def get_aggregates(self, date, delta):
prenatal = self.inputs[0].get_result()
aggregates = [
Count(),
Aggregate(days('visit_d', 'date_of_birth'), ['min', 'max'],
'visit'),
Aggregate(list(select_regexes(prenatal, ['service_.*'])),
'sum',
fname=False),
Aggregate('preg_nbr_n', 'max', 'previous_pregnancies',
fname=False),
Aggregate('lv_brth_n', 'max', 'previous_births', fname=False),
Aggregate('othr_trm_n',
'max',
'previous_terminations',
fname=False),
Aggregate(lambda p: p.smk3_mth_f == 'Y',
'any',
'smoked_3mo',
fname=False),
Aggregate('cig3_day_n', 'max', 'cigarettes_per_day', fname=False),
Aggregate(lambda p: p.drk3_mth_f == 'Y',
'any',
'drank_3mo',
fname=False),
Aggregate('dr_dy_wk_n', 'max', 'days_drank_per_week', fname=False),
Aggregate('drnk_day_n', 'max', 'drinks_per_day', fname=False),
]
return aggregates
def get_aggregates(self, date, delta):
aggregates = [
Count(),
Aggregate(days('visit_d', 'date_of_birth'), ['min', 'max'],
'visit'),
Aggregate('serv_typ_c', lambda s: set(s), 'service', fname=False),
Aggregate('preg_nbr_n', 'max', 'previous_pregnancies',
fname=False),
Aggregate('lv_brth_n', 'max', 'previous_births', fname=False),
Aggregate('othr_trm_n',
'max',
'previous_terminations',
fname=False),
Aggregate(lambda p: p.smk3_mth_f == 'Y',
'any',
'smoked_3mo',
fname=False),
Aggregate('cig3_day_n', 'max', 'cigarettes_per_day', fname=False),
Aggregate(lambda p: p.drk3_mth_f == 'Y',
'any',
'drank_3mo',
fname=False),
Aggregate('dr_dy_wk_n', 'max', 'days_drank_per_week', fname=False),
Aggregate('drnk_day_n', 'max', 'drinks_per_day', fname=False),
Aggregate('clinicid_i', lambda c: set(c), 'clinic', fname=False)
]
return aggregates
def get_aggregates(self, date, delta):
kid_count = Aggregate('kid_id',
'nunique',
name='kid_count',
fname=False)
aggregates = [
Count(),
Aggregate('bll', ['mean', 'median', 'max', 'min', 'std']),
Aggregate(lambda t: t.bll.where(t.increase),
['mean', 'median', 'max', 'min', 'std'], 'increase_bll'),
Count(lambda t: t.bll <= 2, 'bll2', prop=True),
# prevalences
Fraction(Count(['first_bll6', 'first_bll10']),
kid_count,
include_numerator=True,
include_denominator=True),
]
# incidences
if delta != 'all':
start_date = date - data.parse_delta(delta)
no_bll6_count = Aggregate(lambda k: k.kid_id.where(
(k.first_bll6_sample_date >= start_date).fillna(True)),
'nunique',
name='no_bll6_count',
fname=False)
no_bll10_count = Aggregate(lambda k: k.kid_id.where(
(k.first_bll10_sample_date >= start_date).fillna(True)),
'nunique',
name='no_bll10_count',
fname=False)
aggregates.extend([
no_bll6_count, no_bll10_count,
Count('first_bll6') / no_bll6_count,
Count('first_bll10') / no_bll10_count
])
if delta == 'all':
aggregates.extend([
Aggregate(days('date', date), ['min', 'max'],
'days_since_test'),
Aggregate([
lambda t:
(date - t.date.where(t.bll >= 6)) / day, lambda t:
(date - t.date.where(t.bll >= 10)) / day
], ['min', 'max'], ['days_since_bll6', 'days_since_bll10'])
])
return aggregates
def get_aggregates(self, date, delta):
aggregates = [
Count(),
Aggregate(days('visit_d', 'date_of_birth'), ['min', 'max'], 'visit'),
Aggregate('serv_typ_c', lambda s: set(s), 'service', fname=False),
