.update_layout(mapbox_style=\"open-street-map\")\n",
+    "fig.update_layout(margin={\"r\":0,\"t\":0,\"l\":0,\"b\":0})\n",
+    "\n",
+    "# Karte anzeigen: \n",
+    "fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "83307d4d-f459-4064-a4ae-e08b6e6648da",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Karte bei Bedarf als HTML-Datei speichern: \n",
+    "fig.write_html(\"places_map_plotly.html\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}