def search_proximity(cls, lat=50.848, lon=4.351, radius=8):
"""List stations within given radius from a location.
Args:
lat: latitude of the center of search, in decimal degrees
lon: longitude of the center of search, in decimal degrees
radius: maximum distance from center, in kilometers
Default values are the approximate center and radius of
Brussels.
Returns:
Dataframe of matching stations, listing sensor types,
locations and distances in kilometers from the search
center, indexed by station ID
The search is based on the station list retrieved as part of the
metadata.
The irceline.be API offers an alternative way to get an
(unordered) list of stations near a location:
`https://geo.irceline.be/sos/api/v1/stations?
near={{"center":{{"type":"Point","coordinates":[{lon},
{lat}]}},"radius":{radius}}}`
"""
near_stations = cls.stations.copy()
near_stations["distance"] = (near_stations.apply(
lambda x: haversine(lat, lon, x["lat"], x["lon"]), axis=1))
near_stations = (near_stations[
near_stations["distance"] <= radius].sort_values("distance"))
return near_stations
def search_proximity(lat=50.848, lon=4.351, radius=8):
"""Find sensors within given radius from a location.
Args:
lat: latitude of the center of search, in decimal degrees
lon: longitude of the center of search, in decimal degrees
radius: maximum distance from center, in kilometers
Default values are the approximate center and radius of Brussels.
Returns:
Dataframe of matching sensors, listing sensor types, locations
and distances in kilometers from the search center, indexed by
sensor ID
Raises:
requests.HTTPError if request failed
"""
url = (API_ENDPOINTS["proximity search pattern"].format(lat=lat,
lon=lon,
radius=radius))
call_rate_limiter()
response = requests.get(url)
response.raise_for_status()
sensors = json_normalize(response.json())
if len(sensors) == 0:
sensors = pd.DataFrame(
columns=["sensor_type", "latitude", "longitude", "distance"])
sensors.index.name = "sensor_id"
return sensors
sensors = (sensors[[
"sensor.id", "sensor.sensor_type.name", "location.latitude",
"location.longitude"
]].rename(
columns={
"sensor.id": "sensor_id",
"sensor.sensor_type.name": "sensor_type",
"location.latitude": "latitude",
"location.longitude": "longitude"
}))
for col in "latitude", "longitude":
sensors[col] = pd.to_numeric(sensors[col], downcast="float")
sensors.set_index("sensor_id", inplace=True)
# Drop duplicates - sensors appear once for each measurement in past 5 mins
sensors = sensors[~sensors.index.duplicated()]
# Calculate distances from search center and sort by those distances
sensors["distance"] = sensors.apply(lambda x: utils.haversine(
lat, lon, float(x["latitude"]), float(x["longitude"])),
axis=1)
sensors.sort_values("distance", inplace=True)
return sensors
def query_time_series(cls, phenomenon, lat_nearest=None, lon_nearest=None):
"""Convenience method to filter time series for those that
measure a given phenomenon, and sort by distance to a point if
given.
Args:
phenomenon: character sequence or regular expression to
filter phenomena by; operates on the "phenomenon" column
of the time_series dataframe
lat_nearest: latitude of the reference point
lon_nearest: longitude of the reference point
Returns:
Subset of time_series property. If lat_nearest and
lon_nearest are given, the result has an additional
column indicating distance in km from that point, and is
sorted by that distance.
Raises:
ValueError if only one of lat_nearest, lon_nearest is given
"""
if bool(lat_nearest is None) != bool(lon_nearest is None):
raise ValueError("Provide both or none of lat_nearest, "
"lon_nearest")
phenomena_lower = cls.time_series["phenomenon"].str.lower()
matches = phenomena_lower.str.contains(phenomenon.lower())
results = cls.time_series[matches].copy()
if lat_nearest is None:
return results
if len(results) == 0:
results["distance"] = None
return results
results["distance"] = results.apply(lambda row: haversine(
lat_nearest, lon_nearest, row["station_lat"], row["station_lon"]),
axis=1)
results = results.sort_values("distance")
return results