def _get_features(self,
ew,
signal_to_truth_shift=0,
valid=False,
mask=np.ones((10), dtype=bool)):
X = np.zeros((1, 10))
i = self.ew2i[ew]
X[0, 0] = 1
for lag in range(3):
if valid and not self.valid[i - lag][lag]:
w = self.i2ew[i - lag]
raise Exception('missing unstable wILI (ew=%d|lag=%d)' %
(w, lag))
try:
X[0, 1 + lag] = np.log(
np.maximum(
0.01,
self.data[i - lag - signal_to_truth_shift]['stable']))
except Exception:
X[0, 1 + lag] = np.nan
for holiday in range(4):
if EW.split_epiweek(EW.add_epiweeks(ew, holiday))[1] == 1:
X[0, 4 + holiday] = 1
y, w = EW.split_epiweek(ew)
N = EW.get_num_weeks(y)
offset = np.pi * 2 * w / N
X[0, 8] = np.sin(offset)
X[0, 9] = np.cos(offset)
# todo linear time trend covariate?
return X[:, mask]
def from_epiweek(year, week):
if year < 1 or week < 1 or week > get_num_weeks(year):
raise Exception('invalid year or week')
date = EpiDate(year, 7, 1)
while date.get_ew_week() < week:
date = date.add_weeks(+1)
while date.get_ew_week() > week:
date = date.add_weeks(-1)
while date.get_day_of_week() < 3:
date = date.add_days(+1)
while date.get_day_of_week() > 3:
date = date.add_days(-1)
return date
def _get_features(self, ew, valid=True):
X = np.zeros((1, 7))
i = self.ew2i[ew]
X[0, 0] = 1
for holiday in range(4):
if EW.split_epiweek(EW.add_epiweeks(ew, holiday))[1] == 1:
X[0, 1 + holiday] = 1
y, w = EW.split_epiweek(ew)
N = EW.get_num_weeks(y)
offset = np.pi * 2 * w / N
X[0, 5] = np.sin(offset)
X[0, 6] = np.cos(offset)
# todo linear time trend covariate?
return X
def _get_features(self, ew, valid=True):
X = np.zeros((1, 10))
i = self.ew2i[ew]
X[0, 0] = 1
for lag in range(3):
if valid and not self.valid[i - lag][lag]:
w = self.i2ew[i - lag]
raise Exception('missing unstable %s (ew=%d|lag=%d)' % (self.target, w, lag))
X[0, 1 + lag] = self.data[i - lag][lag]
for holiday in range(4):
if EW.split_epiweek(EW.add_epiweeks(ew, holiday))[1] == 1:
X[0, 4 + holiday] = 1
y, w = EW.split_epiweek(ew)
N = EW.get_num_weeks(y)
offset = np.pi * 2 * w / N
X[0, 8] = np.sin(offset)
X[0, 9] = np.cos(offset)
return X
def test_from_epiweek(self):
for y, m, d, ey, ew in FunctionTests.sample_epiweeks:
epwk = utils_epiweek.join_epiweek(ey, ew)
with self.subTest(y=y, m=m, d=d, epwk=epwk):
date1 = EpiDate(y, m, d)
date2 = EpiDate.from_epiweek(ey, ew)
self.assertEqual(date1.get_ew(), epwk)
self.assertEqual(date2.get_ew(), epwk)
self.assertEqual(date2.get_day_of_week(), 3)
for year in range(2000, 2020):
for week in range(1, utils_epiweek.get_num_weeks(year) + 1):
epwk = utils_epiweek.join_epiweek(year, week)
date = EpiDate.from_epiweek(year, week)
self.assertEqual(date.get_ew(), epwk)
self.assertEqual(date.get_day_of_week(), 3)
with self.assertRaises(Exception):
EpiDate.from_epiweek(2017, 0)
with self.assertRaises(Exception):
EpiDate.from_epiweek(2017, 53)
with self.assertRaises(Exception):
EpiDate.from_epiweek(0, 30)
def cum_to_week(data):
epiweeks = list(data.keys())
all_epiweeks = list(
EW.range_epiweeks(min(epiweeks), max(epiweeks), inclusive=True))
result = np.zeros((len(all_epiweeks)))
last_valid = (-1, 0) # (idx, value)
for i in range(len(result)):
ew = all_epiweeks[i]
if ew in data:
if data[all_epiweeks[i]] is not None:
result[last_valid[0] + 1:i +
1] = (data[ew] - last_valid[1]) / float(
i -
last_valid[0]) # Evenly distribute missing counts
last_valid = (i, data[ew])
yr, wk = EW.split_epiweek(all_epiweeks[i])
if EW.get_num_weeks(yr) == wk:
result[
last_valid[0] + 1:i +
1] = 0 # Fill rest of year with 0s, not getting this information
last_valid = (i, 0) # Start new year at 0
return {all_epiweeks[i]: result[i] for i in range(len(all_epiweeks))}