def test_encode_features_topn(entityset):
topn = Feature(entityset['log']['product_id'],
parent_entity=entityset['customers'],
primitive=NMostCommon(n=3))
features, feature_defs = dfs(entityset=entityset,
instance_ids=[0, 1, 2],
target_entity="customers",
agg_primitives=[NMostCommon(n=3)])
features_enc, feature_defs_enc = encode_features(features,
feature_defs,
include_unknown=True)
assert topn.hash() in [feat.hash() for feat in feature_defs_enc]
for name in topn.get_feature_names():
assert name in features_enc.columns
def test_encode_features_topn(pd_es):
topn = Feature(Feature(pd_es['log'].ww['product_id']),
parent_dataframe_name='customers',
primitive=NMostCommon(n=3))
features, feature_defs = dfs(entityset=pd_es,
instance_ids=[0, 1, 2],
target_dataframe_name="customers",
agg_primitives=[NMostCommon(n=3)])
features_enc, feature_defs_enc = encode_features(features,
feature_defs,
include_unknown=True)
assert topn.unique_name() in [
feat.unique_name() for feat in feature_defs_enc
]
for name in topn.get_feature_names():
assert name in features_enc.columns
assert features_enc.columns.tolist().count(name) == 1