From 3d55bdc592cb4ab1b27ddb48d6123d53f8acaeae Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?David=20Sch=C3=A4fer?= <david.schaefer@ufz.de>
Date: Mon, 28 Sep 2020 10:47:30 +0200
Subject: [PATCH] fixing numba type checking: on windows we need to specify the
word size of integers to make numba happy
---
saqc/funcs/spikes_detection.py | 14 +++++++-------
saqc/lib/tools.py | 13 ++++++-------
2 files changed, 13 insertions(+), 14 deletions(-)
diff --git a/saqc/funcs/spikes_detection.py b/saqc/funcs/spikes_detection.py
index e20a4960b..93a23c6d0 100644
--- a/saqc/funcs/spikes_detection.py
+++ b/saqc/funcs/spikes_detection.py
@@ -940,7 +940,7 @@ def spikes_flagBasic(data, field, flagger, thresh, tolerance, window, numba_kick
to_roll = post_jumps.reindex(dataseries.index, method="bfill", tolerance=window, fill_value=False).dropna()
# define spike testing function to roll with:
- def spike_tester(chunk, thresh=thresh, tol=tolerance):
+ def spikeTester(chunk, thresh=thresh, tol=tolerance):
# signum change!!!
chunk_stair = (np.abs(chunk - chunk[-1]) < thresh)[::-1].cumsum()
initial = np.searchsorted(chunk_stair, 2)
@@ -957,21 +957,21 @@ def spikes_flagBasic(data, field, flagger, thresh, tolerance, window, numba_kick
engine=None
if roll_mask.sum() > numba_kickin:
engine = 'numba'
- result = customRolling(to_roll, window, spike_tester, roll_mask, closed='both', engine=engine)
+ result = customRolling(to_roll, window, spikeTester, roll_mask, closed='both', engine=engine)
+
group_col = np.nancumsum(result)
group_frame = pd.DataFrame({'group_col': group_col[:-1],
'diff_col': np.diff(group_col).astype(int)},
index=result.index[:-1])
-
groups = group_frame.groupby('group_col')
- def g_func(x):
- r = np.array([False] * x.shape[0])
+ def gFunc(x):
+ r = np.zeros(shape=x.shape[0], dtype=np.bool)
r[-x[-1]:] = True
return r
- to_flag = groups['diff_col'].transform(g_func)
- flagger = flagger.setFlags(field, to_flag, **kwargs)
+ to_flag = groups['diff_col'].transform(gFunc)
+ flagger = flagger.setFlags(field, to_flag[to_flag == True].index, **kwargs)
return data, flagger
diff --git a/saqc/lib/tools.py b/saqc/lib/tools.py
index 646ddec08..395e88e8b 100644
--- a/saqc/lib/tools.py
+++ b/saqc/lib/tools.py
@@ -460,26 +460,25 @@ def customRolling(to_roll, winsz, func, roll_mask, min_periods=1, center=False,
"""
i_roll = to_roll.copy()
- i_roll.index = np.arange(to_roll.shape[0])
+ i_roll.index = np.arange(to_roll.shape[0], dtype=np.int64)
if isinstance(winsz, str):
- winsz = int(pd.Timedelta(winsz).total_seconds()*10**9)
+ winsz = np.int64(pd.Timedelta(winsz).total_seconds()*10**9)
indexer = FreqIndexer(window_size=winsz,
win_points=roll_mask,
- index_array=to_roll.index.to_numpy(int),
+ index_array=to_roll.index.to_numpy(np.int64),
center=center,
closed=closed)
elif isinstance(winsz, int):
indexer = PeriodsIndexer(window_size=winsz,
- win_points=roll_mask,
- center=center,
- closed=closed)
+ win_points=roll_mask,
+ center=center,
+ closed=closed)
i_roll = i_roll.rolling(indexer,
min_periods=min_periods,
center=center,
closed=closed).apply(func, raw=raw, engine=engine)
-
return pd.Series(i_roll.values, index=to_roll.index)
--
GitLab