tomasr/ReSSPublica
1
0
Fork 0
mirror of https://github.com/tomasriveral/ReSSPublica.git synced 2026-08-11 18:28:38 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix: clean up new code

Browse Source
This commit is contained in:
tomasr
2026-07-29 18:03:19 +02:00
parent 37efbd03b0
commit df2ce393eb
1 changed files with 49 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files
resspublica/baselLuftQualitat.py
+28 -73
View File
@@ -12,12 +12,12 @@ logger = logging.getLogger("resspublica")
from .translations import * from .translations import *
from .utils import * from .utils import *
start_date = pd.Timestamp("2026-01-01") startDate = pd.Timestamp("2026-01-01")
start_date_datetime = date.fromisoformat("2026-01-01") # a bit dumb we need those two formats startDateDatetimeFormat = date.fromisoformat("2026-01-01") # a bit dumb we need those two formats
end_date = pd.Timestamp((date.today() - timedelta(days=1)).isoformat()) endDate = pd.Timestamp((date.today() - timedelta(days=1)).isoformat())
station_information = { stationInformation = {
"100048": { "100048": {
"name": "Basel Chrischona", "name": "Basel Chrischona",
"coordinates": (47.571709338, 7.687073826) "coordinates": (47.571709338, 7.687073826)
@@ -48,7 +48,7 @@ pollutants = [
"o3" "o3"
] ]
pollutant_units = { pollutantUnits = {
"pm10": "µg/m³", "pm10": "µg/m³",
"pm2_5": "µg/m³", "pm2_5": "µg/m³",
"no2": "µg/m³", "no2": "µg/m³",
@@ -57,7 +57,7 @@ pollutant_units = {
# Fixed scale per pollutant so colors remain comparable day-to-day # Fixed scale per pollutant so colors remain comparable day-to-day
pollutant_scales = { pollutantScales = {
"pm10": (0, 50), "pm10": (0, 50),
"pm2_5": (0, 30), "pm2_5": (0, 30),
"no2": (0, 100), "no2": (0, 100),
@@ -76,30 +76,24 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
"https://data.bl.ch/api/v2/catalog/datasets/12510/exports/parquet" "https://data.bl.ch/api/v2/catalog/datasets/12510/exports/parquet"
] ]
# ---------------------------------------------------------
# Load data
# ---------------------------------------------------------
dataframes = [] dataframes = []
for url in urls: for url in urls:
logger.debug(f"Querying {url}...") logger.debug(f"Querying {url}...")
df = pd.read_parquet(url) df = pd.read_parquet(url)
station_id = url.split("/")[-3] stationId = url.split("/")[-3]
df["station_id"] = station_id df["stationId"] = stationId
# Always define station name # Always define station name
# Use dataset id as fallback until manually mapped # Use dataset id as fallback until manually mapped
df["station_name"] = station_id df["stationName"] = stationId
if station_id in station_information: if stationId in stationInformation:
df["station_name"] = station_information[station_id]["name"] df["stationName"] = stationInformation[stationId]["name"]
# ----------------------------------------------------- possibleVariableNameForDates = [
# Normalize datetime to Swiss time
# -----------------------------------------------------
possible_dates = [
"datum_zeit", "datum_zeit",
"timestamp", "timestamp",
"anfangszeit", "anfangszeit",
@@ -109,7 +103,7 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
date_column = next( date_column = next(
( (
col col
for col in possible_dates for col in possibleVariableNameForDates
if col in df.columns if col in df.columns
), ),
None None
@@ -134,23 +128,17 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
) )
# ----------------------------------------------------- if stationId in stationInformation:
# Add coordinates for BL datasets
# -----------------------------------------------------
if station_id in station_information:
lat, lon = station_information[station_id]["coordinates"] lat, lon = stationInformation[stationId]["coordinates"]
df["latitude"] = lat df["latitude"] = lat
df["longitude"] = lon df["longitude"] = lon
df["station_name"] = ( df["stationName"] = (
station_information[station_id]["name"] stationInformation[stationId]["name"]
) )
# -----------------------------------------------------
# Convert long format datasets
# -----------------------------------------------------
if ( if (
"parameter" in df.columns "parameter" in df.columns
and "messwert" in df.columns and "messwert" in df.columns
@@ -167,9 +155,6 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
).reset_index() ).reset_index()
# -----------------------------------------------------
# Pollutant normalization
# -----------------------------------------------------
pollutant_mapping = { pollutant_mapping = {
"pm10": [ "pm10": [
@@ -214,11 +199,6 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
] ]
} }
# -----------------------------------------------------
# Melt everything into:
# date_time | station_id | pollutant | value | geometry
# -----------------------------------------------------
parts = [] parts = []
for pollutant, candidates in pollutant_mapping.items(): for pollutant, candidates in pollutant_mapping.items():
@@ -230,8 +210,8 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
keep = [ keep = [
"date_time", "date_time",
"station_id", "stationId",
"station_name", "stationName",
column column
] ]
@@ -271,20 +251,12 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
dataframes.append(df) dataframes.append(df)
# ---------------------------------------------------------
# Combine datasets
# ---------------------------------------------------------
dataframe = pd.concat( dataframe = pd.concat(
dataframes, dataframes,
ignore_index=True, ignore_index=True,
sort=False sort=False
) )
# ---------------------------------------------------------
# Geometry
# ---------------------------------------------------------
def safe_load(x): def safe_load(x):
try: try:
geom = wkb.loads(x) geom = wkb.loads(x)
@@ -294,10 +266,8 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
except Exception: except Exception:
return None return None
dataframe["geometry"] = None dataframe["geometry"] = None
if "geo_point_2d" in dataframe.columns: if "geo_point_2d" in dataframe.columns:
dataframe["geometry"] = dataframe[ dataframe["geometry"] = dataframe[
@@ -325,9 +295,6 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
crs="EPSG:4326" crs="EPSG:4326"
) )
# ---------------------------------------------------------
# Boundaries
# ---------------------------------------------------------
gdb = ( gdb = (
ASSETS / ASSETS /
"swissBOUNDARIES3D_1_5_LV95_LN02.gdb" "swissBOUNDARIES3D_1_5_LV95_LN02.gdb"
@@ -346,11 +313,8 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
cantons["KANTONSNUMMER"] == 13 cantons["KANTONSNUMMER"] == 13
].to_crs("EPSG:4326") ].to_crs("EPSG:4326")
# ---------------------------------------------------------
# Time filter
# ---------------------------------------------------------
logger.info("Generating daily image...") logger.info("Generating daily image...")
