rainfallqc 0.2.0__tar.gz → 0.2.2__tar.gz

{rainfallqc-0.2.0 → rainfallqc-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rainfallqc
-Version: 0.2.0
+Version: 0.2.2
 Summary: Quality control for rainfall data
 Author-email: Tom Keel <tomkee@ceh.ac.uk>
 Maintainer-email: Tom Keel <tomkee@ceh.ac.uk>
@@ -23,10 +23,13 @@ Requires-Dist: scipy
 Requires-Dist: numpy
 Requires-Dist: polars>=1.30
 Requires-Dist: pandas
+Requires-Dist: pyarrow
 Requires-Dist: xarray
 Requires-Dist: netCDF4
 Requires-Dist: bottleneck
 Requires-Dist: geopy
+Requires-Dist: poligrain
+Requires-Dist: pypwsqc
 Requires-Dist: pip ; extra == "dev"
 Requires-Dist: numpy ; extra == "dev"
 Requires-Dist: bump-my-version ; extra == "dev"

{rainfallqc-0.2.0 → rainfallqc-0.2.2}/pyproject.toml

@@ -30,10 +30,13 @@ dependencies = [
   "numpy",
   "polars>=1.30",
   "pandas",
+  "pyarrow",
   "xarray",
   "netCDF4",
   "bottleneck",
-  "geopy"
+  "geopy",
+  "poligrain",
+  "pypwsqc",
 ]
 
 [project.optional-dependencies]
@@ -65,7 +68,7 @@ homepage = "https://github.com/thomasjkeel/RainfallQC"
 target-version = ["py310", "py311", "py312", "py313"]
 
 [tool.bumpversion]
-current_version = "0.2.0"
+current_version = "0.2.2"
 commit = true
 message = "Bump version: {current_version} → {new_version}"
 commit_args = ""
@@ -146,8 +149,10 @@ case-sensitive = true
 
 [tool.ruff.lint.per-file-ignores]
 "tests/*.py" = [
-  "ANN001", "ANN201", "ANN202", # Missing type annotation
-  "D103" # Missing docstring in public function
+  "ANN001",
+  "ANN201",
+  "ANN202", # Missing type annotation
+  "D103",   # Missing docstring in public function
 ]
 
 [tool.mypy]

{rainfallqc-0.2.0 → rainfallqc-0.2.2}/src/rainfallqc/__init__.py

@@ -2,8 +2,9 @@
 
 __author__ = """Tom Keel"""
 __email__ = "tomkee@ceh.ac.uk"
-__version__ = "0.2.0"
+__version__ = "0.2.2"
 
+from rainfallqc import core, utils
 from rainfallqc.checks import (
     comparison_checks,
     gauge_checks,
@@ -18,4 +19,6 @@ __all__ = [
     "gauge_checks",
     "neighbourhood_checks",
     "timeseries_checks",
+    "core",
+    "utils",
 ]

{rainfallqc-0.2.0 → rainfallqc-0.2.2}/src/rainfallqc/checks/comparison_checks.py

@@ -11,9 +11,11 @@ import numpy as np
 import polars as pl
 import xarray as xr
 
+from rainfallqc.core.all_qc_checks import qc_check
 from rainfallqc.utils import data_readers, data_utils, neighbourhood_utils, stats
 
 
+@qc_check("check_annual_exceedance_etccdi_r99p", require_non_negative=True)
 def check_annual_exceedance_etccdi_r99p(
     data: pl.DataFrame, target_gauge_col: str, gauge_lat: int | float, gauge_lon: int | float
 ) -> list:
@@ -43,7 +45,9 @@ def check_annual_exceedance_etccdi_r99p(
     etccdi_r99p = data_readers.load_etccdi_data(etccdi_var="R99p")
 
     # 2. Get nearest local R99p value to the gauge coordinates
-    nearby_etccdi_r99p = neighbourhood_utils.get_nearest_etccdi_val_to_gauge(etccdi_r99p, gauge_lat, gauge_lon)
+    nearby_etccdi_r99p = neighbourhood_utils.get_nearest_non_nan_etccdi_val_to_gauge(
+        etccdi_r99p, etccdi_name="R99p", gauge_lat=gauge_lat, gauge_lon=gauge_lon
+    )
 
