clean up unnecessary files

main
Nikola Sebastian Munder 2026-01-05 11:47:57 +01:00
parent 0c611f2a75
commit 3098403b65
10 changed files with 54900 additions and 791771 deletions

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

Binary file not shown.

File diff suppressed because one or more lines are too long

Binary file not shown.

Before

Width:  |  Height:  |  Size: 43 KiB

View File

@ -1,48 +0,0 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "2f3b328c",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b12ab0da",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"../data/bikesharing/sharing_stations.csv\", delimiter=\",\")\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "dat",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -1,149 +0,0 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\David Gaming\\AppData\\Local\\Temp\\ipykernel_18604\\2711366225.py:8: DtypeWarning: Columns (10,11,14,15,16) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" df = pd.concat((pd.read_csv(f) for f in all_files), ignore_index=True)\n",
"C:\\Users\\David Gaming\\AppData\\Local\\Temp\\ipykernel_18604\\2711366225.py:8: DtypeWarning: Columns (10,11,14,15,16) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" df = pd.concat((pd.read_csv(f) for f in all_files), ignore_index=True)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" operator_name domain_name domain_id \\\n",
"0 Eco Counter GmbH Stadt Tübingen 667 \n",
"1 Eco Counter GmbH Stadt Tübingen 667 \n",
"2 Eco Counter GmbH Stadt Tübingen 667 \n",
"3 Eco Counter GmbH Stadt Tübingen 667 \n",
"4 Eco Counter GmbH Stadt Tübingen 667 \n",
"\n",
" counter_site counter_site_id \\\n",
"0 Fuß- & Radtunnel Südportal - Derendinger Allee 100003358 \n",
"1 Fuß- & Radtunnel Südportal - Derendinger Allee 100003358 \n",
"2 Fuß- & Radtunnel Südportal - Derendinger Allee 100003358 \n",
"3 Fuß- & Radtunnel Südportal - Derendinger Allee 100003358 \n",
"4 Fuß- & Radtunnel Südportal - Derendinger Allee 100003358 \n",
"\n",
" counter_serial longitude latitude timezone \\\n",
"0 YAH24052174 9.04806 48.518 (UTC+01:00) Europe/Paris DST \n",
"1 YAH24052174 9.04806 48.518 (UTC+01:00) Europe/Paris DST \n",
"2 YAH24052174 9.04806 48.518 (UTC+01:00) Europe/Paris DST \n",
"3 YAH24052174 9.04806 48.518 (UTC+01:00) Europe/Paris DST \n",
"4 YAH24052174 9.04806 48.518 (UTC+01:00) Europe/Paris DST \n",
"\n",
" iso_timestamp channels_in channels_out channels_unknown \\\n",
"0 2013-06-21T00:00:00+02:00 2844 2647 na \n",
"1 2013-06-22T00:00:00+02:00 2412 2233 na \n",
"2 2013-06-23T00:00:00+02:00 1884 1808 na \n",
"3 2013-06-24T00:00:00+02:00 2072 1878 na \n",
"4 2013-06-25T00:00:00+02:00 2426 2419 na \n",
"\n",
" channels_all site_temperature site_rain_accumulation site_snow_accumulation \n",
"0 5491 17.5 1.5 0.0 \n",
"1 4645 16.5 0.2 0.0 \n",
"2 3692 14.5 0.0 0.0 \n",
"3 3950 12.5 5.4 0.0 \n",
"4 4845 11.5 6.0 0.0 \n"
]
}
],
"source": [
"\n",
"import pandas as pd\n",
"import glob\n",
"import os\n",
"\n",
"path = '../data/tageswerte_pro_Jahr/'\n",
"all_files = glob.glob(os.path.join(path , \"*.csv\")) #kein plan was das hier genau ist, hab es in Stack Overflow gefunden https://stackoverflow.com/questions/20906474/import-multiple-csv-files-into-pandas-and-concatenate-into-one-dataframe\n",
"\n",
"df = pd.concat((pd.read_csv(f) for f in all_files), ignore_index=True)\n",
"\n",
"print(df.head())"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Hotspots Durchschnitt Jahre\n",
"6 Kurpfalzbrücke 4994.045846\n",
"10 Renzstraße 3394.062305\n",
"5 Konrad-Adenauer-Brücke 2120.285610\n",
"1 Fernmeldeturm. 1828.993555\n",
"11 Schlosspark Lindenhof (Richtung Jugendherberge) 1333.949980\n",
"4 Jungbuschbrücke 1104.775576\n",
"9 Neckarauer Übergang -Schwetzinger Str. 1011.494404\n",
"7 Lindenhofüberführung 943.561290\n",
"8 Luzenbergstr. 667.606890\n",
"3 Feudenheimstr. stadtauswärts 512.098278\n"
]
}
],
"source": [
"\n",
"#Hotspots seit Aufzeichnungsbeginn bis 2025 - gemittelt über die Jahre. \n",
"# Vllt noch den Vergleich zu den einzelnen Jahren ziehen und zeigen wie es sich verändert hat?!\n",
"hotspots = (\n",
" df[df[\"domain_name\"].str.strip() == \"Stadt Mannheim\"]\n",
" .groupby(\"counter_site\", as_index=False)[\"channels_all\"]\n",
" .mean()\n",
" .sort_values(\"channels_all\", ascending=False)\n",
" .head(10)\n",
").rename(columns={\n",
" \"counter_site\": \"Hotspots\",\n",
" \"channels_all\": \"Durchschnitt Jahre\"\n",
" })\n",
"print(hotspots)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

File diff suppressed because one or more lines are too long