Lint and format all files with ruff

dataretrieval/__init__.py

@@ -5,11 +5,11 @@
 except PackageNotFoundError:
     __version__ = "version-unknown"
 
-from dataretrieval.nadp import *
-from dataretrieval.nwis import *
-from dataretrieval.samples import *
-from dataretrieval.streamstats import *
-from dataretrieval.utils import *
-from dataretrieval.waterdata import *
-from dataretrieval.waterwatch import *
-from dataretrieval.wqp import *
+from dataretrieval.nadp import *  # noqa: F403
+from dataretrieval.nwis import *  # noqa: F403
+from dataretrieval.samples import *  # noqa: F403
+from dataretrieval.streamstats import *  # noqa: F403
+from dataretrieval.utils import *  # noqa: F403
+from dataretrieval.waterdata import *  # noqa: F403
+from dataretrieval.waterwatch import *  # noqa: F403
+from dataretrieval.wqp import *  # noqa: F403

dataretrieval/codes/__init__.py

@@ -1,2 +1,2 @@
-from .states import *
-from .timezones import *
+from .states import *  # noqa: F403
+from .timezones import *  # noqa: F403

dataretrieval/nldi.py

@@ -5,8 +5,8 @@
 
 try:
     import geopandas as gpd
-except ImportError:
-    raise ImportError("Install geopandas to use the NLDI module.")
+except ImportError as err:
+    raise ImportError("Install geopandas to use the NLDI module.") from err
 
 NLDI_API_BASE_URL = "https://api.water.usgs.gov/nldi/linked-data"
 _AVAILABLE_DATA_SOURCES = None
@@ -281,7 +281,7 @@ def get_features(
             query_params = {}
 
     if lat:
-        err_msg = f"Error getting features for lat '{lat}'" f" and long '{long}'"
+        err_msg = f"Error getting features for lat '{lat}' and long '{long}'"
     elif feature_source:
         err_msg = (
             f"Error getting features for feature source '{feature_source}'"

dataretrieval/nwis.py

@@ -26,7 +26,7 @@
     "The 'nwis' services are deprecated and being decommissioned. "
     "Please use the 'waterdata' module to access the new services.",
     DeprecationWarning,
-    stacklevel=2
+    stacklevel=2,
 )
 
 WATERDATA_BASE_URL = "https://nwis.waterdata.usgs.gov/"
@@ -141,7 +141,7 @@ def get_qwdata(
     """
     raise NameError(
         "`nwis.get_qwdata` has been replaced with `waterdata.get_samples()`."
-        )
+    )
 
 
 def get_discharge_measurements(
@@ -157,7 +157,7 @@ def get_discharge_measurements(
     Parameters
     ----------
     sites: string or list of strings, optional, default is None
-    start: string, optional, default is None 
+    start: string, optional, default is None
         Supply date in the format: YYYY-MM-DD
     end: string, optional, default is None
         Supply date in the format: YYYY-MM-DD
@@ -344,7 +344,7 @@ def get_gwlevels(
 
     if datetime_index is True:
         df = format_datetime(df, "lev_dt", "lev_tm", "lev_tz_cd")
-    
+
     # Filter by kwarg parameterCd because the service doesn't do it
     if "parameterCd" in kwargs:
         pcodes = kwargs["parameterCd"]
@@ -696,7 +696,8 @@ def get_info(ssl_check: bool = True, **kwargs) -> Tuple[pd.DataFrame, BaseMetada
                 "refer to https://waterdata.usgs.gov.nwis/qwdata and "
                 "https://doi-usgs.github.io/dataRetrieval/articles/Status.html "
                 "or email CompTools@usgs.gov."
-            )
+            ),
+            stacklevel=2,
         )
         # convert bool to string if necessary
         kwargs["seriesCatalogOutput"] = "True"

dataretrieval/samples.py

@@ -6,18 +6,19 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Literal, get_args
-
-import pandas as pd
 import warnings
+from typing import TYPE_CHECKING
 
 from dataretrieval.utils import BaseMetadata
 
 if TYPE_CHECKING:
     from typing import Optional, Tuple, Union
-    from dataretrieval.waterdata import SERVICES, PROFILES
+
     from pandas import DataFrame
 