     # 3. Get sum of rainfall above the 99th percentile per year
     sum_rainfall_above_99percentile_per_year = get_sum_rainfall_above_percentile_per_year(
@@ -58,6 +62,7 @@ def check_annual_exceedance_etccdi_r99p(
     return exceedance_flags
 
 
+@qc_check("check_annual_exceedance_etccdi_prcptot", require_non_negative=True)
 def check_annual_exceedance_etccdi_prcptot(
     data: pl.DataFrame, target_gauge_col: str, gauge_lat: int | float, gauge_lon: int | float
 ) -> list:
@@ -87,7 +92,9 @@ def check_annual_exceedance_etccdi_prcptot(
     etccdi_prcptot = data_readers.load_etccdi_data(etccdi_var="PRCPTOT")
 
     # 2. Get nearest local PRCPTOT value to the gauge coordinates
-    nearby_etccdi_prcptot = neighbourhood_utils.get_nearest_etccdi_val_to_gauge(etccdi_prcptot, gauge_lat, gauge_lon)
+    nearby_etccdi_prcptot = neighbourhood_utils.get_nearest_non_nan_etccdi_val_to_gauge(
+        etccdi_prcptot, etccdi_name="PRCPTOT", gauge_lat=gauge_lat, gauge_lon=gauge_lon
+    )
 
     # 3. Get sum of rainfall above the 99th percentile per year
     sum_rainfall_above_99percentile_per_year = get_sum_rainfall_above_percentile_per_year(
@@ -102,6 +109,7 @@ def check_annual_exceedance_etccdi_prcptot(
     return exceedance_flags
 
 
+@qc_check("check_exceedance_of_rainfall_world_record", require_non_negative=True)
 def check_exceedance_of_rainfall_world_record(data: pl.DataFrame, target_gauge_col: str, time_res: str) -> pl.DataFrame:
     """
     Check exceedance of rainfall world record.
@@ -135,6 +143,7 @@ def check_exceedance_of_rainfall_world_record(data: pl.DataFrame, target_gauge_c
     return data_w_flags.select(["time", "world_record_check"])
 
 
+@qc_check("check_hourly_exceedance_etccdi_rx1day", require_non_negative=True)
 def check_hourly_exceedance_etccdi_rx1day(
     data: pl.DataFrame, target_gauge_col: str, gauge_lat: int | float, gauge_lon: int | float
 ) -> pl.DataFrame:
@@ -173,7 +182,9 @@ def check_hourly_exceedance_etccdi_rx1day(
     etccdi_rx1day = data_readers.load_etccdi_data(etccdi_var="Rx1day")
 
     # 3. Get nearest local Rx1day value to the gauge coordinates
-    nearby_etccdi_rx1day = neighbourhood_utils.get_nearest_etccdi_val_to_gauge(etccdi_rx1day, gauge_lat, gauge_lon)
+    nearby_etccdi_rx1day = neighbourhood_utils.get_nearest_non_nan_etccdi_val_to_gauge(
+        etccdi_rx1day, etccdi_name="Rx1day", gauge_lat=gauge_lat, gauge_lon=gauge_lon
+    )
 
     # 4. Get local maximum ETCCDI value
     max_nearby_etccdi_rx1day = np.max(nearby_etccdi_rx1day["Rx1day"])

{rainfallqc-0.2.0 → rainfallqc-0.2.2}/src/rainfallqc/checks/gauge_checks.py

@@ -10,9 +10,11 @@ Classes and functions ordered by appearance in IntenseQC framework.
 import polars as pl
 import scipy.stats
 
+from rainfallqc.core.all_qc_checks import qc_check
 from rainfallqc.utils import data_utils, stats
 
 
+@qc_check("check_years_where_nth_percentile_is_zero", require_non_negative=True)
 def check_years_where_nth_percentile_is_zero(data: pl.DataFrame, target_gauge_col: str, quantile: float) -> list:
     """
     Return years where the n-th percentiles is zero.
@@ -38,6 +40,7 @@ def check_years_where_nth_percentile_is_zero(data: pl.DataFrame, target_gauge_co
     return nth_perc.filter(pl.col(target_gauge_col) == 0)["time"].dt.year().to_list()
 
