Merge branch 'main' into add-continuous

Author: ehinman

README.md

@@ -66,7 +66,7 @@ location for water year 2025, where a "/" between two dates in the "time"
 input argument indicates a desired date range:
 
 ```python
-import dataretrieval.waterdata as waterdata
+from dataretrieval import waterdata
 
 # Get daily streamflow data (returns DataFrame and metadata)
 df, metadata = waterdata.get_daily(
@@ -130,7 +130,7 @@ logging.basicConfig(filename='waterdata.log', level=logging.INFO)
 The `nwis` module accesses legacy NWIS Water Services:
 
 ```python
-import dataretrieval.nwis as nwis
+from dataretrieval import nwis
 
 # Get site information
 info, metadata = nwis.get_info(sites='01646500')
@@ -153,7 +153,7 @@ print(f"Retrieved {len(dv)} daily values")
 Access water quality data from multiple agencies:
 
 ```python
-import dataretrieval.wqp as wqp
+from dataretrieval import wqp
 
 # Find water quality monitoring sites
 sites = wqp.what_sites(
@@ -177,7 +177,7 @@ print(f"Retrieved {len(results)} temperature measurements")
 Discover and navigate hydrologic networks:
 
 ```python
-import dataretrieval.nldi as nldi
+from dataretrieval import nldi
 
 # Get watershed basin for a stream reach
 basin = nldi.get_basin(

dataretrieval/waterdata/api.py

@@ -161,12 +161,11 @@ def get_daily(
     limit : numeric, optional
         The optional limit parameter is used to control the subset of the
         selected features that should be returned in each page. The maximum
-        allowable limit is 10000. It may be beneficial to set this number lower
+        allowable limit is 50000. It may be beneficial to set this number lower
         if your internet connection is spotty. The default (NA) will set the
         limit to the maximum allowable limit for the service.
     convert_type : boolean, optional
-        If True, the function will convert the data to dates and qualifier to
-        string vector
+        If True, converts columns to appropriate types.
 
     Returns
     -------
@@ -632,14 +631,16 @@ def get_monitoring_locations(
     limit : numeric, optional
         The optional limit parameter is used to control the subset of the
         selected features that should be returned in each page. The maximum
-        allowable limit is 10000. It may be beneficial to set this number lower
+        allowable limit is 50000. It may be beneficial to set this number lower
         if your internet connection is spotty. The default (NA) will set the
         limit to the maximum allowable limit for the service.
     skip_geometry : boolean, optional
         This option can be used to skip response geometries for each feature.
         The returning object will be a data frame with no spatial information.
         Note that the USGS Water Data APIs use camelCase "skipGeometry" in
         CQL2 queries.
+    convert_type : boolean, optional
+        If True, converts columns to appropriate types.
 
     Returns
     -------
@@ -827,12 +828,11 @@ def get_time_series_metadata(
     limit : numeric, optional
         The optional limit parameter is used to control the subset of the
         selected features that should be returned in each page. The maximum
-        allowable limit is 10000. It may be beneficial to set this number lower
+        allowable limit is 50000. It may be beneficial to set this number lower
         if your internet connection is spotty. The default (None) will set the
         limit to the maximum allowable limit for the service.
     convert_type : boolean, optional
-        If True, the function will convert the data to dates and qualifier to
-        string vector
+        If True, converts columns to appropriate types.
 
     Returns
     -------
@@ -1003,12 +1003,11 @@ def get_latest_continuous(
     limit : numeric, optional
         The optional limit parameter is used to control the subset of the
         selected features that should be returned in each page. The maximum
-        allowable limit is 10000. It may be beneficial to set this number lower
+        allowable limit is 50000. It may be beneficial to set this number lower
         if your internet connection is spotty. The default (None) will set the
         limit to the maximum allowable limit for the service.
     convert_type : boolean, optional
-        If True, the function will convert the data to dates and qualifier to
-        string vector
+        If True, converts columns to appropriate types.
 
