def test_init_and_name(es):
log = es['log']
rating = ft.Feature(es["products"]["rating"], es["log"])
features = [ft.Feature(v) for v in log.variables] +\
[ft.Feature(rating, primitive=GreaterThanScalar(2.5))]
# Add Timedelta feature
# features.append(pd.Timestamp.now() - ft.Feature(log['datetime']))
for transform_prim in get_transform_primitives().values():
# skip automated testing if a few special cases
if transform_prim in [NotEqual, Equal]:
continue
# use the input_types matching function from DFS
input_types = transform_prim.input_types
if type(input_types[0]) == list:
matching_inputs = match(input_types[0], features)
else:
matching_inputs = match(input_types, features)
if len(matching_inputs) == 0:
raise Exception("Transform Primitive %s not tested" %
transform_prim.name)
for s in matching_inputs:
instance = ft.Feature(s, primitive=transform_prim)
# try to get name and calculate
instance.get_name()
ft.calculate_feature_matrix([instance], entityset=es).head(5)
def test_init_and_name(es):
log = es['log']
features = [Feature(v) for v in log.variables] +\
[GreaterThan(Feature(es["products"]["rating"], es["log"]), 2.5)]
# Add Timedelta feature
features.append(pd.Timestamp.now() - Feature(log['datetime']))
for transform_prim in get_transform_primitives():
if issubclass(transform_prim, Compare):
continue
# use the input_types matching function from DFS
input_types = transform_prim.input_types
if type(input_types[0]) == list:
matching_inputs = [
g for s in input_types for g in match(s, features)
]
else:
matching_inputs = match(input_types, features)
if len(matching_inputs) == 0:
raise Exception("Transform Primitive %s not tested" %
transform_prim.name)
for s in matching_inputs:
instance = transform_prim(*s)
# try to get name and calculate
instance.get_name()
instance.head()
def test_init_and_name(es):
log = es['log']
features = [Feature(v) for v in log.variables] +\
[GreaterThan(Feature(es["products"]["rating"], es["log"]), 2.5)]
# Add Timedelta feature
features.append(pd.Timestamp.now() - Feature(log['datetime']))
for transform_prim in get_transform_primitives().values():
if issubclass(transform_prim, Compare):
continue
# use the input_types matching function from DFS
input_types = transform_prim.input_types
if type(input_types[0]) == list:
matching_inputs = [g for s in input_types
for g in match(s, features)]
else:
matching_inputs = match(input_types, features)
if len(matching_inputs) == 0:
raise Exception(
"Transform Primitive %s not tested" % transform_prim.name)
for s in matching_inputs:
instance = transform_prim(*s)
# try to get name and calculate
instance.get_name()
instance.head()
def test_init_and_name(es):
log = es['log']
rating = ft.Feature(ft.IdentityFeature(es["products"].ww["rating"]), "log")
log_features = [ft.Feature(es['log'].ww[col]) for col in log.columns] +\
[ft.Feature(rating, primitive=GreaterThanScalar(2.5)),
ft.Feature(rating, primitive=GreaterThanScalar(3.5))]
# Add Timedelta feature
# features.append(pd.Timestamp.now() - ft.Feature(log['datetime']))
customers_features = [
ft.Feature(es["customers"].ww[col]) for col in es["customers"].columns
]
# check all transform primitives have a name
for attribute_string in dir(ft.primitives):
attr = getattr(ft.primitives, attribute_string)
if isclass(attr):
if issubclass(attr,
TransformPrimitive) and attr != TransformPrimitive:
assert getattr(attr, "name") is not None
trans_primitives = get_transform_primitives().values()
# If Dask EntitySet use only Dask compatible primitives
if es.dataframe_type == Library.DASK.value:
trans_primitives = [
prim for prim in trans_primitives
if Library.DASK in prim.compatibility
]
if es.dataframe_type == Library.KOALAS.value:
trans_primitives = [
prim for prim in trans_primitives
if Library.KOALAS in prim.compatibility
]
for transform_prim in trans_primitives:
# skip automated testing if a few special cases
features_to_use = log_features
if transform_prim in [NotEqual, Equal]:
continue
if transform_prim in [Age]:
features_to_use = customers_features
# use the input_types matching function from DFS
input_types = transform_prim.input_types
if type(input_types[0]) == list:
