rainfallqc 0.4.2__tar.gz → 0.4.4__tar.gz

{rainfallqc-0.4.2 → rainfallqc-0.4.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rainfallqc
-Version: 0.4.2
+Version: 0.4.4
 Summary: Quality control for rainfall data
 Author-email: Tom Keel <tomkee@ceh.ac.uk>
 Maintainer-email: Tom Keel <tomkee@ceh.ac.uk>
@@ -21,7 +21,7 @@ Classifier: Topic :: Scientific/Engineering :: Hydrology
 License-File: LICENSE
 Requires-Dist: scipy
 Requires-Dist: numpy
-Requires-Dist: polars>=1.30
+Requires-Dist: polars
 Requires-Dist: pandas
 Requires-Dist: pyarrow
 Requires-Dist: xarray

{rainfallqc-0.4.2 → rainfallqc-0.4.4}/pyproject.toml

@@ -28,7 +28,7 @@ license = { file = "LICENSE" }
 dependencies = [
   "scipy",
   "numpy",
-  "polars>=1.30",
+  "polars",
   "pandas",
   "pyarrow",
   "xarray",
@@ -80,7 +80,7 @@ homepage = "https://github.com/thomasjkeel/RainfallQC"
 target-version = ["py310", "py311", "py312", "py313"]
 
 [tool.bumpversion]
-current_version = "0.4.2"
+current_version = "0.4.4"
 commit = true
 message = "Bump version: {current_version} → {new_version}"
 commit_args = ""

{rainfallqc-0.4.2 → rainfallqc-0.4.4}/src/rainfallqc/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = """Tom Keel"""
 __email__ = "tomkee@ceh.ac.uk"
-__version__ = "0.4.2"
+__version__ = "0.4.4"
 
 from rainfallqc import core, utils
 from rainfallqc.checks import (

{rainfallqc-0.4.2 → rainfallqc-0.4.4}/src/rainfallqc/checks/neighbourhood_checks.py

@@ -980,7 +980,9 @@ def flag_percentage_diff_of_neighbour(neighbour_data: pl.DataFrame, nearest_neig
 
     """
     return neighbour_data.with_columns(
-        pl.when((pl.col("perc_diff") <= -100.0))
+        pl.when(pl.col("perc_diff").is_null() | pl.col("perc_diff").is_nan())
+        .then(np.nan)
+        .when((pl.col("perc_diff") <= -100.0))
         .then(-3)
         .when((pl.col("perc_diff") <= -50.0) & (pl.col("perc_diff") > -100.0))
         .then(-2)
@@ -1183,7 +1185,9 @@ def add_wet_flags_to_data(
 
     """
     return neighbour_data_diff.with_columns(
-        pl.when(
+        pl.when(pl.col(target_gauge_col).is_null() | pl.col(target_gauge_col).is_nan())
+        .then(np.nan)
+        .when(
             (pl.col(target_gauge_col) >= wet_threshold)
             & (pl.col(f"diff_{nearest_neighbour}") <= expon_percentiles[0.95])
         )

{rainfallqc-0.4.2 → rainfallqc-0.4.4}/src/rainfallqc/checks/timeseries_checks.py

@@ -1045,7 +1045,9 @@ def flag_dry_spell_duration(
     """
     # May need to rethink how this is done uniformly (as could use day check)
     dry_spell_lengths_flags = dry_spell_lengths.with_columns(
-        pl.when(pl.col("dry_spell_length") / DAILY_DIVIDING_FACTOR[time_res] >= ref_dry_spell_length * 1.5)
+        pl.when(pl.col("dry_spell_length").is_null() | pl.col("dry_spell_length").is_nan())
+        .then(np.nan)
+        .when(pl.col("dry_spell_length") / DAILY_DIVIDING_FACTOR[time_res] >= ref_dry_spell_length * 1.5)
         .then(4)
         .when(pl.col("dry_spell_length") / DAILY_DIVIDING_FACTOR[time_res] >= ref_dry_spell_length * 1.33)
         .then(3)

{rainfallqc-0.4.2 → rainfallqc-0.4.4}/src/rainfallqc/qc_frameworks/inbuilt_qc_frameworks.py

@@ -31,6 +31,39 @@ INTENSE_QC = {
     "QC25": {"function": neighbourhood_checks.check_monthly_factor},
 }
 
