def _make_entity_set(self, X):
"""Helper method that creates and returns the entity set given the input data"""
ft_es = EntitySet()
if self.index not in X.columns:
es = ft_es.entity_from_dataframe(entity_id="X", dataframe=X, index=self.index, make_index=True)
else:
es = ft_es.entity_from_dataframe(entity_id="X", dataframe=X, index=self.index)
return es
def test_encode_unknown_features():
# Dataframe with categorical column with "unknown" string
df = pd.DataFrame({'category': ['unknown', 'b', 'c', 'd', 'e']})
es = EntitySet('test')
es.entity_from_dataframe(entity_id='a', dataframe=df, index='index', make_index=True)
features, feature_defs = dfs(entityset=es, target_entity='a')
# Specify unknown token for replacement
features_enc, feature_defs_enc = encode_features(features, feature_defs,
include_unknown=True)
assert list(features_enc.columns) == ['category = unknown', 'category = e', 'category = d',
'category = c', 'category = b', 'category is unknown']
def test_encode_unknown_features():
# Dataframe with categorical column with "unknown" string
df = pd.DataFrame({'category': ['unknown', 'b', 'c', 'd', 'e']})
es = EntitySet('test')
es.entity_from_dataframe(entity_id='a', dataframe=df, index='index', make_index=True)
features, feature_defs = dfs(entityset=es, target_entity='a')
# Specify unknown token for replacement
features_enc, feature_defs_enc = encode_features(features, feature_defs,
include_unknown=True)
assert list(features_enc.columns) == ['category = unknown', 'category = e', 'category = d',
'category = c', 'category = b', 'category is unknown']
def test_encode_features_drop_first():
df = pd.DataFrame({'category': ['ao', 'b', 'c', 'd', 'e']})
es = EntitySet('test')
es.entity_from_dataframe(entity_id='a', dataframe=df, index='index', make_index=True)
features, feature_defs = dfs(entityset=es, target_entity='a')
features_enc, feature_defs_enc = encode_features(features, feature_defs,
drop_first=True, include_unknown=False)
assert len(features_enc.columns) == 4
features_enc, feature_defs = encode_features(features, feature_defs, top_n=3, drop_first=True,
include_unknown=False)
assert len(features_enc.columns) == 2
def test_cfm_approximate_correct_ordering():
trips = {
'trip_id': [i for i in range(1000)],
'flight_time': [datetime(1998, 4, 2) for i in range(350)] + [datetime(1997, 4, 3) for i in range(650)],
'flight_id': [randint(1, 25) for i in range(1000)],
'trip_duration': [randint(1, 999) for i in range(1000)]
}
df = pd.DataFrame.from_dict(trips)
es = EntitySet('flights')
es.entity_from_dataframe("trips",
dataframe=df,
index="trip_id",
time_index='flight_time')
es.normalize_entity(base_entity_id="trips",
new_entity_id="flights",
index="flight_id",
make_time_index=True)
features = dfs(entityset=es, target_entity='trips', features_only=True)
flight_features = [feature for feature in features
if isinstance(feature, DirectFeature) and
isinstance(feature.base_features[0],
AggregationPrimitive)]
property_feature = IdentityFeature(es['trips']['trip_id'])
# direct_agg_feat = DirectFeature(Sum(es['trips']['trip_duration'],
# es['flights']),
# es['trips'])
cutoff_time = pd.DataFrame.from_dict({'instance_id': df['trip_id'],
'time': df['flight_time']})
time_feature = IdentityFeature(es['trips']['flight_time'])
feature_matrix = calculate_feature_matrix(flight_features + [property_feature, time_feature],
cutoff_time_in_index=True,
cutoff_time=cutoff_time)
feature_matrix.index.names = ['instance', 'time']
assert(np.all(feature_matrix.reset_index('time').reset_index()[['instance', 'time']].values == feature_matrix[['trip_id', 'flight_time']].values))
feature_matrix_2 = calculate_feature_matrix(flight_features + [property_feature, time_feature],
cutoff_time=cutoff_time,
cutoff_time_in_index=True,
approximate=Timedelta(2, 'd'))
feature_matrix_2.index.names = ['instance', 'time']
assert(np.all(feature_matrix_2.reset_index('time').reset_index()[['instance', 'time']].values == feature_matrix_2[['trip_id', 'flight_time']].values))
for column in feature_matrix:
for x, y in zip(feature_matrix[column], feature_matrix_2[column]):