for day in pd.date_range(start_date, end_date, freq="D"): for day in pd.date_range(startDate, endDate, freq="D"):
if Path( CACHE / f"baselAirQuality-{day.strftime("%Y-%m-%d")}.png").exists(): if Path( CACHE / f"baselAirQuality-{day.strftime("%Y-%m-%d")}.png").exists():
logger.debug(f"Day {day.strftime("%Y-%m-%d")} is already cached. Skipping...") logger.debug(f"Day {day.strftime("%Y-%m-%d")} is already cached. Skipping...")
@@ -365,14 +329,11 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
(geo["date_time"] < next_day) (geo["date_time"] < next_day)
] ]
# ---------------------------------------------------------
# Average per station
# ---------------------------------------------------------
averaged = ( averaged = (
geo_day.groupby( geo_day.groupby(
[ [
"station_id", "stationId",
"station_name", "stationName",
"pollutant", "pollutant",
"geometry" "geometry"
], ],
@@ -389,12 +350,6 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
crs="EPSG:4326" crs="EPSG:4326"
) )
# ---------------------------------------------------------
# Plot
# ---------------------------------------------------------
fig, axes = plt.subplots( fig, axes = plt.subplots(
2, 2,
2, 2,
@@ -418,7 +373,7 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
ax.set_visible(False) ax.set_visible(False)
continue continue
vmin, vmax = pollutant_scales[pollutant] vmin, vmax = pollutantScales[pollutant]
subset.plot( subset.plot(
ax=ax, ax=ax,
@@ -469,12 +424,12 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
for _, row in subset.iterrows(): for _, row in subset.iterrows():
dx, dy = label_offsets.get( dx, dy = label_offsets.get(
row["station_name"], row["stationName"],
(0, 8) (0, 8)
) )
ax.annotate( ax.annotate(
row["station_name"], row["stationName"],
xy=( xy=(
row.geometry.x, row.geometry.x,
row.geometry.y row.geometry.y
@@ -492,7 +447,7 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
) )
ax.set_title( ax.set_title(
f"{pollutant} ({pollutant_units[pollutant]})" f"{pollutant} ({pollutantUnits[pollutant]})"
) )
ax.axis("off") ax.axis("off")
@@ -514,7 +469,7 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
} }
yesterday = date.today() - timedelta(days=1) yesterday = date.today() - timedelta(days=1)
current = start_date_datetime current = startDateDatetimeFormat
while current <= yesterday: while current <= yesterday:
dailyEntry = {} dailyEntry = {}
@@ -523,7 +478,7 @@ def generateBaselLuftqualitat(ASSETS, CACHE):
dailyEntry["date"] = current.isoformat() dailyEntry["date"] = current.isoformat()
dailyEntry["source"] = "https://luftqualitaet.ch/" dailyEntry["source"] = "https://luftqualitaet.ch/"
dailyEntry["url"] = "https://luftqualitaet.ch/" dailyEntry["url"] = "https://luftqualitaet.ch/"
dailyEntry["text"] = f"<img src\"https://resspublica.tomasrivera.ch/images/baselAirQuality-{current.isoformat()}.png\"alt=\"basel air quality {current.isoformat()}\">" dailyEntry["text"] = f"<img src=\"https://resspublica.tomasrivera.ch/images/baselAirQuality-{current.isoformat()}.png\"alt=\"basel air quality {current.isoformat()}\">"
for lang in ["fr", "de", "it", "rm", "en"]: for lang in ["fr", "de", "it", "rm", "en"]:
dailyEntry["title"] = f"{translatedAirQualityInBasel[lang]} {current.isoformat()}" dailyEntry["title"] = f"{translatedAirQualityInBasel[lang]} {current.isoformat()}"