+INTENSE_RULEBASE_QC = {
+    "QC2": {
+        "function": gauge_checks.check_years_where_annual_mean_k_top_rows_are_zero,
+    },
+    "QC10": {
+        "function": comparison_checks.check_exceedance_of_rainfall_world_record,
+    },
+    "QC11": {
+        "function": comparison_checks.check_hourly_exceedance_etccdi_rx1day,
+    },
+    "QC12": {
+        "function": timeseries_checks.check_dry_period_cdd,
+    },
+    "QC13": {
+        "function": timeseries_checks.check_daily_accumulations,
+    },
+    "QC14": {
+        "function": timeseries_checks.check_monthly_accumulations,
+    },
+    "QC15": {
+        "function": timeseries_checks.check_streaks,
+    },
+    "QC17": {
+        "function": neighbourhood_checks.check_wet_neighbours,
+    },
+    "QC19": {
+        "function": neighbourhood_checks.check_dry_neighbours,
+    },
+    "QC20": {
+        "function": neighbourhood_checks.check_monthly_neighbours,
+    },
+}
+
 PYPWSQC = {
     "BC": {"function": pypwsqc_filters.run_bias_correction},
     "EBF": {"function": pypwsqc_filters.run_event_based_filter},
@@ -41,4 +74,4 @@ PYPWSQC = {
     "SO": {"function": pypwsqc_filters.check_station_outlier},
 }
 
-INBUILT_QC_FRAMEWORKS = {"intenseqc": INTENSE_QC, "pypwsqc": PYPWSQC}
+INBUILT_QC_FRAMEWORKS = {"intenseqc": INTENSE_QC, "intenseqc_rulebase_only": INTENSE_RULEBASE_QC, "pypwsqc": PYPWSQC}

{rainfallqc-0.4.2 → rainfallqc-0.4.4}/src/rainfallqc/utils/data_utils.py

@@ -422,7 +422,12 @@ def extract_positive_values_from_data(data: pl.DataFrame, cols_to_extract_from:
         [
             "time",
             *[
-                pl.when(pl.col(col) >= 0).then(pl.col(col)).otherwise(None).alias(col)
+                pl.when(pl.col(col).is_null() | pl.col(col).is_nan())
+                .then(np.nan)
+                .when(pl.col(col) >= 0)
+                .then(pl.col(col))
+                .otherwise(None)
+                .alias(col)
                 for col in cols_to_extract_from
                 if col != "time"
             ],

{rainfallqc-0.4.2 → rainfallqc-0.4.4}/src/rainfallqc/utils/neighbourhood_utils.py

@@ -256,6 +256,10 @@ def compute_temporal_overlap_days_from_target_id(
     """
     # 1. Get target station and start and end date
     target_station = gauge_network_metadata.filter(pl.col(station_id_col) == target_id)
+    assert len(target_station) > 0, (
+        f"gauge_network_metadata does not contain value: '{target_id}' in column '{station_id_col}'"
+    )
+
     start_1, end_1 = (
         target_station[start_datetime_col].item(),
         target_station[end_datetime_col].item(),
@@ -328,6 +332,9 @@ def compute_km_distances_from_target_id(
     """
     # 1. Get target station lat and lon
     target_station = gauge_network_metadata.filter(pl.col(station_id_col) == target_id)
+    assert len(target_station) > 0, (
+        f"gauge_network_metadata does not contain value: '{target_id}' in column '{station_id_col}'"
+    )
     target_latlon = (
         target_station["latitude"].item(),
         target_station["longitude"].item(),

{rainfallqc-0.4.2 → rainfallqc-0.4.4}/src/rainfallqc/utils/stats.py

@@ -126,7 +126,9 @@ def filter_out_rain_world_records(data: pl.DataFrame, target_gauge_col: str, tim
     rainfall_world_records = get_rainfall_world_records()
     # 2. Filter out world records
     data_not_wr = data.with_columns(
-        pl.when(pl.col(target_gauge_col) > rainfall_world_records[time_res])
+        pl.when(pl.col(target_gauge_col).is_null() | pl.col(target_gauge_col).is_nan())
+        .then(np.nan)
+        .when(pl.col(target_gauge_col) > rainfall_world_records[time_res])
         .then(np.nan)
         .otherwise(pl.col(target_gauge_col))
         .alias(target_gauge_col)