meteostat 1.7.6__py3-none-any.whl → 2.0.1__py3-none-any.whl

meteostat/providers/index.py

@@ -0,0 +1,496 @@
+"""
+Provider Index
+
+This module contains a list of all available data providers.
+"""
+
+from datetime import date, timedelta
+
+from meteostat.typing import License, ProviderSpec
+from meteostat.enumerations import Grade, Granularity, Parameter, Provider, Priority
+
+PROVIDER_HOURLY = ProviderSpec(
+    id=Provider.HOURLY,
+    name="Meteostat Hourly",
+    granularity=Granularity.HOURLY,
+    priority=Priority.NONE,
+    grade=None,
+    license=None,
+    requires=["id"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.RHUM,
+        Parameter.PRCP,
+        Parameter.SNWD,
+        Parameter.WDIR,
+        Parameter.WSPD,
+        Parameter.WPGT,
+        Parameter.PRES,
+        Parameter.TSUN,
+        Parameter.CLDC,
+        Parameter.COCO,
+    ],
+    start=date(1931, 1, 1),
+    module="meteostat.providers.meteostat.hourly",
+)
+
+PROVIDER_DAILY = ProviderSpec(
+    id=Provider.DAILY,
+    name="Meteostat Daily",
+    granularity=Granularity.DAILY,
+    priority=Priority.NONE,
+    grade=None,
+    license=None,
+    requires=["id"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.TMIN,
+        Parameter.TMAX,
+        Parameter.RHUM,
+        Parameter.PRCP,
+        Parameter.SNWD,
+        Parameter.WSPD,
+        Parameter.WPGT,
+        Parameter.PRES,
+        Parameter.TSUN,
+        Parameter.CLDC,
+    ],
+    start=date(1899, 1, 1),
+    module="meteostat.providers.meteostat.daily",
+)
+
+PROVIDER_DAILY_DERIVED = ProviderSpec(
+    id=Provider.DAILY_DERIVED,
+    name="Meteostat Daily Derived",
+    granularity=Granularity.DAILY,
+    priority=Priority.NONE,
+    grade=None,
+    license=None,
+    requires=["id"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.TMIN,
+        Parameter.TMAX,
+        Parameter.PRCP,
+        Parameter.SNOW,
+        Parameter.WSPD,
+        Parameter.WDIR,
+        Parameter.WPGT,
+        Parameter.PRES,
+        Parameter.TSUN,
+        Parameter.CLDC,
+    ],
+    start=date(1931, 1, 1),
+    module="meteostat.providers.meteostat.daily_derived",
+)
+
+PROVIDER_MONTHLY = ProviderSpec(
+    id=Provider.MONTHLY,
+    name="Meteostat Monthly",
+    granularity=Granularity.MONTHLY,
+    priority=Priority.NONE,
+    grade=None,
+    license=None,
+    requires=["id"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.TMIN,
+        Parameter.TMAX,
+        Parameter.PRCP,
+        Parameter.PRES,
+        Parameter.TSUN,
+    ],
+    start=date(1899, 1, 1),
+    module="meteostat.providers.meteostat.monthly",
+)
+
+PROVIDER_MONTHLY_DERIVED = ProviderSpec(
+    id=Provider.MONTHLY_DERIVED,
+    name="Meteostat Monthly Derived",
+    granularity=Granularity.MONTHLY,
+    priority=Priority.NONE,
+    grade=None,
+    license=None,
+    requires=["id"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.TMIN,
+        Parameter.TMAX,
+        Parameter.PRCP,
+        Parameter.PRES,
+        Parameter.TSUN,
+    ],
+    start=date(1899, 1, 1),
+    module="meteostat.providers.meteostat.monthly_derived",
+)
+
+PROVIDER_DWD_HOURLY = ProviderSpec(
+    id=Provider.DWD_HOURLY,
+    name="DWD Hourly",
+    granularity=Granularity.HOURLY,
+    priority=Priority.HIGHEST,
+    grade=Grade.RECORD,
+    license=License(
+        commercial=True,
+        attribution="Deutscher Wetterdienst",
+        name="CC BY 4.0",
+        url="https://creativecommons.org/licenses/by/4.0/",
+    ),
+    requires=["identifiers"],
+    countries=["DE"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.RHUM,
+        Parameter.PRCP,
+        Parameter.WDIR,