Aggregate('preg_nbr_n', 'max', 'previous_pregnancies', fname=False),
Aggregate('lv_brth_n', 'max', 'previous_births', fname=False),
Aggregate('othr_trm_n', 'max', 'previous_terminations', fname=False),
Aggregate(lambda p: p.smk3_mth_f == 'Y', 'any', 'smoked_3mo', fname=False),
Aggregate('cig3_day_n', 'max', 'cigarettes_per_day', fname=False),
Aggregate(lambda p: p.drk3_mth_f == 'Y', 'any', 'drank_3mo', fname=False),
Aggregate('dr_dy_wk_n', 'max', 'days_drank_per_week', fname=False),
Aggregate('drnk_day_n', 'max', 'drinks_per_day', fname=False),
Aggregate('clinicid_i', lambda c: set(c), 'clinic', fname=False)
]
return aggregates
def get_aggregates(self, date, delta):
kid_count = Aggregate('kid_id', 'nunique',
name='kid_count', fname=False)
aggregates = [
Count(),
Aggregate('bll', ['mean', 'median', 'max', 'min', 'std']),
Count(lambda t: t.bll <= 2, 'bll2', prop=True),
Fraction(Count(['first_bll6', 'first_bll10']), kid_count,
include_numerator=True, include_denominator=True),
]
if delta == 'all':
aggregates.extend([
Aggregate(days('date',date), ['min','max'],
'days_since_test'),
Aggregate([
lambda t: (date - t.date.where(t.bll >= 6))/day,
lambda t: (date - t.date.where(t.bll >= 10))/day],
['min','max'], ['days_since_bll6', 'days_since_bll10'])
])
return aggregates
def get_aggregates(self, date, index, delta):
if index == 'kid':
return [
Aggregate(
['test_address_count', 'address_count', 'test_count'],
'max',
fname=False),
Aggregate(['max_bll'], 'max', fname=False),
# Comment out this and all other wic aggregates because they can't be lagged
# and they're not useful for predicting poisoning
#Aggregate(lambda k: k.last_wic_date == k.address_wic_max_date,
# 'any', 'last_wic_address', fname=False),
#Aggregate(['address_wic_mother', 'address_wic_infant'], 'any', fname=False),
#Aggregate([days('address_wic_max_date', date),
# days('address_wic_min_date', date),
# days('last_wic_date', date),
# days('first_wic_date', date)],
# ['max'], ['address_wic_min_date', 'address_wic_max_date',
# 'last_wic_date', 'first_wic_date'], fname=False)
]
sample_2y = lambda k: ((k.last_sample_date - k.date_of_birth) / day >
365 * 2) | (k.max_bll >= 6)
counts = Count([np.float32(1), sample_2y], ['kid', 'kid_sample_2y'])
aggregates = [
counts,
Aggregate(['test_address_count', 'test_count', 'address_count'],
['median', 'mean', 'min', 'max']),
Count([
lambda k: k.address_test_min_date.notnull(),
lambda k: k.first_sample_date.notnull()
],
prop=True,
name=['tested_here', 'tested_ever']),
#Count(lambda k: k.first_wic_date.notnull(), prop=True, name='wic'),
#Count([lambda k: k.address_wic_min_date.notnull() & k.address_test_min_date.notnull(),
# lambda k: k.address_wic_min_date.notnull() & k.first_sample_date.notnull()],
# name=['wic_tested_here', 'wic_tested_ever'],
# prop=lambda k: k.first_wic_date.notnull(), prop_name='wic'),
Aggregate(
[
days('address_min_date', 'address_max_date'),
#days('address_wic_min_date', 'address_wic_max_date'),
days('address_test_min_date', 'address_test_max_date')
],
['mean'],
[
'address_total_time', #'address_wic_time',
'address_test_time'