 
+@qc_check("check_years_where_annual_mean_k_top_rows_are_zero", require_non_negative=True)
 def check_years_where_annual_mean_k_top_rows_are_zero(data: pl.DataFrame, target_gauge_col: str, k: int) -> list:
     """
     Return year list where the annual mean top-K rows are zero.
@@ -63,6 +66,7 @@ def check_years_where_annual_mean_k_top_rows_are_zero(data: pl.DataFrame, target
     return data_top_k.filter(pl.col(target_gauge_col) == 0)["time"].dt.year().to_list()
 
 
+@qc_check("check_temporal_bias", require_non_negative=True)
 def check_temporal_bias(
     data: pl.DataFrame,
     target_gauge_col: str,
@@ -109,6 +113,7 @@ def check_temporal_bias(
     return int(p_val < p_threshold)
 
 
+@qc_check("check_intermittency", require_non_negative=True)
 def check_intermittency(
     data: pl.DataFrame, target_gauge_col: str, no_data_threshold: int = 2, annual_count_threshold: int = 5
 ) -> list:
@@ -135,20 +140,24 @@ def check_intermittency(
         List of years with intermittency issues.
 
     """
-    # 1. Replace missing values with NaN
+    # 1. Check data has consistent time step
+    data_utils.check_data_has_consistent_time_step(data)
+
+    # 2. Replace missing values with NaN
     data = data_utils.replace_missing_vals_with_nan(data, target_gauge_col)
 
-    # --- Step 2: Mark missing values ---
+    # 3. Mark missing values
     data = data.with_columns(pl.col(target_gauge_col).is_nan().alias("is_missing"))
 
-    # 3. Assign group numbers to consecutive missing values
+    # 4. Assign group numbers to consecutive missing values
     grouped = data.with_columns(
         pl.when(pl.col("is_missing"))
         .then((~pl.col("is_missing")).cum_sum())  # Only number missing stretches
         .otherwise(None)
         .alias("group")
     )
-    # 4. Count size of each missing group
+
+    # 5. Count size of each missing group
     group_counts = (
         grouped.filter(pl.col("is_missing"))
         .group_by("group")
@@ -156,21 +165,21 @@ def check_intermittency(
         .filter(pl.col("count") >= no_data_threshold)
     )
 
-    # 5. Keep only valid groups
+    # 6. Keep only valid groups
     valid_missing_groups = group_counts["group"].to_list()
     valid_missing = grouped.filter(pl.col("group").is_in(valid_missing_groups))
 
-    # 6. Get first and last time for each group
+    # 7. Get first and last time for each group
     first_last = (
         valid_missing.sort("time")
         .group_by("group")
         .agg([pl.first("time").alias("start_time"), pl.last("time").alias("end_time")])
     )
 
-    # 7. Add stable row index to full sorted data
+    # 8. Add stable row index to full sorted data
     df_sorted = data.sort("time").with_row_index("row_idx")
 
-    # 8. Lookup row indices of group bounds
+    # 9. Lookup row indices of group bounds
     first_last_with_idx = (
         first_last.join(df_sorted.select(["time", "row_idx"]), left_on="start_time", right_on="time")
         .rename({"row_idx": "start_idx"})
@@ -178,7 +187,7 @@ def check_intermittency(
         .rename({"row_idx": "end_idx"})
     )
 
-    # 9. Compute prev/next indices and fetch values
+    # 10. Compute prev/next indices and fetch values
     row_lookup = df_sorted.select([pl.col("row_idx"), pl.col(target_gauge_col)])
 
     first_last_with_vals = (
@@ -189,21 +198,22 @@ def check_intermittency(
         .join(row_lookup.rename({target_gauge_col: "next_val"}), left_on="next_idx", right_on="row_idx")
     )
 
-    # 10. Filter to groups bounded by zero
+    # 11. Filter to groups bounded by zero
     bounded_by_zero = first_last_with_vals.filter((pl.col("prev_val") == 0) & (pl.col("next_val") == 0))
 
