Add waterdata.get_combined_metadata for combined location + time-series inventory

Wraps the Water Data API's combined-metadata collection, which joins the
monitoring-locations catalog with the time-series-metadata catalog and
returns one row per (location, parameter, statistic) inventory entry.
Each row carries every column from both source endpoints, so any
location attribute (state, HUC, site type, drainage area, well depth,
...) can be combined with any time-series attribute (parameter code,
statistic, data type, period of record, ...) in a single query.

Mirrors R's read_waterdata_combined_meta. Implementation re-uses the
existing get_ogc_data infrastructure: the function is a thin parameter
declaration plus a service / output_id pair (combined-metadata,
combined_meta_id), since _switch_arg_id, _switch_properties_id,
_construct_api_requests, and _walk_pages are all already
service-agnostic.

Closes #263.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: thodson-usgs

NEWS.md

@@ -1,3 +1,5 @@
+**05/05/2026:** Added `waterdata.get_combined_metadata(...)` — wraps the Water Data API's `combined-metadata` collection, which joins the monitoring-locations catalog with the time-series-metadata catalog and returns one row per (location, parameter, statistic) inventory entry. This is the most flexible "what data is available" endpoint in the API: any location attribute (state, HUC, site type, drainage area, well-construction depth, …) can be combined with any time-series attribute (parameter code, statistic, data type, period of record, …) in a single query. Mirrors R's `read_waterdata_combined_meta`.
+
 **05/05/2026:** Added `waterdata.get_samples_summary(monitoringLocationIdentifier=...)` — wraps the Samples database `/summary/{id}` endpoint, returning per-characteristic result and activity counts plus first / most recent activity dates for a single monitoring location. Useful for taking inventory of available discrete-sample data before pulling observations with `get_samples`.
 
 **05/01/2026:** The `nadp` module is now deprecated. Calling any of `get_annual_MDN_map`, `get_annual_NTN_map`, or `get_zip` will emit a `DeprecationWarning`. The module is scheduled for removal on or after **2026-11-01**. NADP is not a USGS data source; users should retrieve NADP data directly from https://nadp.slh.wisc.edu/.

dataretrieval/waterdata/__init__.py

@@ -13,6 +13,7 @@
 from .api import (
     get_channel,
     get_codes,
+    get_combined_metadata,
     get_continuous,
     get_daily,
     get_field_measurements,
@@ -43,6 +44,7 @@
     "SERVICES",
     "get_channel",
     "get_codes",
+    "get_combined_metadata",
     "get_continuous",
     "get_daily",
     "get_field_measurements",

dataretrieval/waterdata/api.py

@@ -932,6 +932,219 @@ def get_time_series_metadata(
     return get_ogc_data(args, output_id, service)
 
