rainfallqc 0.2.2__tar.gz → 0.2.4__tar.gz

{rainfallqc-0.2.2 → rainfallqc-0.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rainfallqc
-Version: 0.2.2
+Version: 0.2.4
 Summary: Quality control for rainfall data
 Author-email: Tom Keel <tomkee@ceh.ac.uk>
 Maintainer-email: Tom Keel <tomkee@ceh.ac.uk>

{rainfallqc-0.2.2 → rainfallqc-0.2.4}/pyproject.toml

@@ -68,7 +68,7 @@ homepage = "https://github.com/thomasjkeel/RainfallQC"
 target-version = ["py310", "py311", "py312", "py313"]
 
 [tool.bumpversion]
-current_version = "0.2.2"
+current_version = "0.2.4"
 commit = true
 message = "Bump version: {current_version} → {new_version}"
 commit_args = ""

{rainfallqc-0.2.2 → rainfallqc-0.2.4}/src/rainfallqc/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = """Tom Keel"""
 __email__ = "tomkee@ceh.ac.uk"
-__version__ = "0.2.2"
+__version__ = "0.2.4"
 
 from rainfallqc import core, utils
 from rainfallqc.checks import (

{rainfallqc-0.2.2 → rainfallqc-0.2.4}/src/rainfallqc/checks/neighbourhood_checks.py

@@ -80,11 +80,17 @@ def check_wet_neighbours(
         )
 
     # 2. Loop through each neighbour and get wet_flags
-    for neighbouring_gauge_col in neighbouring_gauge_cols_new:
+    neighbouring_gauge_cols_iterable = neighbouring_gauge_cols_new.copy()  # make copy again to allow removal in loop
+    for neighbouring_gauge_col in neighbouring_gauge_cols_iterable:
         # 2.1 Flag data based on comparison of wet values in neighbours
-        one_neighbour_data_wet_flags = flag_wet_day_errors_based_on_neighbours(
-            neighbour_data, target_gauge_col, neighbouring_gauge_col, wet_threshold
-        )
+        try:
+            one_neighbour_data_wet_flags = flag_wet_day_errors_based_on_neighbours(
+                neighbour_data, target_gauge_col, neighbouring_gauge_col, wet_threshold
+            )
+        except ValueError as ve:
+            neighbouring_gauge_cols_new.remove(neighbouring_gauge_col)
+            print(f"Warning: removing '{neighbouring_gauge_col}' from neighbouring_gauge_cols because: {ve}")
+            continue
 
         # 2.2 Join to all data
         neighbour_data = neighbour_data.join(
@@ -197,15 +203,21 @@ def check_dry_neighbours(
             neighbour_data, rain_cols=rain_cols, hour_offset=hour_offset
         )
 
-    # 3. Loop through each neighbour and get wet_flags
-    for neighbouring_gauge_col in neighbouring_gauge_cols_new:
+    # 3. Loop through each neighbour and get dry_flags
+    neighbouring_gauge_cols_iterable = neighbouring_gauge_cols_new.copy()  # make copy again to allow removal in loop
+    for neighbouring_gauge_col in neighbouring_gauge_cols_iterable:
         # 3.1 Convert to dry spell fraction
-        one_neighbour_data = get_dry_spell_fraction_col(
-            neighbour_data,
-            target_gauge_col=target_gauge_col,
-            dry_period_days=dry_period_days,
-            neighbouring_gauge_col=neighbouring_gauge_col,
-        )
+        try:
+            one_neighbour_data = get_dry_spell_fraction_col(
+                neighbour_data,
+                target_gauge_col=target_gauge_col,
+                dry_period_days=dry_period_days,
+                neighbouring_gauge_col=neighbouring_gauge_col,
+            )
+        except ValueError as ve:
+            neighbouring_gauge_cols_new.remove(neighbouring_gauge_col)
+            print(f"Warning: {ve}. Removing {neighbouring_gauge_col} from neighbouring_gauge_cols.")
+            continue
 
         # 3.2 Flag dry spell fractions
         one_neighbour_data_dry_flags = flag_dry_spell_fractions(
@@ -1092,6 +1104,7 @@ def flag_wet_day_errors_based_on_neighbours(
     expon_percentiles = stats.fit_expon_and_get_percentile(
         neighbour_data_filtered_diff[f"diff_{neighbouring_gauge_col}"], percentiles=[0.95, 0.99, 0.999]
     )
+
     # 5. Assign flags
     all_neighbour_data_wet_flags = add_wet_flags_to_data(
         neighbour_data_diff, target_gauge_col, neighbouring_gauge_col, expon_percentiles, wet_threshold

