def example_mean():
l = TimeSeries()
l[datetime.datetime(2010, 1, 1)] = 0
l[datetime.datetime(2010, 1, 3, 10)] = 1
l[datetime.datetime(2010, 1, 5)] = 0
l[datetime.datetime(2010, 1, 8)] = 1
l[datetime.datetime(2010, 1, 17)] = 0
l[datetime.datetime(2010, 1, 19)] = 1
l[datetime.datetime(2010, 1, 23)] = 0
l[datetime.datetime(2010, 1, 26)] = 1
l[datetime.datetime(2010, 1, 28)] = 0
l[datetime.datetime(2010, 1, 31)] = 1
l[datetime.datetime(2010, 2, 5)] = 0
for time, value in l:
print time.isoformat(), 0.1 * value + 1.1
print ''
timestep = {'hours': 25}
start_time = datetime.datetime(2010, 1, 1)
while start_time <= datetime.datetime(2010, 2, 5):
end_time = start_time + datetime.timedelta(**timestep)
print start_time.isoformat(), l.mean(start_time, end_time)
start_time = end_time
print ''
start_time = datetime.datetime(2010, 1, 1)
while start_time <= datetime.datetime(2010, 2, 5):
end_time = start_time + datetime.timedelta(**timestep)
print start_time.isoformat(), -0.2
print start_time.isoformat(), 1.2
start_time = end_time
def test_mask():
start = datetime.datetime(2015, 3, 1)
# v. simple
a = TimeSeries()
a.set(start, 1)
a.set(datetime.datetime(2015, 4, 2), 0)
a.set(datetime.datetime(2015, 4, 3), 1)
a.set(datetime.datetime(2015, 4, 4), 0)
end = datetime.datetime(2015, 4, 5)
mask = Domain()
mask[datetime.datetime(2015, 4, 1)] = True
mask[datetime.datetime(2015, 4, 3)] = False
# not normalized
distribution = a.distribution(
start=start,
end=end,
normalized=False,
mask=mask,
)
assert distribution[0] == 24 * 60 * 60 # one day
assert distribution[1] == 24 * 60 * 60
# normalized
distribution = a.distribution(
start=start,
end=end,
mask=mask,
)
assert distribution[0] == 0.5
assert distribution[1] == 0.5
def test_distribution():
start = datetime.datetime(2015, 3, 1)
# v. simple
a = TimeSeries()
a.set(start, 1)
a.set(datetime.datetime(2015, 3, 2), 0)
a.set(datetime.datetime(2015, 3, 3), 1)
a.set(datetime.datetime(2015, 3, 4), 0)
end = datetime.datetime(2015, 3, 5)
# not normalized
distribution = a.distribution(
start=start,
end=end,
normalized=False,
)
assert distribution[0] == 24 * 60 * 60 * 2 # two days
assert distribution[1] == 24 * 60 * 60 * 2
# normalized
distribution = a.distribution(start=start, end=end)
assert distribution[0] == 0.5
assert distribution[1] == 0.5
def test_set_domain():
ts = TimeSeries()
assert ts.domain == Domain([-inf, inf])
ts.domain = None
assert ts.domain == Domain([-inf, inf])
ts.domain = [-inf, 5]
assert ts.domain == Domain([-inf, 5])
ts.domain = [5, inf]
assert ts.domain == Domain([5, inf])
ts.domain = [-inf, inf]
assert ts.domain == Domain([-inf, inf])
ts.domain = [2, 5]
assert ts.domain == Domain([2, 5])
ts.domain = [[2, 5], [9, 10]]
assert ts.domain == Domain([2, 5], [9, 10])
ts = TimeSeries(data=[(1, 2), (2, 3), (6, 1), (8, 4)])
nose.tools.assert_raises(ValueError, setattr, ts, 'domain', [1.5, 7])
nose.tools.assert_raises(ValueError, setattr, ts, 'domain', [0, 7])
nose.tools.assert_raises(ValueError, setattr, ts, 'domain', [1.5, 9])
