def test_make_agg_feat_using_prev_n_events(entityset, backend):
agg_feat_1 = Min(entityset['log']['value'],
parent_entity=entityset['sessions'],
use_previous=Timedelta(1,
'observations',
entity=entityset['log']))
agg_feat_2 = Min(entityset['log']['value'],
parent_entity=entityset['sessions'],
use_previous=Timedelta(3,
'observations',
entity=entityset['log']))
assert agg_feat_1.get_name() != agg_feat_2.get_name(), \
'Features should have different names based on use_previous'
pandas_backend = backend([agg_feat_1, agg_feat_2])
df = pandas_backend.calculate_all_features(instance_ids=[0],
time_last=datetime(
2011, 4, 9, 10, 30, 6))
# time_last is included by default
v1 = df[agg_feat_1.get_name()][0]
v2 = df[agg_feat_2.get_name()][0]
assert v1 == 5
assert v2 == 0
df = pandas_backend.calculate_all_features(instance_ids=[0],
time_last=datetime(
2011, 4, 9, 10, 30, 30))
v1 = df[agg_feat_1.get_name()][0]
v2 = df[agg_feat_2.get_name()][0]
assert v1 == 20
assert v2 == 10
def test_make_agg_feat_using_prev_n_events(entityset, backend):
agg_feat_1 = Min(entityset['log']['value'],
parent_entity=entityset['sessions'],
use_previous=Timedelta(1, 'observations',
entity=entityset['log']))
agg_feat_2 = Min(entityset['log']['value'],
parent_entity=entityset['sessions'],
use_previous=Timedelta(3, 'observations',
entity=entityset['log']))
assert agg_feat_1.get_name() != agg_feat_2.get_name(), \
'Features should have different names based on use_previous'
pandas_backend = backend([agg_feat_1, agg_feat_2])
df = pandas_backend.calculate_all_features(instance_ids=[0],
time_last=datetime(2011, 4, 9, 10, 30, 6))
# time_last is included by default
v1 = df[agg_feat_1.get_name()][0]
v2 = df[agg_feat_2.get_name()][0]
assert v1 == 5
assert v2 == 0
df = pandas_backend.calculate_all_features(instance_ids=[0],
time_last=datetime(2011, 4, 9, 10, 30, 30))
v1 = df[agg_feat_1.get_name()][0]
v2 = df[agg_feat_2.get_name()][0]
assert v1 == 20
assert v2 == 10
def test_uses_full_entity_feat_of_approximate(entityset):
es = entityset
agg_feat = Sum(es['log']['value'], es['sessions'])
agg_feat2 = Sum(agg_feat, es['customers'])
agg_feat3 = Min(agg_feat, es['customers'])
dfeat = DirectFeature(agg_feat2, es['sessions'])
dfeat2 = DirectFeature(agg_feat3, es['sessions'])
p = Percentile(dfeat)
# only dfeat2 should be approximated
# because Percentile needs all values
feature_matrix_only_dfeat2 = calculate_feature_matrix(
[dfeat2],
instance_ids=[0, 2],
approximate=Timedelta(10, 's'),
cutoff_time_in_index=True,
cutoff_time=[
datetime(2011, 4, 9, 10, 31, 19),
datetime(2011, 4, 9, 11, 0, 0)
])
assert feature_matrix_only_dfeat2[dfeat2.get_name()].tolist() == [1, 0]
feature_matrix_approx = calculate_feature_matrix(
[p, dfeat, dfeat2, agg_feat],
instance_ids=[0, 2],
approximate=Timedelta(10, 's'),
cutoff_time_in_index=True,
cutoff_time=[
datetime(2011, 4, 9, 10, 31, 19),
datetime(2011, 4, 9, 11, 0, 0)
])
assert feature_matrix_only_dfeat2[dfeat2.get_name()].tolist(
) == feature_matrix_approx[dfeat2.get_name()].tolist()
feature_matrix_small_approx = calculate_feature_matrix(
[p, dfeat, dfeat2, agg_feat],
instance_ids=[0, 2],
approximate=Timedelta(10, 'ms'),
cutoff_time_in_index=True,
cutoff_time=[
datetime(2011, 4, 9, 10, 31, 19),
datetime(2011, 4, 9, 11, 0, 0)
])
feature_matrix_no_approx = calculate_feature_matrix(
[p, dfeat, dfeat2, agg_feat],
instance_ids=[0, 2],
cutoff_time_in_index=True,
cutoff_time=[
datetime(2011, 4, 9, 10, 31, 19),
datetime(2011, 4, 9, 11, 0, 0)
])
for f in [p, dfeat, agg_feat]:
for fm1, fm2 in combinations([
feature_matrix_approx, feature_matrix_small_approx,
feature_matrix_no_approx
], 2):
assert fm1[f.get_name()].tolist() == fm2[f.get_name()].tolist()
def test_approx_base_feature_is_also_first_class_feature(entityset):
es = entityset
log_to_products = DirectFeature(es['products']['rating'], es['log'])
# This should still be computed properly
agg_feat = Min(log_to_products, es['sessions'])
customer_agg_feat = Sum(agg_feat, es['customers'])
# This is to be approximated
sess_to_cust = DirectFeature(customer_agg_feat, es['sessions'])
times = [datetime(2011, 4, 9, 10, 31, 19), datetime(2011, 4, 9, 11, 0, 0)]
cutoff_time = pd.DataFrame({'time': times, 'instance_id': [0, 2]})
feature_matrix = calculate_feature_matrix([sess_to_cust, agg_feat],
entityset,
approximate=Timedelta(10, 's'),
cutoff_time=cutoff_time)
vals1 = feature_matrix[sess_to_cust.get_name()].tolist()
assert vals1 == [8.5, 7]
vals2 = feature_matrix[agg_feat.get_name()].tolist()
assert vals2 == [4, 1.5]
def test_approx_base_feature_is_also_first_class_feature(entityset):
es = entityset
log_to_products = DirectFeature(es['products']['rating'], es['log'])
# This should still be computed properly
agg_feat = Min(log_to_products, es['sessions'])
customer_agg_feat = Sum(agg_feat, es['customers'])
# This is to be approximated
sess_to_cust = DirectFeature(customer_agg_feat, es['sessions'])
times = [datetime(2011, 4, 9, 10, 31, 19), datetime(2011, 4, 9, 11, 0, 0)]
cutoff_time = pd.DataFrame({'time': times, 'instance_id': [0, 2]})
feature_matrix = calculate_feature_matrix([sess_to_cust, agg_feat],
entityset,
approximate=Timedelta(10, 's'),
cutoff_time=cutoff_time)
vals1 = feature_matrix[sess_to_cust.get_name()].tolist()
assert vals1 == [8.5, 7]
vals2 = feature_matrix[agg_feat.get_name()].tolist()
assert vals2 == [4, 1.5]