{rainfallqc-0.2.2 → rainfallqc-0.2.4}/src/rainfallqc/core/all_qc_checks.py

@@ -2,6 +2,7 @@
 """Registry of all the QC checks in RainfallQC."""
 
 import functools
+import inspect
 import itertools
 
 import polars as pl
@@ -37,16 +38,20 @@ def qc_check(name: str, require_non_negative: bool = False) -> callable:
     def decorator(func: callable) -> callable:
         @functools.wraps(func)
         def wrapper(df: pl.DataFrame, *args, **kwargs) -> list:
-            # Determine which column the user wants checked
+            # Bind args/kwargs to signature to include defaults
+            bound = inspect.signature(func).bind_partial(df, *args, **kwargs)
+            bound.apply_defaults()
+            full_kwargs = bound.arguments  # dict including defaults
+
             columns_to_check = []
             columns_to_check = get_columns_in_kwargs(
-                kwargs, kwarg_name="target_gauge_col", column_list=columns_to_check, name=name
+                full_kwargs, kwarg_name="target_gauge_col", column_list=columns_to_check, name=name
             )
 
             for kwarg_name in ["neighbouring_gauge_col", "neighbouring_gauge_cols"]:
-                if kwarg_name in kwargs:
+                if kwarg_name in full_kwargs:
                     columns_to_check = get_columns_in_kwargs(
-                        kwargs, kwarg_name=kwarg_name, column_list=columns_to_check, name=name
+                        full_kwargs, kwarg_name=kwarg_name, column_list=columns_to_check, name=name
                     )
 
             # flatten column list for neighbouring_gauge_cols
@@ -93,6 +98,6 @@ def get_columns_in_kwargs(kwargs: dict, kwarg_name: str, column_list: list, name
     col_name = kwargs.get(kwarg_name)  # user defined column name for that kwarg
 
     if col_name is None:
-        raise ValueError(f"{name} requires '{kwarg_name}' to be provided.")
+        raise ValueError(f"The QC check '{name}' requires the '{kwarg_name}' to be set.")
     column_list.append(col_name)
     return column_list

{rainfallqc-0.2.2 → rainfallqc-0.2.4}/src/rainfallqc/utils/spatial_utils.py

@@ -42,19 +42,19 @@ def compute_spatial_mean_xr(data: xr.Dataset, var_name: str) -> xr.Dataset:
     return data
 
 
-def haversine(lon1: float, lat1: float, lon2: float, lat2: float) -> float:
+def haversine(lon1: xr.DataArray, lat1: xr.DataArray, lon2: np.ndarray | float, lat2: np.ndarray | float) -> float:
     """
     Great circle distance (km) between two points on Earth.
 
     Parameters
     ----------
-    lon1 : float
+    lon1 : xr.DataArray
         Longitude of point 1
-    lat1 : float
+    lat1 : xr.DataArray
         Latitude of point 1
-    lon2 : float
+    lon2 : np.ndarray | float
         Longitude of point 2
-    lat2 : float
+    lat2 : np.ndarray | float
         Latitude of point 2
 
     Returns
@@ -63,10 +63,13 @@ def haversine(lon1: float, lat1: float, lon2: float, lat2: float) -> float:
         Distance between the two points in km
 
     """
-    R = EARTH_RADIUS_KM
-    lon1, lat1, lon2, lat2 = map(np.radians, [lon1, lat1, float(lon2), float(lat2)])
+    # convert lat2 and lon2 to numpy arrays for safety
+    lon2 = np.asarray(lon2, dtype=np.float64)
+    lat2 = np.asarray(lat2, dtype=np.float64)
+
+    lon1, lat1, lon2, lat2 = map(np.radians, [lon1, lat1, lon2, lat2])
     dlon = lon2 - lon1
     dlat = lat2 - lat1
     a = np.sin(dlat / 2) ** 2 + np.cos(lat1) * np.cos(lat2) * np.sin(dlon / 2) ** 2
     c = 2 * np.arcsin(np.sqrt(a))
-    return R * c
+    return EARTH_RADIUS_KM * c