]),
# the first of these are kid level, not address-kid level
# that means kids get double counted when aggregated to above the address level
# if they lived in multiple addresses on that e.g. census tract. oh well.
Aggregate([
'max_bll', 'avg_bll', 'cumulative_bll', 'avg_cumulative_bll',
'mean_bll', 'address_max_bll', 'address_mean_bll'
], ['mean', 'median', 'min', 'max']),
# ebll past, present, future, ever count the number of kids who
# moved into this address in the period defined by date and delta
# and who were poisoned before, during, after or ever relative to their time living there
Fraction(Count([
lambda k: k.first_bll6_sample_date.notnull(),
lambda k: k.first_bll10_sample_date.notnull()
], ['bll6_ever', 'bll10_ever']),
counts,
include_numerator=True),
Fraction(Count([
lambda k: k.first_bll6_sample_date > k.address_max_date,
lambda k: k.first_bll10_sample_date > k.address_max_date
], ['bll6_future', 'bll10_future']),
counts,
include_numerator=True),
Fraction(Count([
lambda k: k.first_bll6_sample_date < k.address_min_date,
lambda k: k.first_bll10_sample_date < k.address_min_date
], ['bll6_past', 'bll10_past']),
counts,
include_numerator=True),
Fraction(Count([
lambda k: k.first_bll6_sample_date.between(
k.address_min_date, k.address_max_date),
lambda k: k.first_bll10_sample_date.between(
k.address_min_date, k.address_max_date)
], ['bll6_present', 'bll10_present']),
counts,
include_numerator=True),
Aggregate('last_name', 'nunique', fname='count', astype=str)
# TODO: min_last_sample_age cutoffs
]
if delta == 'all':
aggregates.extend([
#Aggregate(days('address_wic_min_date', date), ['min', 'max'], 'days_since_wic'),
Aggregate(days('date_of_birth', date), ['min', 'max', 'mean'],
'date_of_birth'),
])
return aggregates
def get_aggregates(self, date, index, delta):
if index == 'kid':
return [
Aggregate(['address_count', 'test_count'], 'max', fname=False),
Aggregate(['max_bll'], 'max', fname=False),
Aggregate(lambda k: k.last_wic_date == k.address_wic_max_date,
'any',
'last_wic_address',
fname=False),
Aggregate(['address_wic_mother', 'address_wic_infant'],
'any',
fname=False),
Aggregate([
days('address_wic_max_date', date),
days('address_wic_min_date', date),
days('last_wic_date', date),
days('first_wic_date', date)
], ['max'], [
'address_wic_min_date', 'address_wic_max_date',
'last_wic_date', 'first_wic_date'
],
fname=False)
]
sample_2y = lambda k: ((k.last_sample_date - k.date_of_birth) / day >
365 * 2) | (k.max_bll >= 6)
counts = Count([np.float32(1), sample_2y], ['kid', 'kid_sample_2y'])
aggregates = [
counts,
Aggregate(['address_count', 'test_count'],
['median', 'mean', 'min', 'max']),
Count([
lambda k: k.address_test_min_date.notnull(),
lambda k: k.first_sample_date.notnull(),
lambda k: k.first_wic_date.notnull()
],
prop=True,
name=['tested_here', 'tested_ever', 'wic']),
Count([
lambda k: k.address_wic_min_date.notnull(
) & k.address_test_min_date.notnull(), lambda k: k.
