redetermined interpolation behaviour for frequency aligned values, seperated...

redetermined interpolation behaviour for frequency aligned values, seperated by a margin exactly sized 2*freq

saqc/funcs/harm_functions.py

 #! /usr/bin/env python
 # -*- coding: utf-8 -*-
 
+import pdb
 import pandas as pd
 import numpy as np
 import logging
@@ -368,10 +369,22 @@ def _interpolateGrid(
     # Interpolations:
     elif method in interpolations:
 
+        # account for annoying case of subsequent frequency alligned values, differing exactly by the margin
+        # 2*freq:
+        spec_case_mask = data.asfreq(freq).dropna().index.to_series()
+        spec_case_mask = (spec_case_mask - spec_case_mask.shift(1)) == 2 * pd.Timedelta(freq)
+        spec_case_mask = spec_case_mask[spec_case_mask]
+        if not spec_case_mask.empty:
+            spec_case_mask = spec_case_mask.tshift(-1, freq)
+
         data = _insertGrid(data, freq)
         data, chunk_bounds = _interpolate(
             data, method, order=order, inter_limit=2, downcast_interpolation=downcast_interpolation,
         )
+
+        # exclude falsely interpolated values:
+        data[spec_case_mask.index] = np.nan
+
         if total_range is None:
             data = data.asfreq(freq, fill_value=np.nan)
 

test/funcs/test_harm_funcs.py

@@ -343,18 +343,16 @@ def test_wrapper(data, flagger):
     interpolate2Grid(data, field, flagger, freq, method="spline")
 
 if __name__ == "__main__":
-    dat = pd.read_csv('/home/luenensc/PyPojects/testSpace/current_single_raw.csv')
-    dat.set_index('TIMESTAMP_MEASUREMENT', inplace=True)
-    dat.set_index(pd.DatetimeIndex(dat.index), inplace=True)
+    #dat = pd.read_csv('/home/luenensc/PyPojects/testSpace/current_single_raw.csv')
+    #dat.set_index('TIMESTAMP_MEASUREMENT', inplace=True)
+    #dat.set_index(pd.DatetimeIndex(dat.index), inplace=True)
+    index = pd.date_range('2000-1-1T00:00:00', periods=10, freq='15min')
+    index=index.drop(index[3])
+    dat = pd.DataFrame(data={'testdata': np.arange(0, len(index))}, index=index)
     field = dat.columns[0]
     flagger = TESTFLAGGER[0]
-    freq = '1D'
+    freq = '15min'
     flagger = flagger.initFlags(dat)
-    data, flagger = aggregate2Grid(dat, field, flagger, freq, value_func="sum",
-                   flag_func="max")
-    data, flagger = aggregate2Grid(data, dat.columns[1], flagger, freq, value_func="sum",
-                                   flag_func="max")
-    data, flagger = aggregate2Grid(data, dat.columns[2], flagger, freq, value_func="sum",
-                                   flag_func="max")
+    data, flagger = linear2Grid(dat, field, flagger, freq)
 
     print('bugstop')
\ No newline at end of file