diff --git a/CHANGELOG.md b/CHANGELOG.md
index ac30aa2daa071ca4c817132294bb514d34e49ab1..1ca291eaf7344bedbdbe1c5fe61e8eca90c402ce 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,14 @@
# Changelog
All notable changes to this project will be documented in this file.
+## v0.6.0 - 2023-07-13 - adding custom sampling
+
+### general:
+* added new custom sampling
+
+### new features:
+* arbitrary intervals can now be aggregated (#11)
+
## v0.5.0 - 2023-06-06 - moving block bootstrap
### general:
@@ -15,8 +23,8 @@ All notable changes to this project will be documented in this file.
## v0.4.0 - 2023-02-21 - renaming of metrics
### general:
-* renaming some metrics
-* renaming data_capture argument to min_data_capture
+* renamed some metrics
+* renamed data_capture argument to min_data_capture
### technical:
* all metrics now match their respective result key (#2)
diff --git a/README.md b/README.md
index 77991cffff4e3217fff991f441881203d6bd2bce..815fd7477b756cb82cd0d59864f1b287f87bc8e2 100644
--- a/README.md
+++ b/README.md
@@ -49,7 +49,7 @@ calculate_statistics(
:param sampling: temporal aggregation, one of ``daily``,
``monthly``, ``seasonal``, ``vegseason``,
- ``summer``, ``xsummer``, or ``annual``;
+ ``summer``, ``xsummer``, ``annual``, or ``custom``;
``summer`` will pick the 6-months summer season in
the hemisphere where the station is located;
``xsummer`` does the same for a 7-months summer
@@ -57,7 +57,9 @@ calculate_statistics(
``vegseason`` requires also the ``crops`` argument
and will then determine the appropriate growing
seasons based on the ``climatic_zone`` metadata and
- crop type
+ crop type;
+ ``custom`` will create one aggregate value over the
+ entire time series
:param statistics: a single statistic or metric or a list of
statistics and metrics to call, these must be
defined in ``stats.py`` or ``ozone_metrics.py``
diff --git a/dist/toarstats-0.6.0-py3-none-any.whl b/dist/toarstats-0.6.0-py3-none-any.whl
new file mode 100644
index 0000000000000000000000000000000000000000..2a44f132ffc756e84282021eeb21af7c03d13587
Binary files /dev/null and b/dist/toarstats-0.6.0-py3-none-any.whl differ
diff --git a/docs/conf.py b/docs/conf.py
index bf5410a18825bf81d0094318d582ed94b5e7395f..3a4261baa156d92a649ffc2a36049dee9a7bbb80 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -9,7 +9,7 @@
project = 'toarstats'
copyright = '2021, Forschungszentrum Jülich GmbH'
author = 'Niklas Selke'
-release = '0.5.0'
+release = '0.6.0'
# -- General configuration ---------------------------------------------------
# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
diff --git a/requirements.txt b/requirements.txt
index 230944e66338b4839640688ead8beef2134e9a2c..7dc2b9201a7fd1614a49004b1948e5952f17e4fb 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,4 @@
-numpy==1.24.3
-pandas==2.0.2
-scipy==1.10.1
+numpy==1.25.1
+pandas==2.0.3
+scipy==1.11.1
statsmodels==0.14.0
diff --git a/setup.cfg b/setup.cfg
index a2ced23c78fef13f2cdd3a22ae032552aa8ae5dd..b3c54bb77a53248c38656bf4d1f324e3eb985292 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -1,6 +1,6 @@
[metadata]
name = toarstats
-version = 0.5.0
+version = 0.6.0
author = Niklas Selke
author_email = n.selke@fz-juelich.de
description = Collection of statistics for the TOAR community
diff --git a/tests/test_metrics/test_interface.py b/tests/test_metrics/test_interface.py
index ad1dc6375c1b7088516ca68af82bfb65422ab40f..1bf22d7cee9676314d0ba1b4456fa3f15eb421fc 100644
--- a/tests/test_metrics/test_interface.py
+++ b/tests/test_metrics/test_interface.py
@@ -74,7 +74,7 @@ def test_calculate_statistics_run_all_statistics_with_all_samplings(
elif statistic == "percentiles1":
expected_num_columns *= 3
elif statistic == "percentiles2":
- if sampling in {"daily", "monthly", "seasonal", "vegseason"}:
+ if sampling not in {"summer", "xsummer", "annual"}:
expected_num_columns *= 7
else:
expected_num_columns *= 9
diff --git a/toarstats/metrics/constants.py b/toarstats/metrics/constants.py
index af2d0aa4e6017db08afb9c0657fa8360348e7d1d..ba019589889c7a2da813cf4d9ee3074e42cccd19 100644
--- a/toarstats/metrics/constants.py
+++ b/toarstats/metrics/constants.py
@@ -16,7 +16,8 @@ ALLOWED_SAMPLING_VALUES = [
"vegseason",
"summer",
"xsummer",
- "annual"
+ "annual",
+ "custom"
]
STATISTICS_LIST = [
@@ -156,5 +157,6 @@ RSTAGS = {
"seasonal": "AS",
"summer": "AS",
"xsummer": "AS",
- "annual": "AS"
+ "annual": "AS",
+ "custom": "100AS"
}
diff --git a/toarstats/metrics/interface.py b/toarstats/metrics/interface.py
index bba7fb5e5233d48c45ce08ad3ac3b01108dc9b05..8bbccf6973a7b85643e15525d027f2a9d026d347 100644
--- a/toarstats/metrics/interface.py
+++ b/toarstats/metrics/interface.py
@@ -26,7 +26,7 @@ def calculate_statistics(
:param sampling: temporal aggregation, one of ``daily``,
``monthly``, ``seasonal``, ``vegseason``,
- ``summer``, ``xsummer``, or ``annual``;
+ ``summer``, ``xsummer``, ``annual``, or ``custom``;
``summer`` will pick the 6-months summer season in
the hemisphere where the station is located;
``xsummer`` does the same for a 7-months summer
@@ -34,7 +34,9 @@ def calculate_statistics(
``vegseason`` requires also the ``crops`` argument
and will then determine the appropriate growing
seasons based on the ``climatic_zone`` metadata and
- crop type
+ crop type;
+ ``custom`` will create one aggregate value over the
+ entire time series
:param statistics: a single statistic or metric or a list of
statistics and metrics to call, these must be
defined in ``stats.py`` or ``ozone_metrics.py``
diff --git a/toarstats/metrics/stats.py b/toarstats/metrics/stats.py
index b67ba062b493ab2d899218a951fb7e4123ee8037..e7cea61b12eded303b0dda2d953747e9a3de212d 100644
--- a/toarstats/metrics/stats.py
+++ b/toarstats/metrics/stats.py
@@ -484,7 +484,7 @@ def diurnal_cycle(ser, ref, mtype, metadata, seasons, min_data_capture):
# data record.
nyears = ser.index.year.unique().size
vmax = {"daily": 1, "monthly": 29, "seasonal": 91, "summer": 182,
- "xsummer": 212, "annual": 365}
+ "xsummer": 212, "annual": 365, "custom": 365}
dcap = int(min_data_capture * vmax[mtype] * nyears)
for r in res:
grouped = r["ser"].groupby(r["ser"].index.hour)