{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "112e14ce",
   "metadata": {},
   "source": [
    "## Merge state data and user data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "e75eccbf",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "tw_tweets = pd.read_csv(r'..\\data\\copbird_table_tweet.csv')\n",
    "tw_user_data = pd.read_csv(r'..\\data\\copbird_table_user.csv')\n",
    "tw_pol_geo_data = pd.read_csv(r'..\\geolocations\\polizei_accounts_geo.csv', delimiter='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "be63403d",
   "metadata": {},
   "outputs": [],
   "source": [
    "def add_state_to_user_df():\n",
    "    tw_user_df = tw_user_data.rename(columns={\"id\": \"user_id\"})\n",
    "    tw_pol_geo_df = tw_pol_geo_data.rename(columns={\"Name\": \"name\", \"Bundesland\": \"bundesland\", \"Stadt\": \"stadt\"})\n",
    "\n",
    "    # merge tw_pol_geo_df into tw_user_df on key_col ('name') and only add col 'bundesland' to new df based on user_df\n",
    "    return pd.merge(tw_user_df, tw_pol_geo_df[['name', 'stadt', 'bundesland']], on='name', how='left')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "a9093ae6",
   "metadata": {},
   "outputs": [
    {
     "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>user_id</th>\n",
       "      <th>name</th>\n",
       "      <th>handle</th>\n",
       "      <th>stadt</th>\n",
       "      <th>bundesland</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1032561433102434304</td>\n",
       "      <td>Polizei Wittlich</td>\n",
       "      <td>PolizeiWittlich</td>\n",
       "      <td>Wittlich</td>\n",
       "      <td>Rheinland-Pfalz</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1143867545226764293</td>\n",
       "      <td>Bayerisches Landeskriminalamt</td>\n",
       "      <td>LKA_Bayern</td>\n",
       "      <td>München</td>\n",
       "      <td>Bayern</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1169206134189830145</td>\n",
       "      <td>Polizei Stendal</td>\n",
       "      <td>Polizei_SDL</td>\n",
       "      <td>Stendal</td>\n",
       "      <td>Sachsen-Anhalt</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1184024283342950401</td>\n",
       "      <td>Polizei Ravensburg</td>\n",
       "      <td>PolizeiRV</td>\n",
       "      <td>Ravensburg</td>\n",
       "      <td>Baden-Württemberg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1232548941889228808</td>\n",
       "      <td>Polizei Bad Nenndorf</td>\n",
       "      <td>Polizei_BadN</td>\n",
       "      <td>Bad Nenndorf</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1295978598034284546</td>\n",
       "      <td>Polizei ZPD NI</td>\n",
       "      <td>Polizei_ZPD_NI</td>\n",
       "      <td>Hannover</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>1487390240</td>\n",
       "      <td>Polizei Koblenz</td>\n",
       "      <td>Polizei_KO</td>\n",
       "      <td>Koblenz</td>\n",
       "      <td>Rheinland-Pfalz</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1968267000</td>\n",
       "      <td>Polizei Mainz</td>\n",
       "      <td>PolizeiMainz</td>\n",
       "      <td>Mainz</td>\n",
       "      <td>Rheinland-Pfalz</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1979596724</td>\n",
       "      <td>Polizei NRW OB</td>\n",
       "      <td>polizei_nrw_ob</td>\n",
       "      <td>Oberhausen</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2176104583</td>\n",
       "      <td>Polizei Rheinpfalz</td>\n",
       "      <td>PP_Rheinpfalz</td>\n",
       "      <td>Ludwigshafen am Rhein</td>\n",
       "      <td>Rheinland-Pfalz</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               user_id                           name           handle  \\\n",
       "0  1032561433102434304               Polizei Wittlich  PolizeiWittlich   \n",
       "1  1143867545226764293  Bayerisches Landeskriminalamt       LKA_Bayern   \n",
       "2  1169206134189830145                Polizei Stendal      Polizei_SDL   \n",
       "3  1184024283342950401             Polizei Ravensburg        PolizeiRV   \n",
       "4  1232548941889228808           Polizei Bad Nenndorf     Polizei_BadN   \n",
       "5  1295978598034284546                 Polizei ZPD NI   Polizei_ZPD_NI   \n",
       "6           1487390240                Polizei Koblenz       Polizei_KO   \n",
       "7           1968267000                  Polizei Mainz     PolizeiMainz   \n",
       "8           1979596724                 Polizei NRW OB   polizei_nrw_ob   \n",
       "9           2176104583             Polizei Rheinpfalz    PP_Rheinpfalz   \n",
       "\n",
       "                   stadt           bundesland  \n",
       "0               Wittlich      Rheinland-Pfalz  \n",
       "1                München               Bayern  \n",
       "2                Stendal       Sachsen-Anhalt  \n",
       "3             Ravensburg    Baden-Württemberg  \n",
       "4           Bad Nenndorf        Niedersachsen  \n",
       "5               Hannover        Niedersachsen  \n",
       "6                Koblenz      Rheinland-Pfalz  \n",
       "7                  Mainz      Rheinland-Pfalz  \n",
       "8             Oberhausen  Nordrhein-Westfalen  \n",
       "9  Ludwigshafen am Rhein      Rheinland-Pfalz  "
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "add_state_to_user_df()[:10]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f7f32d78",
   "metadata": {},
   "source": [
    "## insert state data into tweet data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "20d4a15a",
   "metadata": {},
   "outputs": [],
   "source": [
    "def add_state_to_tweets_df():\n",
    "    tw_tweets_ext = pd.merge(tw_tweets, add_state_to_user_df()[['user_id', 'stadt', 'bundesland', 'name', 'handle'\n",
    "                                                                ]], on='user_id', how='left')\n",
    "    return tw_tweets_ext[['id', 'tweet_text', 'created_at', 'user_id', 'name', 'handle', 'stadt', 'bundesland'\n",
    "                          ]].rename(columns={'id': 'tweet_id', 'name': 'user_name'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "7c9f4add",
   "metadata": {},
   "outputs": [
    {
     "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>tweet_id</th>\n",
       "      <th>tweet_text</th>\n",
       "      <th>created_at</th>\n",
       "      <th>user_id</th>\n",
       "      <th>user_name</th>\n",
       "      <th>handle</th>\n",
       "      <th>stadt</th>\n",
       "      <th>bundesland</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1321021123463663616</td>\n",
       "      <td>@mahanna196 Da die Stadt keine Ausnahme für Ra...</td>\n",
       "      <td>2020-10-27 09:29:13</td>\n",
       "      <td>778895426007203840</td>\n",
       "      <td>Polizei Oldenburg-Stadt/Ammerl</td>\n",
       "      <td>Polizei_OL</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1321023114071969792</td>\n",
       "      <td>#Zeugengesucht\\nDie Hintergründe zu dem Tötung...</td>\n",
       "      <td>2020-10-27 09:37:08</td>\n",
       "      <td>2397974054</td>\n",
       "      <td>Polizei Berlin</td>\n",
       "      <td>polizeiberlin</td>\n",
       "      <td>Berlin</td>\n",
       "      <td>Berlin</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1321025127388188673</td>\n",
       "      <td>RT @bka: EUROPE´S MOST WANTED – Sexualstraftät...</td>\n",
       "      <td>2020-10-27 09:45:08</td>\n",
       "      <td>2397974054</td>\n",
       "      <td>Polizei Berlin</td>\n",
       "      <td>polizeiberlin</td>\n",
       "      <td>Berlin</td>\n",
       "      <td>Berlin</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1321028108665950208</td>\n",
       "      <td>@StrupeitVolker Wir verstehen nicht so recht w...</td>\n",
       "      <td>2020-10-27 09:56:59</td>\n",
       "      <td>2810902381</td>\n",
       "      <td>Polizei München</td>\n",
       "      <td>PolizeiMuenchen</td>\n",
       "      <td>München</td>\n",
       "      <td>Bayern</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1321029199998656513</td>\n",
       "      <td>Wir unterstützen das @bka bei der #Öffentlichk...</td>\n",
       "      <td>2020-10-27 10:01:19</td>\n",
       "      <td>223758384</td>\n",
       "      <td>Polizei Sachsen</td>\n",
       "      <td>PolizeiSachsen</td>\n",
       "      <td>Dresden</td>\n",
       "      <td>Sachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1321029204964745218</td>\n",
       "      <td>Heute früh brannte es auf unserem Sicherstellu...</td>\n",
       "      <td>2020-10-27 10:01:20</td>\n",
       "      <td>2397974054</td>\n",
       "      <td>Polizei Berlin</td>\n",
       "      <td>polizeiberlin</td>\n",
       "      <td>Berlin</td>\n",
       "      <td>Berlin</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>1321031650483019776</td>\n",
       "      <td>Als ein Supermarktmitarbeiter in #Fürstenwalde...</td>\n",
       "      <td>2020-10-27 10:11:03</td>\n",
       "      <td>720244303566483456</td>\n",
       "      <td>Polizei Brandenburg</td>\n",
       "      <td>PolizeiBB</td>\n",
       "      <td>Potsdam</td>\n",
       "      <td>Brandenburg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1321031765209829379</td>\n",
       "      <td>Auf der Waldecker Straße haben bislang unbekan...</td>\n",
       "      <td>2020-10-27 10:11:31</td>\n",
       "      <td>2389222849</td>\n",
       "      <td>Polizei NRW DU</td>\n",
       "      <td>polizei_nrw_du</td>\n",
       "      <td>Duisburg</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1321032307277443072</td>\n",
       "      <td>@Sitewinder Es handelte sich um einen 22-jähri...</td>\n",