+    from dataretrieval.waterdata import PROFILES, SERVICES
+
+
 def get_usgs_samples(
     ssl_check: bool = True,
     service: SERVICES = "results",
@@ -111,7 +112,7 @@ def get_usgs_samples(
         A user supplied characteristic name describing one or more results.
     boundingBox: list of four floats, optional
         Filters on the the associated monitoring location's point location
-        by checking if it is located within the specified geographic area. 
+        by checking if it is located within the specified geographic area.
         The logic is inclusive, i.e. it will include locations that overlap
         with the edge of the bounding box. Values are separated by commas,
         expressed in decimal degrees, NAD83, and longitudes west of Greenwich
@@ -120,7 +121,7 @@ def get_usgs_samples(
         - Western-most longitude
         - Southern-most latitude
         - Eastern-most longitude
-        - Northern-most longitude 
+        - Northern-most longitude
         Example: [-92.8,44.2,-88.9,46.0]
     countryFips : string or list of strings, optional
         Example: "US" (United States)
@@ -143,7 +144,7 @@ def get_usgs_samples(
     usgsPCode : string or list of strings, optional
         5-digit number used in the US Geological Survey computerized
         data system, National Water Information System (NWIS), to
-        uniquely identify a specific constituent. Check the 
+        uniquely identify a specific constituent. Check the
         `characteristic_lookup()` function in this module for all possible
         inputs.
         Example: "00060" (Discharge, cubic feet per second)
@@ -173,7 +174,7 @@ def get_usgs_samples(
     recordIdentifierUserSupplied : string or list of strings, optional
         Internal AQS record identifier that returns 1 entry. Only available
         for the "results" service.
-    
+
     Returns
     -------
     df : ``pandas.DataFrame``
@@ -187,8 +188,8 @@ def get_usgs_samples(
 
         >>> # Get PFAS results within a bounding box
         >>> df, md = dataretrieval.samples.get_usgs_samples(
-        ...     boundingBox=[-90.2,42.6,-88.7,43.2],
-        ...     characteristicGroup="Organics, PFAS"
+        ...     boundingBox=[-90.2, 42.6, -88.7, 43.2],
+        ...     characteristicGroup="Organics, PFAS",
         ... )
 
         >>> # Get all activities for the Commonwealth of Virginia over a date range
@@ -197,22 +198,31 @@ def get_usgs_samples(
         ...     profile="sampact",
         ...     activityStartDateLower="2023-10-01",
         ...     activityStartDateUpper="2024-01-01",
-        ...     stateFips="US:51")
+        ...     stateFips="US:51",
+        ... )
 
         >>> # Get all pH samples for two sites in Utah
         >>> df, md = dataretrieval.samples.get_usgs_samples(
-        ...     monitoringLocationIdentifier=['USGS-393147111462301', 'USGS-393343111454101'],
-        ...     usgsPCode='00400')
+        ...     monitoringLocationIdentifier=[
+        ...         "USGS-393147111462301",
+        ...         "USGS-393343111454101",
+        ...     ],
+        ...     usgsPCode="00400",
+        ... )
 
     """
 
     warnings.warn(
-        "`get_usgs_samples` is deprecated and will be removed. Use `waterdata.get_samples` instead.",
+        (
+            "`get_usgs_samples` is deprecated and will be removed. "
+            "Use `waterdata.get_samples` instead."
+        ),
         DeprecationWarning,
         stacklevel=2,
     )
 
     from dataretrieval.waterdata import get_samples
+
     result = get_samples(
         ssl_check=ssl_check,
         service=service,
@@ -242,5 +252,3 @@ def get_usgs_samples(
     )
 
     return result
-
-

dataretrieval/streamstats.py

@@ -158,4 +158,4 @@ def from_streamstats_json(cls, streamstats_json):
 
     def __init__(self, rcode, xlocation, ylocation):
         """Init method that calls the :obj:`from_streamstats_json` method."""
-        self = get_watershed(rcode, xlocation, ylocation)
+        get_watershed(rcode, xlocation, ylocation)

dataretrieval/utils.py

@@ -39,16 +39,16 @@ def to_str(listlike, delimiter=","):
         '0+10+42'
 
     """
-    if type(listlike) == list:
+    if isinstance(listlike, list):
         return delimiter.join([str(x) for x in listlike])
 
-    elif type(listlike) == pd.core.series.Series:
+    elif isinstance(listlike, pd.core.series.Series):
         return delimiter.join(listlike.tolist())
 
-    elif type(listlike) == pd.core.indexes.base.Index:
+    elif isinstance(listlike, pd.core.indexes.base.Index):
         return delimiter.join(listlike.tolist())
 
-    elif type(listlike) == str:
+    elif isinstance(listlike, str):
         return listlike
 
 
@@ -91,6 +91,7 @@ def format_datetime(df, date_field, time_field, tz_field):
             f"Warning: {count} incomplete dates found, "
             + "consider setting datetime_index to False.",
             UserWarning,
+            stacklevel=2,
         )
 
     return df
@@ -229,6 +230,5 @@ def __init__(self, url):
 
     def __str__(self):
         return (
-            "No sites/data found using the selection criteria specified in url: "
-            "{url}"
+            "No sites/data found using the selection criteria specified in url: {url}"
         ).format(url=self.url)