2212719
/
DAT_Projekt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ran black and isort for sorting imports and reformating

main
Nikola Sebastian Munder 2026-01-05 12:00:41 +01:00
parent 3098403b65
commit 30e8fbc33e
2 changed files with 23 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
data/combine_hourly.py
View File

@ -1,16 +1,18 @@
import glob
import pandas as pd
import os
import pandas as pd
def main():
path = "./stundenwerte/*.csv"
path = "./stundenwerte/*.csv"
files = glob.glob(path)
dfs = []
print("Working", end="", flush=True)
for file in files:
df_temp= pd.read_csv(file,low_memory=False)
df_temp = pd.read_csv(file, low_memory=False)
df_temp["year"] = os.path.basename(file).split("_")[2].split(".")[0]
dfs.append(df_temp.astype({"year":int}))
dfs.append(df_temp.astype({"year": int}))
print(".", end="", flush=True)
max_df = pd.concat(dfs, ignore_index=True)
@ -18,7 +20,7 @@ def main():
# Mannheim subset
df_ma = max_df[max_df["domain_name"] == "Stadt Mannheim"]
df_ma.to_csv("../data/processed/hourly_bikes_mannheim.csv", index=False)
if __name__ == "__main__":
main()
main()

28
data/hourly.py
View File

@ -1,29 +1,31 @@
# script to get hourly counters from 2014-present
import requests
import gzip
import shutil
import os
import glob
import gzip
import os
import shutil
import pandas as pd
import requests
def main():
for year in range(2014,2026):
for month in range(1,13):
month = str(month) if len(str(month))==2 else f"0{month}"
for year in range(2014, 2026):
for month in range(1, 13):
month = str(month) if len(str(month)) == 2 else f"0{month}"
year_month = f"{year}{month}"
url = f"https://mobidata-bw.de/daten/eco-counter/v2/fahrradzaehler_stundenwerten_{year_month}.csv.gz"
os.makedirs("hourly_archives",exist_ok=True)
os.makedirs("hourly_archives", exist_ok=True)
filename = url.split("/")[-1]
with open(f"hourly_archives/{filename}", "wb") as f:
r = requests.get(url)
f.write(r.content)
os.makedirs("stundenwerte", exist_ok=True)
with gzip.open(f"hourly_archives/{filename}", 'rb') as f_in:
f_name = "stundenwerte/"+filename.split(".")[0]
with open(f"{f_name}.csv", 'wb') as f_out:
with gzip.open(f"hourly_archives/{filename}", "rb") as f_in:
f_name = "stundenwerte/" + filename.split(".")[0]
with open(f"{f_name}.csv", "wb") as f_out:
shutil.copyfileobj(f_in, f_out)
if __name__ == "__main__":
main()
main()