       "      <td>2020-10-27 10:13:40</td>\n",
       "      <td>720244303566483456</td>\n",
       "      <td>Polizei Brandenburg</td>\n",
       "      <td>PolizeiBB</td>\n",
       "      <td>Potsdam</td>\n",
       "      <td>Brandenburg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1321033945467834368</td>\n",
       "      <td>@GunstickULM Es bestand der Verdacht, dass Pla...</td>\n",
       "      <td>2020-10-27 10:20:10</td>\n",
       "      <td>720244303566483456</td>\n",
       "      <td>Polizei Brandenburg</td>\n",
       "      <td>PolizeiBB</td>\n",
       "      <td>Potsdam</td>\n",
       "      <td>Brandenburg</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              tweet_id                                         tweet_text  \\\n",
       "0  1321021123463663616  @mahanna196 Da die Stadt keine Ausnahme für Ra...   \n",
       "1  1321023114071969792  #Zeugengesucht\\nDie Hintergründe zu dem Tötung...   \n",
       "2  1321025127388188673  RT @bka: EUROPE´S MOST WANTED – Sexualstraftät...   \n",
       "3  1321028108665950208  @StrupeitVolker Wir verstehen nicht so recht w...   \n",
       "4  1321029199998656513  Wir unterstützen das @bka bei der #Öffentlichk...   \n",
       "5  1321029204964745218  Heute früh brannte es auf unserem Sicherstellu...   \n",
       "6  1321031650483019776  Als ein Supermarktmitarbeiter in #Fürstenwalde...   \n",
       "7  1321031765209829379  Auf der Waldecker Straße haben bislang unbekan...   \n",
       "8  1321032307277443072  @Sitewinder Es handelte sich um einen 22-jähri...   \n",
       "9  1321033945467834368  @GunstickULM Es bestand der Verdacht, dass Pla...   \n",
       "\n",
       "            created_at             user_id                       user_name  \\\n",
       "0  2020-10-27 09:29:13  778895426007203840  Polizei Oldenburg-Stadt/Ammerl   \n",
       "1  2020-10-27 09:37:08          2397974054                  Polizei Berlin   \n",
       "2  2020-10-27 09:45:08          2397974054                  Polizei Berlin   \n",
       "3  2020-10-27 09:56:59          2810902381                 Polizei München   \n",
       "4  2020-10-27 10:01:19           223758384                 Polizei Sachsen   \n",
       "5  2020-10-27 10:01:20          2397974054                  Polizei Berlin   \n",
       "6  2020-10-27 10:11:03  720244303566483456             Polizei Brandenburg   \n",
       "7  2020-10-27 10:11:31          2389222849                  Polizei NRW DU   \n",
       "8  2020-10-27 10:13:40  720244303566483456             Polizei Brandenburg   \n",
       "9  2020-10-27 10:20:10  720244303566483456             Polizei Brandenburg   \n",
       "\n",
       "            handle     stadt           bundesland  \n",
       "0       Polizei_OL       NaN                  NaN  \n",
       "1    polizeiberlin    Berlin               Berlin  \n",
       "2    polizeiberlin    Berlin               Berlin  \n",
       "3  PolizeiMuenchen   München               Bayern  \n",
       "4   PolizeiSachsen   Dresden              Sachsen  \n",
       "5    polizeiberlin    Berlin               Berlin  \n",
       "6        PolizeiBB   Potsdam          Brandenburg  \n",
       "7   polizei_nrw_du  Duisburg  Nordrhein-Westfalen  \n",
       "8        PolizeiBB   Potsdam          Brandenburg  \n",
       "9        PolizeiBB   Potsdam          Brandenburg  "
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "add_state_to_tweets_df()[:10]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "327f77a1",
   "metadata": {},
   "source": [
    "## Mapping citys/police stations from Pressemitteilungen and twitter-data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "de1410ce",
   "metadata": {},
   "source": [
    "### Extract cities, user_id from Pressemitteilungen and Tweets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "387de0f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "def map_bl_tw_citys():\n",
    "    import re\n",
    "    df_blaulicht = pd.read_csv(r'..\\mod_data\\2020-12_2021-05_presseportal.csv')\n",
    "    df_blaulicht.sort_index(inplace=True)\n",
    "    tw_locations = list(df_tw_user[['stadt', 'user_id']].itertuples(index=False, name=None))\n",
    "    tw_locations = [(loc, id) for loc, id in tw_locations if len(str(loc)) > 1]\n",
    "    bl_locations = list(set([str(city) for city in df_blaulicht['location'].values]))\n",
    "    bl_tw_locations = {}\n",
    "    for bl_loc in bl_locations:\n",
    "        for tw_loc, tw_id in tw_locations:\n",
    "            if re.search(r'\\b' + re.escape(str(tw_loc).lower()) + r'\\b', str(bl_loc).lower()):\n",
    "                bl_tw_locations[bl_loc] = [tw_loc, tw_id]\n",
    "    return bl_tw_locations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "cd8b388a",
   "metadata": {},
   "outputs": [],
   "source": [
    "def find_location(txt, mp):\n",
    "    mapped_blaulicht = mp.get(txt, \"\")\n",
    "    return mapped_blaulicht[1] if mapped_blaulicht != \"\" else \"\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5c29d275",
   "metadata": {},
   "source": [
    "### Add col tw_user_id to Blaulichtmeldungen"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "5ee5a263",
   "metadata": {},
   "outputs": [],
   "source": [
    "def extend_blaulicht_data():\n",
    "    df_blaulicht = concat_blaulicht_dfs()\n",
    "    mapping = map_bl_tw_citys()\n",
    "    df_blaulicht['tw_user_id'] = df_blaulicht['location'].apply(lambda x: find_location(x, mapping))\n",
    "    return df_blaulicht"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "f869435d",
   "metadata": {},
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "[Errno 2] No such file or directory: '..\\\\mod_data\\x820-12_2021-05_presseportal.csv'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-52-99cb996bfb79>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mextend_blaulicht_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m<ipython-input-51-e2ff330579db>\u001b[0m in \u001b[0;36mextend_blaulicht_data\u001b[1;34m()\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mextend_blaulicht_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      2\u001b[0m     \u001b[0mdf_blaulicht\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mconcat_blaulicht_dfs\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m     \u001b[0mmapping\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmap_bl_tw_citys\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      4\u001b[0m     \u001b[0mdf_blaulicht\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'tw_user_id'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdf_blaulicht\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'location'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;32mlambda\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mfind_location\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmapping\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0mdf_blaulicht\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m<ipython-input-49-ad9dc4eef61d>\u001b[0m in \u001b[0;36mmap_bl_tw_citys\u001b[1;34m()\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mmap_bl_tw_citys\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      2\u001b[0m     \u001b[1;32mimport\u001b[0m \u001b[0mre\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m     \u001b[0mdf_blaulicht\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'..\\mod_data\\2020-12_2021-05_presseportal.csv'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      4\u001b[0m     \u001b[0mdf_blaulicht\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msort_index\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0minplace\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m     \u001b[0mtw_locations\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf_tw_user\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'stadt'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'user_id'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitertuples\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\simon\\programming\\hackathons\\copbird-group-16\\copbird-venv\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36mread_csv\u001b[1;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, dialect, error_bad_lines, warn_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options)\u001b[0m\n\u001b[0;32m    608\u001b[0m     \u001b[0mkwds\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkwds_defaults\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    609\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 610\u001b[1;33m     \u001b[1;32mreturn\u001b[0m \u001b[0m_read\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    611\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    612\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\simon\\programming\\hackathons\\copbird-group-16\\copbird-venv\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36m_read\u001b[1;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[0;32m    460\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    461\u001b[0m     \u001b[1;31m# Create the parser.