def _beh_interval(self, ts: TimeSeries):
if ts.is_empty():
return 0
return sum([
en - st for st, en, _ in ts.iterperiods()
if en - st < self.decay_time
])
def example_mean():
l = TimeSeries()
l[datetime.datetime(2010, 1, 1)] = 0
l[datetime.datetime(2010, 1, 3, 10)] = 1
l[datetime.datetime(2010, 1, 5)] = 0
l[datetime.datetime(2010, 1, 8)] = 1
l[datetime.datetime(2010, 1, 17)] = 0
l[datetime.datetime(2010, 1, 19)] = 1
l[datetime.datetime(2010, 1, 23)] = 0
l[datetime.datetime(2010, 1, 26)] = 1
l[datetime.datetime(2010, 1, 28)] = 0
l[datetime.datetime(2010, 1, 31)] = 1
l[datetime.datetime(2010, 2, 5)] = 0
for time, value in l:
print(time.isoformat(), 0.1 * value + 1.1)
print('')
timestep = {'hours': 25}
start = datetime.datetime(2010, 1, 1)
while start <= datetime.datetime(2010, 2, 5):
end = start + datetime.timedelta(**timestep)
print(start.isoformat(), l.mean(start, end))
start = end
print('')
start = datetime.datetime(2010, 1, 1)
while start <= datetime.datetime(2010, 2, 5):
end = start + datetime.timedelta(**timestep)
print(start.isoformat(), -0.2)
print(start.isoformat(), 1.2)
start = end
def add_annotation(self, file: os.PathLike, **kwargs):
self.file_list.append(file)
# setup default kwargs #
if self.ordinal:
kwargs.update({'value_transform': lambda cls: self.order.get(cls)})
if not kwargs.get('time_transform', None):
kwargs.update({'time_transform': lambda t: float(t)})
if not kwargs.get('skip_header', None):
kwargs.update({'skip_header': False})
if not os.path.isfile(file):
raise FileNotFoundError(f'File {file} not found.')
if os.path.getsize(file):
ts = TimeSeries.from_csv(file,
**kwargs).slice(self.start_time,
self.end_time)
meta = pd.read_csv(file, names=COLUMNS.keys())
meta.drop(meta[meta['time'] < self.start_time].index)
meta.drop(meta[meta['time'] > self.end_time].index)
else:
ts = TimeSeries()
meta = pd.DataFrame()
self.metadata.append(meta)
self.series.append(ts)
self._data = self._report()
def example_arrow():
l = TimeSeries()
l[arrow.Arrow(2010, 1, 1)] = 0
l[arrow.Arrow(2010, 1, 3, 10)] = 1
l[arrow.Arrow(2010, 1, 5)] = 0
l[arrow.Arrow(2010, 1, 8)] = 1
l[arrow.Arrow(2010, 1, 17)] = 0
l[arrow.Arrow(2010, 1, 19)] = 1
l[arrow.Arrow(2010, 1, 23)] = 0
l[arrow.Arrow(2010, 1, 26)] = 1
l[arrow.Arrow(2010, 1, 28)] = 0
l[arrow.Arrow(2010, 1, 31)] = 1
l[arrow.Arrow(2010, 2, 5)] = 0
for time, value in l:
print(time.naive.isoformat(), 0.1 * value + 1.1)
print('')
start = arrow.Arrow(2010, 1, 1)
end = arrow.Arrow(2010, 2, 5)
unit = {'hours': 25}
for start, end in span_range(start, end, unit):
print(start.naive.isoformat(), l.mean(start, end))
print('')
for start, end in span_range(start, end, unit):
print(start.naive.isoformat(), -0.2)
print(start.naive.isoformat(), 1.2)
def test_init_data():
ts = TimeSeries([(1, 2), (2, 3), (6, 1), (8, 4)])
assert ts[0] == 2
assert ts[1] == 2
assert ts[1.5] == 2
assert ts[6] == 1
assert ts[7] == 1
assert ts[8] == 4
assert ts[10] == 4
ts = TimeSeries([[1, 2], [2, 3], [6, 1], [8, 4]])
assert ts[0] == 2
assert ts[1] == 2
