diff --git a/CHANGELOG.md b/CHANGELOG.md
index 77a69c738f44c306e304609bde5ed8e995ac6508..20d67405593f1188b18dc57f3f2d0902ad37a766 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,15 @@
# Changelog
All notable changes to this project will be documented in this file.
+## v0.6.3 - 2024-07-30 - fixed custom-sampling
+
+### general:
+* reference series now also uses the sampling type and adapts the data range accordingly
+* fixed calc_data_capture
+
+### technical:
+* custom sample statistics now returns with an index that matches the start-date instead of the start of the year
+
## v0.6.2 - 2024-07-22 - bugfixes
### general:
diff --git a/dist/toarstats-0.6.3-py3-none-any.whl b/dist/toarstats-0.6.3-py3-none-any.whl
new file mode 100644
index 0000000000000000000000000000000000000000..fff61d4df197c040285c71c9064ab4341973cb3f
Binary files /dev/null and b/dist/toarstats-0.6.3-py3-none-any.whl differ
diff --git a/setup.cfg b/setup.cfg
index 1199ee5938b1fb1f95f4093e161bb8bc76a81d55..29ab0fc3f343d8883ce9dda6ef55d78f3342e75b 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -1,6 +1,6 @@
[metadata]
name = toarstats
-version = 0.6.2
+version = 0.6.3
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
diff --git a/toarstats/metrics/interface.py b/toarstats/metrics/interface.py
index 9cf39d7cd8eb95e20562b8e0eeb993d2085808e3..a34d97aeecf2db7eadadb7d05e629dd9c572d945 100644
--- a/toarstats/metrics/interface.py
+++ b/toarstats/metrics/interface.py
@@ -127,7 +127,7 @@ def calculate_statistics(
else DEFAULT_CROPS, input_parameters.required.seasons,
input_parameters.required.crops
)
- ref = create_reference_series(input_parameters.data.index, daterange)
+ ref = create_reference_series(input_parameters.data.index, input_parameters.sampling, daterange)
resample_rule = ("seasonal" if input_parameters.sampling == "vegseason"
else input_parameters.sampling)
min_data_capture_value = (input_parameters.min_data_capture
@@ -145,8 +145,14 @@ def calculate_statistics(
min_data_capture_value
)
)
- results = harmonize_time(
- results, resample_rule,
- "H" if "diurnal_cycle" in input_parameters.statistics else None
- )
+
+ if resample_rule == "custom":
+ custom_index = pd.DatetimeIndex([ref.index.min().strftime("%Y-%m-%d")])
+ for res in results:
+ res["ser"].index = custom_index
+ else:
+ results = harmonize_time(
+ results, resample_rule,
+ "H" if "diurnal_cycle" in input_parameters.statistics else None
+ )
return pd.DataFrame({res["name"]: res["ser"] for res in results})
diff --git a/toarstats/metrics/stats_utils.py b/toarstats/metrics/stats_utils.py
index 11545fa9bd43ff43baad9280d6e5dfd15857e2f2..5483663d3954283837d158f1cc0a3522654480c5 100644
--- a/toarstats/metrics/stats_utils.py
+++ b/toarstats/metrics/stats_utils.py
@@ -113,40 +113,48 @@ def calc_data_capture(ser, ref, sampling, how, mincount=0, minfrac=None,
:return: A series with the data capture fraction
"""
- if sampling == "100YS":
- ser_tmp = ser.resample(sampling).count().values
- fcov = ser_tmp / ref.resample(sampling).count().values
- data_capture = pd.Series([fcov[0]], index=[ref.index[0].round('H')], name="data_capture")
- else:
- ser_tmp = ser.resample(sampling).count()
- fcov = ser_tmp / ref.resample(sampling).count()
- data_capture = fcov.reindex(ser_tmp.index)
- return data_capture
+ # brings the series to the form of the reference time series, no values in series are represented by NaN
+ ser_com = ser.combine(ref, max, fill_value=None)
+
+ ser_tmp = ser_com.resample(sampling).count()
+ fcov = ser_tmp / ref.resample(sampling).count()
+ return fcov.reindex(ser_tmp.index)
-def create_reference_series(index, daterange=None):
- """Create a reference series.
+def create_reference_series(index, sampling, daterange):
+ """Create a reference series by the daterange. Additional extends to the intervals specified by the sampling.
:param index: the given index
+ :param sampling: sampling rate defines the daterange of the ref-series
+ e.g. monthly changes the daterange to fill in all months touched by daterange
+
: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
+ :return: A series with a date range based on the specified date range. The date range is extended based on the
+ specified sampling.
"""
min_date = index.min()
max_date = index.max()
- if daterange:
- 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)
- else:
- start_date = f"{min_date.year}-01-01 00:{min_date.minute}"
- end_date = f"{max_date.year}-12-31 23:{max_date.minute}"
+ # 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")
return pd.Series(0, reference_index)