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 462\u001b[1;33m     \u001b[0mparser\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mTextFileReader\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    463\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    464\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mchunksize\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0miterator\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\simon\\programming\\hackathons\\copbird-group-16\\copbird-venv\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[0;32m    817\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0moptions\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"has_index_names\"\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mkwds\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"has_index_names\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    818\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 819\u001b[1;33m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_make_engine\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    820\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    821\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mclose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\simon\\programming\\hackathons\\copbird-group-16\\copbird-venv\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36m_make_engine\u001b[1;34m(self, engine)\u001b[0m\n\u001b[0;32m   1048\u001b[0m             )\n\u001b[0;32m   1049\u001b[0m         \u001b[1;31m# error: Too many arguments for \"ParserBase\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1050\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mmapping\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mengine\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0moptions\u001b[0m\u001b[1;33m)\u001b[0m  \u001b[1;31m# type: ignore[call-arg]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1051\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1052\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_failover_to_python\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\simon\\programming\\hackathons\\copbird-group-16\\copbird-venv\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, src, **kwds)\u001b[0m\n\u001b[0;32m   1865\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1866\u001b[0m         \u001b[1;31m# open handles\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1867\u001b[1;33m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_open_handles\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msrc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1868\u001b[0m         \u001b[1;32massert\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhandles\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1869\u001b[0m         \u001b[1;32mfor\u001b[0m \u001b[0mkey\u001b[0m \u001b[1;32min\u001b[0m \u001b[1;33m(\u001b[0m\u001b[1;34m\"storage_options\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"encoding\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"memory_map\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"compression\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\simon\\programming\\hackathons\\copbird-group-16\\copbird-venv\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36m_open_handles\u001b[1;34m(self, src, kwds)\u001b[0m\n\u001b[0;32m   1360\u001b[0m         \u001b[0mLet\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mreaders\u001b[0m \u001b[0mopen\u001b[0m \u001b[0mIOHanldes\u001b[0m \u001b[0mafter\u001b[0m \u001b[0mthey\u001b[0m \u001b[0mare\u001b[0m \u001b[0mdone\u001b[0m \u001b[1;32mwith\u001b[0m \u001b[0mtheir\u001b[0m \u001b[0mpotential\u001b[0m \u001b[0mraises\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1361\u001b[0m         \"\"\"\n\u001b[1;32m-> 1362\u001b[1;33m         self.handles = get_handle(\n\u001b[0m\u001b[0;32m   1363\u001b[0m             \u001b[0msrc\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1364\u001b[0m             \u001b[1;34m\"r\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\simon\\programming\\hackathons\\copbird-group-16\\copbird-venv\\lib\\site-packages\\pandas\\io\\common.py\u001b[0m in \u001b[0;36mget_handle\u001b[1;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[0;32m    640\u001b[0m                 \u001b[0merrors\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m\"replace\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    641\u001b[0m             \u001b[1;31m# Encoding\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 642\u001b[1;33m             handle = open(\n\u001b[0m\u001b[0;32m    643\u001b[0m                 \u001b[0mhandle\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    644\u001b[0m                 \u001b[0mioargs\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '..\\\\mod_data\\x820-12_2021-05_presseportal.csv'"
     ]
    }
   ],
   "source": [
    "extend_blaulicht_data()[:10]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2b756af2",
   "metadata": {},
   "source": [
    "## Extract tweets from specific topic by keywords"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "89fb5ba0",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_topics_by_str_lst(topic, df, col_name):\n",
    "    df_topiced = df[df[col_name].str.contains('|'.join(topic))]\n",
    "    return df_topiced"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "7b545748",
   "metadata": {},
   "outputs": [],
   "source": [
    "topic_1 = ['demonstr', 'kundgeb']\n",
    "topic_2 = ['drogen', 'weed', 'graas', 'lsd', 'cannabis', 'ecstasy', 'kokain', 'meth', 'crystal']\n",
    "topic_3 = ['rassis', 'diskriminier', 'ausländerfeindlich', 'fremdenfeindlich', 'fremdenhass']\n",
    "topic_4 = ['antisem', 'juden', 'synagoge', 'judenhass', 'judenfeindlich', 'holocaust']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "9bb43006",
   "metadata": {},
   "outputs": [
    {
     "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>tweet_id</th>\n",
       "      <th>tweet_text</th>\n",
       "      <th>created_at</th>\n",
       "      <th>user_id</th>\n",
       "      <th>user_name</th>\n",
       "      <th>handle</th>\n",
       "      <th>stadt</th>\n",
       "      <th>bundesland</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1031</th>\n",
       "      <td>1322543875169333250</td>\n",
       "      <td>Freitagabend beleidigten zwei Männer eine 20-j...</td>\n",
       "      <td>2020-10-31 14:20:06</td>\n",
       "      <td>808666671468658688</td>\n",
       "      <td>Polizei Bremen</td>\n",
       "      <td>BremenPolizei</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>Bremen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1239</th>\n",
       "      <td>1323187306698858499</td>\n",
       "      <td>@hin_fort Die verwendeten Begriffe spielen für...</td>\n",
       "      <td>2020-11-02 08:56:52</td>\n",
       "      <td>808666671468658688</td>\n",
       "      <td>Polizei Bremen</td>\n",
       "      <td>BremenPolizei</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>Bremen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1429</th>\n",
       "      <td>1323269343183015938</td>\n",
       "      <td>#Zeugensuche\\r\\n\\r\\n#Frankfurt-#Kalbach: Am 30...</td>\n",
       "      <td>2020-11-02 14:22:51</td>\n",
       "      <td>2272909014</td>\n",
       "      <td>Polizei Frankfurt</td>\n",
       "      <td>Polizei_Ffm</td>\n",
       "      <td>Frankfurt am Main</td>\n",
       "      <td>Hessen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5300</th>\n",
       "      <td>1328341355626721282</td>\n",
       "      <td>@MeineMe53821610 rassistischen Motiven? 🤔</td>\n",
       "      <td>2020-11-16 14:17:13</td>\n",
       "      <td>4201961439</td>\n",
       "      <td>Polizei Mannheim</td>\n",
       "      <td>PolizeiMannheim</td>\n",
       "      <td>Mannheim</td>\n",
       "      <td>Baden-Württemberg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8149</th>\n",
       "      <td>1331972789801267201</td>\n",
       "      <td>@werner42726904 Wenn Sie konkrete Hinweise auf...</td>\n",
       "      <td>2020-11-26 14:47:14</td>\n",
       "      <td>2904886151</td>\n",
       "      <td>Polizei Hamburg</td>\n",
       "      <td>PolizeiHamburg</td>\n",
       "      <td>Hamburg</td>\n",
       "      <td>Hamburg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9176</th>\n",
       "      <td>1333452133623078914</td>\n",
       "      <td>@Fuchsbau_22 @ARD_Recht Wie bereits zuvor nich...</td>\n",
       "      <td>2020-11-30 16:45:37</td>\n",
       "      <td>3029998264</td>\n",
       "      <td>Polizei Karlsruhe</td>\n",
       "      <td>Polizei_KA</td>\n",
       "      <td>Karlsruhe</td>\n",
       "      <td>Baden-Württemberg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9763</th>\n",
       "      <td>1334075361416581120</td>\n",
       "      <td>@Initiative_PKD @Fuchsbau_22 @ARD_Recht Wie wi...</td>\n",
       "      <td>2020-12-02 10:02:06</td>\n",
       "      <td>3029998264</td>\n",
       "      <td>Polizei Karlsruhe</td>\n",
       "      <td>Polizei_KA</td>\n",
       "      <td>Karlsruhe</td>\n",
       "      <td>Baden-Württemberg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11702</th>\n",
       "      <td>1335957493365813250</td>\n",
       "      <td>👉Auto eines behinderten Menschen in #Willich #...</td>\n",
       "      <td>2020-12-07 14:41:01</td>\n",
       "      <td>2389266775</td>\n",
       "      <td>Polizei NRW VIE</td>\n",
       "      <td>polizei_nrw_vie</td>\n",
       "      <td>Viersen</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11752</th>\n",
       "      <td>1335978008457392129</td>\n",
       "      <td>Gestern Abend erschien auf der #Davidwache in ...</td>\n",
       "      <td>2020-12-07 16:02:33</td>\n",
       "      <td>2397974054</td>\n",
       "      <td>Polizei Berlin</td>\n",
       "      <td>polizeiberlin</td>\n",
       "      <td>Berlin</td>\n",
       "      <td>Berlin</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15082</th>\n",
       "      <td>1339960301815537665</td>\n",
