{ "cells": [ { "cell_type": "markdown", "id": "83885e86-1ccb-46ec-bee9-a33f3b541569", "metadata": {}, "source": [ "# Zusammenfassung der Analysen vom Hackathon für die Webside\n", "\n", "- womöglich zur Darstellung auf der Webside\n" ] }, { "cell_type": "code", "execution_count": 2, "id": "9bd1686f-9bbc-4c05-a5f5-e0c4ce653fb2", "metadata": { "tags": [] }, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd\n", "import altair as alt" ] }, { "cell_type": "markdown", "id": "81780c9a-7721-438b-9726-ff5a70910ce8", "metadata": {}, "source": [ "## Daten aufbereitung\n", "\n", "Dump der Datenbank vom 25.03.2023. Die verschiedene Tabellen der Datenbank werden einzeln eingelesen. Zusätzlich werden alle direkt zu einem Tweet zugehörige Information in ein Datenobjekt gesammelt. Die Informationen zu den GIS-Daten zu den einzelnen Polizeistadtion (\"police_stations\") sind noch unvollständig und müssen gegebenfalls nocheinmal überprüft werden.\n", "\n" ] }, { "cell_type": "code", "execution_count": 117, "id": "fcc48831-7999-4d79-b722-736715b1ced6", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "((479991, 3), (151690, 8), (151690, 4), (13327, 3))" ] }, "execution_count": 117, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tweets_meta = pd.concat([pd.read_csv(\"data/entity_old.tsv\", sep = \"\\t\"), # data from old scraper\n", " pd.read_csv(\"data/tweets.csv\")]) # data from new scraper\n", "\n", "tweets_text = pd.concat([pd.read_csv(\"data/tweet_old.tsv\", sep = \"\\t\")[['id', \n", " 'tweet_text', \n", " 'created_at', \n", " 'user_id']].rename(columns = {\"id\":\"tweet_id\"}),\n", " pd.read_csv(\"data/tweets-1679742698645.csv\")])\n", "\n", "tweets_statistics = pd.concat([pd.read_csv(\"data/tweet_old.tsv\", sep = \"\\t\")[['id', \n", " 'like_count', \n", " 'retweet_count', \n", " 'reply_count', \n", " 'quote_count']].rename(columns = {\"id\":\"tweet_id\"}),\n", " pd.read_csv(\"data/tweets-1679742620302.csv\")])\n", "\n", "tweets_user = pd.read_csv(\"data/user_old.tsv\", \n", " sep = \"\\t\").rename(columns = {\"id\":\"user_id\",\"name\": \"user_name\"}\n", " ).merge(pd.read_csv(\"data/tweets-1679742702794.csv\"\n", " ).rename(columns = {\"username\":\"handle\", \"handle\": \"user_name\"}),\n", " on = \"user_id\",\n", " how = \"outer\",\n", " suffixes = [\"_2021\", \"_2022\"])\n", "\n", "# Some usernames corresponding to one user_id have changed overtime. For easier handling only the latest username and handle is kept\n", "tweets_user = tweets_user.assign(handle = tweets_user.apply(lambda row: row['handle_2021'] if pd.isna(row['handle_2022']) else row['handle_2022'], axis=1),\n", " user_name = tweets_user.apply(lambda row: row['user_name_2021'] if pd.isna(row['user_name_2022']) else row['user_name_2022'], axis=1)\n", " ).drop(['handle_2021', 'handle_2022', 'user_name_2021', 'user_name_2022'], axis =1)\n", "\n", "police_stations = pd.read_csv(\"data/polizei_accounts_geo.csv\", sep = \"\\t\" # addiditional on police stations\n", " ).rename(columns = {\"Polizei Account\": \"handle\"})\n", "\n", "tweets_meta.shape, tweets_statistics.shape, tweets_text.shape, tweets_user.shape" ] }, { "cell_type": "markdown", "id": "0f7b2b95-0a6c-42c6-a308-5f68d4ba94b9", "metadata": {}, "source": [ "Jetzt können noch alle Tweet bezogenen informationen in einem Data Frame gespeichert werden:" ] }, { "cell_type": "code", "execution_count": 118, "id": "f30c2799-02c6-4e6a-ae36-9e039545b6b3", "metadata": { "tags": [] }, "outputs": [], "source": [ "# Merge like statistics, tweet text and user information in one data frame\n", "tweets_combined = pd.merge(tweets_statistics, \n", " tweets_text,\n", " on = 'tweet_id').merge(tweets_user, on = 'user_id'\n", " ).drop(['id'], axis = 1) # drop unascessary id column (redundant to index)\n", " " ] }, { "cell_type": "code", "execution_count": 119, "id": "bd407aba-eec1-41ed-bff9-4c5fcdf6cb9d", "metadata": { "tags": [] }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/nix/store/4105l1v2llsjz4j7qaqsz0fljc9z0z2r-python3-3.10.9-env/lib/python3.10/site-packages/IPython/lib/pretty.py:778: FutureWarning: In a future version, object-dtype columns with all-bool values will not be included in reductions with bool_only=True. Explicitly cast to bool dtype instead.\n", " output = repr(obj)\n", "/nix/store/4105l1v2llsjz4j7qaqsz0fljc9z0z2r-python3-3.10.9-env/lib/python3.10/site-packages/IPython/core/formatters.py:342: FutureWarning: In a future version, object-dtype columns with all-bool values will not be included in reductions with bool_only=True. Explicitly cast to bool dtype instead.\n", " return method()\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
tweet_idlike_countretweet_countreply_countquote_countmeasured_atis_deletedtweet_textcreated_atuser_idhandleuser_name
013210211234636636162120NaTNaN@mahanna196 Da die Stadt keine Ausnahme für Ra...2020-10-27 09:29:13778895426007203840polizei_olPolizei Oldenburg-Stadt/Ammerland
113210378342460661812000NaTNaN@mahanna196 Ja. *sr2020-10-27 10:35:38778895426007203840polizei_olPolizei Oldenburg-Stadt/Ammerland
2132106823495577600019330NaTNaN#Aktuell Auf dem ehem. Bundeswehrkrankenhausge...2020-10-27 12:36:26778895426007203840polizei_olPolizei Oldenburg-Stadt/Ammerland
313210739401991004160000NaTNaN@Emma36166433 Bitte lesen Sie unseren Tweet 2/...2020-10-27 12:59:06778895426007203840polizei_olPolizei Oldenburg-Stadt/Ammerland
413210886465067540492000NaTNaNIn der vergangenen Woche wurde die Wohnung des...2020-10-27 13:57:32778895426007203840polizei_olPolizei Oldenburg-Stadt/Ammerland
.......................................
151685162582880380400435451102023-02-19 13:40:36False#Sicherheit durch #Sichtbarkeit\\nUnsere #Dir3 ...2023-02-15 12:06:071168873095614160896polizeiberlin_pPolizei Berlin Prävention
151686162800410562390016720002023-02-25 13:14:49FalseUnser Präventionsteam vom #A44 berät heute und...2023-02-21 12:10:001168873095614160896polizeiberlin_pPolizei Berlin Prävention
151687162800481018301644860002023-02-25 13:14:49FalseAuch unser #A52 war heute aktiv und hat zum Th...2023-02-21 12:12:481168873095614160896polizeiberlin_pPolizei Berlin Prävention
151688162835289635287859320002023-02-26 13:15:05FalseGestern führte unser #A13 in einer Wohnsiedlun...2023-02-22 11:15:581168873095614160896polizeiberlin_pPolizei Berlin Prävention
1516891628709531998998529101002023-02-27 12:17:33FalseAuf dem Gelände der @BUFAStudios (Oberlandstr....2023-02-23 10:53:071168873095614160896polizeiberlin_pPolizei Berlin Prävention
\n", "

151690 rows × 12 columns

\n", "