-    # 11. Extract year from each bounded group's start time
+    # 12. Extract year from each bounded group's start time
     bounded_years = bounded_by_zero.select(pl.col("start_time").dt.year().alias("year"))
 
-    # 12. Count how many bounded groups occur per year
+    # 13. Count how many bounded groups occur per year
     year_counts = bounded_years.group_by("year").len()
 
-    # 13. Get years exceeding threshold
+    # 14. Get years exceeding threshold
     years_w_intermittency = year_counts.filter(pl.col("len") >= annual_count_threshold)["year"].to_list()
 
     return years_w_intermittency
 
 
+@qc_check("check_breakpoints", require_non_negative=True)
 def check_breakpoints(
     data: pl.DataFrame,
     target_gauge_col: str,
@@ -240,6 +250,7 @@ def check_breakpoints(
         return 0
 
 
+@qc_check("check_min_val_change", require_non_negative=True)
 def check_min_val_change(data: pl.DataFrame, target_gauge_col: str, expected_min_val: float) -> list:
     """
     Return years when the minimum recorded value changes.

{rainfallqc-0.2.0 → rainfallqc-0.2.2}/src/rainfallqc/checks/neighbourhood_checks.py

@@ -12,9 +12,11 @@ from typing import Iterable, List
 import numpy as np
 import polars as pl
 
+from rainfallqc.core.all_qc_checks import qc_check
 from rainfallqc.utils import data_readers, data_utils, neighbourhood_utils, stats
 
 
+@qc_check("check_wet_neighbours", require_non_negative=True)
 def check_wet_neighbours(
     neighbour_data: pl.DataFrame,
     target_gauge_col: str,
@@ -129,6 +131,7 @@ def check_wet_neighbours(
         return neighbour_data_w_wet_flags
 
 
+@qc_check("check_dry_neighbours", require_non_negative=True)
 def check_dry_neighbours(
     neighbour_data: pl.DataFrame,
     target_gauge_col: str,
@@ -261,6 +264,7 @@ def check_dry_neighbours(
         return neighbour_data_w_dry_flags
 
 
+@qc_check("check_monthly_neighbours", require_non_negative=True)
 def check_monthly_neighbours(
     monthly_neighbour_data: pl.DataFrame,
     target_gauge_col: str,
@@ -355,6 +359,7 @@ def check_monthly_neighbours(
     return monthly_neighbour_data_w_flags.select(["time", "majority_monthly_flag"])
 
 
+@qc_check("check_timing_offset", require_non_negative=True)
 def check_timing_offset(
     neighbour_data: pl.DataFrame,
     target_gauge_col: str,
@@ -436,6 +441,7 @@ def check_timing_offset(
     return offset_flag
 
 
+@qc_check("check_neighbour_affinity_index", require_non_negative=True)
 def check_neighbour_affinity_index(
     neighbour_data: pl.DataFrame, target_gauge_col: str, neighbouring_gauge_col: str
 ) -> float:
@@ -471,6 +477,7 @@ def check_neighbour_affinity_index(
     return stats.affinity_index(neighbour_data, binary_col="rain_not_minima")
 
 
+@qc_check("check_neighbour_correlation", require_non_negative=True)
 def check_neighbour_correlation(
     neighbour_data: pl.DataFrame, target_gauge_col: str, neighbouring_gauge_col: str
 ) -> float:
@@ -501,6 +508,7 @@ def check_neighbour_correlation(
     return stats.gauge_correlation(neighbour_data, target_col=target_gauge_col, other_col=neighbouring_gauge_col)
 
 
+@qc_check("check_daily_factor", require_non_negative=True)
 def check_daily_factor(
     neighbour_data: pl.DataFrame, target_gauge_col: str, neighbouring_gauge_col: str, averaging_method: str = "mean"
 ) -> float:
@@ -553,6 +561,7 @@ def check_daily_factor(
         raise ValueError(f"{averaging_method} not recognised, please use 'mean' or 'median'")
 
 
+@qc_check("check_monthly_factor", require_non_negative=True)
 def check_monthly_factor(
     neighbour_data: pl.DataFrame, target_gauge_col: str, neighbouring_gauge_col: str
 ) -> pl.DataFrame: