refactor(waterdata): drop the pandas-path hash-dropping; keep it in xarray

Scope this PR to the xarray module. The earlier work added an include_hash
flag and a hash-valued-ID drop (plus a server-side queryables whitelist) to
the plain DataFrame getters; revert that public-API surface so api.py / utils.py
and their tests match main, and the getters again return every column.

The xarray datasets stay hash-free on their own: the timeseries/samples
builders surface only the columns they convert (so per-record UUIDs and
per-series join keys never appear), and _build_stats now drops the stats
service's computation_id / parent_time_series_id explicitly since its flat
conversion keeps every column. _fetch still swallows a stray include_hash kwarg
so passing it to an xarray wrapper stays harmless. Adds tests pinning the
hash-free guarantee for the stats and ragged paths.

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

Author: thodson-usgs

dataretrieval/waterdata/api.py

@@ -33,7 +33,6 @@
     SAMPLES_URL,
     _check_profiles,
     _default_headers,
-    _drop_hash_columns,
     _get_args,
     get_ogc_data,
     get_stats_data,
@@ -62,7 +61,6 @@ def get_daily(
     filter: str | None = None,
     filter_lang: FILTER_LANG | None = None,
     convert_type: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """Daily data provide one data value to represent water conditions for the
     day.
@@ -195,9 +193,6 @@ def get_daily(
         and the lexicographic-comparison pitfall.
     convert_type : boolean, optional
         If True, converts columns to appropriate types.
-    include_hash : boolean, optional
-        If False (default), drop the opaque hash-valued ID columns. Set True to
-        keep the secondary hashes (e.g. ``time_series_id``) that join to metadata.
 
     Returns
     -------
@@ -281,7 +276,6 @@ def get_continuous(
     filter: str | None = None,
     filter_lang: FILTER_LANG | None = None,
     convert_type: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """
     Continuous data provide instantaneous water conditions.
@@ -409,9 +403,6 @@ def get_continuous(
     convert_type : boolean, optional
         If True, the function will convert the data to dates and qualifier to
         string vector
-    include_hash : boolean, optional
-        If False (default), drop the opaque hash-valued ID columns. Set True to
-        keep the secondary hashes (e.g. ``time_series_id``) that join to metadata.
 
     Returns
     -------
@@ -505,7 +496,6 @@ def get_monitoring_locations(
     filter: str | None = None,
     filter_lang: FILTER_LANG | None = None,
     convert_type: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """Location information is basic information about the monitoring location
     including the name, identifier, agency responsible for data collection, and
@@ -721,9 +711,6 @@ def get_monitoring_locations(
         and the lexicographic-comparison pitfall.
     convert_type : boolean, optional
         If True, converts columns to appropriate types.
-    include_hash : boolean, optional
-        If False (default), drop the opaque hash-valued ID columns. Set True to
-        keep the secondary hashes (e.g. ``time_series_id``) that join to metadata.
 
     Returns
     -------
@@ -787,7 +774,6 @@ def get_time_series_metadata(
     filter: str | None = None,
     filter_lang: FILTER_LANG | None = None,
     convert_type: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """Daily data and continuous measurements are grouped into time series,
     which represent a collection of observations of a single parameter,
@@ -948,9 +934,6 @@ def get_time_series_metadata(
         and the lexicographic-comparison pitfall.
     convert_type : boolean, optional
         If True, converts columns to appropriate types.
-    include_hash : boolean, optional
-        If False (default), drop the opaque hash-valued ID columns. Set True to
-        keep the secondary hashes (e.g. ``time_series_id``) that join to metadata.
 
     Returns
     -------
@@ -1048,7 +1031,6 @@ def get_combined_metadata(
     filter: str | None = None,
     filter_lang: FILTER_LANG | None = None,
     convert_type: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """Get combined monitoring-location and time-series metadata.
 
@@ -1149,9 +1131,6 @@ def get_combined_metadata(
         and the lexicographic-comparison pitfall.
     convert_type : boolean, optional
         If True, converts columns to appropriate types.
-    include_hash : boolean, optional
-        If False (default), drop the opaque hash-valued ID columns. Set True to
-        keep the secondary hashes (e.g. ``time_series_id``) that join to metadata.
 
     Returns
     -------
@@ -1240,7 +1219,6 @@ def get_latest_continuous(
     filter: str | None = None,
     filter_lang: FILTER_LANG | None = None,
     convert_type: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """This endpoint provides the most recent observation for each time series
     of continuous data. Continuous data are collected via automated sensors
@@ -1370,9 +1348,6 @@ def get_latest_continuous(
         and the lexicographic-comparison pitfall.
     convert_type : boolean, optional
         If True, converts columns to appropriate types.
-    include_hash : boolean, optional
-        If False (default), drop the opaque hash-valued ID columns. Set True to
-        keep the secondary hashes (e.g. ``time_series_id``) that join to metadata.
 
     Returns
     -------
@@ -1439,7 +1414,6 @@ def get_latest_daily(
     filter: str | None = None,
     filter_lang: FILTER_LANG | None = None,
     convert_type: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """Daily data provide one data value to represent water conditions for the
     day.
@@ -1571,9 +1545,6 @@ def get_latest_daily(
         and the lexicographic-comparison pitfall.
     convert_type : boolean, optional
         If True, converts columns to appropriate types.
-    include_hash : boolean, optional
-        If False (default), drop the opaque hash-valued ID columns. Set True to
-        keep the secondary hashes (e.g. ``time_series_id``) that join to metadata.
 
     Returns
     -------
@@ -1641,7 +1612,6 @@ def get_field_measurements(
     filter: str | None = None,
     filter_lang: FILTER_LANG | None = None,
     convert_type: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """Field measurements are physically measured values collected during a
     visit to the monitoring location. Field measurements consist of measurements
@@ -1763,9 +1733,6 @@ def get_field_measurements(
         and the lexicographic-comparison pitfall.
     convert_type : boolean, optional
         If True, converts columns to appropriate types.
-    include_hash : boolean, optional
-        If False (default), drop the opaque hash-valued ID columns. Set True to
-        keep the secondary hashes (e.g. ``time_series_id``) that join to metadata.
 
     Returns
     -------
@@ -1829,7 +1796,6 @@ def get_field_measurements_metadata(
     filter: str | None = None,
     filter_lang: FILTER_LANG | None = None,
     convert_type: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """Get field-measurement metadata: one row per (location, parameter) series.
 
@@ -1885,9 +1851,6 @@ def get_field_measurements_metadata(
         and the lexicographic-comparison pitfall.
     convert_type : boolean, optional
         If True, converts columns to appropriate types.
-    include_hash : boolean, optional
-        If False (default), drop the opaque hash-valued ID columns. Set True to
-        keep the secondary hashes (e.g. ``time_series_id``) that join to metadata.
 
     Returns
     -------
@@ -1954,7 +1917,6 @@ def get_peaks(
     filter: str | None = None,
     filter_lang: FILTER_LANG | None = None,
     convert_type: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """Get the annual peak streamflow / stage record for a monitoring location.
 
@@ -2013,9 +1975,6 @@ def get_peaks(
         and the lexicographic-comparison pitfall.
     convert_type : boolean, optional
         If True, converts columns to appropriate types.
-    include_hash : boolean, optional
-        If False (default), drop the opaque hash-valued ID columns. Set True to
-        keep the secondary hashes (e.g. ``time_series_id``) that join to metadata.
 
     Returns
     -------
@@ -2193,7 +2152,6 @@ def get_samples(
     pointLocationWithinMiles: float | None = None,
     projectIdentifier: str | Iterable[str] | None = None,
     recordIdentifierUserSupplied: str | Iterable[str] | None = None,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """Search Samples database for USGS water quality data.
     This is a wrapper function for the Samples database API. All potential
@@ -2324,9 +2282,6 @@ def get_samples(
     recordIdentifierUserSupplied : string or iterable of strings, optional
         Internal AQS record identifier that returns 1 entry. Only available
         for the "results" service.
-    include_hash : boolean, optional
-        If False (default), drop the opaque per-activity / per-result UUID columns
-        (``Activity_ActivityIdentifier``, ``Result_MeasureIdentifier``).
 