if not ((pd.isnull(x) and pd.isnull(y)) or (x == y)):
import pdb
pdb.set_trace()
assert ((pd.isnull(x) and pd.isnull(y)) or (x == y))
def test_serialization(es):
dirname = os.path.dirname(integration_data.__file__)
path = os.path.join(dirname, 'test_entityset.p')
if os.path.exists(path):
shutil.rmtree(path)
es.to_pickle(path)
new_es = EntitySet.read_pickle(path)
assert es.__eq__(new_es, deep=True)
shutil.rmtree(path)
def test_raise_key_error_missing_entity(es):
error_text = "Entity this entity doesn't exist does not exist in ecommerce"
with pytest.raises(KeyError, match=error_text):
es["this entity doesn't exist"]
es_without_id = EntitySet()
error_text = "Entity this entity doesn't exist does not exist in entity set"
with pytest.raises(KeyError, match=error_text):
es_without_id["this entity doesn't exist"]
def test_serialization(es):
dirname = os.path.dirname(integration_data.__file__)
path = os.path.join(dirname, 'test_entityset.p')
if os.path.exists(path):
shutil.rmtree(path)
es.to_pickle(path)
new_es = EntitySet.read_pickle(path)
assert es.__eq__(new_es, deep=True)
shutil.rmtree(path)
def test_raise_key_error_missing_dataframe(es):
error_text = "DataFrame testing does not exist in ecommerce"
with pytest.raises(KeyError, match=error_text):
es["testing"]
es_without_id = EntitySet()
error_text = "DataFrame testing does not exist in entity set"
with pytest.raises(KeyError, match=error_text):
es_without_id["testing"]
def test_encode_features_drop_first():
df = pd.DataFrame({"category": ["ao", "b", "c", "d", "e"]}).astype(
{"category": "category"}
)
pd_es = EntitySet("test")
pd_es.add_dataframe(
dataframe_name="a", dataframe=df, index="index", make_index=True
)
features, feature_defs = dfs(entityset=pd_es, target_dataframe_name="a")
features_enc, _ = encode_features(
features, feature_defs, drop_first=True, include_unknown=False
)
assert len(features_enc.columns) == 4
features_enc, feature_defs = encode_features(
features, feature_defs, top_n=3, drop_first=True, include_unknown=False
)
assert len(features_enc.columns) == 2
def test_encode_features_matches_calculate_feature_matrix():
df = pd.DataFrame({"category": ["b", "c", "d", "e"]}).astype(
{"category": "category"}
)
pd_es = EntitySet("test")
pd_es.add_dataframe(
dataframe_name="a", dataframe=df, index="index", make_index=True
)
features, feature_defs = dfs(entityset=pd_es, target_dataframe_name="a")
features_enc, feature_defs_enc = encode_features(
features, feature_defs, to_encode=["category"]
)
features_calc = calculate_feature_matrix(feature_defs_enc, entityset=pd_es)
pd.testing.assert_frame_equal(features_enc, features_calc)
assert features_calc.ww._schema == features_enc.ww._schema
def test_encode_features_matches_calculate_feature_matrix():
df = pd.DataFrame({'category': ['b', 'c', 'd', 'e']})
pd_es = EntitySet('test')
pd_es.entity_from_dataframe(entity_id='a',
dataframe=df,
index='index',
make_index=True)
features, feature_defs = dfs(entityset=pd_es, target_entity='a')
features_enc, feature_defs_enc = encode_features(features,
feature_defs,
to_encode=['category'])
features_calc = calculate_feature_matrix(feature_defs_enc, entityset=pd_es)
assert features_enc['category = e'].dtypes == bool
assert features_enc['category = e'].dtypes == features_calc[
'category = e'].dtypes
def test_encode_features_matches_calculate_feature_matrix():
df = pd.DataFrame({
'category': ['b', 'c', 'd', 'e']
}).astype({'category': 'category'})
pd_es = EntitySet('test')
pd_es.add_dataframe(dataframe_name='a',
dataframe=df,
index='index',
make_index=True)
features, feature_defs = dfs(entityset=pd_es, target_dataframe_name='a')
features_enc, feature_defs_enc = encode_features(features,
feature_defs,
to_encode=['category'])
features_calc = calculate_feature_matrix(feature_defs_enc, entityset=pd_es)
pd.testing.assert_frame_equal(features_enc, features_calc)
assert features_calc.ww._schema == features_enc.ww._schema
def main():
holding = Holding(
'HDFCBANK', Price('buy', 97.89), 5, 112.1, 95.4
)
print(holding.to_json())
es = EntitySet('user').entity_from_dataframe(
entity_id='parent', dataframe=pd.DataFrame({