assert ts[1.5] == 2
assert ts[6] == 1
assert ts[7] == 1
assert ts[8] == 4
assert ts[10] == 4
ts = TimeSeries({1: 2, 2: 3, 6: 1, 8: 4})
assert ts[0] == 2
assert ts[1] == 2
assert ts[1.5] == 2
assert ts[6] == 1
assert ts[7] == 1
assert ts[8] == 4
assert ts[10] == 4
def test_mean():
ts = TimeSeries([[1, 2], [2, 3], [6, 1], [8, 4]], domain=Domain(0, 9))
assert ts.mean() == 22. / 9
ts = TimeSeries([[1, 2], [2, 3], [6, 1], [8, 4]],
domain=Domain([1, 2], [3, 5], [6, 8]))
nose.tools.assert_raises(NotImplementedError, ts.mean)
def test_difference():
a = TimeSeries(data=[(0, 0), (2, 2)], default=0)
b = TimeSeries(data=[(1, 1), (3, 2)], default=0)
c = a - b
nose.tools.eq_(list(c.items()), [(0, 0), (1, -1), (2, 1), (3, 0)])
def example_arrow():
l = TimeSeries()
l[arrow.Arrow(2010, 1, 1)] = 0
l[arrow.Arrow(2010, 1, 3, 10)] = 1
l[arrow.Arrow(2010, 1, 5)] = 0
l[arrow.Arrow(2010, 1, 8)] = 1
l[arrow.Arrow(2010, 1, 17)] = 0
l[arrow.Arrow(2010, 1, 19)] = 1
l[arrow.Arrow(2010, 1, 23)] = 0
l[arrow.Arrow(2010, 1, 26)] = 1
l[arrow.Arrow(2010, 1, 28)] = 0
l[arrow.Arrow(2010, 1, 31)] = 1
l[arrow.Arrow(2010, 2, 5)] = 0
for time, value in l:
print time.naive.isoformat(), 0.1 * value + 1.1
print ''
start = arrow.Arrow(2010, 1, 1)
end = arrow.Arrow(2010, 2, 5)
unit = {'hours': 25}
for start_time, end_time in span_range(start, end, unit):
print start_time.naive.isoformat(), l.mean(start_time, end_time)
print ''
for start_time, end_time in span_range(start, end, unit):
print start_time.naive.isoformat(), -0.2
print start_time.naive.isoformat(), 1.2
def test_exists():
ts = TimeSeries([(-5, 0), (0, 23), (5, None)])
ts_exists = ts.exists()
assert ts_exists[-10] is False
assert ts_exists[-2] is True
assert ts_exists[3] is True
assert ts_exists[10] is False
def test_none_handling():
ts = TimeSeries()
ts[1] = (0, 1)
ts[2] = (None, 0)
ts[3] = (2, 0)
# print(ts.distribution(normalized=False))
assert (ts.distribution()[(0, 1)] == 0.5)
assert (ts.distribution()[(None, 0)] == 0.5)
def test_is_data_in_domain():
data1 = [(1, 2), (2, 3), (6, 1), (7, 4)]
ts = TimeSeries(data=data1)
# this shouldn't work
nose.tools.assert_raises(ValueError, setattr, ts, 'domain', [3, 4])
# this should work
ts.domain = [0, 8]
def test_merge():
ts_a = TimeSeries(default=None)
ts_b = TimeSeries(default=None)
ts_a[0] = None
ts_b[0] = True
ts_merge = TimeSeries.merge([ts_a, ts_b])
assert True in ts_merge[0]
assert None in ts_merge[0]
def test_set_interval_datetime():
ts = TimeSeries(default=400)
ts[datetime(2012, 1, 4, 12)] = 5
ts[datetime(2012, 1, 9, 18)] = 10
ts[datetime(2012, 1, 8):datetime(2012, 1, 10)] = 100
assert ts.items() == [(datetime(2012, 1, 4, 12, 0), 5),
(datetime(2012, 1, 8, 0, 0), 100),
(datetime(2012, 1, 10, 0, 0), 10)]
def group_total_beh(self):
"""
Returns: float of group total behavior index as a fraction of interval
"""
if len(self.ts_list) > 1:
ts = TimeSeries()
ts = ts.merge(self.ts_list)
return self.beh_index(ts)
else:
return self.individual_total_beh()
def test_default():
ts = TimeSeries(data=[(0, 0), (1, 2)])
