def test_percentiles(self):
c=api.Calendar()
t0=c.time(2016, 1, 1)
dt=api.deltahours(1)
n=240
ta=api.TimeAxisFixedDeltaT(t0, dt, n)
timeseries=api.TsVector()
for i in range(10):
timeseries.append(
api.TimeSeries(ta=ta, fill_value=i, point_fx=api.point_interpretation_policy.POINT_AVERAGE_VALUE))
wanted_percentiles=api.IntVector([api.statistics_property.MIN_EXTREME,
0, 10, 50,
api.statistics_property.AVERAGE,
70, 100,
api.statistics_property.MAX_EXTREME])
ta_day=api.TimeAxisFixedDeltaT(t0, dt*24, n//24)
ta_day2=api.TimeAxis(t0, dt*24, n//24)
percentiles=api.percentiles(timeseries, ta_day, wanted_percentiles)
percentiles2=timeseries.percentiles(ta_day2, wanted_percentiles) # just to verify it works with alt. syntax
self.assertEqual(len(percentiles2), len(percentiles))
for i in range(len(ta_day)):
self.assertAlmostEqual(0.0, percentiles[0].value(i), 3, "min-extreme ")
self.assertAlmostEqual(0.0, percentiles[1].value(i), 3, " 0-percentile")
self.assertAlmostEqual(0.9, percentiles[2].value(i), 3, " 10-percentile")
self.assertAlmostEqual(4.5, percentiles[3].value(i), 3, " 50-percentile")
self.assertAlmostEqual(4.5, percentiles[4].value(i), 3, " -average")
self.assertAlmostEqual(6.3, percentiles[5].value(i), 3, " 70-percentile")
self.assertAlmostEqual(9.0, percentiles[6].value(i), 3, "100-percentile")
self.assertAlmostEqual(9.0, percentiles[7].value(i), 3, "max-extreme")
def test_percentiles(self):
c = api.Calendar()
t0 = c.time(2016, 1, 1)
dt = api.deltahours(1)
n = 240
ta = api.Timeaxis(t0, dt, n)
timeseries = api.TsVector()
for i in range(10):
timeseries.append(
api.Timeseries(ta=ta, fill_value=i, point_fx=api.point_interpretation_policy.POINT_AVERAGE_VALUE))
wanted_percentiles = api.IntVector([0, 10, 50, -1, 70, 100])
ta_day = api.Timeaxis(t0, dt * 24, n // 24)
ta_day2 = api.Timeaxis2(t0, dt * 24, n // 24)
percentiles = api.percentiles(timeseries, ta_day, wanted_percentiles)
percentiles2 = timeseries.percentiles(ta_day2, wanted_percentiles) # just to verify it works with alt. syntax
self.assertEqual(len(percentiles2), len(percentiles))
for i in range(len(ta_day)):
self.assertAlmostEqual(0.0, percentiles[0].value(i), 3, " 0-percentile")
self.assertAlmostEqual(0.9, percentiles[1].value(i), 3, " 10-percentile")
self.assertAlmostEqual(4.5, percentiles[2].value(i), 3, " 50-percentile")
self.assertAlmostEqual(4.5, percentiles[3].value(i), 3, " -average")
self.assertAlmostEqual(6.3, percentiles[4].value(i), 3, " 70-percentile")
self.assertAlmostEqual(9.0, percentiles[5].value(i), 3, "100-percentile")
def test_percentiles_with_min_max_extremes(self):
""" the percentiles function now also supports picking out the min-max peak value
within each interval.
Setup test-data so that we have a well known percentile result,
but also have peak-values within the interval that we can
verify.
We let hour ts 0..9 have values 0..9 constant 24*10 days
then modify ts[1], every day first value to a peak min value equal to - day_no*1
every day second value to a peak max value equal to + day_no*1
every day 3rd value to a nan value
ts[1] should then have same average value for each day (so same percentile)
but min-max extreme should be equal to +- day_no*1
"""
c=api.Calendar()
t0=c.time(2016, 1, 1)
dt=api.deltahours(1)
n=240
ta=api.TimeAxis(t0, dt, n)
timeseries=api.TsVector()
p_fx=api.point_interpretation_policy.POINT_AVERAGE_VALUE
for i in range(10):
timeseries.append(api.TimeSeries(ta=ta, fill_value=i, point_fx=p_fx))
ts=timeseries[1] # pick this one to insert min/max extremes
for i in range(0, 240, 24):
ts.set(i + 0, 1.0 - 100*i/24.0)
ts.set(i + 1, 1.0 + 100*i/24.0) # notice that when i==0, this gives 1.0
ts.set(i + 2, float('nan')) # also put in a nan, just to verify it is ignored during average processing
wanted_percentiles=api.IntVector([api.statistics_property.MIN_EXTREME,
0, 10, 50,
api.statistics_property.AVERAGE,
70, 100,
api.statistics_property.MAX_EXTREME])
ta_day=api.TimeAxis(t0, dt*24, n//24)
percentiles=api.percentiles(timeseries, ta_day, wanted_percentiles)
for i in range(len(ta_day)):
if i == 0: # first timestep, the min/max extremes are picked from 0'th and 9'th ts.