+        Parameter.WSPD,
+        Parameter.PRES,
+        Parameter.TSUN,
+        Parameter.VSBY,
+        Parameter.COCO,
+    ],
+    start=date(1939, 1, 1),
+    module="meteostat.providers.dwd.hourly",
+)
+
+PROVIDER_DWD_POI = ProviderSpec(
+    id=Provider.DWD_POI,
+    name="DWD POI",
+    granularity=Granularity.HOURLY,
+    priority=Priority.MEDIUM,
+    grade=Grade.OBSERVATION,
+    license=License(
+        commercial=True,
+        attribution="Deutscher Wetterdienst",
+        name="CC BY 4.0",
+        url="https://creativecommons.org/licenses/by/4.0/",
+    ),
+    requires=["identifiers"],
+    parameters=[
+        Parameter.CLDC,
+        Parameter.TEMP,
+        Parameter.VSBY,
+        Parameter.WSPD,
+        Parameter.WPGT,
+        Parameter.PRCP,
+        Parameter.RHUM,
+        Parameter.WDIR,
+        Parameter.PRES,
+        Parameter.TSUN,
+        Parameter.COCO,
+        Parameter.SNWD,
+    ],
+    start=date.today() - timedelta(days=1),
+    module="meteostat.providers.dwd.poi",
+)
+
+PROVIDER_DWD_MOSMIX = ProviderSpec(
+    id=Provider.DWD_MOSMIX,
+    name="DWD MOSMIX",
+    granularity=Granularity.HOURLY,
+    priority=Priority.LOWEST,
+    grade=Grade.FORECAST,
+    license=License(
+        commercial=True,
+        attribution="Deutscher Wetterdienst",
+        name="CC BY 4.0",
+        url="https://creativecommons.org/licenses/by/4.0/",
+    ),
+    requires=["identifiers"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.RHUM,
+        Parameter.PRCP,
+        Parameter.WDIR,
+        Parameter.WSPD,
+        Parameter.WPGT,
+        Parameter.PRES,
+        Parameter.TSUN,
+        Parameter.CLDC,
+        Parameter.COCO,
+    ],
+    start=date.today(),
+    module="meteostat.providers.dwd.mosmix",
+)
+
+PROVIDER_DWD_DAILY = ProviderSpec(
+    id=Provider.DWD_DAILY,
+    name="DWD Daily",
+    granularity=Granularity.DAILY,
+    priority=Priority.HIGHEST,
+    grade=Grade.RECORD,
+    license=License(
+        commercial=True,
+        attribution="Deutscher Wetterdienst",
+        name="CC BY 4.0",
+        url="https://creativecommons.org/licenses/by/4.0/",
+    ),
+    requires=["identifiers"],
+    countries=["DE"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.TMIN,
+        Parameter.TMAX,
+        Parameter.RHUM,
+        Parameter.PRCP,
+        Parameter.SNWD,
+        Parameter.WSPD,
+        Parameter.WPGT,
+        Parameter.PRES,
+        Parameter.TSUN,
+        Parameter.CLDC,
+    ],
+    start=date(1781, 1, 1),
+    module="meteostat.providers.dwd.daily",
+)
+
+PROVIDER_DWD_MONTHLY = ProviderSpec(
+    id=Provider.DWD_MONTHLY,
+    name="DWD Monthly",
+    granularity=Granularity.MONTHLY,
+    priority=Priority.HIGHEST,
+    grade=Grade.RECORD,
+    license=License(
+        commercial=True,
+        attribution="Deutscher Wetterdienst",
+        name="CC BY 4.0",
+        url="https://creativecommons.org/licenses/by/4.0/",
+    ),
+    requires=["identifiers"],
+    countries=["DE"],
+    parameters=[Parameter.TEMP, Parameter.TMIN, Parameter.TMAX, Parameter.PRCP],
+    start=date(1851, 1, 1),
+    module="meteostat.providers.dwd.monthly",
+)
+
+PROVIDER_ECCC_HOURLY = ProviderSpec(
+    id=Provider.ECCC_HOURLY,
+    name="ECCC Hourly",
+    granularity=Granularity.HOURLY,
+    priority=Priority.HIGHEST,
+    grade=Grade.RECORD,
+    license=License(
+        commercial=True,
+        attribution="Environment and Climate Change Canada",
+        name="Environment and Climate Change Canada Data Servers End-use Licence",
+        url="https://eccc-msc.github.io/open-data/licence/readme_en/",
+    ),
+    requires=["identifiers"],