       "      <td>Eine Kollegin unserer #Dir3 bemerkte, dass ein...</td>\n",
       "      <td>2020-12-18 15:46:45</td>\n",
       "      <td>2397974054</td>\n",
       "      <td>Polizei Berlin</td>\n",
       "      <td>polizeiberlin</td>\n",
       "      <td>Berlin</td>\n",
       "      <td>Berlin</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16675</th>\n",
       "      <td>1343918555495084032</td>\n",
       "      <td>#Frankfurt - #Gallus #Griesheim #Nied  \\r\\n\\r\\...</td>\n",
       "      <td>2020-12-29 13:55:27</td>\n",
       "      <td>2272909014</td>\n",
       "      <td>Polizei Frankfurt</td>\n",
       "      <td>Polizei_Ffm</td>\n",
       "      <td>Frankfurt am Main</td>\n",
       "      <td>Hessen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17388</th>\n",
       "      <td>1349742682885775365</td>\n",
       "      <td>Zwei Ladendetektive erwischten einen 37-Jährig...</td>\n",
       "      <td>2021-01-14 15:38:27</td>\n",
       "      <td>808666671468658688</td>\n",
       "      <td>Polizei Bremen</td>\n",
       "      <td>BremenPolizei</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>Bremen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17406</th>\n",
       "      <td>1349757570114846721</td>\n",
       "      <td>@ArizonaStranger Ob die Beleidigung als \"auslä...</td>\n",
       "      <td>2021-01-14 16:37:36</td>\n",
       "      <td>808666671468658688</td>\n",
       "      <td>Polizei Bremen</td>\n",
       "      <td>BremenPolizei</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>Bremen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21801</th>\n",
       "      <td>1356540977343836166</td>\n",
       "      <td>#Zeugengesucht \\r\\n\\r\\nMontagnachmittag hat ei...</td>\n",
       "      <td>2021-02-02 09:52:26</td>\n",
       "      <td>808666671468658688</td>\n",
       "      <td>Polizei Bremen</td>\n",
       "      <td>BremenPolizei</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>Bremen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26772</th>\n",
       "      <td>1364958369426133012</td>\n",
       "      <td>#Tagesticker 📝 No. 1\\r\\n\\r\\n➡️ Magdeburg \\r\\n⤵...</td>\n",
       "      <td>2021-02-25 15:20:09</td>\n",
       "      <td>2849730251</td>\n",
       "      <td>Polizei Magdeburg</td>\n",
       "      <td>Polizei_MD</td>\n",
       "      <td>Magdeburg</td>\n",
       "      <td>Sachsen-Anhalt</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27421</th>\n",
       "      <td>1367063451483340801</td>\n",
       "      <td>Eine 41-jähr. Deutsche aus #Fürstenfeldbruck g...</td>\n",
       "      <td>2021-03-03 10:45:00</td>\n",
       "      <td>3169867654</td>\n",
       "      <td>Bundespolizei Bayern</td>\n",
       "      <td>bpol_by</td>\n",
       "      <td>München</td>\n",
       "      <td>Bayern</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29212</th>\n",
       "      <td>1370091362536853508</td>\n",
       "      <td>@amzdo @Polizei_NRW @RN_DORTMUND @Nordstadtblo...</td>\n",
       "      <td>2021-03-11 19:16:50</td>\n",
       "      <td>769128278</td>\n",
       "      <td>Polizei NRW DO</td>\n",
       "      <td>polizei_nrw_do</td>\n",
       "      <td>Dortmund</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30475</th>\n",
       "      <td>1372110500742434816</td>\n",
       "      <td>Wir beteiligen uns an den Internationalen Woch...</td>\n",
       "      <td>2021-03-17 09:00:10</td>\n",
       "      <td>2389375698</td>\n",
       "      <td>Polizei NRW HX</td>\n",
       "      <td>polizei_nrw_hx</td>\n",
       "      <td>Höxter</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30622</th>\n",
       "      <td>1372171253809876996</td>\n",
       "      <td>Ein klares Statement der #PolizeiSaarland gege...</td>\n",
       "      <td>2021-03-17 13:01:35</td>\n",
       "      <td>821727790374469632</td>\n",
       "      <td>Polizei Saarland</td>\n",
       "      <td>PolizeiSaarland</td>\n",
       "      <td>Saarbrücken</td>\n",
       "      <td>Saarland</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30801</th>\n",
       "      <td>1372471378650234882</td>\n",
       "      <td>Wir schließen uns dem Beitrag der #PolizeiBrau...</td>\n",
       "      <td>2021-03-18 08:54:10</td>\n",
       "      <td>773438463068766208</td>\n",
       "      <td>Polizei Nienburg</td>\n",
       "      <td>Polizei_NBG</td>\n",
       "      <td>Nienburg (Weser)</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30804</th>\n",
       "      <td>1372476310208061442</td>\n",
       "      <td>+++Solidarität-Grenzenlos+++\\r\\n\\r\\nDie diesjä...</td>\n",
       "      <td>2021-03-18 09:13:46</td>\n",
       "      <td>773132811238768640</td>\n",
       "      <td>Polizei Hildesheim</td>\n",
       "      <td>Polizei_HI</td>\n",
       "      <td>Hildesheim</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30806</th>\n",
       "      <td>1372477266383532034</td>\n",
       "      <td>Zum heutigen #Aktionstag \"Vorsicht, Vorurteile...</td>\n",
       "      <td>2021-03-18 09:17:34</td>\n",
       "      <td>1169206134189830145</td>\n",
       "      <td>Polizei Stendal</td>\n",
       "      <td>Polizei_SDL</td>\n",
       "      <td>Stendal</td>\n",
       "      <td>Sachsen-Anhalt</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30821</th>\n",
       "      <td>1372483689221853187</td>\n",
       "      <td>Weiter ging es in die Innenstadt von #Stendal,...</td>\n",
       "      <td>2021-03-18 09:43:05</td>\n",
       "      <td>1169206134189830145</td>\n",
       "      <td>Polizei Stendal</td>\n",
       "      <td>Polizei_SDL</td>\n",
       "      <td>Stendal</td>\n",
       "      <td>Sachsen-Anhalt</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30845</th>\n",
       "      <td>1372491481294987264</td>\n",
       "      <td>Letzte Station für uns war vor dem Landratsamt...</td>\n",
       "      <td>2021-03-18 10:14:03</td>\n",
       "      <td>1169206134189830145</td>\n",
       "      <td>Polizei Stendal</td>\n",
       "      <td>Polizei_SDL</td>\n",
       "      <td>Stendal</td>\n",
       "      <td>Sachsen-Anhalt</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30866</th>\n",
       "      <td>1372497013946847236</td>\n",
       "      <td>#DemokratieLeben! – Die PI #Cuxhaven unterstüt...</td>\n",
       "      <td>2021-03-18 10:36:02</td>\n",
       "      <td>948208635448094720</td>\n",
       "      <td>Polizei Cuxhaven</td>\n",
       "      <td>Polizei_CUX</td>\n",
       "      <td>Cuxhaven</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31609</th>\n",
       "      <td>1373545951684665344</td>\n",
       "      <td>👉Internationaler Tag gegen Rassismus #Solidari...</td>\n",
       "      <td>2021-03-21 08:04:08</td>\n",
       "      <td>1232548941889228808</td>\n",
       "      <td>Polizei Bad Nenndorf</td>\n",
       "      <td>Polizei_BadN</td>\n",
       "      <td>Bad Nenndorf</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31610</th>\n",
       "      <td>1373545975726415876</td>\n",
       "      <td>👉Internationaler Tag gegen Rassismus #Solidari...</td>\n",
       "      <td>2021-03-21 08:04:14</td>\n",
       "      <td>772751356230823936</td>\n",
       "      <td>Polizei Göttingen</td>\n",
       "      <td>Polizei_GOE</td>\n",
       "      <td>Göttingen</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31611</th>\n",
       "      <td>1373545977727045635</td>\n",
       "      <td>👉Internationaler Tag gegen Rassismus #Solidari...</td>\n",
       "      <td>2021-03-21 08:04:14</td>\n",
       "      <td>773132811238768640</td>\n",
       "      <td>Polizei Hildesheim</td>\n",
       "      <td>Polizei_HI</td>\n",
       "      <td>Hildesheim</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31612</th>\n",
       "      <td>1373545985532645384</td>\n",
       "      <td>👉Internationaler Tag gegen Rassismus #Solidari...</td>\n",
       "      <td>2021-03-21 08:04:16</td>\n",
       "      <td>773785655340048384</td>\n",
       "      <td>Polizei Holzminden</td>\n",
       "      <td>Polizei_HOL</td>\n",
       "      <td>Holzminden</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31613</th>\n",
       "      <td>1373545986056916993</td>\n",
       "      <td>👉Internationaler Tag gegen Rassismus #Solidari...</td>\n",
       "      <td>2021-03-21 08:04:16</td>\n",
       "      <td>773438463068766208</td>\n",
       "      <td>Polizei Nienburg</td>\n",
       "      <td>Polizei_NBG</td>\n",
       "      <td>Nienburg (Weser)</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31614</th>\n",
       "      <td>1373545990226067458</td>\n",
       "      <td>👉Internationaler Tag gegen Rassismus #Solidari...</td>\n",
       "      <td>2021-03-21 08:04:17</td>\n",
       "      <td>773805850687340544</td>\n",
       "      <td>Polizei Osterode</td>\n",
       "      <td>Polizei_OHA</td>\n",
       "      <td>Osterode am Harz</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31615</th>\n",
       "      <td>1373545990339366912</td>\n",
       "      <td>👉Internationaler Tag gegen Rassismus #Solidari...</td>\n",
       "      <td>2021-03-21 08:04:18</td>\n",
       "      <td>773811779013083136</td>\n",
       "      <td>Polizei Stadthagen</td>\n",
       "      <td>Polizei_STH</td>\n",
       "      <td>Stadthagen</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31616</th>\n",
       "      <td>1373545994428817410</td>\n",
       "      <td>👉Internationaler Tag gegen Rassismus #Solidari...</td>\n",
       "      <td>2021-03-21 08:04:18</td>\n",
       "      <td>775277344705609732</td>\n",
       "      <td>Polizei Bückeburg</td>\n",
