Klimabaeume open data

python_scripts/parse_wurzburg_open_data/.gitignore

+input/*.parquet
\ No newline at end of file

python_scripts/parse_wurzburg_open_data/parse_open_data.py

+"""
+Würzburger Klimabaeume - Bodenfeuchte
+https://opendata.wuerzburg.de/explore/dataset/sls-klimabaeume/export/?disjunctive.species_german
+
+"""
+
+
+from pathlib import Path
+import requests
+import shutil
+import pandas as pd
+from rich import print
+
+SCRIPT_DIR = Path(__file__).resolve().parent
+INPUT_DIR = SCRIPT_DIR / 'input'
+
+INPUT_FILE = INPUT_DIR / 'wuerzburg_trees.parquet'
+INPUT_URL = "https://opendata.wuerzburg.de/api/explore/v2.1/catalog/datasets/sls-klimabaeume/exports/parquet?lang=en&timezone=Europe%2FBerlin"
+USER_AGENT = {'User-agent': 'Mozilla/5.0'}
+
+
+def download_file(download_url, download_path):
+    with requests.get(download_url, stream=True, headers=USER_AGENT) as r:
+        with open(download_path, 'wb') as f:
+            shutil.copyfileobj(r.raw, f)
+
+
+if INPUT_FILE.exists() and INPUT_FILE.stat().st_size > 0:
+    print(f"{INPUT_FILE} already here.")
+else:
+    print(f"Downloading {INPUT_URL}")
+    download_file(INPUT_URL, INPUT_FILE)
+    print("  Done")
+
+df = pd.read_parquet(INPUT_FILE, engine='fastparquet')
+
+print(df)
+
+interesting_columns = ['tree_number', 'species_latin', 'latitude', 'longitude']
+
+species = 'species_latin'
+coordinates = ['latitude', 'longitude']
+df[interesting_columns].drop_duplicates().groupby(species).apply(print)
+
+df[interesting_columns].drop_duplicates().groupby(coordinates).apply(print)

python_scripts/parse_wurzburg_open_data/requirements.txt

+pandas
+requests
+fastparquet
+folium