Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update properties of cumulative transform primitives #320

Merged
merged 4 commits into from Nov 26, 2018
Merged

Update properties of cumulative transform primitives #320

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
12fa940
fix cum primitives. add test
kmax12 Nov 14, 2018
ab990c7
add cum min
kmax12 Nov 26, 2018
4a5c43a
Merge branch 'master' into fix-cum-primitives
kmax12 Nov 26, 2018
b7947ef
add cum count
kmax12 Nov 26, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion featuretools/primitives/cum_transform_feature.py
View file
Open in desktop
Expand Up @@ -19,7 +19,7 @@ class CumFeature(TransformPrimitive):
allow_where = True
agg_feature = None
rolling_function = True
needs_all_values = True
uses_full_entity = True

# Note: Any row with a nan value in the group by feature will have a
# NaN value in the cumfeat
Expand Down
15 changes: 15 additions & 0 deletions featuretools/tests/feature_function_tests/test_transform_features.py
View file
Open in desktop
Expand Up @@ -617,6 +617,21 @@ def test_cum_sum_use_previous_and_where_absolute(es):
assert v == cvalues[i]


def test_cum_handles_uses_full_entity(es):
def check(feature):
pandas_backend = PandasBackend(es, [feature])
df_1 = pandas_backend.calculate_all_features(instance_ids=[0, 1, 2], time_last=None)
df_2 = pandas_backend.calculate_all_features(instance_ids=[2], time_last=None)

# check that the value for instance id 2 matches
assert (df_2.loc[2] == df_1.loc[2]).all()

for primitive in [CumSum, CumMean, CumMax, CumMin]:
check(primitive(es['log']['value'], es['log']['session_id']))

check(CumCount(es['log']['id'], es['log']['session_id']))


def test_cum_mean(es):
log_value_feat = es['log']['value']
cum_mean = CumMean(log_value_feat, es['log']['session_id'])
Expand Down