       "      <td>Polizei_BBG</td>\n",
       "      <td>Bückeburg</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31617</th>\n",
       "      <td>1373546003354300417</td>\n",
       "      <td>👉Internationaler Tag gegen Rassismus #Solidari...</td>\n",
       "      <td>2021-03-21 08:04:21</td>\n",
       "      <td>773413449267281920</td>\n",
       "      <td>Polizei Hameln</td>\n",
       "      <td>Polizei_HM</td>\n",
       "      <td>Hameln-Pyrmont</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31618</th>\n",
       "      <td>1373546006219010049</td>\n",
       "      <td>👉Internationaler Tag gegen Rassismus #Solidari...</td>\n",
       "      <td>2021-03-21 08:04:21</td>\n",
       "      <td>773778874979287040</td>\n",
       "      <td>Polizei Northeim</td>\n",
       "      <td>Polizei_NOM</td>\n",
       "      <td>Northeim</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31621</th>\n",
       "      <td>1373552485424635904</td>\n",
       "      <td>In unserer Gesellschaft ist weder Platz für Ha...</td>\n",
       "      <td>2021-03-21 08:30:06</td>\n",
       "      <td>2389342951</td>\n",
       "      <td>Polizei NRW PB</td>\n",
       "      <td>polizei_nrw_pb</td>\n",
       "      <td>Paderborn</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31664</th>\n",
       "      <td>1373627984574345217</td>\n",
       "      <td>Wir nahmen am Do einen 53-jähirgen Paderborner...</td>\n",
       "      <td>2021-03-21 13:30:06</td>\n",
       "      <td>2389146030</td>\n",
       "      <td>Polizei NRW BI</td>\n",
       "      <td>polizei_nrw_bi</td>\n",
       "      <td>Bielefeld</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31826</th>\n",
       "      <td>1373939038982397953</td>\n",
       "      <td>Am Freitagabend ist ein Mann an der Endhaltest...</td>\n",
       "      <td>2021-03-22 10:06:08</td>\n",
       "      <td>223758384</td>\n",
       "      <td>Polizei Sachsen</td>\n",
       "      <td>PolizeiSachsen</td>\n",
       "      <td>Dresden</td>\n",
       "      <td>Sachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32081</th>\n",
       "      <td>1374039903827333120</td>\n",
       "      <td>Zwei unbekannte Männer haben heute Morgen auf ...</td>\n",
       "      <td>2021-03-22 16:46:56</td>\n",
       "      <td>223758384</td>\n",
       "      <td>Polizei Sachsen</td>\n",
       "      <td>PolizeiSachsen</td>\n",
       "      <td>Dresden</td>\n",
       "      <td>Sachsen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32098</th>\n",
       "      <td>1374060177591271425</td>\n",
       "      <td>Zeugen nach gefährlicher Körperverletzung gesu...</td>\n",
       "      <td>2021-03-22 18:07:29</td>\n",
       "      <td>769128278</td>\n",
       "      <td>Polizei NRW DO</td>\n",
       "      <td>polizei_nrw_do</td>\n",
       "      <td>Dortmund</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32365</th>\n",
       "      <td>1374382966768472075</td>\n",
       "      <td>Fremdenfeindliches Graffiti - #Polizei #Aachen...</td>\n",
       "      <td>2021-03-23 15:30:08</td>\n",
       "      <td>2389142300</td>\n",
       "      <td>Polizei NRW AC</td>\n",
       "      <td>Polizei_NRW_AC</td>\n",
       "      <td>Aachen</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32471</th>\n",
       "      <td>1374628552499466240</td>\n",
       "      <td>Fremdenfeindliches Graffiti - #Polizei #Aachen...</td>\n",
       "      <td>2021-03-24 07:46:00</td>\n",
       "      <td>2389142300</td>\n",
       "      <td>Polizei NRW AC</td>\n",
       "      <td>Polizei_NRW_AC</td>\n",
       "      <td>Aachen</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33210</th>\n",
       "      <td>1375372215303208961</td>\n",
       "      <td>Hass im Netz - Handeln gegen Hater\\r\\nHass, Be...</td>\n",
       "      <td>2021-03-26 09:01:03</td>\n",
       "      <td>783322939580092418</td>\n",
       "      <td>Polizei Ulm</td>\n",
       "      <td>PolizeiUL</td>\n",
       "      <td>Ulm</td>\n",
       "      <td>Baden-Württemberg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33666</th>\n",
       "      <td>1376021420564693000</td>\n",
       "      <td>Gemeinsam stark gegen Rassismus\\r\\n\\r\\nUnser S...</td>\n",
       "      <td>2021-03-28 04:00:46</td>\n",
       "      <td>821727790374469632</td>\n",
       "      <td>Polizei Saarland</td>\n",
       "      <td>PolizeiSaarland</td>\n",
       "      <td>Saarbrücken</td>\n",
       "      <td>Saarland</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36612</th>\n",
       "      <td>1379754045099945984</td>\n",
       "      <td>#FriedrichsGymnasium #StadttheaterHerford #Rav...</td>\n",
       "      <td>2021-04-07 11:12:53</td>\n",
       "      <td>2389146030</td>\n",
       "      <td>Polizei NRW BI</td>\n",
       "      <td>polizei_nrw_bi</td>\n",
       "      <td>Bielefeld</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36744</th>\n",
       "      <td>1379876164932616197</td>\n",
       "      <td>@Hase_Zwo @Einzelfallinfos Wie Sie der Pressem...</td>\n",
       "      <td>2021-04-07 19:18:09</td>\n",
       "      <td>808666671468658688</td>\n",
       "      <td>Polizei Bremen</td>\n",
       "      <td>BremenPolizei</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>Bremen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37736</th>\n",
       "      <td>1381566100052312066</td>\n",
       "      <td>Am Samstagabend skandierte eine Gruppe von etw...</td>\n",
       "      <td>2021-04-12 11:13:21</td>\n",
       "      <td>808666671468658688</td>\n",
       "      <td>Polizei Bremen</td>\n",
       "      <td>BremenPolizei</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>Bremen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39878</th>\n",
       "      <td>1384459042496593920</td>\n",
       "      <td>Unbekannte Täter beschmierten im Zeitraum zwis...</td>\n",
       "      <td>2021-04-20 10:48:52</td>\n",
       "      <td>2389142300</td>\n",
       "      <td>Polizei NRW AC</td>\n",
       "      <td>Polizei_NRW_AC</td>\n",
       "      <td>Aachen</td>\n",
       "      <td>Nordrhein-Westfalen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40525</th>\n",
       "      <td>1387051636627894285</td>\n",
       "      <td>Unser #LKA sucht 2 Männer, die letztes Jahr im...</td>\n",
       "      <td>2021-04-27 14:30:55</td>\n",
       "      <td>2397974054</td>\n",
       "      <td>Polizei Berlin</td>\n",
       "      <td>polizeiberlin</td>\n",
       "      <td>Berlin</td>\n",
       "      <td>Berlin</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42085</th>\n",
       "      <td>1389136356211892226</td>\n",
       "      <td>Zwei Festnahmen nach Beleidigung mit fremdenfe...</td>\n",
       "      <td>2021-05-03 08:34:50</td>\n",
       "      <td>2904886151</td>\n",
       "      <td>Polizei Hamburg</td>\n",
       "      <td>PolizeiHamburg</td>\n",
       "      <td>Hamburg</td>\n",
       "      <td>Hamburg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42217</th>\n",
       "      <td>1389182069499105280</td>\n",
       "      <td>BürgerInnen in Sömmerda machten am vergangenen...</td>\n",
       "      <td>2021-05-03 11:36:29</td>\n",
       "      <td>3064348636</td>\n",
       "      <td>Polizei Thüringen</td>\n",
       "      <td>Polizei_Thuer</td>\n",
       "      <td>Erfurt</td>\n",
       "      <td>Thüringen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42220</th>\n",
       "      <td>1389182634836832257</td>\n",
       "      <td>BürgerInnen in Sömmerda machten am vergangenen...</td>\n",
       "      <td>2021-05-03 11:38:44</td>\n",
       "      <td>3064348636</td>\n",
       "      <td>Polizei Thüringen</td>\n",
       "      <td>Polizei_Thuer</td>\n",
       "      <td>Erfurt</td>\n",
       "      <td>Thüringen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42237</th>\n",
       "      <td>1389190825406513158</td>\n",
       "      <td>🔵 44-Jähriger bedroht Minderjährige mit Schrec...</td>\n",
       "      <td>2021-05-03 12:11:17</td>\n",
       "      <td>770652658566852608</td>\n",
       "      <td>Polizei Hannover</td>\n",
       "      <td>Polizei_H</td>\n",
       "      <td>Hannover</td>\n",
       "      <td>Niedersachsen</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  tweet_id                                         tweet_text  \\\n",
       "1031   1322543875169333250  Freitagabend beleidigten zwei Männer eine 20-j...   \n",
       "1239   1323187306698858499  @hin_fort Die verwendeten Begriffe spielen für...   \n",
       "1429   1323269343183015938  #Zeugensuche\\r\\n\\r\\n#Frankfurt-#Kalbach: Am 30...   \n",
       "5300   1328341355626721282          @MeineMe53821610 rassistischen Motiven? 🤔   \n",
       "8149   1331972789801267201  @werner42726904 Wenn Sie konkrete Hinweise auf...   \n",
       "9176   1333452133623078914  @Fuchsbau_22 @ARD_Recht Wie bereits zuvor nich...   \n",
       "9763   1334075361416581120  @Initiative_PKD @Fuchsbau_22 @ARD_Recht Wie wi...   \n",
       "11702  1335957493365813250  👉Auto eines behinderten Menschen in #Willich #...   \n",
       "11752  1335978008457392129  Gestern Abend erschien auf der #Davidwache in ...   \n",
       "15082  1339960301815537665  Eine Kollegin unserer #Dir3 bemerkte, dass ein...   \n",
       "16675  1343918555495084032  #Frankfurt - #Gallus #Griesheim #Nied  \\r\\n\\r\\...   \n",
       "17388  1349742682885775365  Zwei Ladendetektive erwischten einen 37-Jährig...   \n",
       "17406  1349757570114846721  @ArizonaStranger Ob die Beleidigung als \"auslä...   \n",