ts_no_default = ts.operation(ts, lambda a, b: a + b)
assert ts_no_default.default == None
ts_default = ts.operation(ts, lambda a, b: a + b, default=1)
assert ts_default.default == 1
ts_none = ts.operation(ts, lambda a, b: a + b, default=None)
assert ts_none.default == None
def test_scalar_ops():
a = TimeSeries()
a.set(datetime.datetime(2015, 3, 1), 1)
a.set(datetime.datetime(2015, 3, 2), 0)
a.set(datetime.datetime(2015, 3, 3), 3)
a.set(datetime.datetime(2015, 3, 4), 2)
ts_half = a.multiply(0.5)
ts_bool = a.to_bool(invert=False)
ts_threshold = a.threshold(value=1.1)
# test before domain, should give default value
assert ts_half[datetime.datetime(2015, 2, 24)] is None
assert ts_bool[datetime.datetime(2015, 2, 24)] == None
assert ts_threshold[datetime.datetime(2015, 2, 24)] == None
# test values throughout series
assert ts_half[datetime.datetime(2015, 3, 1, 6)] == 0.5
assert ts_bool[datetime.datetime(2015, 3, 1, 6)] == True
assert ts_threshold[datetime.datetime(2015, 3, 1, 6)] == False
assert ts_half[datetime.datetime(2015, 3, 2, 6)] == 0
assert ts_bool[datetime.datetime(2015, 3, 2, 6)] == False
assert ts_threshold[datetime.datetime(2015, 3, 2, 6)] == False
assert ts_half[datetime.datetime(2015, 3, 3, 6)] == 1.5
assert ts_bool[datetime.datetime(2015, 3, 3, 6)] == True
assert ts_threshold[datetime.datetime(2015, 3, 3, 6)] == True
# test after domain, should give last value
assert ts_half[datetime.datetime(2015, 3, 4, 18)] == 1
assert ts_bool[datetime.datetime(2015, 3, 4, 18)] == True
assert ts_threshold[datetime.datetime(2015, 3, 4, 18)] == True
def test_distribution():
ts = TimeSeries([[1, 1], [2, 0], [6, 1], [8, 0]],
domain=Domain([1, 2], [3, 5], [6, 8]))
distribution = ts.distribution()
assert distribution[0] == 2. / 5
assert distribution[1] == 3. / 5
distribution = ts.distribution(0, 9)
assert distribution[0] == 2. / 5
assert distribution[1] == 3. / 5
def test_merge():
ts_a = TimeSeries()
ts_b = TimeSeries()
# ts_a[0] = None
ts_b[0] = True
ts_merge = TimeSeries.merge([ts_a, ts_b])
assert True in ts_merge[0]
assert None in ts_merge[0]
ts_c = TimeSeries.merge([])
assert list(ts_c.items()) == []
def test_csv():
def time_parse(value):
return int(value)
def value_parse(value):
try:
return int(value)
except ValueError:
return None
filename = 'sample.csv'
with open(filename, 'w') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(['hour', 'value'])
writer.writerow(['10', '15'])
writer.writerow(['11', '34'])
writer.writerow(['12', '19'])
writer.writerow(['13', 'nan'])
writer.writerow(['14', '18'])
writer.writerow(['15', 'nan'])
ts = TimeSeries.from_csv(filename,
time_column=0,
time_transform=time_parse,
value_column=1,
value_transform=value_parse,
default=None)
os.remove(filename)
assert ts[9] is None
assert ts[20] is None
assert ts[13.5] is None
histogram = ts.distribution()
nose.tools.assert_almost_equal(histogram.mean(), (15 + 34 + 19 + 18) / 4.0)
filename = 'sample.csv'
with open(filename, 'w') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(['hour', 'value'])
