Merge branch 'max_version_0.6.1' into 'master'

reference_series creation allows daterange argument, updated toarstats to 0.6.1

See merge request !13

CHANGELOG.md

 # Changelog
 All notable changes to this project will be documented in this file.
 
+## v0.6.1 - 2024-07-15 - bugfixes
+
+### general:
+* updated sampling daterange to exact dates
+
+### technical:
+* bugfix for reference_series creation by adding optional daterange argument
+* updated deprecated constants
+
 ## v0.6.0 - 2023-07-13 - adding custom sampling
 
 ### general:

CITATION.cff

@@ -17,6 +17,11 @@ authors:
   family-names: Schultz
   given-names: Martin
   affiliation: Forschungszentrum Jülich
+- email: m.lensing@fz-juelich.de
+  orcid: https://orcid.org/0009-0004-2443-8792
+  family-names: Lensing
+  given-names: Max
+  affiliation: Forschungszentrum Jülich
 contact:
 - email: m.schultz@fz-juelich.de
   orcid: https://orcid.org/0000-0003-3455-774X

docs/conf.py

@@ -8,8 +8,8 @@
 
 project = 'toarstats'
 copyright = '2021, Forschungszentrum Jülich GmbH'
-author = 'Niklas Selke'
-release = '0.6.0'
+author = 'Niklas Selke, Martin Schultz, Max Lensing'
+release = '0.6.1'
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

setup.cfg

 [metadata]
 name = toarstats
-version = 0.6.0
-author = Niklas Selke
-author_email = n.selke@fz-juelich.de
+version = 0.6.1
+author = Niklas Selke, Martin Schultz, Max Lensing
+author_email = n.selke@fz-juelich.de, m.schultz@fz-juelich.de, m.lensing@fz-juelich.de
 description = Collection of statistics for the TOAR community
 long_description = file: README.md
 long_description_content_type = text/markdown

toarstats/metrics/constants.py

@@ -154,9 +154,9 @@ ALLOWED_CROPS_VALUES = [
 RSTAGS = {
     "daily": "D",
     "monthly": "MS",
-    "seasonal": "AS",
-    "summer": "AS",
-    "xsummer": "AS",
-    "annual": "AS",
-    "custom": "100AS"
+    "seasonal": "YS",
+    "summer": "YS",
+    "xsummer": "YS",
+    "annual": "YS",
+    "custom": "100YS"
 }

toarstats/metrics/interface.py

@@ -16,7 +16,8 @@ from toarstats.metrics.stats_utils import (
 def calculate_statistics(
     sampling=None, statistics=None, data=None, metadata=None, seasons=None,
     crops=None, min_data_capture=None, datetimes=None, values=None,
-    station_lat=None, station_lon=None, station_climatic_zone=None
+    station_lat=None, station_lon=None, station_climatic_zone=None,
+    daterange=None
 ):
     """Calculate the requested statistics.
 
@@ -126,7 +127,7 @@ def calculate_statistics(
         else DEFAULT_CROPS, input_parameters.required.seasons,
         input_parameters.required.crops
     )
-    ref = create_reference_series(input_parameters.data.index)
+    ref = create_reference_series(input_parameters.data.index, daterange)
     resample_rule = ("seasonal" if input_parameters.sampling == "vegseason"
                      else input_parameters.sampling)
     min_data_capture_value = (input_parameters.min_data_capture

toarstats/metrics/stats_utils.py

@@ -118,20 +118,28 @@ def calc_data_capture(ser, ref, sampling, how, mincount=0, minfrac=None,
     return fcov.reindex(ser_tmp.index)
 
 
-def create_reference_series(index):
+def create_reference_series(index, daterange=None):
     """Create a reference series.
 
     :param index: the given index
 
+    :param daterange: start- and end-date separated by comma
+           if set, the reference series creates a series from start to end-date
+
+
     :return: A series with a date range spanning from the beginning of
              the earliest given year to the ending of the latest given
              year and filled with zeros
     """
-    min_date = index.min()
-    max_date = index.max()
-    start_date = f"{min_date.year}-01-01 00:{min_date.minute}"
-    end_date = f"{max_date.year}-12-31 23:{max_date.minute}"
-    reference_index = pd.date_range(start=start_date, end=end_date, freq="H")
+    if daterange:
+        start_date = daterange.split(",")[0]
+        end_date = daterange.split(",")[1]
+    else:
+        min_date = index.min()
+        max_date = index.max()
+        start_date = f"{min_date.year}-01-01 00:{min_date.minute}"
+        end_date = f"{max_date.year}-12-31 23:{max_date.minute}"
+    reference_index = pd.date_range(start=start_date, end=end_date, freq="h")
     return pd.Series(0, reference_index)
 
 
@@ -494,6 +502,8 @@ def stat_processor_1(label, ser, ref, mtype, seasons, func=resample,
     :return: A list of dictionaries containing the processed data
     """
     res = prepare_data(ser, ref, mtype, seasons, label)
+    if minfrac == 0:
+        minfrac = None
     for r in res:
         r["ser"] = func(r["ser"], r["ref"], RSTAGS[mtype], how,
                         mincount=mincount, minfrac=minfrac,