From 413c77e603e7e1d23d277efc9ee7cbeb5ca57945 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?David=20Sch=C3=A4fer?= <david.schaefer@ufz.de>
Date: Wed, 20 Mar 2024 17:31:13 +0100
Subject: [PATCH] Bump pandas from 2.1.4 to 2.2.1
---
CHANGELOG.md | 4 ++--
requirements.txt | 2 +-
saqc/core/translation/basescheme.py | 3 ++-
saqc/lib/tools.py | 19 ++++++++++++++++++-
tests/funcs/test_functions.py | 2 +-
tests/funcs/test_outlier_detection.py | 2 +-
tests/fuzzy/lib.py | 4 ++--
7 files changed, 27 insertions(+), 9 deletions(-)
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 9296a9dd5..f24a24883 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -13,12 +13,12 @@ SPDX-License-Identifier: GPL-3.0-or-later
- Option to change the flagging scheme after initialization
- `flagByClick`: manually assign flags using a graphical user interface
- `SaQC`: support for selection, slicing and setting of items by use of subscription on SaQC objects (e.g. `qc[key]` and `qc[key] = value`).
- Selection works with single keys, collections of keys and string slices (e.g. `qc["a":"f"]`). Values can be SaQC objects, pd.Series,
+ Selection works with single keys, collections of keys and string slices (e.g. `qc["a":"f"]`). Values can be SaQC objects, pd.Series,
Iterable of Series and dict-like with series values.
- `transferFlags` is a multivariate function
- `plot`: added `yscope` keyword
- `setFlags`: function to replace `flagManual`
-- `flagUniLOF`: added defaultly applied correction to mitigate phenomenon of overflagging at relatively steep data value slopes. (parameter `slope_correct`).
+- `flagUniLOF`: added defaultly applied correction to mitigate phenomenon of overflagging at relatively steep data value slopes. (parameter `slope_correct`).
### Changed
### Removed
### Fixed
diff --git a/requirements.txt b/requirements.txt
index c9553ab49..d79dee2b7 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -9,7 +9,7 @@ matplotlib==3.8.3
numpy==1.26.4
outlier-utils==0.0.5
pyarrow==15.0.0
-pandas==2.1.4
+pandas==2.2.1
scikit-learn==1.4.1.post1
scipy==1.12.0
typing_extensions==4.5.0
diff --git a/saqc/core/translation/basescheme.py b/saqc/core/translation/basescheme.py
index c072907c8..66f9cb8db 100644
--- a/saqc/core/translation/basescheme.py
+++ b/saqc/core/translation/basescheme.py
@@ -148,7 +148,8 @@ class MappingScheme(TranslationScheme):
out = DictOfSeries()
expected = pd.Index(trans_map.values())
for field in flags.columns:
- out[field] = flags[field].replace(trans_map)
+ with pd.option_context("future.no_silent_downcasting", True):
+ out[field] = flags[field].replace(trans_map).infer_objects()
diff = pd.Index(out[field]).difference(expected)
if not diff.empty:
raise ValueError(
diff --git a/saqc/lib/tools.py b/saqc/lib/tools.py
index 4dbcf7108..feb33af8e 100644
--- a/saqc/lib/tools.py
+++ b/saqc/lib/tools.py
@@ -177,7 +177,24 @@ def periodicMask(
x[e:e] = True
return x
- freq = "1" + "mmmhhhdddMMMYYY"[len(season_start)]
+ freq = (
+ "1",
+ "m",
+ "m",
+ "m",
+ "h",
+ "h",
+ "h",
+ "d",
+ "d",
+ "d",
+ "M",
+ "M",
+ "M",
+ "YE",
+ "YE",
+ "YE",
+ )[len(season_start)]
out = mask.groupby(pd.Grouper(freq=freq)).transform(_selector)
if invert:
out = ~out
diff --git a/tests/funcs/test_functions.py b/tests/funcs/test_functions.py
index e56783568..d956e39b1 100644
--- a/tests/funcs/test_functions.py
+++ b/tests/funcs/test_functions.py
@@ -52,7 +52,7 @@ def test_flagRange(data, field):
assert all(flagged == expected)
-def test_flagSeasonalRange(data, field):
+def test_selectTime(data, field):
data[field].iloc[::2] = 0
data[field].iloc[1::2] = 50
nyears = len(data[field].index.year.unique())
diff --git a/tests/funcs/test_outlier_detection.py b/tests/funcs/test_outlier_detection.py
index d23ef30b5..f6941947b 100644
--- a/tests/funcs/test_outlier_detection.py
+++ b/tests/funcs/test_outlier_detection.py
@@ -33,7 +33,7 @@ def test_flagMad(spiky_data):
field, *_ = data.columns
flags = initFlagsLike(data)
qc = SaQC(data, flags).flagZScore(
- field, window="1H", method="modified", thresh=3.5, flag=BAD
+ field, window="1h", method="modified", thresh=3.5, flag=BAD
)
flag_result = qc.flags[field]
test_sum = (flag_result.iloc[spiky_data[1]] == BAD).sum()
diff --git a/tests/fuzzy/lib.py b/tests/fuzzy/lib.py
index 3604bd472..a70a159f3 100644
--- a/tests/fuzzy/lib.py
+++ b/tests/fuzzy/lib.py
@@ -104,13 +104,13 @@ def daterangeIndexes(draw, min_size=0, max_size=100):
max_date = pd.Timestamp("2099-12-31").to_pydatetime()
start = draw(datetimes(min_value=min_date, max_value=max_date))
periods = draw(integers(min_value=min_size, max_value=max_size))
- freq = draw(sampled_from(["D", "H", "T", "min", "S", "L", "ms", "U", "us", "N"]))
+ freq = draw(sampled_from(["D", "h", "min", "s", "ms", "us", "ns"]))
return pd.date_range(start, periods=periods, freq=freq)
@composite
def frequencyStrings(draw, _):
- freq = draw(sampled_from(["D", "H", "T", "min", "S", "L", "ms", "U", "us", "N"]))
+ freq = draw(sampled_from(["D", "h", "min", "s", "ms", "us", "ns"]))
mult = draw(integers(min_value=1, max_value=10))
value = f"{mult}{freq}"
return value
--
GitLab