bugfix create_reference_series, updated toarstats to 0.6.4

CHANGELOG.md

 # Changelog
 All notable changes to this project will be documented in this file.
 
+## v0.6.4 - 2024-09-16 - bugfix reference-series
+
+### general:
+* daterange in create_reference_series is now optional, therefore the series is created by dataframe indices
+
 ## v0.6.3 - 2024-07-30 - fixed custom-sampling
 
 ### general:

setup.cfg

 [metadata]
 name = toarstats
-version = 0.6.3
+version = 0.6.4
 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

toarstats/metrics/stats_utils.py

@@ -121,8 +121,9 @@ def calc_data_capture(ser, ref, sampling, how, mincount=0, minfrac=None,
     return fcov.reindex(ser_tmp.index)
 
 
-def create_reference_series(index, sampling, daterange):
+def create_reference_series(index, sampling, daterange=None):
     """Create a reference series by the daterange. Additional extends to the intervals specified by the sampling.
+    If no daterange is given, the series is based on the indices of the dataframe.
 
     :param index: the given index
 
@@ -133,29 +134,31 @@ def create_reference_series(index, sampling, daterange):
            if set, the reference series creates a series from start to end-date
 
 
-    :return: A series with a date range based on the specified date range. The date range is extended based on the
+    :return: A series with a date range based on the specified date range or indices. The date range is extended based on the
             specified sampling.
     """
     min_date = index.min()
     max_date = index.max()
-    # adjust start and end-date by the minute-offset of the timeseries
-    start_date = pd.to_datetime(daterange.split(",")[0])
-    start_date = start_date.replace(minute=min_date.minute)
-    end_date = pd.to_datetime(daterange.split(",")[1])
-    end_date = end_date.replace(minute=max_date.minute)
-
-    if sampling in ["annual", "seasonal", "summer", "xsummer"]:
-        start_date = start_date.replace(month=1, day=1, hour=0)
-        end_date = end_date.replace(month=12, day=31, hour=23)
-    elif sampling == "monthly":
-        start_date = start_date.replace(day=1, hour=0)
-        end_date = pd.offsets.MonthEnd().rollforward(end_date)
-        end_date = end_date.replace(hour=23)
-    elif sampling == "daily":
-        start_date = start_date.replace(hour=0)
-        end_date = end_date.replace(hour=23)
-
-    reference_index = pd.date_range(start=start_date, end=end_date, freq="h")
+    if daterange is not None:
+        # adjust start and end-date by the minute-offset of the timeseries
+        start_date = pd.to_datetime(daterange.split(",")[0])
+        start_date = start_date.replace(minute=min_date.minute)
+        end_date = pd.to_datetime(daterange.split(",")[1])
+        end_date = end_date.replace(minute=max_date.minute)
+
+        if sampling in ["annual", "seasonal", "summer", "xsummer"]:
+            start_date = start_date.replace(month=1, day=1, hour=0)
+            end_date = end_date.replace(month=12, day=31, hour=23)
+        elif sampling == "monthly":
+            start_date = start_date.replace(day=1, hour=0)
+            end_date = pd.offsets.MonthEnd().rollforward(end_date)
+            end_date = end_date.replace(hour=23)
+        elif sampling == "daily":
+            start_date = start_date.replace(hour=0)
+            end_date = end_date.replace(hour=23)
+        reference_index = pd.date_range(start=start_date, end=end_date, freq="h")
+    else:
+        reference_index = pd.date_range(start=min_date, end=max_date, freq="h")
     return pd.Series(0, reference_index)