writer.writerow(['2000-01-01 10:00:00', '15'])
writer.writerow(['2000-01-01 11:00:00', '34'])
writer.writerow(['2000-01-01 12:00:00', '19'])
writer.writerow(['2000-01-01 13:00:00', 'nan'])
writer.writerow(['2000-01-01 14:00:00', '18'])
writer.writerow(['2000-01-01 15:00:00', 'nan'])
ts = TimeSeries.from_csv(filename)
os.remove(filename)
assert ts[datetime(2000, 1, 1, 9)] is None
assert ts[datetime(2000, 1, 1, 10, 30)] == '15'
assert ts[datetime(2000, 1, 1, 20)] == 'nan'
def test_integer_times():
# v. simple
a = TimeSeries()
a[0] = 1
a[1] = 0
a[3] = 1
a[4] = 0
distribution = a.distribution(start=0, end=6)
assert distribution[0] == 2.0 / 3
assert distribution[1] == 1.0 / 3
def test_iterperiods():
# timeseries with no points raises a KeyError
ts = TimeSeries()
with nose.tools.assert_raises(KeyError):
next(ts.iterperiods())
ts.set(datetime.datetime(2015, 3, 1), 1)
ts.set(datetime.datetime(2015, 3, 2), 0)
ts.set(datetime.datetime(2015, 3, 3), 1)
ts.set(datetime.datetime(2015, 3, 4), 2)
answer = [(datetime.datetime(2015, 3, 1), datetime.datetime(2015, 3,
2), 1),
(datetime.datetime(2015, 3, 2), datetime.datetime(2015, 3,
3), 0),
(datetime.datetime(2015, 3, 3), datetime.datetime(2015, 3,
4), 1)]
result = []
for (t0, t1, v0) in ts.iterperiods(start=datetime.datetime(2015, 3, 1),
end=datetime.datetime(2015, 3, 4)):
result.append((t0, t1, v0))
assert answer == result
answer = [
(datetime.datetime(2015, 3, 1), datetime.datetime(2015, 3, 2), 1),
(datetime.datetime(2015, 3, 3), datetime.datetime(2015, 3, 4), 1),
]
result = []
for (t0, t1, v0) in ts.iterperiods(
start=datetime.datetime(2015, 3, 1),
end=datetime.datetime(2015, 3, 4),
value=1,
):
result.append((t0, t1, v0))
assert answer == result
def filter(t0, t1, value):
return True if not value else False
answer = [
(datetime.datetime(2015, 3, 2), datetime.datetime(2015, 3, 3), 0),
]
result = []
for (t0, t1, v0) in ts.iterperiods(
start=datetime.datetime(2015, 3, 1),
end=datetime.datetime(2015, 3, 4),
value=filter,
):
result.append((t0, t1, v0))
assert answer == result
def test_scalar_ops():
a = TimeSeries()
a.set(datetime.datetime(2015, 3, 1), 1)
a.set(datetime.datetime(2015, 3, 2), 0)
a.set(datetime.datetime(2015, 3, 3), 3)
a.set(datetime.datetime(2015, 3, 4), 2)
ts_half = a.scale_by(0.5)
ts_bool = a.to_bool(invert=False)
ts_threshold = a.threshold(value=1.1)
# test before domain, should give default value
assert ts_half[datetime.datetime(2015, 2, 24)] == 0
assert ts_bool[datetime.datetime(2015, 2, 24)] == False
assert ts_threshold[datetime.datetime(2015, 2, 24)] == False
# test values throughout series
assert ts_half[datetime.datetime(2015, 3, 1, 6)] == 0.5
assert ts_bool[datetime.datetime(2015, 3, 1, 6)] == True
assert ts_threshold[datetime.datetime(2015, 3, 1, 6)] == False
assert ts_half[datetime.datetime(2015, 3, 2, 6)] == 0
assert ts_bool[datetime.datetime(2015, 3, 2, 6)] == False
assert ts_threshold[datetime.datetime(2015, 3, 2, 6)] == False
assert ts_half[datetime.datetime(2015, 3, 3, 6)] == 1.5