self.assertAlmostEqual(0.0, percentiles[0].value(i), 3, "min-extreme ")
self.assertAlmostEqual(9.0, percentiles[7].value(i), 3, "min-extreme ")
else:
self.assertAlmostEqual(1.0 - 100.0*i*24.0/24.0, percentiles[0].value(i), 3, "min-extreme ")
self.assertAlmostEqual(1.0 + 100.0*i*24.0/24.0, percentiles[7].value(i), 3, "max-extreme")
self.assertAlmostEqual(0.0, percentiles[1].value(i), 3, " 0-percentile")
self.assertAlmostEqual(0.9, percentiles[2].value(i), 3, " 10-percentile")
self.assertAlmostEqual(4.5, percentiles[3].value(i), 3, " 50-percentile")
self.assertAlmostEqual(4.5, percentiles[4].value(i), 3, " -average")
self.assertAlmostEqual(6.3, percentiles[5].value(i), 3, " 70-percentile")
self.assertAlmostEqual(9.0, percentiles[6].value(i), 3, "100-percentile")
def test_partition_by(self):
"""
verify/demo exposure of the .partition_by function that can
be used to produce yearly percentiles statistics for long historical
time-series
"""
c=api.Calendar()
t0=c.time(1930, 9, 1)
dt=api.deltahours(1)
n=c.diff_units(t0, c.time(2016, 9, 1), dt)
ta=api.TimeAxis(t0, dt, n)
pattern_values=api.DoubleVector.from_numpy(np.arange(len(ta))) # increasing values
src_ts=api.TimeSeries(ta=ta, values=pattern_values,
point_fx=api.point_interpretation_policy.POINT_AVERAGE_VALUE)
partition_t0=c.time(2016, 9, 1)
n_partitions=80
partition_interval=api.Calendar.YEAR
# get back TsVector,
# where all TsVector[i].index_of(partition_t0)
# is equal to the index ix for which the TsVector[i].value(ix) correspond to start value of that particular partition.
ts_partitions=src_ts.partition_by(c, t0, partition_interval, n_partitions, partition_t0)
self.assertEqual(len(ts_partitions), n_partitions)
ty=t0
for ts in ts_partitions:
ix=ts.index_of(partition_t0)
vix=ts.value(ix)
expected_value=c.diff_units(t0, ty, dt)
self.assertEqual(vix, expected_value)
ty=c.add(ty, partition_interval, 1)
# Now finally, try percentiles on the partitions
wanted_percentiles=[0, 10, 25, -1, 50, 75, 90, 100]
ta_percentiles=api.TimeAxis(partition_t0, api.deltahours(24), 365)
percentiles=api.percentiles(ts_partitions, ta_percentiles, wanted_percentiles)
self.assertEqual(len(percentiles), len(wanted_percentiles))
def test_partition_by(self):
"""
verify/demo exposure of the .partition_by function that can
be used to produce yearly percentiles statistics for long historical
time-series
"""
c = api.Calendar()
t0 = c.time(1930, 9, 1)
dt = api.deltahours(1)
n = c.diff_units(t0, c.time(2016, 9, 1), dt)
ta = api.Timeaxis2(t0, dt, n)
pattern_values = api.DoubleVector.from_numpy(np.arange(len(ta))) # increasing values
src_ts = api.Timeseries(ta=ta, values=pattern_values, point_fx=api.point_interpretation_policy.POINT_AVERAGE_VALUE)
partition_t0 = c.time(2016, 9, 1)
n_partitions = 80
partition_interval = api.Calendar.YEAR
# get back TsVector,
# where all TsVector[i].index_of(partition_t0)
# is equal to the index ix for which the TsVector[i].value(ix) correspond to start value of that particular partition.
ts_partitions = src_ts.partition_by(c, t0, partition_interval, n_partitions, partition_t0)
self.assertEqual(len(ts_partitions),n_partitions)
ty = t0
for ts in ts_partitions:
ix = ts.index_of(partition_t0)
vix = ts.value(ix)
expected_value = c.diff_units(t0, ty, dt)
self.assertEqual(vix, expected_value)
ty = c.add(ty, partition_interval, 1)
# Now finally, try percentiles on the partitions
wanted_percentiles = [0, 10, 25, -1, 50, 75, 90, 100]
ta_percentiles = api.Timeaxis2(partition_t0, api.deltahours(24), 365)
percentiles = api.percentiles(ts_partitions,ta_percentiles,wanted_percentiles)
self.assertEqual(len(percentiles), len(wanted_percentiles))
