From bac2aaeccbaa709b8f6a337fd38aa55ec5c7a913 Mon Sep 17 00:00:00 2001
From: Bert Palm <bert.palm@ufz.de>
Date: Thu, 3 Dec 2020 16:35:05 +0100
Subject: [PATCH] adjusted saqc calls to customRoller
---
saqc/funcs/constants_detection.py | 2 +-
saqc/funcs/modelling.py | 12 +++++-------
saqc/lib/rolling.py | 6 +++---
3 files changed, 9 insertions(+), 11 deletions(-)
diff --git a/saqc/funcs/constants_detection.py b/saqc/funcs/constants_detection.py
index c8382ab5c..d40205690 100644
--- a/saqc/funcs/constants_detection.py
+++ b/saqc/funcs/constants_detection.py
@@ -50,7 +50,7 @@ def constants_flagBasic(data, field, flagger, thresh, window, **kwargs):
# min_periods=2 ensures that at least two non-nan values are present
# in each window and also min() == max() == d[i] is not possible.
- kws = dict(window=window, min_periods=2)
+ kws = dict(window=window, min_periods=2, expand=False)
# find all consecutive constant values in one direction...
r = customRoller(d, **kws)
diff --git a/saqc/funcs/modelling.py b/saqc/funcs/modelling.py
index 704a8b52b..59f169c52 100644
--- a/saqc/funcs/modelling.py
+++ b/saqc/funcs/modelling.py
@@ -512,13 +512,11 @@ def modelling_changePointCluster(data, field, flagger, stat_func, thresh_func, b
if reduce_window is None:
reduce_window = f"{int(pd.Timedelta(bwd_window).total_seconds() + pd.Timedelta(fwd_window).total_seconds())}s"
- # native pandas.rolling also fails
- data_ser.rolling(window=bwd_window, min_periods=min_periods_bwd, closed=closed)
- roller = customRoller(data_ser, window=bwd_window, min_periods=min_periods_bwd, closed=closed)
- bwd_start, bwd_end = roller.window.get_window_bounds()
+ roller = customRoller(data_ser, window=bwd_window)
+ bwd_start, bwd_end = roller.window.get_window_bounds(len(data_ser), min_periods=min_periods_bwd, closed=closed)
- roller = customRoller(data_ser, window=fwd_window, min_periods=min_periods_fwd, closed=closed, forward=True)
- fwd_start, fwd_end = roller.window.get_window_bounds()
+ roller = customRoller(data_ser, window=fwd_window, forward=True)
+ fwd_start, fwd_end = roller.window.get_window_bounds(len(data_ser), min_periods=min_periods_fwd, closed=closed)
min_mask = ~((fwd_end - fwd_start <= min_periods_fwd) | (bwd_end - bwd_start <= min_periods_bwd))
fwd_end = fwd_end[min_mask]
@@ -560,7 +558,7 @@ def modelling_changePointCluster(data, field, flagger, stat_func, thresh_func, b
detected = pd.Series(True, index=det_index)
if reduce_window is not False:
l = detected.shape[0]
- roller = customRoller(detected, window=reduce_window, min_periods=1, closed='both', center=True)
+ roller = customRoller(detected, window=reduce_window)
start, end = roller.window.get_window_bounds(num_values=l, min_periods=1, closed='both', center=True)
detected = _reduceCPCluster(stat_arr[result_arr], thresh_arr[result_arr], start, end, reduce_func, l)
diff --git a/saqc/lib/rolling.py b/saqc/lib/rolling.py
index 49e7f4316..323cf1789 100644
--- a/saqc/lib/rolling.py
+++ b/saqc/lib/rolling.py
@@ -324,9 +324,9 @@ def customRoller(obj, window, min_periods=None, # aka minimum non-nan values
Notes
-----
If for some reason the start and end numeric indices of the window are needed, one can call
- `start, end = customRoller(obj, ...).window.get_window_bounds()`, which return two arrays,
- holding the start and end indices. Any passed (allowed) parameter to `get_window_bounds()` is
- ignored and the arguments that was passed to `customRoller()` beforehand will be used instead.
+ `start, end = customRoller(obj, window).window.get_window_bounds(num_values, min_periods)`,
+ which return two np.arrays, that are holding the start and end indices. Fill at least all
+ parameter which are shown in the example.
See Also
--------
--
GitLab