From dfb5a90a94e15f4122225199edead71530e1e63a Mon Sep 17 00:00:00 2001
From: Peter Luenenschloss <peter.luenenschloss@ufz.de>
Date: Tue, 2 Jul 2019 12:41:02 +0200
Subject: [PATCH] added sample rate estimation function to lib.tools
---
saqc/funcs/functions.py | 4 ++--
saqc/lib/tools.py | 15 +++++++++++++++
2 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/saqc/funcs/functions.py b/saqc/funcs/functions.py
index 210fa743c..f3025aa19 100644
--- a/saqc/funcs/functions.py
+++ b/saqc/funcs/functions.py
@@ -227,8 +227,8 @@ def flagSoilMoistureByPrecipitationEvents(data, flags, field, flagger, prec_refe
ef = eval_frame[0]
ef.index = eval_frame['level_0']
- # make raise and std. dev tester function (returns True for values that
- # should be flagged bad and False respectively. (must be this way, since np.nan gets casted to True))
+ # make raise and std. dev tester function (returns False for values that
+ # should be flagged bad and True respectively. (must be this way, since np.nan gets casted to True)))
def prec_test(x):
x_moist = x[0::2]
x_rain = x[1::2]
diff --git a/saqc/lib/tools.py b/saqc/lib/tools.py
index f47cf65d8..3a2d28fcc 100644
--- a/saqc/lib/tools.py
+++ b/saqc/lib/tools.py
@@ -100,3 +100,18 @@ def inferFrequency(data):
return pd.tseries.frequencies.to_offset(pd.infer_freq(data.index))
+def estimateSamplingRate(index):
+ """The function estimates the sampling rate of a datetime index.
+ The estimation basically evaluates a histogram of bins with seconds-accuracy. This means, that the
+ result may be contra intuitive very likely, if the input series is not rastered (harmonized with skips)
+ to an interval divisible by seconds.
+
+ :param index: A DatetimeIndex or array like Datetime listing, of wich you want the sampling rate to be
+ estimated.
+ """
+ scnds_series = (pd.Series(index).diff().dt.total_seconds()).dropna()
+ max_scnds = scnds_series.max()
+ min_scnds = scnds_series.min()
+ hist = np.histogram(scnds_series, range=(min_scnds, max_scnds + 1), bins=int(max_scnds - min_scnds + 1))
+ # return smallest non zero sample difference (this works, because input is expected to be harmonized)
+ return pd.tseries.frequencies.to_offset(str(int(hist[1][:-1][hist[0] > 0].min())) + 's')
--
GitLab