assert ts_bool[datetime.datetime(2015, 3, 3, 6)] == True
assert ts_threshold[datetime.datetime(2015, 3, 3, 6)] == True
# test after domain, should give last value
assert ts_half[datetime.datetime(2015, 3, 4, 18)] == True
assert ts_bool[datetime.datetime(2015, 3, 4, 18)] == True
assert ts_threshold[datetime.datetime(2015, 3, 4, 18)] == True
def test_slice():
ts = TimeSeries(int)
ts[0] = 1
ts[1] = 5
ts[4] = 0
ts[6] = 2
assert ts.slice(0.5, 2.5).items() == [(0.5, 1), (1, 5)]
assert ts.slice(1.0, 2.5).items() == [(1.0, 5)]
assert ts.slice(-1, 1).items() == [(-1, 1), (0, 1), (1, 5)]
assert ts.slice(-1, 0.5).items() == [(-1, 1), (0, 1)]
nose.tools.assert_raises(ValueError, ts.slice, 2.5, 0)
def test_distribution_set():
time_series = TimeSeries()
time_series[1.2] = {'broccoli'}
time_series[1.4] = {'broccoli', 'orange'}
time_series[1.7] = {'broccoli', 'orange', 'banana'}
time_series[2.2] = {'orange', 'banana'}
time_series[3.5] = {'orange', 'banana', 'beets'}
def example_dictlike():
# test overwriting keys
ts = TimeSeries()
ts[datetime.datetime(2010, 1, 1)] = 5
ts[datetime.datetime(2010, 1, 2)] = 4
ts[datetime.datetime(2010, 1, 3)] = 3
ts[datetime.datetime(2010, 1, 7)] = 2
ts[datetime.datetime(2010, 1, 4)] = 1
ts[datetime.datetime(2010, 1, 4)] = 10
ts[datetime.datetime(2010, 1, 4)] = 5
ts[datetime.datetime(2010, 1, 1)] = 1
ts[datetime.datetime(2010, 1, 7)] = 1.2
ts[datetime.datetime(2010, 1, 8)] = 1.3
ts[datetime.datetime(2010, 1, 12)] = 1.3
# do some wackiness with a bunch of points
dt = datetime.datetime(2010, 1, 12)
for i in range(1000):
dt += datetime.timedelta(hours=random.random())
ts[dt] = math.sin(i / float(math.pi))
dt -= datetime.timedelta(hours=500)
dt -= datetime.timedelta(minutes=30)
for i in range(1000):
dt += datetime.timedelta(hours=random.random())
ts[dt] = math.cos(i / float(math.pi))
# output the time series
for i, j in ts:
print(i.isoformat(), j)
def test_remove_points_from_interval():
ts = TimeSeries(default=0)
ts[0] = 0
ts[1] = 2
ts[3] = 1
ts[4] = 0
assert ts[5] == 0
del ts[3.5:4.5]
assert ts[5] == 1
ts[4] = 0
del ts[3:4.5]
assert ts[5] == 2
ts[3] = 1
ts[4] = 0
del ts[3.5:4]
assert ts[5] == 0
def example_dictlike():
# test overwriting keys
l = TimeSeries()
l[datetime.datetime(2010, 1, 1)] = 5
l[datetime.datetime(2010, 1, 2)] = 4
l[datetime.datetime(2010, 1, 3)] = 3
l[datetime.datetime(2010, 1, 7)] = 2
l[datetime.datetime(2010, 1, 4)] = 1
l[datetime.datetime(2010, 1, 4)] = 10
l[datetime.datetime(2010, 1, 4)] = 5
l[datetime.datetime(2010, 1, 1)] = 1
l[datetime.datetime(2010, 1, 7)] = 1.2
l[datetime.datetime(2010, 1, 8)] = 1.3
l[datetime.datetime(2010, 1, 12)] = 1.3
# do some wackiness with a bunch of points
dt = datetime.datetime(2010, 1, 12)
for i in range(1000):
dt += datetime.timedelta(hours=random.random())
l[dt] = math.sin(i / float(math.pi))
dt -= datetime.timedelta(hours=500)
dt -= datetime.timedelta(minutes=30)
for i in range(1000):
dt += datetime.timedelta(hours=random.random())
l[dt] = math.cos(i / float(math.pi))
