From 0381881f002ef1cceebf9e56ee4dfc62c20aeda9 Mon Sep 17 00:00:00 2001
From: Max Lensing <max.lensing@alumni.fh-aachen.de>
Date: Mon, 22 Jul 2024 11:12:42 +0200
Subject: [PATCH] bugfix create_reference_series and calc_data_capture, updated
toarstats to 0.6.2
---
CHANGELOG.md | 6 ++++++
toarstats/metrics/stats_utils.py | 22 +++++++++++++++-------
2 files changed, 21 insertions(+), 7 deletions(-)
diff --git a/CHANGELOG.md b/CHANGELOG.md
index c48a301..77a69c7 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,12 @@
# Changelog
All notable changes to this project will be documented in this file.
+## v0.6.2 - 2024-07-22 - bugfixes
+
+### general:
+* corrected calc_data_capture when using custom sampling
+* updated reference_series creation to correct minute-offset
+
## v0.6.1 - 2024-07-15 - bugfixes
### general:
diff --git a/toarstats/metrics/stats_utils.py b/toarstats/metrics/stats_utils.py
index d745c03..11545fa 100644
--- a/toarstats/metrics/stats_utils.py
+++ b/toarstats/metrics/stats_utils.py
@@ -113,9 +113,15 @@ def calc_data_capture(ser, ref, sampling, how, mincount=0, minfrac=None,
:return: A series with the data capture fraction
"""
- ser_tmp = ser.resample(sampling).count()
- fcov = ser_tmp / ref.resample(sampling).count()
- return fcov.reindex(ser_tmp.index)
+ 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
def create_reference_series(index, daterange=None):
@@ -131,12 +137,14 @@ def create_reference_series(index, daterange=None):
the earliest given year to the ending of the latest given
year and filled with zeros
"""
+ min_date = index.min()
+ max_date = index.max()
if daterange:
- start_date = daterange.split(",")[0]
- end_date = daterange.split(",")[1]
+ 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:
- 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")
--
GitLab