'id': [10, 14, 24, 34, 54, 64, 84, ],
'age': [10, 14, 24, 34, 54, 64, 84, ],
'salary': [1, 1, 10000, 25000, 50000, 60000, 80000, ]
}))
es.entity_from_dataframe(
entity_id='child', dataframe=pd.DataFrame({
'id': [10, 14, 24, 34, 54, 64, 84, ],
'user_id': [10, 14, 24, 34, 54, 64, 84, ],
'sex': [0, 1, 0, 1, 1, 0, 1]
}))
es.add_relationship(
Relationship(
es['parent']['id'],
es['child']['user_id']
)
)
es.entity_from_dataframe(
entity_id='child_0', dataframe=pd.DataFrame({
'id': [10, 14, 24, 34, 54, 64, 84, ],
'user_id': [10, 14, 24, 34, 54, 64, 84, ],
'diet': [0, 1, 0, 1, 1, 0, 1]
}))
es.add_relationship(
Relationship(
es['parent']['id'],
es['child_0']['user_id']
)
)
# print(es)
e_s = CustomEntity(entity_set=es)
print(e_s.to_json())
def test_encode_unknown_features():
# Dataframe with categorical column with "unknown" string
df = pd.DataFrame({"category": ["unknown", "b", "c", "d", "e"]}).astype(
{"category": "category"}
)
pd_es = EntitySet("test")
pd_es.add_dataframe(
dataframe_name="a", dataframe=df, index="index", make_index=True
)
features, feature_defs = dfs(entityset=pd_es, target_dataframe_name="a")
# Specify unknown token for replacement
features_enc, _ = encode_features(features, feature_defs, include_unknown=True)
assert list(features_enc.columns) == [
"category = unknown",
"category = e",
"category = d",
"category = c",
"category = b",
"category is unknown",
]
def test_cfm_approximate_correct_ordering():
trips = {
'trip_id': [i for i in range(1000)],
'flight_time':
[datetime(1998, 4, 2)
for i in range(350)] + [datetime(1997, 4, 3) for i in range(650)],
'flight_id': [randint(1, 25) for i in range(1000)],
'trip_duration': [randint(1, 999) for i in range(1000)]
}
df = pd.DataFrame.from_dict(trips)
es = EntitySet('flights')
es.entity_from_dataframe("trips",
dataframe=df,
index="trip_id",
time_index='flight_time')
es.normalize_entity(base_entity_id="trips",
new_entity_id="flights",
index="flight_id",
make_time_index=True)
features = dfs(entityset=es, target_entity='trips', features_only=True)
flight_features = [
feature for feature in features if isinstance(feature, DirectFeature)
and isinstance(feature.base_features[0], AggregationPrimitive)
]
property_feature = IdentityFeature(es['trips']['trip_id'])
# direct_agg_feat = DirectFeature(Sum(es['trips']['trip_duration'],
# es['flights']),
# es['trips'])
cutoff_time = pd.DataFrame.from_dict({
'instance_id': df['trip_id'],
'time': df['flight_time']
})
time_feature = IdentityFeature(es['trips']['flight_time'])
feature_matrix = calculate_feature_matrix(flight_features +
[property_feature, time_feature],
es,
cutoff_time_in_index=True,
cutoff_time=cutoff_time)
feature_matrix.index.names = ['instance', 'time']
assert (np.all(
feature_matrix.reset_index('time').reset_index()[['instance', 'time']].
values == feature_matrix[['trip_id', 'flight_time']].values))
feature_matrix_2 = calculate_feature_matrix(
flight_features + [property_feature, time_feature],
es,
cutoff_time=cutoff_time,
cutoff_time_in_index=True,
approximate=Timedelta(2, 'd'))
feature_matrix_2.index.names = ['instance', 'time']
assert (np.all(
feature_matrix_2.reset_index('time').reset_index()[[
'instance', 'time'
]].values == feature_matrix_2[['trip_id', 'flight_time']].values))
for column in feature_matrix:
for x, y in zip(feature_matrix[column], feature_matrix_2[column]):
if not ((pd.isnull(x) and pd.isnull(y)) or (x == y)):
import pdb
pdb.set_trace()
assert ((pd.isnull(x) and pd.isnull(y)) or (x == y))
def test_encode_features_drop_first():
df = pd.DataFrame({
'category': ['ao', 'b', 'c', 'd', 'e']
}).astype({'category': 'category'})
pd_es = EntitySet('test')
pd_es.add_dataframe(dataframe_name='a',
dataframe=df,
index='index',
make_index=True)
features, feature_defs = dfs(entityset=pd_es, target_dataframe_name='a')
features_enc, _ = encode_features(features,
feature_defs,
drop_first=True,
include_unknown=False)
assert len(features_enc.columns) == 4
features_enc, feature_defs = encode_features(features,
feature_defs,
top_n=3,
drop_first=True,
include_unknown=False)
assert len(features_enc.columns) == 2