# what does this get?
print >> sys.stderr, l[datetime.datetime(2010, 1, 3, 23, 59, 59)]
# output the time series
for i, j in l:
print(i.isoformat(), j)
def test_merge():
# since this is random, do it a bunch of times
for n_trial in range(1000):
# make a list of TimeSeries that is anywhere from 0 to 5
# long. Each TimeSeries is of random length between 0 and 20,
# with random time points and random values.
ts_list = []
for i in range(random.randint(1, 5)):
ts_list.append(make_random_timeseries())
method_a = list(TimeSeries.merge(ts_list, compact=False))
method_b = list(TimeSeries.iter_merge(ts_list))
msg = '%s != %s' % (pprint.pformat(method_a), pprint.pformat(method_b))
assert method_a == method_b, msg
def from_pandas(df, compact=True):
'''TODO'''
domain = Domain(df.index[0], df.index[-1])
data = {col: TimeSeries(df[col].T, domain=domain) for col in df.columns}
if compact:
for val in data.values():
val.compact()
return data
def test_distribution():
start_time = datetime.datetime(2015, 3, 1)
# v. simple
a = TimeSeries()
a.set(start_time, 1)
a.set(datetime.datetime(2015, 3, 2), 0)
a.set(datetime.datetime(2015, 3, 3), 1)
a.set(datetime.datetime(2015, 3, 4), 0)
end_time = datetime.datetime(2015, 3, 5)
# not normalized
distribution = a.distribution(
start_time=start_time, end_time=end_time, normalized=False,
)
assert distribution[0] == 24 * 60 * 60 * 2 # two days
assert distribution[1] == 24 * 60 * 60 * 2
# normalized
distribution = a.distribution(start_time=start_time, end_time=end_time)
assert distribution[0] == 0.5
assert distribution[1] == 0.5
def test_default_values():
# v. simple
a = TimeSeries()
a.set(datetime.datetime(2015, 3, 1), 1)
a.set(datetime.datetime(2015, 3, 2), 0)
a.set(datetime.datetime(2015, 3, 3), 1)
a.set(datetime.datetime(2015, 3, 4), 0)
# not normalized
distribution = a.distribution()
total = 24 * 60 * 60 * 3
assert distribution[0] == 24 * 60 * 60 * 1 / float(total)
assert distribution[1] == 24 * 60 * 60 * 2 / float(total)
def test_mask():
start_time = datetime.datetime(2015, 3, 1)
# v. simple
a = TimeSeries()
a.set(start_time, 1)
a.set(datetime.datetime(2015, 3, 2), 0)
a.set(datetime.datetime(2015, 3, 3), 1)
a.set(datetime.datetime(2015, 3, 4), 0)
end_time = datetime.datetime(2015, 3, 5)
mask = TimeSeries()
mask.set(datetime.datetime(2015, 3, 1), 1)
mask.set(datetime.datetime(2015, 3, 3), 0)
# not normalized
distribution = a.distribution(
start_time=start_time, end_time=end_time, normalized=False, mask=mask,
)
assert distribution[0] == 24 * 60 * 60 # one day
assert distribution[1] == 24 * 60 * 60
# normalized
distribution = a.distribution(
start_time=start_time, end_time=end_time, mask=mask,
)
assert distribution[0] == 0.5
assert distribution[1] == 0.5
def example_sum():
a = TimeSeries()
a.set(datetime.datetime(2015, 3, 1), 1)
