bump up numba version

requirements.txt

@@ -2,7 +2,7 @@ atomicwrites==1.3.0
 attrs==19.1.0
 llvmlite==0.28.0
 more-itertools==7.0.0
-numba==0.43.1
+numba==0.46.0
 numpy==1.16.2
 pandas==0.24.2
 pluggy==0.9.0
@@ -10,6 +10,5 @@ py==1.8.0
 pytest==4.4.0
 python-dateutil==2.8.0
 pytz==2018.9
-PyYAML==5.1
 scipy==1.3.0
 six==1.12.0

saqc/funcs/spike_detection.py

@@ -32,8 +32,7 @@ def slidingOutlier(data, flags, field, flagger, winsz, dx, count=1, deg=1, z=3.5
     3.  the outlier `method` detect potential outlier
     4.  the window is continued by `dx` to the next data-slot.
     5.  processing continue at 1. until end of data.
-    5.  all potential outlier, that are detected `count`-many times, are promoted to real outlier and flagged by the
-    `flagger`
+    6.  all potential outlier, that are detected `count`-many times, are promoted to real outlier and flagged by the `flagger`
 
     :param data:        pandas dataframe. holding the data
     :param flags:       pandas dataframe. holding the flags
@@ -108,6 +107,7 @@ def slidingOutlier(data, flags, field, flagger, winsz, dx, count=1, deg=1, z=3.5
             for i in range(0, len(arr) - wsz + 1, step):
                 yield i, i + wsz
 
+
     for start, end in loopfun(d.index, winsz, dx):
         # mask points that have been already discarded
         mask = counters[start:end] > 0

saqc/lib/tools.py

@@ -19,9 +19,6 @@ def findIndex(iterable, value, start):
     while i < len(iterable):
         v = iterable[i]
         if v >= value:
-            # if v == value:
-                # include the end_date if present
-                # return i + 1
             return i
         i = i + 1
     return -1
@@ -45,8 +42,9 @@ def slidingWindowIndices(dates, window_size, iter_delta=None):
     if isinstance(dates, pd.DataFrame):
         dates = dates.index
     dates = np.array(dates, dtype=np.int64)
+
     if np.any(np.diff(dates) <= 0):
-        raise ValueError("strictly monotic index needed")
+        raise ValueError("strictly monotonic index needed")
 
     window_size = pd.to_timedelta(window_size).to_timedelta64().astype(np.int64)
     if iter_delta:

test/funcs/test_spike_detection.py

@@ -9,9 +9,13 @@ from saqc.flagger.baseflagger import BaseFlagger
 from saqc.flagger.dmpflagger import DmpFlagger
 from saqc.flagger.simpleflagger import SimpleFlagger
 
-from saqc.funcs.spike_detection import flagSpikes_SpektrumBased, flagMad, slidingOutlier, flagSpikes_Basic
-
 from saqc.lib.tools import getPandasData
+from saqc.funcs.spike_detection import (
+    flagSpikes_SpektrumBased,
+    flagMad,
+    slidingOutlier,
+    flagSpikes_Basic)
+
 
 TESTFLAGGERS = [
     BaseFlagger(['NIL', 'GOOD', 'BAD']),
@@ -56,16 +60,16 @@ def test_slidingOutlier(spiky_data, flagger, method):
     # test for numeric input
     data = spiky_data[0].to_frame()
     flags = flagger.initFlags(data)
-    _, flag_result = slidingOutlier(data, flags, 'spiky_data', flagger, winsz=300, dx=50, method=method)
-    flag_result = getPandasData(flag_result, 0)
-    test_sum = (flag_result[spiky_data[1]] == flagger.BAD).sum()
-    assert test_sum == len(spiky_data[1])
 
-    # test for offset input
-    _, flag_result = slidingOutlier(data, flags, 'spiky_data', flagger, winsz='1500min', dx='250min', method=method)
-    flag_result = getPandasData(flag_result, 0)
-    test_sum = (flag_result[spiky_data[1]] == flagger.BAD).sum()
-    assert test_sum == len(spiky_data[1])
+    tests = [
+        slidingOutlier(data, flags, 'spiky_data', flagger, winsz=300, dx=50, method=method),
+        slidingOutlier(data, flags, 'spiky_data', flagger, winsz='1500min', dx='250min', method=method)
+    ]
+
+    for _, test_flags in tests:
+        flag_result = flagger.getFlags(test_flags)
+        test_sum = (flag_result.iloc[spiky_data[1]] == flagger.BAD).sum()
+        assert int(test_sum) == len(spiky_data[1])
 
 
 @pytest.mark.parametrize('flagger', TESTFLAGGERS)