     Returns
     -------
@@ -1178,12 +1177,11 @@ def get_latest_daily(
     limit : numeric, optional
         The optional limit parameter is used to control the subset of the
         selected features that should be returned in each page. The maximum
-        allowable limit is 10000. It may be beneficial to set this number lower
+        allowable limit is 50000. It may be beneficial to set this number lower
         if your internet connection is spotty. The default (None) will set the
         limit to the maximum allowable limit for the service.
     convert_type : boolean, optional
-        If True, the function will convert the data to dates and qualifier to
-        string vector
+        If True, converts columns to appropriate types.
 
     Returns
     -------
@@ -1344,12 +1342,11 @@ def get_field_measurements(
     limit : numeric, optional
         The optional limit parameter is used to control the subset of the
         selected features that should be returned in each page. The maximum
-        allowable limit is 10000. It may be beneficial to set this number lower
+        allowable limit is 50000. It may be beneficial to set this number lower
         if your internet connection is spotty. The default (None) will set the
         limit to the maximum allowable limit for the service.
     convert_type : boolean, optional
-        If True, the function will convert the data to dates and qualifier to
-        string vector
+        If True, converts columns to appropriate types.
 
     Returns
     -------

dataretrieval/waterdata/utils.py

@@ -382,10 +382,10 @@ def _construct_api_requests(
     # Set skipGeometry parameter (API expects camelCase)
     params["skipGeometry"] = skip_geometry
 
-    # If limit is none or greater than 10000, then set limit to max results. Otherwise,
+    # If limit is none or greater than 50000, then set limit to max results. Otherwise,
     # use the limit
     params["limit"] = (
-        10000 if limit is None or limit > 10000 else limit
+        50000 if limit is None or limit > 50000 else limit
         )
 
     # Indicate if function needs to perform POST conversion
@@ -667,32 +667,48 @@ def _arrange_cols(
         return df.rename(columns={"id": output_id})
 
 
-def _cleanup_cols(df: pd.DataFrame, service: str = "daily") -> pd.DataFrame:
+def _type_cols(df: pd.DataFrame) -> pd.DataFrame:
     """
-    Cleans and standardizes columns in a pandas DataFrame for water data endpoints.
+    Casts columns into appropriate types.
 
     Parameters
     ----------
     df : pd.DataFrame
         The input DataFrame containing water data.
-    service : str, optional
-        The type of water data service (default is "daily").
 
     Returns
     -------
     pd.DataFrame
-        The cleaned DataFrame with standardized columns.
+        The DataFrame with columns cast to appropriate types.
 
-    Notes
-    -----
-    - If the 'time' column exists and service is "daily", it is converted to date objects.
-    - The 'value' and 'contributing_drainage_area' columns are coerced to numeric types.
     """
-    if "time" in df.columns and service == "daily":
-        df["time"] = pd.to_datetime(df["time"]).dt.date
-    for col in ["value", "contributing_drainage_area"]:
-        if col in df.columns:
-            df[col] = pd.to_numeric(df[col], errors="coerce")
+    cols = set(df.columns)
+    numerical_cols = [
+        "altitude",
+        "altitude_accuracy",
+        "contributing_drainage_area",
+        "drainage_area",
+        "hole_constructed_depth",
+        "value",
+        "well_constructed_depth",
+        ]
+    time_cols = [
+        "begin",
+        "begin_utc",
+        "construction_date",
+        "end",
+        "end_utc",
+        "datetime", # unused
+        "last_modified",
+        "time",
+        ]
+
+    for col in cols.intersection(time_cols):
+        df[col] = pd.to_datetime(df[col], errors="coerce")
+
+    for col in cols.intersection(numerical_cols):
+        df[col] = pd.to_numeric(df[col], errors="coerce")
+
     return df
 
 
@@ -748,8 +764,10 @@ def get_ogc_data(
     )
     # Manage some aspects of the returned dataset
     return_list = _deal_with_empty(return_list, properties, service)
+
     if convert_type:
-        return_list = _cleanup_cols(return_list, service=service)
+        return_list = _type_cols(return_list)
+
     return_list = _arrange_cols(return_list, properties, output_id)
     # Create metadata object from response
     metadata = BaseMetadata(response)