From d07f1e390ebdc6bdedc1bb1e23a5a331eddfba47 Mon Sep 17 00:00:00 2001
From: luenensc <peter.luenenschloss@ufz.de>
Date: Sun, 3 Mar 2024 16:57:21 +0100
Subject: [PATCH] updated doc
---
saqc/funcs/outliers.py | 19 +++++++++++++++----
1 file changed, 15 insertions(+), 4 deletions(-)
diff --git a/saqc/funcs/outliers.py b/saqc/funcs/outliers.py
index ff6f629a7..2a5652ce6 100644
--- a/saqc/funcs/outliers.py
+++ b/saqc/funcs/outliers.py
@@ -179,8 +179,8 @@ class OutliersMixin:
p: int = 1,
density: Literal["auto"] | float = "auto",
fill_na: bool = True,
- slope_correct=True,
- min_offset=None,
+ slope_correct: bool = True,
+ min_offset: float = None,
flag: float = BAD,
**kwargs,
) -> "SaQC":
@@ -249,6 +249,15 @@ class OutliersMixin:
fill_na :
If True, NaNs in the data are filled with a linear interpolation.
+ slope_correct :
+ if True, a correction is applied, that removes outlier cluster that actually
+ just seem to be steep slopes
+
+ min_offset :
+ If set, only those outlier cluster will be flagged, that are preceeded and succeeeded
+ by sufficiently large value "jumps". Defaults to estimating the sufficient value jumps from
+ the median over the absolute step sizes between data points.
+
See Also
--------
:ref:`introduction to outlier detection with
@@ -374,7 +383,7 @@ class OutliersMixin:
g_mask = s_mask.diff()
g_mask = g_mask.cumsum()
dat = self._data[field]
- od_groups = dat.groupby(by=g_mask)
+ od_groups = dat.interpolate('linear').groupby(by=g_mask)
first_vals = od_groups.first()
last_vals = od_groups.last()
max_vals = od_groups.max()
@@ -385,7 +394,9 @@ class OutliersMixin:
eps = d_diff.abs().median()
if eps == 0:
eps = d_diff[d_diff != 0].abs().median()
- eps = 3 * eps
+ else:
+ eps = density
+ eps = 3 * eps
else:
eps = min_offset
up_slopes = (min_vals + eps >= last_vals.shift(1)) & (
--
GitLab