城市传感器气象数据集

import pystac_client
import planetary_computer

catalog = pystac_client.Client.open(
    "https://planetarycomputer.microsoft.com/api/stac/v1",
)
search = catalog.search(collections=["eclipse"], datetime="2022-03-01")
items = planetary_computer.sign(search.get_all_items())
print(f"Found {len(items)} item")
item = items[0]
item

import geopandas
import pandas as pd

asset = item.assets["data"]
df = pd.read_parquet(
    asset.href, storage_options=asset.extra_fields["table:storage_options"]
)
df

df = df[(df.Longitude > -89) & (df.Longitude < -86)]
len(df)

ts = df.resample("H", on="ReadingDateTimeUTC")[
    ["CalibratedPM25", "Humidity", "O3", "NO2", "CO"]
].mean()
ts.plot(subplots=True, sharex=True, figsize=(12, 12));

gdf = geopandas.GeoDataFrame(
    df, geometry=geopandas.points_from_xy(df.Longitude, df.Latitude), crs="epsg:4326"
)


gdf[["LocationName", "geometry"]].drop_duplicates(
    subset="LocationName"
).dropna().explore(marker_kwds=dict(radius=8))

average_pm25 = geopandas.GeoDataFrame(
    gdf.groupby("LocationName").agg(
        mean_pm25=("CalibratedPM25", "mean"), geometry=("geometry", "first")
    ),
    crs="epsg:4326",
)
average_pm25.explore(
    marker_kwds=dict(radius=10),
)

eclipse = catalog.get_collection("eclipse")
asset = planetary_computer.sign(eclipse.assets["data"])

import dask.dataframe as dd

ddf = dd.read_parquet(
    asset.href, storage_options=asset.extra_fields["table:storage_options"]
)
ddf