" ], "text/plain": [ " tweet_id like_count retweet_count reply_count \\\n", "0 1321021123463663616 2 1 2 \n", "1 1321037834246066181 2 0 0 \n", "2 1321068234955776000 19 3 3 \n", "3 1321073940199100416 0 0 0 \n", "4 1321088646506754049 2 0 0 \n", "... ... ... ... ... \n", "151685 1625828803804004354 5 1 1 \n", "151686 1628004105623900167 2 0 0 \n", "151687 1628004810183016448 6 0 0 \n", "151688 1628352896352878593 2 0 0 \n", "151689 1628709531998998529 10 1 0 \n", "\n", " quote_count measured_at is_deleted \\\n", "0 0 NaT NaN \n", "1 0 NaT NaN \n", "2 0 NaT NaN \n", "3 0 NaT NaN \n", "4 0 NaT NaN \n", "... ... ... ... \n", "151685 0 2023-02-19 13:40:36 False \n", "151686 0 2023-02-25 13:14:49 False \n", "151687 0 2023-02-25 13:14:49 False \n", "151688 0 2023-02-26 13:15:05 False \n", "151689 0 2023-02-27 12:17:33 False \n", "\n", " tweet_text created_at \\\n", "0 @mahanna196 Da die Stadt keine Ausnahme für Ra... 2020-10-27 09:29:13 \n", "1 @mahanna196 Ja. *sr 2020-10-27 10:35:38 \n", "2 #Aktuell Auf dem ehem. Bundeswehrkrankenhausge... 2020-10-27 12:36:26 \n", "3 @Emma36166433 Bitte lesen Sie unseren Tweet 2/... 2020-10-27 12:59:06 \n", "4 In der vergangenen Woche wurde die Wohnung des... 2020-10-27 13:57:32 \n", "... ... ... \n", "151685 #Sicherheit durch #Sichtbarkeit\\nUnsere #Dir3 ... 2023-02-15 12:06:07 \n", "151686 Unser Präventionsteam vom #A44 berät heute und... 2023-02-21 12:10:00 \n", "151687 Auch unser #A52 war heute aktiv und hat zum Th... 2023-02-21 12:12:48 \n", "151688 Gestern führte unser #A13 in einer Wohnsiedlun... 2023-02-22 11:15:58 \n", "151689 Auf dem Gelände der @BUFAStudios (Oberlandstr.... 2023-02-23 10:53:07 \n", "\n", " user_id handle \\\n", "0 778895426007203840 polizei_ol \n", "1 778895426007203840 polizei_ol \n", "2 778895426007203840 polizei_ol \n", "3 778895426007203840 polizei_ol \n", "4 778895426007203840 polizei_ol \n", "... ... ... \n", "151685 1168873095614160896 polizeiberlin_p \n", "151686 1168873095614160896 polizeiberlin_p \n", "151687 1168873095614160896 polizeiberlin_p \n", "151688 1168873095614160896 polizeiberlin_p \n", "151689 1168873095614160896 polizeiberlin_p \n", "\n", " user_name \n", "0 Polizei Oldenburg-Stadt/Ammerland \n", "1 Polizei Oldenburg-Stadt/Ammerland \n", "2 Polizei Oldenburg-Stadt/Ammerland \n", "3 Polizei Oldenburg-Stadt/Ammerland \n", "4 Polizei Oldenburg-Stadt/Ammerland \n", "... ... \n", "151685 Polizei Berlin Prävention \n", "151686 Polizei Berlin Prävention \n", "151687 Polizei Berlin Prävention \n", "151688 Polizei Berlin Prävention \n", "151689 Polizei Berlin Prävention \n", "\n", "[151690 rows x 12 columns]" ] }, "execution_count": 119, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Convert Counts to integer values\n", "tweets_combined[['like_count', 'retweet_count', 'reply_count', 'quote_count']] = tweets_combined[['like_count', 'retweet_count', 'reply_count', 'quote_count']].fillna(-99).astype(int)\n", "tweets_combined = tweets_combined.assign(measured_at = pd.to_datetime(tweets_combined['measured_at']), # change date to date format\n", " created_at = pd.to_datetime(tweets_combined['created_at']),\n", " handle = tweets_combined['handle'].str.lower(),\n", " is_deleted = tweets_combined['is_deleted'].map(lambda x: False if x == 0.0 else ( True if x == 1.0 else np.nan)))\n", "tweets_combined" ] }, { "cell_type": "markdown", "id": "91dfb8bb-15dc-4b2c-9c5f-3eab18d78ef8", "metadata": { "tags": [] }, "source": [ "### Adjazenzmatrix mentions\n", " \n", "Information, welche nicht direkt enthalten ist: welche Accounts werden erwähnt. Ist nur im Tweet mit @handle gekennzeichnet." ] }, { "cell_type": "code", "execution_count": 53, "id": "5d8bf730-3c8f-4143-b405-c95f1914f54b", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "0 Auch wir schließen uns dem Apell an! \\n\\n#Ukra...\n", "1 @BWeltenbummler Sehr schwer zu sagen. Die Evak...\n", "2 Halten Sie durch – die Evakuierung ist fast ab...\n", "3 Halten Sie durch – die Evakuierung ist fast ab...\n", "4 RT @drkberlin_iuk: 🚨 In enger Abstimmung mit d...\n", "Name: tweet_text, dtype: object" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# TODO" ] }, { "cell_type": "markdown", "id": "0c242090-0748-488c-b604-f521030f468f", "metadata": { "tags": [] }, "source": [ "## Metadaten \n", "\n", "Welche Daten bilden die Grundlage?" ] }, { "cell_type": "code", "execution_count": 112, "id": "0e5eb455-6b12-4572-8f5e-f328a94bd797", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "hashtag 267255\n", "url 141594\n", "mention 71142\n", "Name: entity_type, dtype: int64" ] }, "execution_count": 112, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tweets_meta[\"entity_type\"].value_counts()\n", "# tweets_meta[tweets_meta['entity_type'] == \"mention\"]" ] }, { "cell_type": "markdown", "id": "ef440301-cf89-4e80-8801-eb853d636190", "metadata": { "tags": [] }, "source": [ "Insgesamt haben wir 151690 einzigartige Tweets:" ] }, { "cell_type": "code", "execution_count": 113, "id": "5a438e7f-8735-40bb-b450-2ce168f0f67a", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "151690" ] }, "execution_count": 113, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tweets_combined[\"tweet_id\"].value_counts().shape[0] # Anzahl an Tweets" ] }, { "cell_type": "code", "execution_count": 114, "id": "4f1e8c6c-3610-436e-899e-4d0307259230", "metadata": { "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Die Tweets wurden vom 2020-10-27 bis zum: 2023-03-16 gesammelt. Also genau insgesamt: 870 Tage. (Mit kleinen Unterbrechungen)\n" ] } ], "source": [ "print(\"Die Tweets wurden vom \", tweets_combined['created_at'].min().date(), \"bis zum:\", tweets_combined['created_at'].max().date(), \"gesammelt.\", \"Also genau insgesamt:\", (tweets_combined['created_at'].max() - tweets_combined['created_at'].min()).days, \"Tage. (Mit kleinen Unterbrechungen)\")\n", "# tweets_combined[tweets_combined['created_at'] == tweets_combined['created_at'].max()] # Tweets vom letzten Tag" ] }, { "cell_type": "markdown", "id": "d8b47a60-1535-4d03-913a-73e897bc18df", "metadata": { "tags": [] }, "source": [ "Welche Polizei Accounts haben am meisten getweetet?" ] }, { "cell_type": "code", "execution_count": 122, "id": "9373552e-6baf-46df-ae16-c63603e20a83", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
handlecountNameTypBundeslandStadtLATLONG
11polizei_ffm5512NaNNaNNaNNaNNaNNaN
0polizeisachsen5340Polizei SachsenPolizeiSachsenDresden51.049328613.7381437
3polizei_nrw_do4895Polizei NRW DOPolizeiNordrhein-WestfalenDortmund51.51422737.4652789
92polizeibb4323NaNNaNNaNNaNNaNNaN
61polizeihamburg4042Polizei HamburgPolizeiHamburgHamburg53.55034110.000654
\n", "
" ], "text/plain": [ " handle count Name Typ Bundesland \\\n", "11 polizei_ffm 5512 NaN NaN NaN \n", "0 polizeisachsen 5340 Polizei Sachsen Polizei Sachsen \n", "3 polizei_nrw_do 4895 Polizei NRW DO Polizei Nordrhein-Westfalen \n", "92 polizeibb 4323 NaN NaN NaN \n", "61 polizeihamburg 4042 Polizei Hamburg Polizei Hamburg \n", "\n", " Stadt LAT LONG \n", "11 NaN NaN NaN \n", "0 Dresden 51.0493286 13.7381437 \n", "3 Dortmund 51.5142273 7.4652789 \n", "92 NaN NaN NaN \n", "61 Hamburg 53.550341 10.000654 " ] }, "execution_count": 122, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tweets_agg = tweets_combined.groupby(by = [\"user_id\", \"user_name\", \"handle\"]\n", " )[\"user_id\"].aggregate(['count']\n", " ).merge(police_stations,\n", " on = \"handle\",\n", " how = \"left\"\n", " ).sort_values(['count'], ascending=False)\n", "tweets_agg.shape\n", "activy_police_vis = tweets_agg[0:50]\n", "activy_police_vis.head()" ] }, { "cell_type": "markdown", "id": "9cf5f544-706b-41af-b785-7023f04e3ecb", "metadata": { "tags": [] }, "source": [ "Visualisierung aktivste Polizeistadtionen:" ] }, { "cell_type": "code", "execution_count": 123, "id": "b1c39196-d1cc-4f82-8e01-7529e7b3046f", "metadata": { "tags": [] }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/nix/store/4105l1v2llsjz4j7qaqsz0fljc9z0z2r-python3-3.10.9-env/lib/python3.10/site-packages/altair/utils/core.py:317: FutureWarning: iteritems is deprecated and will be removed in a future version. Use .items instead.\n", " for col_name, dtype in df.dtypes.iteritems():\n" ] }, { "data": { "text/html": [ "\n", "
\n", "" ], "text/plain": [ "alt.Chart(...)" ] }, "execution_count": 123, "metadata": {}, "output_type": "execute_result" } ], "source": [ "barchart = alt.Chart(activy_police_vis[0:15]).mark_bar().encode(\n", " x = 'count:Q',\n", " y = alt.Y('handle:N', sort = '-x'),\n", ")\n", "barchart " ] }, { "cell_type": "markdown", "id": "90f686ff-93c6-44d9-9761-feb35dfe9d1d", "metadata": { "tags": [] }, "source": [ "Welche Tweets ziehen besonders viel Aufmerksamkeit auf sich?" ] }, { "cell_type": "code", "execution_count": 125, "id": "d0549250-b11f-4762-8500-1134c53303b4", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "0 Die Gewalt, die unsere Kolleginnen & Kollegen in der Silvesternacht erleben mussten, ist une...\n", "1 An diejenigen, die vergangene Nacht in eine Schule in #Gesundbrunnen eingebrochen sind und 242 T...\n", "2 WICHTIGE Info:\\nÜber das Internet wird derzeit ein Video verbreitet, in dem von einem Überfall a...\n", "3 Die Experten gehen derzeit davon aus, dass es sich um ein absichtliches \"Fake-Video\" handelt, da...\n", "4 Weil wir dich schieben! @BVG_Kampagne 😉 https://t.co/N8kdlCxhz2\n", " ... \n", "151685 Sinken die Temperaturen ❄, steigt zeitgleich das Risiko für Verkehrsteilnehmer. Höchste Zeit zu ...\n", "151686 📺Am Sonntag, um 19:50 Uhr, geht es bei #KripoLive im \\n@mdrde\\n auch um die Fahndung nach einem ...\n", "151687 Musik verbindet!\\nUnser #Adventskalender der #Bundespolizei startet morgen ➡ https://t.co/V6CaTV...\n", "151688 @gretchen_hann Hallo, diese Frage kann die Bundespolizei Spezialkräfte besser beantworten. Richt...\n", "151689 #Bönen #Holzwickede - Verstöße gegen Coronaschutzverordnung: Polizei löst Gaststättenabend und F...\n", "Name: tweet_text, Length: 151690, dtype: object" ] }, "execution_count": 125, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tweets_attention = tweets_combined.merge(police_stations,\n", " on = \"handle\",\n", " how = \"left\")\n", "pd.options.display.max_colwidth = 100\n", "tweets_attention.sort_values('like_count', ascending = False).reset_index()['tweet_text']\n", "\n" ] }, { "cell_type": "code", "execution_count": 90, "id": "97952234-7957-421e-bd2c-2c8261992c5a", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
user_idhandleuser_name
010000046861566525456jannik9Systemstratege:
11000043230870867969LSollikPhysiolucy
21000405847460151296Achim1949HansSystemstratege:
31000460805719121921WahreWWahreWorte
41000744009638252544derD1ck3Ⓓ①ⓒⓚ①③ (🏡)
............