+    countries=["CA"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.RHUM,
+        Parameter.PRCP,
+        Parameter.WDIR,
+        Parameter.WSPD,
+        Parameter.VSBY,
+    ],
+    start=date(1939, 1, 1),
+    module="meteostat.providers.eccc.hourly",
+)
+
+PROVIDER_ECCC_DAILY = ProviderSpec(
+    id=Provider.ECCC_DAILY,
+    name="ECCC Daily",
+    granularity=Granularity.DAILY,
+    priority=Priority.HIGHEST,
+    grade=Grade.RECORD,
+    license=License(
+        commercial=True,
+        attribution="Environment and Climate Change Canada",
+        name="Environment and Climate Change Canada Data Servers End-use Licence",
+        url="https://eccc-msc.github.io/open-data/licence/readme_en/",
+    ),
+    requires=["identifiers"],
+    countries=["CA"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.TMIN,
+        Parameter.TMAX,
+        Parameter.PRCP,
+        Parameter.SNOW,
+        Parameter.SNWD,
+        Parameter.WPGT,
+    ],
+    start=date(1939, 1, 1),
+    module="meteostat.providers.eccc.daily",
+)
+
+PROVIDER_ECCC_MONTHLY = ProviderSpec(
+    id=Provider.ECCC_MONTHLY,
+    name="ECCC Monthly",
+    granularity=Granularity.MONTHLY,
+    priority=Priority.HIGHEST,
+    grade=Grade.RECORD,
+    license=License(
+        commercial=True,
+        attribution="Environment and Climate Change Canada",
+        name="Environment and Climate Change Canada Data Servers End-use Licence",
+        url="https://eccc-msc.github.io/open-data/licence/readme_en/",
+    ),
+    requires=["identifiers"],
+    countries=["CA"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.TMIN,
+        Parameter.TMAX,
+        Parameter.PRCP,
+        Parameter.PDAY,
+        Parameter.SNOW,
+    ],
+    start=date(1939, 1, 1),
+    module="meteostat.providers.eccc.monthly",
+)
+
+PROVIDER_ISD_LITE = ProviderSpec(
+    id=Provider.ISD_LITE,
+    name="NOAA ISD Lite",
+    granularity=Granularity.HOURLY,
+    priority=Priority.HIGH,
+    grade=Grade.OBSERVATION,
+    license=License(
+        commercial=True,
+        name="CC0 1.0 Universal",
+        url="https://creativecommons.org/publicdomain/zero/1.0/",
+    ),  # source: https://registry.opendata.aws/noaa-isd/
+    requires=["identifiers"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.RHUM,
+        Parameter.PRCP,
+        Parameter.WDIR,
+        Parameter.WSPD,
+        Parameter.WPGT,
+        Parameter.PRES,
+        Parameter.CLDC,
+    ],
+    start=date(1931, 1, 1),
+    module="meteostat.providers.noaa.isd_lite",
+)
+
+PROVIDER_GHCND = ProviderSpec(
+    id=Provider.GHCND,
+    name="NOAA GHCN-Daily",
+    granularity=Granularity.DAILY,
+    priority=Priority.HIGH,
+    grade=Grade.OBSERVATION,
+    license=License(
+        commercial=True,
+        name="CC0 1.0 Universal",
+        url="https://creativecommons.org/publicdomain/zero/1.0/",
+    ),  # source: https://registry.opendata.aws/noaa-ghcn/
+    requires=["identifiers"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.TMIN,
+        Parameter.TMAX,
+        Parameter.PRCP,
+        Parameter.SNOW,
+        Parameter.WSPD,
+        Parameter.WDIR,
+        Parameter.WPGT,
+        Parameter.TSUN,
+        Parameter.CLDC,
+    ],
+    start=date(1931, 1, 1),
+    module="meteostat.providers.noaa.ghcnd",
+)
+
+PROVIDER_CLIMAT = ProviderSpec(
+    id=Provider.CLIMAT,
+    name="DWD CLIMAT",
+    granularity=Granularity.MONTHLY,
+    priority=Priority.HIGH,
+    grade=Grade.RECORD,
+    license=License(
+        commercial=True,
+        attribution="Deutscher Wetterdienst",
+        name="CC BY 4.0",
+        url="https://creativecommons.org/licenses/by/4.0/",
+    ),