       "21801  1356540977343836166  #Zeugengesucht \\r\\n\\r\\nMontagnachmittag hat ei...   \n",
       "26772  1364958369426133012  #Tagesticker 📝 No. 1\\r\\n\\r\\n➡️ Magdeburg \\r\\n⤵...   \n",
       "27421  1367063451483340801  Eine 41-jähr. Deutsche aus #Fürstenfeldbruck g...   \n",
       "29212  1370091362536853508  @amzdo @Polizei_NRW @RN_DORTMUND @Nordstadtblo...   \n",
       "30475  1372110500742434816  Wir beteiligen uns an den Internationalen Woch...   \n",
       "30622  1372171253809876996  Ein klares Statement der #PolizeiSaarland gege...   \n",
       "30801  1372471378650234882  Wir schließen uns dem Beitrag der #PolizeiBrau...   \n",
       "30804  1372476310208061442  +++Solidarität-Grenzenlos+++\\r\\n\\r\\nDie diesjä...   \n",
       "30806  1372477266383532034  Zum heutigen #Aktionstag \"Vorsicht, Vorurteile...   \n",
       "30821  1372483689221853187  Weiter ging es in die Innenstadt von #Stendal,...   \n",
       "30845  1372491481294987264  Letzte Station für uns war vor dem Landratsamt...   \n",
       "30866  1372497013946847236  #DemokratieLeben! – Die PI #Cuxhaven unterstüt...   \n",
       "31609  1373545951684665344  👉Internationaler Tag gegen Rassismus #Solidari...   \n",
       "31610  1373545975726415876  👉Internationaler Tag gegen Rassismus #Solidari...   \n",
       "31611  1373545977727045635  👉Internationaler Tag gegen Rassismus #Solidari...   \n",
       "31612  1373545985532645384  👉Internationaler Tag gegen Rassismus #Solidari...   \n",
       "31613  1373545986056916993  👉Internationaler Tag gegen Rassismus #Solidari...   \n",
       "31614  1373545990226067458  👉Internationaler Tag gegen Rassismus #Solidari...   \n",
       "31615  1373545990339366912  👉Internationaler Tag gegen Rassismus #Solidari...   \n",
       "31616  1373545994428817410  👉Internationaler Tag gegen Rassismus #Solidari...   \n",
       "31617  1373546003354300417  👉Internationaler Tag gegen Rassismus #Solidari...   \n",
       "31618  1373546006219010049  👉Internationaler Tag gegen Rassismus #Solidari...   \n",
       "31621  1373552485424635904  In unserer Gesellschaft ist weder Platz für Ha...   \n",
       "31664  1373627984574345217  Wir nahmen am Do einen 53-jähirgen Paderborner...   \n",
       "31826  1373939038982397953  Am Freitagabend ist ein Mann an der Endhaltest...   \n",
       "32081  1374039903827333120  Zwei unbekannte Männer haben heute Morgen auf ...   \n",
       "32098  1374060177591271425  Zeugen nach gefährlicher Körperverletzung gesu...   \n",
       "32365  1374382966768472075  Fremdenfeindliches Graffiti - #Polizei #Aachen...   \n",
       "32471  1374628552499466240  Fremdenfeindliches Graffiti - #Polizei #Aachen...   \n",
       "33210  1375372215303208961  Hass im Netz - Handeln gegen Hater\\r\\nHass, Be...   \n",
       "33666  1376021420564693000  Gemeinsam stark gegen Rassismus\\r\\n\\r\\nUnser S...   \n",
       "36612  1379754045099945984  #FriedrichsGymnasium #StadttheaterHerford #Rav...   \n",
       "36744  1379876164932616197  @Hase_Zwo @Einzelfallinfos Wie Sie der Pressem...   \n",
       "37736  1381566100052312066  Am Samstagabend skandierte eine Gruppe von etw...   \n",
       "39878  1384459042496593920  Unbekannte Täter beschmierten im Zeitraum zwis...   \n",
       "40525  1387051636627894285  Unser #LKA sucht 2 Männer, die letztes Jahr im...   \n",
       "42085  1389136356211892226  Zwei Festnahmen nach Beleidigung mit fremdenfe...   \n",
       "42217  1389182069499105280  BürgerInnen in Sömmerda machten am vergangenen...   \n",
       "42220  1389182634836832257  BürgerInnen in Sömmerda machten am vergangenen...   \n",
       "42237  1389190825406513158  🔵 44-Jähriger bedroht Minderjährige mit Schrec...   \n",
       "\n",
       "                created_at              user_id             user_name  \\\n",
       "1031   2020-10-31 14:20:06   808666671468658688        Polizei Bremen   \n",
       "1239   2020-11-02 08:56:52   808666671468658688        Polizei Bremen   \n",
       "1429   2020-11-02 14:22:51           2272909014     Polizei Frankfurt   \n",
       "5300   2020-11-16 14:17:13           4201961439      Polizei Mannheim   \n",
       "8149   2020-11-26 14:47:14           2904886151       Polizei Hamburg   \n",
       "9176   2020-11-30 16:45:37           3029998264     Polizei Karlsruhe   \n",
       "9763   2020-12-02 10:02:06           3029998264     Polizei Karlsruhe   \n",
       "11702  2020-12-07 14:41:01           2389266775       Polizei NRW VIE   \n",
       "11752  2020-12-07 16:02:33           2397974054        Polizei Berlin   \n",
       "15082  2020-12-18 15:46:45           2397974054        Polizei Berlin   \n",
       "16675  2020-12-29 13:55:27           2272909014     Polizei Frankfurt   \n",
       "17388  2021-01-14 15:38:27   808666671468658688        Polizei Bremen   \n",
       "17406  2021-01-14 16:37:36   808666671468658688        Polizei Bremen   \n",
       "21801  2021-02-02 09:52:26   808666671468658688        Polizei Bremen   \n",
       "26772  2021-02-25 15:20:09           2849730251     Polizei Magdeburg   \n",
       "27421  2021-03-03 10:45:00           3169867654  Bundespolizei Bayern   \n",
       "29212  2021-03-11 19:16:50            769128278        Polizei NRW DO   \n",
       "30475  2021-03-17 09:00:10           2389375698        Polizei NRW HX   \n",
       "30622  2021-03-17 13:01:35   821727790374469632      Polizei Saarland   \n",
       "30801  2021-03-18 08:54:10   773438463068766208      Polizei Nienburg   \n",
       "30804  2021-03-18 09:13:46   773132811238768640    Polizei Hildesheim   \n",
       "30806  2021-03-18 09:17:34  1169206134189830145       Polizei Stendal   \n",
       "30821  2021-03-18 09:43:05  1169206134189830145       Polizei Stendal   \n",
       "30845  2021-03-18 10:14:03  1169206134189830145       Polizei Stendal   \n",
       "30866  2021-03-18 10:36:02   948208635448094720      Polizei Cuxhaven   \n",
       "31609  2021-03-21 08:04:08  1232548941889228808  Polizei Bad Nenndorf   \n",
       "31610  2021-03-21 08:04:14   772751356230823936     Polizei Göttingen   \n",
       "31611  2021-03-21 08:04:14   773132811238768640    Polizei Hildesheim   \n",
       "31612  2021-03-21 08:04:16   773785655340048384    Polizei Holzminden   \n",
       "31613  2021-03-21 08:04:16   773438463068766208      Polizei Nienburg   \n",
       "31614  2021-03-21 08:04:17   773805850687340544      Polizei Osterode   \n",
       "31615  2021-03-21 08:04:18   773811779013083136    Polizei Stadthagen   \n",
       "31616  2021-03-21 08:04:18   775277344705609732     Polizei Bückeburg   \n",
       "31617  2021-03-21 08:04:21   773413449267281920        Polizei Hameln   \n",
       "31618  2021-03-21 08:04:21   773778874979287040      Polizei Northeim   \n",
       "31621  2021-03-21 08:30:06           2389342951        Polizei NRW PB   \n",
       "31664  2021-03-21 13:30:06           2389146030        Polizei NRW BI   \n",
       "31826  2021-03-22 10:06:08            223758384       Polizei Sachsen   \n",
       "32081  2021-03-22 16:46:56            223758384       Polizei Sachsen   \n",
       "32098  2021-03-22 18:07:29            769128278        Polizei NRW DO   \n",
       "32365  2021-03-23 15:30:08           2389142300        Polizei NRW AC   \n",
       "32471  2021-03-24 07:46:00           2389142300        Polizei NRW AC   \n",
       "33210  2021-03-26 09:01:03   783322939580092418           Polizei Ulm   \n",
       "33666  2021-03-28 04:00:46   821727790374469632      Polizei Saarland   \n",
       "36612  2021-04-07 11:12:53           2389146030        Polizei NRW BI   \n",
       "36744  2021-04-07 19:18:09   808666671468658688        Polizei Bremen   \n",
       "37736  2021-04-12 11:13:21   808666671468658688        Polizei Bremen   \n",
       "39878  2021-04-20 10:48:52           2389142300        Polizei NRW AC   \n",
       "40525  2021-04-27 14:30:55           2397974054        Polizei Berlin   \n",
       "42085  2021-05-03 08:34:50           2904886151       Polizei Hamburg   \n",
       "42217  2021-05-03 11:36:29           3064348636     Polizei Thüringen   \n",
       "42220  2021-05-03 11:38:44           3064348636     Polizei Thüringen   \n",
       "42237  2021-05-03 12:11:17   770652658566852608      Polizei Hannover   \n",
       "\n",
       "                handle              stadt           bundesland  \n",
       "1031     BremenPolizei             Bremen               Bremen  \n",
       "1239     BremenPolizei             Bremen               Bremen  \n",
       "1429       Polizei_Ffm  Frankfurt am Main               Hessen  \n",
       "5300   PolizeiMannheim           Mannheim    Baden-Württemberg  \n",
       "8149    PolizeiHamburg            Hamburg              Hamburg  \n",
       "9176        Polizei_KA          Karlsruhe    Baden-Württemberg  \n",
       "9763        Polizei_KA          Karlsruhe    Baden-Württemberg  \n",
       "11702  polizei_nrw_vie            Viersen  Nordrhein-Westfalen  \n",
       "11752    polizeiberlin             Berlin               Berlin  \n",
       "15082    polizeiberlin             Berlin               Berlin  \n",
       "16675      Polizei_Ffm  Frankfurt am Main               Hessen  \n",
       "17388    BremenPolizei             Bremen               Bremen  \n",
       "17406    BremenPolizei             Bremen               Bremen  \n",
       "21801    BremenPolizei             Bremen               Bremen  \n",
       "26772       Polizei_MD          Magdeburg       Sachsen-Anhalt  \n",
       "27421          bpol_by            München               Bayern  \n",
       "29212   polizei_nrw_do           Dortmund  Nordrhein-Westfalen  \n",