1155499931264Havok1975Systemstratege:
11555999542638226403328Madame_de_SaxeSystemstratege:
11556999901133282754560tungstendie74Systemstratege:
11557999904275080794112_danielheimSystemstratege:
11558999955376454930432amyman6010Systemstratege:
\n", "

11559 rows × 3 columns

\n", "
" ], "text/plain": [ " user_id handle user_name\n", "0 1000004686156652545 6jannik9 Systemstratege: \n", "1 1000043230870867969 LSollik Physiolucy\n", "2 1000405847460151296 Achim1949Hans Systemstratege: \n", "3 1000460805719121921 WahreW WahreWorte\n", "4 1000744009638252544 derD1ck3 Ⓓ①ⓒⓚ①③ (🏡)\n", "... ... ... ...\n", "11554 99931264 Havok1975 Systemstratege: \n", "11555 999542638226403328 Madame_de_Saxe Systemstratege: \n", "11556 999901133282754560 tungstendie74 Systemstratege: \n", "11557 999904275080794112 _danielheim Systemstratege: \n", "11558 999955376454930432 amyman6010 Systemstratege: \n", "\n", "[11559 rows x 3 columns]" ] }, "execution_count": 90, "metadata": {}, "output_type": "execute_result" } ], "source": [ "old = pd.read_csv(\"data/user_old.tsv\",sep = \"\\t\").rename(columns = {\"id\":\"user_id\",\"name\": \"user_name\"} )\n", "new = pd.read_csv(\"data/tweets-1679742702794.csv\").rename(columns = {\"username\":\"handle\", \"handle\": \"user_name\"})\n", "new" ] }, { "cell_type": "code", "execution_count": 121, "id": "ed86b45e-9dd8-436d-9c96-15500ed93985", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
count
user_iduser_name
223758384Polizei Sachsen5340
259607457Polizei NRW K2544
424895827Polizei Stuttgart1913
769128278Polizei NRW DO4895
775664780Polizei Rostock604
.........
1169206134189830145Polizei Stendal842
1184022676488314880Polizei Pforzheim283
1184024283342950401Polizei Ravensburg460
1232548941889228808Systemstratege:168
1295978598034284546Polizei ZPD NI133
\n", "

163 rows × 1 columns

\n", "
" ], "text/plain": [ " count\n", "user_id user_name \n", "223758384 Polizei Sachsen 5340\n", "259607457 Polizei NRW K 2544\n", "424895827 Polizei Stuttgart 1913\n", "769128278 Polizei NRW DO 4895\n", "775664780 Polizei Rostock 604\n", "... ...\n", "1169206134189830145 Polizei Stendal 842\n", "1184022676488314880 Polizei Pforzheim 283\n", "1184024283342950401 Polizei Ravensburg 460\n", "1232548941889228808 Systemstratege: 168\n", "1295978598034284546 Polizei ZPD NI 133\n", "\n", "[163 rows x 1 columns]" ] }, "execution_count": 121, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tweets_combined.groupby(by = [\"user_id\", \"user_name\"]\n", " )[\"user_id\"].aggregate(['count']\n", " )" ] } ], "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 }