a.set(datetime.datetime(2015, 3, 2), 0)
a.set(datetime.datetime(2015, 3, 3), 1)
a.set(datetime.datetime(2015, 3, 5), 0)
a.set(datetime.datetime(2015, 3, 6), 0)
b = TimeSeries()
b.set(datetime.datetime(2015, 3, 1), 0)
b.set(datetime.datetime(2015, 3, 2, 12), 1)
b.set(datetime.datetime(2015, 3, 3, 13, 13), 0)
b.set(datetime.datetime(2015, 3, 4), 1)
b.set(datetime.datetime(2015, 3, 5), 0)
b.set(datetime.datetime(2015, 3, 5, 12), 1)
b.set(datetime.datetime(2015, 3, 5, 19), 0)
c = TimeSeries()
c.set(datetime.datetime(2015, 3, 1, 17), 0)
c.set(datetime.datetime(2015, 3, 1, 21), 1)
c.set(datetime.datetime(2015, 3, 2, 13, 13), 0)
c.set(datetime.datetime(2015, 3, 4, 18), 1)
c.set(datetime.datetime(2015, 3, 5, 4), 0)
# output the three time series
for i, ts in enumerate([a, b, c]):
for (t0, v0), (t1, v1) in ts.iterintervals(1):
print t0.isoformat(), i
print t1.isoformat(), i
print ''
for (t0, v0), (t1, v1) in ts.iterintervals(0):
print t0.isoformat(), i
print t1.isoformat(), i
print ''
# output the sum
# for dt, i in sum([a, b, c]):
# print dt.isoformat(), i
# print ''
for dt, i in TimeSeries.from_many_sum([a, b, c]):
print dt.isoformat(), i
def test_sum():
a = TimeSeries()
a.set(datetime.datetime(2015, 3, 1), 1)
a.set(datetime.datetime(2015, 3, 2), 0)
a.set(datetime.datetime(2015, 3, 3), 1)
a.set(datetime.datetime(2015, 3, 4), 0)
b = TimeSeries()
b.set(datetime.datetime(2015, 3, 1), 0)
b.set(datetime.datetime(2015, 3, 1, 12), 1)
b.set(datetime.datetime(2015, 3, 2), 0)
b.set(datetime.datetime(2015, 3, 2, 12), 1)
b.set(datetime.datetime(2015, 3, 3), 0)
c = TimeSeries()
c.set(datetime.datetime(2015, 3, 1), 0)
c.set(datetime.datetime(2015, 3, 1, 18), 1)
c.set(datetime.datetime(2015, 3, 5), 0)
ts_sum = TimeSeries.from_many_sum([a, b, c])
# test before domain, should give default value
assert ts_sum[datetime.datetime(2015, 2, 24)] == 0
# test values throughout sum
assert ts_sum[datetime.datetime(2015, 3, 1)] == 1
assert ts_sum[datetime.datetime(2015, 3, 1, 6)] == 1
assert ts_sum[datetime.datetime(2015, 3, 1, 12)] == 2
assert ts_sum[datetime.datetime(2015, 3, 1, 13)] == 2
assert ts_sum[datetime.datetime(2015, 3, 1, 17)] == 2
assert ts_sum[datetime.datetime(2015, 3, 1, 18)] == 3
assert ts_sum[datetime.datetime(2015, 3, 1, 19)] == 3
assert ts_sum[datetime.datetime(2015, 3, 3)] == 2
assert ts_sum[datetime.datetime(2015, 3, 4)] == 1
assert ts_sum[datetime.datetime(2015, 3, 4, 18)] == 1
assert ts_sum[datetime.datetime(2015, 3, 5)] == 0
# test after domain, should give last value
assert ts_sum[datetime.datetime(2015, 3, 6)] == 0
baseline = 0
for ts in [a, b, c]:
for i, j in ts:
print i.isoformat(), j + baseline
print ''
baseline += 1.2
ts_sum = TimeSeries.from_many_sum([a, b, c])
for i, j in ts_sum:
print i.isoformat(), j + baseline