       "30475   polizei_nrw_hx             Höxter  Nordrhein-Westfalen  \n",
       "30622  PolizeiSaarland        Saarbrücken             Saarland  \n",
       "30801      Polizei_NBG   Nienburg (Weser)        Niedersachsen  \n",
       "30804       Polizei_HI         Hildesheim        Niedersachsen  \n",
       "30806      Polizei_SDL            Stendal       Sachsen-Anhalt  \n",
       "30821      Polizei_SDL            Stendal       Sachsen-Anhalt  \n",
       "30845      Polizei_SDL            Stendal       Sachsen-Anhalt  \n",
       "30866      Polizei_CUX           Cuxhaven        Niedersachsen  \n",
       "31609     Polizei_BadN       Bad Nenndorf        Niedersachsen  \n",
       "31610      Polizei_GOE          Göttingen        Niedersachsen  \n",
       "31611       Polizei_HI         Hildesheim        Niedersachsen  \n",
       "31612      Polizei_HOL         Holzminden        Niedersachsen  \n",
       "31613      Polizei_NBG   Nienburg (Weser)        Niedersachsen  \n",
       "31614      Polizei_OHA   Osterode am Harz        Niedersachsen  \n",
       "31615      Polizei_STH         Stadthagen        Niedersachsen  \n",
       "31616      Polizei_BBG          Bückeburg        Niedersachsen  \n",
       "31617       Polizei_HM     Hameln-Pyrmont        Niedersachsen  \n",
       "31618      Polizei_NOM           Northeim        Niedersachsen  \n",
       "31621   polizei_nrw_pb          Paderborn  Nordrhein-Westfalen  \n",
       "31664   polizei_nrw_bi          Bielefeld  Nordrhein-Westfalen  \n",
       "31826   PolizeiSachsen            Dresden              Sachsen  \n",
       "32081   PolizeiSachsen            Dresden              Sachsen  \n",
       "32098   polizei_nrw_do           Dortmund  Nordrhein-Westfalen  \n",
       "32365   Polizei_NRW_AC             Aachen  Nordrhein-Westfalen  \n",
       "32471   Polizei_NRW_AC             Aachen  Nordrhein-Westfalen  \n",
       "33210        PolizeiUL                Ulm    Baden-Württemberg  \n",
       "33666  PolizeiSaarland        Saarbrücken             Saarland  \n",
       "36612   polizei_nrw_bi          Bielefeld  Nordrhein-Westfalen  \n",
       "36744    BremenPolizei             Bremen               Bremen  \n",
       "37736    BremenPolizei             Bremen               Bremen  \n",
       "39878   Polizei_NRW_AC             Aachen  Nordrhein-Westfalen  \n",
       "40525    polizeiberlin             Berlin               Berlin  \n",
       "42085   PolizeiHamburg            Hamburg              Hamburg  \n",
       "42217    Polizei_Thuer             Erfurt            Thüringen  \n",
       "42220    Polizei_Thuer             Erfurt            Thüringen  \n",
       "42237        Polizei_H           Hannover        Niedersachsen  "
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_tw = pd.read_csv('..\\mod_data\\copbird_table_tweet_ext_state.csv', na_filter=False)\n",
    "df_tw_col = 'tweet_text'\n",
    "get_topics_by_str_lst(topic=topic_3, df=df_tw, col_name=df_tw_col)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "8d0a53cc",
   "metadata": {},
   "outputs": [
    {
     "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>article_id</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>location</th>\n",
       "      <th>bundesland</th>\n",
       "      <th>content</th>\n",
       "      <th>tw_user_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>7693</th>\n",
       "      <td>4970-4801222</td>\n",
       "      <td>2020-12-29 14:42:00</td>\n",
       "      <td>Frankfurt</td>\n",
       "      <td>hessen</td>\n",
       "      <td>Frankfurt (ots) - (em) Freitagnachmittag (25. ...</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13962</th>\n",
       "      <td>35235-4812557</td>\n",
       "      <td>2021-01-14 16:24:00</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>bremen</td>\n",
       "      <td>Bremen (ots) - - Ort: Bremen-Mitte, Bahnhofsvo...</td>\n",
       "      <td>808666671468658688</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19445</th>\n",
       "      <td>104234-4823502</td>\n",
       "      <td>2021-01-27 17:12:00</td>\n",
       "      <td>Lingen</td>\n",
       "      <td>niedersachsen</td>\n",
       "      <td>Lingen (ots) - Lingen/Brögbern - Am Sonntagnac...</td>\n",
       "      <td>773160525324808193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20919</th>\n",
       "      <td>117687-4825987</td>\n",
       "      <td>2021-01-30 13:38:00</td>\n",
       "      <td>Bad Dürkheim</td>\n",
       "      <td>rheinland-pfalz</td>\n",
       "      <td>Bad Dürkheim (ots) - Am 30.01.2021 um 13 Uhr b...</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22245</th>\n",
       "      <td>126723-4804801</td>\n",
       "      <td>2021-01-05 11:25:00</td>\n",
       "      <td>Mühlhausen</td>\n",
       "      <td>thueringen</td>\n",
       "      <td>Mühlhausen (ots) - Mit ausländerfeindlichen Pa...</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23117</th>\n",
       "      <td>6013-4807245</td>\n",
       "      <td>2021-01-08 12:08:00</td>\n",
       "      <td>Nürnberg</td>\n",
       "      <td>bayern</td>\n",
       "      <td>Nürnberg (ots) - In den vergangenen Tagen wurd...</td>\n",
       "      <td>800718568572612608</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24239</th>\n",
       "      <td>43526-4836365</td>\n",
       "      <td>2021-02-11 15:10:00</td>\n",
       "      <td>Nordwalde</td>\n",
       "      <td>nordrhein-westfalen</td>\n",
       "      <td>Nordwalde (ots) - Gemeinsame Pressemitteilung ...</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26018</th>\n",
       "      <td>24843-4839806</td>\n",
       "      <td>2021-02-16 12:17:00</td>\n",
       "      <td>Isselburg</td>\n",
       "      <td>nordrhein-westfalen</td>\n",
       "      <td>Isselburg (ots) - Einige Konsequenzen eingehan...</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29826</th>\n",
       "      <td>11187-4845946</td>\n",
       "      <td>2021-02-23 11:43:00</td>\n",
       "      <td>Münster</td>\n",
       "      <td>nordrhein-westfalen</td>\n",
       "      <td>Münster (ots) - Nach rassistischen Beleidigung...</td>\n",
       "      <td>2284811875</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31241</th>\n",
       "      <td>35235-4849262</td>\n",
       "      <td>2021-02-26 11:53:00</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>bremen</td>\n",
       "      <td>Bremen (ots) - - Ort: Bremen-Hemelingen, OT He...</td>\n",
       "      <td>808666671468658688</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31719</th>\n",
       "      <td>108747-4849805</td>\n",
       "      <td>2021-02-27 02:30:00</td>\n",
       "      <td>Pasewalk</td>\n",
       "      <td>mecklenburg-vorpommern</td>\n",
       "      <td>Pasewalk (ots) - Am 26.02.2021 wurden die Beam...</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32137</th>\n",
       "      <td>35235-4828445</td>\n",
       "      <td>2021-02-02 14:34:00</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>bremen</td>\n",
       "      <td>Bremen (ots) - - Ort: Bremen-Findorff, OT Weid...</td>\n",
       "      <td>808666671468658688</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32140</th>\n",
       "      <td>35235-4827977</td>\n",
       "      <td>2021-02-02 10:45:00</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>bremen</td>\n",
       "      <td>Bremen (ots) - - Ort: Bremen-Findorff, OT Weid...</td>\n",
       "      <td>808666671468658688</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32641</th>\n",
       "      <td>35235-4828777</td>\n",
       "      <td>2021-02-03 09:34:00</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>bremen</td>\n",
       "      <td>Bremen (ots) - - Ort: Bremen-Findorff Zeit: 02...</td>\n",
       "      <td>808666671468658688</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37060</th>\n",
       "      <td>119277-4863418</td>\n",
       "      <td>2021-03-14 14:35:00</td>\n",
       "      <td>Oldenburg</td>\n",
       "      <td>niedersachsen</td>\n",
       "      <td>Oldenburg (ots) - Am 13.02.21, um 16:20 Uhr, w...</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39547</th>\n",
       "      <td>55625-4868626</td>\n",
       "      <td>2021-03-19 13:35:00</td>\n",
       "      <td>Paderborn</td>\n",
       "      <td>nordrhein-westfalen</td>\n",
       "      <td>Paderborn (ots) - HC - Ein Paderborner beleidi...</td>\n",
       "      <td>2389342951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39575</th>\n",
       "      <td>12522-4868514</td>\n",
       "      <td>2021-03-19 12:39:00</td>\n",
       "      <td>Bielefeld</td>\n",
       "      <td>nordrhein-westfalen</td>\n",
       "      <td>Bielefeld (ots) - HC/ Bielefeld- Paderborn - E...</td>\n",
       "      <td>2389146030</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41162</th>\n",
       "      <td>4971-4870662</td>\n",
       "      <td>2021-03-22 17:13:00</td>\n",
       "      <td>Dortmund</td>\n",
       "      <td>nordrhein-westfalen</td>\n",
       "      <td>Dortmund (ots) - Lfd. Nr.: 0314 In der Nacht v...</td>\n",
       "      <td>769128278</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41777</th>\n",
       "      <td>11559-4871407</td>\n",
       "      <td>2021-03-23 12:53:00</td>\n",
       "      <td>Aachen</td>\n",
       "      <td>nordrhein-westfalen</td>\n",
       "      <td>Aachen (ots) - Unbekannte Täter haben - vermut...</td>\n",
       "      <td>2389142300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44966</th>\n",
       "      <td>117683-4852665</td>\n",