 
+def get_combined_metadata(
+    monitoring_location_id: str | list[str] | None = None,
+    parameter_code: str | list[str] | None = None,
+    parameter_name: str | list[str] | None = None,
+    parameter_description: str | list[str] | None = None,
+    unit_of_measure: str | list[str] | None = None,
+    statistic_id: str | list[str] | None = None,
+    data_type: str | list[str] | None = None,
+    computation_identifier: str | list[str] | None = None,
+    thresholds: int | None = None,
+    sublocation_identifier: str | list[str] | None = None,
+    primary: str | list[str] | None = None,
+    parent_time_series_id: str | list[str] | None = None,
+    web_description: str | list[str] | None = None,
+    last_modified: str | list[str] | None = None,
+    begin: str | list[str] | None = None,
+    end: str | list[str] | None = None,
+    agency_code: str | list[str] | None = None,
+    agency_name: str | list[str] | None = None,
+    monitoring_location_number: str | list[str] | None = None,
+    monitoring_location_name: str | list[str] | None = None,
+    district_code: str | list[str] | None = None,
+    country_code: str | list[str] | None = None,
+    country_name: str | list[str] | None = None,
+    state_code: str | list[str] | None = None,
+    state_name: str | list[str] | None = None,
+    county_code: str | list[str] | None = None,
+    county_name: str | list[str] | None = None,
+    minor_civil_division_code: str | list[str] | None = None,
+    site_type_code: str | list[str] | None = None,
+    site_type: str | list[str] | None = None,
+    hydrologic_unit_code: str | list[str] | None = None,
+    basin_code: str | list[str] | None = None,
+    altitude: str | list[str] | None = None,
+    altitude_accuracy: str | list[str] | None = None,
+    altitude_method_code: str | list[str] | None = None,
+    altitude_method_name: str | list[str] | None = None,
+    vertical_datum: str | list[str] | None = None,
+    vertical_datum_name: str | list[str] | None = None,
+    horizontal_positional_accuracy_code: str | list[str] | None = None,
+    horizontal_positional_accuracy: str | list[str] | None = None,
+    horizontal_position_method_code: str | list[str] | None = None,
+    horizontal_position_method_name: str | list[str] | None = None,
+    original_horizontal_datum: str | list[str] | None = None,
+    original_horizontal_datum_name: str | list[str] | None = None,
+    drainage_area: str | list[str] | None = None,
+    contributing_drainage_area: str | list[str] | None = None,
+    time_zone_abbreviation: str | list[str] | None = None,
+    uses_daylight_savings: str | list[str] | None = None,
+    construction_date: str | list[str] | None = None,
+    aquifer_code: str | list[str] | None = None,
+    national_aquifer_code: str | list[str] | None = None,
+    aquifer_type_code: str | list[str] | None = None,
+    well_constructed_depth: str | list[str] | None = None,
+    hole_constructed_depth: str | list[str] | None = None,
+    depth_source_code: str | list[str] | None = None,
+    properties: str | list[str] | None = None,
+    skip_geometry: bool | None = None,
+    bbox: list[float] | None = None,
+    limit: int | None = None,
+    filter: str | None = None,
+    filter_lang: FILTER_LANG | None = None,
+    convert_type: bool = True,
+) -> tuple[pd.DataFrame, BaseMetadata]:
+    """Get combined monitoring-location and time-series metadata.
+
+    The ``combined-metadata`` collection joins the monitoring-locations
+    catalog with the time-series-metadata catalog so that one row is
+    returned per (location, parameter, statistic) inventory entry,
+    carrying every column from both source endpoints. This makes it the
+    most flexible "what data is available" endpoint in the Water Data
+    API: any monitoring-location attribute (state, HUC, site type,
+    drainage area, well-construction depth, …) can be combined with any
+    time-series attribute (parameter code, statistic, data type, period
+    of record, …) in a single query.
+
+    See the OpenAPI reference for the full list of supported fields:
+    https://api.waterdata.usgs.gov/ogcapi/v0/openapi?f=html#/combined-metadata
+    The R analogue is ``read_waterdata_combined_meta`` in
+    https://github.com/DOI-USGS/dataRetrieval/.
+
+    Parameters
+    ----------
+    monitoring_location_id : string or list of strings, optional
+        A unique identifier representing a single monitoring location.
+        Created by combining the agency code (e.g. ``USGS``) with the ID
+        number (e.g. ``02238500``), separated by a hyphen
+        (e.g. ``"USGS-02238500"``).
+    parameter_code : string or list of strings, optional
+        5-digit codes used to identify the constituent measured and the
+        units of measure. See
+        https://help.waterdata.usgs.gov/codes-and-parameters/parameters.
+    parameter_name : string or list of strings, optional
+        A human-understandable name corresponding to ``parameter_code``.
+    parameter_description : string or list of strings, optional
+        A human-readable description of what is being measured.
+    unit_of_measure : string or list of strings, optional
+        A human-readable description of the units of measurement
+        associated with an observation.
+    statistic_id : string or list of strings, optional
+        A code corresponding to the statistic an observation represents
+        (e.g. ``00001`` max, ``00002`` min, ``00003`` mean). Full list at
+        https://help.waterdata.usgs.gov/code/stat_cd_nm_query?stat_nm_cd=%25&fmt=html.
+    data_type : string or list of strings, optional
+        The type of data the time series represents, e.g.
+        ``"Continuous"``, ``"Daily"``, ``"Field measurements"``.
+    computation_identifier : string or list of strings, optional
+        Indicates whether the data from this time series represent a
+        specific statistical computation.
+    thresholds : numeric or list of numbers, optional
+        Numeric limits known for a time series (e.g. historic maximum,
+        below-which-the-sensor-is-non-operative).
+    sublocation_identifier : string or list of strings, optional
+    primary : string or list of strings, optional
+        A flag identifying whether the time series is "primary". Primary
+        time series are standard observations that have undergone Bureau
+        review and approval. Non-primary (provisional) time series have a
+        missing ``primary`` value, are produced for timely best-science
+        use, and are retained by this system for only 120 days.
+    parent_time_series_id : string or list of strings, optional
+    web_description : string or list of strings, optional
+        A description of what this time series represents, as used by
+        WDFN and other USGS data dissemination products.
+    last_modified, begin, end : string, optional
+        Datetime fields that accept either an RFC 3339 datetime, an
+        interval (``"start/end"``, optionally half-bounded with ``..``),
+        or an ISO 8601 duration (e.g. ``"P1M"``, ``"PT36H"``). See
+        :func:`get_time_series_metadata` for the full grammar.
+    agency_code, agency_name, monitoring_location_number, \
+monitoring_location_name, district_code, country_code, country_name, \
+state_code, state_name, county_code, county_name, \
+minor_civil_division_code, site_type_code, site_type, \
+hydrologic_unit_code, basin_code : string or list of strings, optional
+        Location-catalog filters carried over from the
+        ``monitoring-locations`` collection.
+    altitude, altitude_accuracy, altitude_method_code, \
+altitude_method_name, vertical_datum, vertical_datum_name, \
+horizontal_positional_accuracy_code, horizontal_positional_accuracy, \
+horizontal_position_method_code, horizontal_position_method_name, \
+original_horizontal_datum, original_horizontal_datum_name, \
+drainage_area, contributing_drainage_area, time_zone_abbreviation, \
+uses_daylight_savings, construction_date : string or list of strings, optional
+        Spatial / datum / construction attributes carried over from the
+        ``monitoring-locations`` collection.
+    aquifer_code, national_aquifer_code, aquifer_type_code, \
+well_constructed_depth, hole_constructed_depth, depth_source_code : \
+string or list of strings, optional
+        Groundwater-well attributes (only populated for well sites).
+    properties : string or list of strings, optional
+        Subset of columns to return. Defaults to every available
+        property.
+    skip_geometry : boolean, optional
+        Skip per-feature geometries; the returned object will be a plain
+        ``DataFrame`` with no spatial information. The Water Data APIs
+        use camelCase ``skipGeometry`` in CQL2 queries.
+    bbox : list of numbers, optional
+        Only features whose geometry intersects the bounding box are
+        selected. Format: ``[xmin, ymin, xmax, ymax]`` in CRS 4326
+        (longitude/latitude, west-south-east-north).
+    limit : numeric, optional
+        Page size; the maximum allowable value is 50000. Default
+        (``None``) requests the maximum allowable limit.
+    filter, filter_lang : optional
+        Server-side CQL filter passed through as the OGC ``filter`` /
+        ``filter-lang`` query parameters. See
+        :mod:`dataretrieval.waterdata.filters` for syntax, auto-chunking,
+        and the lexicographic-comparison pitfall.
+    convert_type : boolean, optional
+        If True, converts columns to appropriate types.
+
+    Returns
+    -------
+    df : ``pandas.DataFrame`` or ``geopandas.GeoDataFrame``
+        Formatted data returned from the API query.
+    md : :obj:`dataretrieval.utils.Metadata`
+        A custom metadata object pertaining to the query.
+
+    Examples
+    --------
+    .. code::
+
+        >>> # All time series and field measurements at a single site
+        >>> df, md = dataretrieval.waterdata.get_combined_metadata(
+        ...     monitoring_location_id="USGS-05407000"
+        ... )
+
+        >>> # Inventory across multiple HUCs, restricted to streams and springs
+        >>> df, md = dataretrieval.waterdata.get_combined_metadata(
+        ...     hydrologic_unit_code=["11010008", "11010009"],
+        ...     site_type=["Stream", "Spring"],
+        ... )
+
+        >>> # Discharge time series at three sites with at least one
+        >>> # observation in the past month
+        >>> df, md = dataretrieval.waterdata.get_combined_metadata(
+        ...     monitoring_location_id=[
+        ...         "USGS-07069000",
+        ...         "USGS-07064000",
+        ...         "USGS-07068000",
+        ...     ],
+        ...     end="P1M",
+        ...     parameter_code="00060",
+        ... )
+
+    """
+    service = "combined-metadata"
+    output_id = "combined_meta_id"
+
+    args = _get_args(locals())
+
+    return get_ogc_data(args, output_id, service)
+
+
 def get_latest_continuous(
     monitoring_location_id: str | list[str] | None = None,
     parameter_code: str | list[str] | None = None,