+    requires=["identifiers"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.TMIN,
+        Parameter.TMAX,
+        Parameter.TXMN,
+        Parameter.TXMX,
+        Parameter.PRES,
+        Parameter.PRCP,
+        Parameter.TSUN,
+    ],
+    start=date(1875, 6, 1),
+    module="meteostat.providers.dwd.climat",
+)
+
+PROVIDER_METAR = ProviderSpec(
+    id=Provider.METAR,
+    name="METAR",
+    granularity=Granularity.HOURLY,
+    priority=Priority.LOW,
+    grade=Grade.OBSERVATION,
+    license=License(
+        commercial=True,
+    ),
+    requires=["identifiers"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.RHUM,
+        Parameter.WDIR,
+        Parameter.WSPD,
+        Parameter.PRES,
+        Parameter.COCO,
+    ],
+    start=date.today() - timedelta(days=1),
+    module="meteostat.providers.noaa.metar",
+)
+
+PROVIDER_METNO_FORECAST = ProviderSpec(
+    id=Provider.METNO_FORECAST,
+    name="MET Norway Forecast",
+    granularity=Granularity.HOURLY,
+    priority=Priority.LOWEST - 1,  # MOSMIX is more specific, therefore higher prio
+    grade=Grade.FORECAST,
+    license=License(
+        commercial=True,
+        attribution="MET Norway",
+        name="NLOD 2.0",
+        url="https://data.norge.no/nlod/en/2.0",
+    ),
+    requires=["location"],
+    parameters=[
+        Parameter.TEMP,
+        Parameter.RHUM,
+        Parameter.PRCP,
+        Parameter.WDIR,
+        Parameter.WSPD,
+        Parameter.WPGT,
+        Parameter.PRES,
+        Parameter.CLDC,
+        Parameter.COCO,
+    ],
+    start=date.today(),
+    module="meteostat.providers.metno.forecast",
+)
+
+
+DEFAULT_PROVIDERS = [
+    PROVIDER_HOURLY,
+    PROVIDER_DAILY,
+    PROVIDER_DAILY_DERIVED,
+    PROVIDER_MONTHLY,
+    PROVIDER_MONTHLY_DERIVED,
+    PROVIDER_DWD_HOURLY,
+    PROVIDER_DWD_POI,
+    PROVIDER_DWD_MOSMIX,
+    PROVIDER_DWD_DAILY,
+    PROVIDER_DWD_MONTHLY,
+    PROVIDER_ECCC_HOURLY,
+    PROVIDER_ECCC_DAILY,
+    PROVIDER_ECCC_MONTHLY,
+    PROVIDER_ISD_LITE,
+    PROVIDER_GHCND,
+    PROVIDER_CLIMAT,
+    PROVIDER_METAR,
+    PROVIDER_METNO_FORECAST,
+]

meteostat/providers/meteostat/daily.py

@@ -0,0 +1,65 @@
+"""
+The code is licensed under the MIT license.
+"""
+
+from datetime import datetime
+from typing import Optional
+
+import pandas as pd
+
+from meteostat.providers.meteostat.shared import filter_model_data, handle_exceptions
+from meteostat.typing import ProviderRequest
+from meteostat.core.cache import cache_service
+from meteostat.api.config import config
+from meteostat.utils.data import reshape_by_source
+
+ENDPOINT = config.daily_endpoint
+
+
+def get_ttl(_station: str, year: int) -> int:
+    """
+    Get TTL based on year
+
+    Current + previous year = one day
+    Else = 30 days
+    """
+    current_year = datetime.now().year
+    return 60 * 60 * 24 if current_year - year < 2 else 60 * 60 * 24 * 30
+
+
+@cache_service.cache(get_ttl, "pickle")
+@handle_exceptions
+def get_df(station: str, year: int) -> Optional[pd.DataFrame]:
+    """
+    Get CSV file from Meteostat and convert to DataFrame
+    """
+    file_url = ENDPOINT.format(station=station, year=str(year))
+
+    df = pd.read_csv(file_url, sep=",", compression="gzip")
+
+    time_cols = df.columns[0:3]
+    df["time"] = pd.to_datetime(df[time_cols])
+    df = df.drop(time_cols, axis=1).set_index("time")
+
+    return reshape_by_source(df)
+
+
+@filter_model_data
+def fetch(req: ProviderRequest) -> Optional[pd.DataFrame]:
+    """
+    Fetch daily weather data from Meteostat's central data repository
+    """
+    if req.start is None or req.end is None:
+        return None
+
+    # Get a list of relevant years