address_wic_min_date.notnull() & k.first_sample_date.notnull()
],
name=['wic_tested_here', 'wic_tested_ever'],
parent=lambda k: k.first_wic_date.notnull()),
Aggregate([
days('address_min_date', 'address_max_date'),
days('address_wic_min_date', 'address_wic_max_date'),
days('address_test_min_date', 'address_test_max_date')
], ['mean'], [
'address_total_time', 'address_wic_time', 'address_test_time'
]),
Aggregate(
['max_bll', 'mean_bll', 'address_max_bll', 'address_mean_bll'],
['mean', 'median', 'min', 'max']),
Fraction(Count([
lambda k: k.first_bll6_sample_date.notnull(),
lambda k: k.first_bll10_sample_date.notnull()
], ['bll6_ever', 'bll10_ever']),
counts,
include_numerator=True),
Fraction(Count([
lambda k: k.first_bll6_sample_date > k.address_max_date,
lambda k: k.first_bll10_sample_date > k.address_max_date
], ['bll6_future', 'bll10_future']),
counts,
include_numerator=True),
Fraction(Count([
lambda k: k.first_bll6_sample_date < k.address_min_date,
lambda k: k.first_bll10_sample_date < k.address_min_date
], ['bll6_past', 'bll10_past']),
counts,
include_numerator=True),
Fraction(Count([
lambda k: k.first_bll6_sample_date.between(
k.address_min_date, k.address_max_date),
lambda k: k.first_bll10_sample_date.between(
k.address_min_date, k.address_max_date)
], ['bll6_present', 'bll10_present']),
counts,
include_numerator=True),
Aggregate('last_name', 'nunique', fname='count', astype=str)
# TODO: min_last_sample_age cutoffs
]
if delta == 'all':
aggregates.extend([
Aggregate(days('address_wic_min_date', date), ['min', 'max'],
'days_since_wic'),
Aggregate(days('date_of_birth', date), ['min', 'max', 'mean'],
'date_of_birth'),
])
return aggregates
def get_aggregates(self, date, index, delta):
if index == 'kid':
return [
Aggregate(['address_count', 'test_count'],
'max', fname=False),
Aggregate(['max_bll'], 'max', fname=False),
Aggregate(lambda k: k.last_wic_date == k.address_wic_max_date,
'any', 'last_wic_address', fname=False),
Aggregate(['address_wic_mother', 'address_wic_infant'], 'any', fname=False),
Aggregate([days('address_wic_max_date', date),
days('address_wic_min_date', date),
days('last_wic_date', date),
days('first_wic_date', date)],
['max'], ['address_wic_min_date', 'address_wic_max_date',
'last_wic_date', 'first_wic_date'], fname=False)
]
sample_2y = lambda k: ((k.last_sample_date - k.date_of_birth)/day > 365*2) | (k.max_bll >= 6)
counts = Count([np.float32(1), sample_2y], ['kid', 'kid_sample_2y'])
aggregates = [
counts,
Aggregate(['address_count', 'test_count'],
['median', 'mean', 'min', 'max']),
Count([lambda k: k.address_test_min_date.notnull(),
lambda k: k.first_sample_date.notnull(),
lambda k: k.first_wic_date.notnull()], prop=True,
name=['tested_here', 'tested_ever', 'wic']),
Count([lambda k: k.address_wic_min_date.notnull() & k.address_test_min_date.notnull(),
lambda k: k.address_wic_min_date.notnull() & k.first_sample_date.notnull()],
name=['wic_tested_here', 'wic_tested_ever'], parent=lambda k: k.first_wic_date.notnull()),
Aggregate([days('address_min_date', 'address_max_date'),
days('address_wic_min_date', 'address_wic_max_date'),
days('address_test_min_date', 'address_test_max_date')],
['mean'], ['address_total_time', 'address_wic_time', 'address_test_time']),
Aggregate(['max_bll', 'mean_bll', 'address_max_bll', 'address_mean_bll'],
['mean', 'median', 'min', 'max']),
Fraction(Count([lambda k: k.first_bll6_sample_date.notnull(),
lambda k: k.first_bll10_sample_date.notnull()],
['bll6_ever', 'bll10_ever']),
counts, include_numerator=True),
Fraction(Count([lambda k: k.first_bll6_sample_date > k.address_max_date,
lambda k: k.first_bll10_sample_date > k.address_max_date],
['bll6_future', 'bll10_future']),
counts, include_numerator=True),
Fraction(Count([lambda k: k.first_bll6_sample_date < k.address_min_date,
lambda k: k.first_bll10_sample_date < k.address_min_date],
['bll6_past', 'bll10_past']),
counts, include_numerator=True),
Fraction(Count([lambda k: k.first_bll6_sample_date.between(
k.address_min_date, k.address_max_date),
lambda k: k.first_bll10_sample_date.between(
k.address_min_date, k.address_max_date)],
['bll6_present', 'bll10_present']),
counts, include_numerator=True),
Aggregate('last_name', 'nunique', fname='count', astype=str)
# TODO: min_last_sample_age cutoffs
]
if delta == 'all':
aggregates.extend([
Aggregate(days('address_wic_min_date', date), ['min', 'max'], 'days_since_wic'),
Aggregate(days('date_of_birth', date), ['min', 'max', 'mean'], 'date_of_birth'),
])
return aggregates