def test_cum_sum_use_previous_and_where(es):
log_value_feat = es['log']['value']
compare_feat = GreaterThan(log_value_feat, 3)
# todo should this be cummean?
dfeat = Feature(es['sessions']['customer_id'], es['log'])
cum_sum = CumSum(log_value_feat,
dfeat,
where=compare_feat,
use_previous=Timedelta(3,
'observations',
entity=es['log']))
features = [cum_sum]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(instance_ids=range(15),
time_last=None)
cum_sum_values = [0, 5, 15, 30, 45, 45, 45, 45, 45, 45, 0, 5, 5, 12, 26]
cvalues = df[cum_sum.get_name()].values
assert len(cvalues) == 15
for i, v in enumerate(cum_sum_values):
assert v == cvalues[i]
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'])
feature_matrix = calculate_feature_matrix(
[sess_to_cust, agg_feat],
instance_ids=[0, 2],
approximate=Timedelta(10, 's'),
cutoff_time=[
datetime(2011, 4, 9, 10, 31, 19),
datetime(2011, 4, 9, 11, 0, 0)
])
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_training_window(entityset):
property_feature = Count(entityset['log']['id'], entityset['customers'])
top_level_agg = Count(entityset['customers']['id'], entityset[u'régions'])
# make sure features that have a direct to a higher level agg
# so we have multiple "filter eids" in get_pandas_data_slice,
# and we go through the loop to pull data with a training_window param more than once
dagg = DirectFeature(top_level_agg, entityset['customers'])
# for now, warns if last_time_index not present
feature_matrix = calculate_feature_matrix([property_feature, dagg],
entityset,
instance_ids=[0, 1, 2],
cutoff_time=[datetime(2011, 4, 9, 12, 31),
datetime(2011, 4, 10, 11),
datetime(2011, 4, 10, 13, 10, 1)],
training_window='2 hours')
entityset.add_last_time_indexes()
with pytest.raises(AssertionError):
feature_matrix = calculate_feature_matrix([property_feature],
entityset,
instance_ids=[0, 1, 2],
cutoff_time=[datetime(2011, 4, 9, 12, 31),
datetime(2011, 4, 10, 11),
datetime(2011, 4, 10, 13, 10, 1)],
training_window=Timedelta(2, 'observations', entity='log'))
feature_matrix = calculate_feature_matrix([property_feature, dagg],
entityset,
instance_ids=[0, 1, 2, 4],
cutoff_time=[datetime(2011, 4, 9, 12, 31),
datetime(2011, 4, 10, 11),
datetime(2011, 4, 10, 13, 10, 1)],
training_window='2 hours')
prop_values = [5, 5, 1]
dagg_values = [3, 2, 1]
assert (feature_matrix[property_feature.get_name()] == prop_values).values.all()
assert (feature_matrix[dagg.get_name()] == dagg_values).values.all()
def test_make_agg_feat_using_prev_time(es):
agg_feat = ft.Feature(es['log']['id'],
parent_entity=es['sessions'],
use_previous=Timedelta(10, 's'),
primitive=Count)
feature_set = FeatureSet([agg_feat])
calculator = FeatureSetCalculator(es,
time_last=datetime(2011, 4, 9, 10, 30, 10),
feature_set=feature_set)
df = calculator.run(np.array([0]))
v = df[agg_feat.get_name()][0]
assert (v == 2)
calculator = FeatureSetCalculator(es,
time_last=datetime(2011, 4, 9, 10, 30, 30),
feature_set=feature_set)
df = calculator.run(np.array([0]))
v = df[agg_feat.get_name()][0]
assert (v == 1)
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],
entityset,
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],
entityset,
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],
entityset,
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],
entityset,
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()