+    years = range(req.start.year, req.end.year + 1)
+    # Get list of annual DataFrames
+    df_yearly = [get_df(req.station.id, year) for year in years]
+    # Concatenate into a single DataFrame
+    df = (
+        pd.concat(df_yearly)
+        if len(df_yearly) and not all(d is None for d in df_yearly)
+        else None
+    )
+    return df

meteostat/providers/meteostat/daily_derived.py

@@ -0,0 +1,110 @@
+from typing import Optional
+
+import numpy as np
+import pandas as pd
+
+from meteostat.enumerations import Parameter, Provider
+from meteostat.api.hourly import hourly
+from meteostat.typing import ProviderRequest
+from meteostat.utils.data import aggregate_sources, reshape_by_source
+
+
+def daily_mean(group: pd.Series):
+    """
+    Calculate the daily mean from a series of hourly data
+    """
+    if group.isna().sum() > 3:
+        return np.nan
+    return group.interpolate(axis=0).mean()
+
+
+def daily_min(group: pd.Series):
+    """
+    Calculate the daily minimum from a series of hourly data
+    """
+    if group.isna().sum() > 0:
+        return np.nan
+    return group.min()
+
+
+def daily_max(group: pd.Series):
+    """
+    Calculate the daily maximum from a series of hourly data
+    """
+    if group.isna().sum() > 0:
+        return np.nan
+    return group.max()
+
+
+def daily_sum(group: pd.Series):
+    """
+    Calculate the daily sum from a series of hourly data
+    """
+    if group.isna().sum() > 0:
+        return np.nan
+    return group.sum()
+
+
+# Available parameters with source column and aggregation method
+PARAMETER_AGGS = {
+    Parameter.TEMP: (Parameter.TEMP, daily_mean),
+    Parameter.TMIN: (Parameter.TEMP, daily_min),
+    Parameter.TMAX: (Parameter.TEMP, daily_max),
+    Parameter.RHUM: (Parameter.RHUM, daily_mean),
+    Parameter.DWPT: (Parameter.DWPT, daily_mean),
+    Parameter.PRCP: (Parameter.PRCP, daily_sum),
+    Parameter.SNWD: (Parameter.SNWD, daily_max),
+    Parameter.WSPD: (Parameter.WSPD, daily_mean),
+    Parameter.WPGT: (Parameter.WPGT, daily_max),
+    Parameter.PRES: (Parameter.PRES, daily_mean),
+    Parameter.TSUN: (Parameter.TSUN, daily_sum),
+    Parameter.CLDC: (Parameter.CLDC, daily_mean),
+}
+
+
+def fetch(req: ProviderRequest) -> Optional[pd.DataFrame]:
+    """
+    Fetch hourly weather data from Meteostat's central data
+    repository and aggregate to daily granularity
+    """
+    # Get all source columns
+    source_cols = list(dict.fromkeys([PARAMETER_AGGS[p][0] for p in req.parameters]))
+
+    # Get hourly DataFrame
+    ts_hourly = hourly(
+        req.station.id,
+        req.start,
+        req.end,
+        parameters=source_cols,
+        providers=[Provider.HOURLY],
+        timezone=req.station.timezone,
+    )
+
+    df_hourly = ts_hourly.fetch(fill=True, sources=True)
+
+    # If no hourly data is available, exit
+    if df_hourly is None:
+        return None
+
+    # Create daily aggregations
+    df = pd.DataFrame()
+    for parameter in req.parameters:
+        [hourly_param_name, agg_func] = PARAMETER_AGGS[parameter]
+        df[parameter] = (
+            df_hourly[hourly_param_name]
+            .groupby(pd.Grouper(level="time", freq="1D"))
+            .agg(agg_func)
+        )
+        df[f"{parameter}_source"] = (
+            df_hourly[f"{hourly_param_name}_source"]
+            .groupby(pd.Grouper(level="time", freq="1D"))
+            .agg(aggregate_sources)
+        )
+
+    # Adjust DataFrame and add index
+    df = df.round(1)
+    df.index = pd.to_datetime(df.index.astype("datetime64").dt.date)  # type: ignore[union-attr]
+    df.index.name = "time"
+
+    # Return reshaped DataFrame
+    return reshape_by_source(df)