       "      <td>2021-03-02 14:13:00</td>\n",
       "      <td>Kaiserslautern</td>\n",
       "      <td>rheinland-pfalz</td>\n",
       "      <td>Kaiserslautern (ots) - Unbekannte Schmierfinke...</td>\n",
       "      <td>886595382</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48417</th>\n",
       "      <td>104236-4858302</td>\n",
       "      <td>2021-03-08 14:58:00</td>\n",
       "      <td>Osnabrück</td>\n",
       "      <td>niedersachsen</td>\n",
       "      <td>Osnabrück (ots) - Unbekannte machten sich zwis...</td>\n",
       "      <td>760752388454113280</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49864</th>\n",
       "      <td>35235-4886661</td>\n",
       "      <td>2021-04-12 12:46:00</td>\n",
       "      <td>Bremen</td>\n",
       "      <td>bremen</td>\n",
       "      <td>Bremen (ots) - - Ort: Bremen-Blumenthal, OT Lü...</td>\n",
       "      <td>808666671468658688</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53479</th>\n",
       "      <td>65846-4880317</td>\n",
       "      <td>2021-04-01 20:30:00</td>\n",
       "      <td>Herford</td>\n",
       "      <td>nordrhein-westfalen</td>\n",
       "      <td>Herford (ots) - (mmb) Am Donnerstag (01.04.202...</td>\n",
       "      <td>2389393237</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54109</th>\n",
       "      <td>11559-4893710</td>\n",
       "      <td>2021-04-20 11:41:00</td>\n",
       "      <td>Aachen</td>\n",
       "      <td>nordrhein-westfalen</td>\n",
       "      <td>Aachen (ots) - Unbekannte Täter beschmierten i...</td>\n",
       "      <td>2389142300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>56428</th>\n",
       "      <td>43648-4899539</td>\n",
       "      <td>2021-04-26 14:43:00</td>\n",
       "      <td>Marburg-Biedenkopf</td>\n",
       "      <td>hessen</td>\n",
       "      <td>Marburg-Biedenkopf (ots) - Mahnmal beschädigt-...</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67410</th>\n",
       "      <td>66841-4905162</td>\n",
       "      <td>2021-05-03 12:26:00</td>\n",
       "      <td>Hannover</td>\n",
       "      <td>niedersachsen</td>\n",
       "      <td>Hannover (ots) - Am Freitagabend, 30.04.2021, ...</td>\n",
       "      <td>770652658566852608</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67743</th>\n",
       "      <td>126719-4905163</td>\n",
       "      <td>2021-05-03 12:27:00</td>\n",
       "      <td>Sömmerda</td>\n",
       "      <td>thueringen</td>\n",
       "      <td>Sömmerda (ots) - Am Freitagnachmittag pöbelte ...</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>69663</th>\n",
       "      <td>126723-4909419</td>\n",
       "      <td>2021-05-07 11:34:00</td>\n",
       "      <td>Nordhausen</td>\n",
       "      <td>thueringen</td>\n",
       "      <td>Nordhausen (ots) - Bisherigen Ermittlungen zuf...</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           article_id            timestamp            location  \\\n",
       "7693     4970-4801222  2020-12-29 14:42:00           Frankfurt   \n",
       "13962   35235-4812557  2021-01-14 16:24:00              Bremen   \n",
       "19445  104234-4823502  2021-01-27 17:12:00              Lingen   \n",
       "20919  117687-4825987  2021-01-30 13:38:00        Bad Dürkheim   \n",
       "22245  126723-4804801  2021-01-05 11:25:00          Mühlhausen   \n",
       "23117    6013-4807245  2021-01-08 12:08:00            Nürnberg   \n",
       "24239   43526-4836365  2021-02-11 15:10:00           Nordwalde   \n",
       "26018   24843-4839806  2021-02-16 12:17:00           Isselburg   \n",
       "29826   11187-4845946  2021-02-23 11:43:00             Münster   \n",
       "31241   35235-4849262  2021-02-26 11:53:00              Bremen   \n",
       "31719  108747-4849805  2021-02-27 02:30:00            Pasewalk   \n",
       "32137   35235-4828445  2021-02-02 14:34:00              Bremen   \n",
       "32140   35235-4827977  2021-02-02 10:45:00              Bremen   \n",
       "32641   35235-4828777  2021-02-03 09:34:00              Bremen   \n",
       "37060  119277-4863418  2021-03-14 14:35:00           Oldenburg   \n",
       "39547   55625-4868626  2021-03-19 13:35:00           Paderborn   \n",
       "39575   12522-4868514  2021-03-19 12:39:00           Bielefeld   \n",
       "41162    4971-4870662  2021-03-22 17:13:00            Dortmund   \n",
       "41777   11559-4871407  2021-03-23 12:53:00              Aachen   \n",
       "44966  117683-4852665  2021-03-02 14:13:00      Kaiserslautern   \n",
       "48417  104236-4858302  2021-03-08 14:58:00           Osnabrück   \n",
       "49864   35235-4886661  2021-04-12 12:46:00              Bremen   \n",
       "53479   65846-4880317  2021-04-01 20:30:00             Herford   \n",
       "54109   11559-4893710  2021-04-20 11:41:00              Aachen   \n",
       "56428   43648-4899539  2021-04-26 14:43:00  Marburg-Biedenkopf   \n",
       "67410   66841-4905162  2021-05-03 12:26:00            Hannover   \n",
       "67743  126719-4905163  2021-05-03 12:27:00            Sömmerda   \n",
       "69663  126723-4909419  2021-05-07 11:34:00          Nordhausen   \n",
       "\n",
       "                   bundesland  \\\n",
       "7693                   hessen   \n",
       "13962                  bremen   \n",
       "19445           niedersachsen   \n",
       "20919         rheinland-pfalz   \n",
       "22245              thueringen   \n",
       "23117                  bayern   \n",
       "24239     nordrhein-westfalen   \n",
       "26018     nordrhein-westfalen   \n",
       "29826     nordrhein-westfalen   \n",
       "31241                  bremen   \n",
       "31719  mecklenburg-vorpommern   \n",
       "32137                  bremen   \n",
       "32140                  bremen   \n",
       "32641                  bremen   \n",
       "37060           niedersachsen   \n",
       "39547     nordrhein-westfalen   \n",
       "39575     nordrhein-westfalen   \n",
       "41162     nordrhein-westfalen   \n",
       "41777     nordrhein-westfalen   \n",
       "44966         rheinland-pfalz   \n",
       "48417           niedersachsen   \n",
       "49864                  bremen   \n",
       "53479     nordrhein-westfalen   \n",
       "54109     nordrhein-westfalen   \n",
       "56428                  hessen   \n",
       "67410           niedersachsen   \n",
       "67743              thueringen   \n",
       "69663              thueringen   \n",
       "\n",
       "                                                 content          tw_user_id  \n",
       "7693   Frankfurt (ots) - (em) Freitagnachmittag (25. ...                      \n",
       "13962  Bremen (ots) - - Ort: Bremen-Mitte, Bahnhofsvo...  808666671468658688  \n",
       "19445  Lingen (ots) - Lingen/Brögbern - Am Sonntagnac...  773160525324808193  \n",
       "20919  Bad Dürkheim (ots) - Am 30.01.2021 um 13 Uhr b...                      \n",
       "22245  Mühlhausen (ots) - Mit ausländerfeindlichen Pa...                      \n",
       "23117  Nürnberg (ots) - In den vergangenen Tagen wurd...  800718568572612608  \n",
       "24239  Nordwalde (ots) - Gemeinsame Pressemitteilung ...                      \n",
       "26018  Isselburg (ots) - Einige Konsequenzen eingehan...                      \n",
       "29826  Münster (ots) - Nach rassistischen Beleidigung...          2284811875  \n",
       "31241  Bremen (ots) - - Ort: Bremen-Hemelingen, OT He...  808666671468658688  \n",
       "31719  Pasewalk (ots) - Am 26.02.2021 wurden die Beam...                      \n",
       "32137  Bremen (ots) - - Ort: Bremen-Findorff, OT Weid...  808666671468658688  \n",
       "32140  Bremen (ots) - - Ort: Bremen-Findorff, OT Weid...  808666671468658688  \n",
       "32641  Bremen (ots) - - Ort: Bremen-Findorff Zeit: 02...  808666671468658688  \n",
       "37060  Oldenburg (ots) - Am 13.02.21, um 16:20 Uhr, w...                      \n",
       "39547  Paderborn (ots) - HC - Ein Paderborner beleidi...          2389342951  \n",
       "39575  Bielefeld (ots) - HC/ Bielefeld- Paderborn - E...          2389146030  \n",
       "41162  Dortmund (ots) - Lfd. Nr.: 0314 In der Nacht v...           769128278  \n",
       "41777  Aachen (ots) - Unbekannte Täter haben - vermut...          2389142300  \n",
       "44966  Kaiserslautern (ots) - Unbekannte Schmierfinke...           886595382  \n",
       "48417  Osnabrück (ots) - Unbekannte machten sich zwis...  760752388454113280  \n",
       "49864  Bremen (ots) - - Ort: Bremen-Blumenthal, OT Lü...  808666671468658688  \n",
       "53479  Herford (ots) - (mmb) Am Donnerstag (01.04.202...          2389393237  \n",
       "54109  Aachen (ots) - Unbekannte Täter beschmierten i...          2389142300  \n",
       "56428  Marburg-Biedenkopf (ots) - Mahnmal beschädigt-...                      \n",
       "67410  Hannover (ots) - Am Freitagabend, 30.04.2021, ...  770652658566852608  \n",
       "67743  Sömmerda (ots) - Am Freitagnachmittag pöbelte ...                      \n",
       "69663  Nordhausen (ots) - Bisherigen Ermittlungen zuf...                      "
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_pm = pd.read_csv(r'..\\mod_data\\2020-12_2021-05_presseportal.csv', na_filter=False)\n",
    "df_pm_col = 'content'\n",
    "get_topics_by_str_lst(topic=topic_3, df=df_pm, col_name=df_pm_col)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a205693e",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6fb4345e",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "python-scientific kernel",
   "language": "python",
   "name": "python-scientific"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}