tests/waterdata_test.py

@@ -9,6 +9,7 @@
 
 from dataretrieval.waterdata import (
     get_channel,
+    get_combined_metadata,
     get_continuous,
     get_daily,
     get_field_measurements,
@@ -335,6 +336,40 @@ def test_get_time_series_metadata():
     assert hasattr(md, "query_time")
 
 
+def test_get_combined_metadata():
+    df, md = get_combined_metadata(
+        monitoring_location_id="USGS-05407000",
+        skip_geometry=True,
+    )
+    # Combined metadata returns one row per (parameter, statistic, data_type),
+    # carrying both location-catalog and time-series-catalog columns.
+    assert "monitoring_location_id" in df.columns
+    assert "parameter_code" in df.columns
+    assert "data_type" in df.columns
+    assert "drainage_area" in df.columns
+    assert (df["monitoring_location_id"] == "USGS-05407000").all()
+    assert hasattr(md, "url")
+    assert hasattr(md, "query_time")
+
+
+def test_get_combined_metadata_multi_site_post():
+    df, md = get_combined_metadata(
+        monitoring_location_id=[
+            "USGS-07069000",
+            "USGS-07064000",
+            "USGS-07068000",
+        ],
+        parameter_code="00060",
+        skip_geometry=True,
+    )
+    assert set(df["monitoring_location_id"].unique()) == {
+        "USGS-07069000",
+        "USGS-07064000",
+        "USGS-07068000",
+    }
+    assert (df["parameter_code"] == "00060").all()
+
+
 def test_get_reference_table():
     df, md = get_reference_table("agency-codes")
     assert "agency_code" in df.columns