     Returns
     -------
@@ -2376,7 +2331,7 @@ def get_samples(
     _check_profiles(service, profile)
 
     # Build argument dictionary, omitting None values
-    params = _get_args(locals(), exclude={"ssl_check", "profile", "include_hash"})
+    params = _get_args(locals(), exclude={"ssl_check", "profile"})
 
     params.update({"mimeType": "text/csv"})
 
@@ -2399,7 +2354,6 @@ def get_samples(
 
     df = pd.read_csv(StringIO(response.text), delimiter=",")
     df = _attach_datetime_columns(df)
-    df = _drop_hash_columns(df, include_hash)
 
     return df, BaseMetadata(response)
 
@@ -2492,7 +2446,6 @@ def get_stats_por(
     site_type_name: str | Iterable[str] | None = None,
     parameter_code: str | Iterable[str] | None = None,
     expand_percentiles: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """Get day-of-year and month-of-year water data statistics from the
     USGS Water Data API.
@@ -2571,9 +2524,6 @@ def get_stats_por(
         argument will return both the "values" column, containing the list
         of percentile threshold values, and a "value" column, containing
         the singular summary value for the other statistics.
-    include_hash : boolean, optional
-        If False (default), drop the hash columns (``computation_id``,
-        ``parent_time_series_id``); set True to keep them for joining to metadata.
 
     Examples
     --------
@@ -2598,13 +2548,10 @@ def get_stats_por(
         ... )
     """
     # Build argument dictionary, omitting None values
-    params = _get_args(locals(), exclude={"expand_percentiles", "include_hash"})
+    params = _get_args(locals(), exclude={"expand_percentiles"})
 
     return get_stats_data(
-        args=params,
-        service="observationNormals",
-        expand_percentiles=expand_percentiles,
-        include_hash=include_hash,
+        args=params, service="observationNormals", expand_percentiles=expand_percentiles
     )
 
 
@@ -2623,7 +2570,6 @@ def get_stats_date_range(
     site_type_name: str | Iterable[str] | None = None,
     parameter_code: str | Iterable[str] | None = None,
     expand_percentiles: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """Get monthly and annual water data statistics from the USGS Water Data API.
     This service (called the "observationIntervals" endpoint on api.waterdata.usgs.gov)
@@ -2706,9 +2652,6 @@ def get_stats_date_range(
         argument will return both the "values" column, containing the list
         of percentile threshold values, and a "value" column, containing
         the singular summary value for the other statistics.
-    include_hash : boolean, optional
-        If False (default), drop the hash columns (``computation_id``,
-        ``parent_time_series_id``); set True to keep them for joining to metadata.
 
     Examples
     --------
@@ -2734,13 +2677,12 @@ def get_stats_date_range(
         ... )
     """
     # Build argument dictionary, omitting None values
-    params = _get_args(locals(), exclude={"expand_percentiles", "include_hash"})
+    params = _get_args(locals(), exclude={"expand_percentiles"})
 
     return get_stats_data(
         args=params,
         service="observationIntervals",
         expand_percentiles=expand_percentiles,
-        include_hash=include_hash,
     )
 
 
@@ -2776,7 +2718,6 @@ def get_channel(
     filter: str | None = None,
     filter_lang: FILTER_LANG | None = None,
     convert_type: bool = True,
-    include_hash: bool = False,
 ) -> tuple[pd.DataFrame, BaseMetadata]:
     """
     Channel measurements taken as part of streamflow field measurements.
@@ -2891,9 +2832,6 @@ def get_channel(
     convert_type : boolean, optional
         If True, the function will convert the data to dates and qualifier to
         string vector
-    include_hash : boolean, optional
-        If False (default), drop the opaque hash-valued ID columns. Set True to
-        keep the secondary hashes (e.g. ``time_series_id``) that join to metadata.
 
     Returns
     -------