matching_inputs = match(input_types[0], features_to_use)
else:
matching_inputs = match(input_types, features_to_use)
if len(matching_inputs) == 0:
raise Exception("Transform Primitive %s not tested" %
transform_prim.name)
for prim in matching_inputs:
instance = ft.Feature(prim, primitive=transform_prim)
# try to get name and calculate
instance.get_name()
ft.calculate_feature_matrix([instance], entityset=es)
def test_init_and_name(es):
session = es['sessions']
log = es['log']
features = [ft.Feature(v) for v in log.variables]
for agg_prim in get_aggregation_primitives().values():
input_types = agg_prim.input_types
if type(input_types[0]) != list:
input_types = [input_types]
# test each allowed input_types for this primitive
for it in input_types:
# use the input_types matching function from DFS
matching_types = match(it, features)
if len(matching_types) == 0:
raise Exception("Agg Primitive %s not tested" % agg_prim.name)
for t in matching_types:
instance = ft.Feature(t,
parent_entity=session,
primitive=agg_prim)
# try to get name and calculate
instance.get_name()
ft.calculate_feature_matrix([instance], entityset=es).head(5)
def test_init_and_name(es):
log = es['log']
rating = ft.Feature(es["products"]["rating"], es["log"])
log_features = [ft.Feature(v) for v in log.variables] +\
[ft.Feature(rating, primitive=GreaterThanScalar(2.5))]
# Add Timedelta feature
# features.append(pd.Timestamp.now() - ft.Feature(log['datetime']))
customers_features = [ft.Feature(v) for v in es["customers"].variables]
trans_primitives = get_transform_primitives().values()
# If Dask EntitySet use only Dask compatible primitives
if isinstance(es['log'].df, dd.DataFrame):
trans_primitives = [
prim for prim in trans_primitives
if Library.DASK in prim.compatibility
]
if ks and isinstance(es['log'].df, ks.DataFrame):
trans_primitives = [
prim for prim in trans_primitives
if Library.KOALAS in prim.compatibility
]
for transform_prim in trans_primitives:
# skip automated testing if a few special cases
features_to_use = log_features
if transform_prim in [NotEqual, Equal]:
continue
if transform_prim in [Age]:
features_to_use = customers_features
# use the input_types matching function from DFS
input_types = transform_prim.input_types
if type(input_types[0]) == list:
matching_inputs = match(input_types[0], features_to_use)
else:
matching_inputs = match(input_types, features_to_use)
if len(matching_inputs) == 0:
raise Exception("Transform Primitive %s not tested" %
transform_prim.name)
for prim in matching_inputs:
instance = ft.Feature(prim, primitive=transform_prim)
# try to get name and calculate
instance.get_name()
ft.calculate_feature_matrix([instance], entityset=es)
def test_init_and_name(es):
log = es['log']
# Add a BooleanNullable column so primitives with that input type get tested
boolean_nullable = log.ww['purchased']
boolean_nullable = boolean_nullable.ww.set_logical_type('BooleanNullable')
log.ww['boolean_nullable'] = boolean_nullable
features = [ft.Feature(es['log'].ww[col]) for col in log.columns]
# check all primitives have name
for attribute_string in dir(ft.primitives):
attr = getattr(ft.primitives, attribute_string)
if isclass(attr):
if issubclass(
attr,
AggregationPrimitive) and attr != AggregationPrimitive:
assert getattr(attr, "name") is not None
agg_primitives = get_aggregation_primitives().values()
# If Dask EntitySet use only Dask compatible primitives
if es.dataframe_type == Library.DASK.value:
agg_primitives = [
prim for prim in agg_primitives
if Library.DASK in prim.compatibility
]
if es.dataframe_type == Library.KOALAS.value:
agg_primitives = [
prim for prim in agg_primitives
if Library.KOALAS in prim.compatibility
]
for agg_prim in agg_primitives:
input_types = agg_prim.input_types
if type(input_types[0]) != list:
input_types = [input_types]
# test each allowed input_types for this primitive
for it in input_types:
# use the input_types matching function from DFS
matching_types = match(it, features)
if len(matching_types) == 0:
raise Exception("Agg Primitive %s not tested" % agg_prim.name)
for t in matching_types:
instance = ft.Feature(t,
parent_dataframe_name='sessions',
primitive=agg_prim)
# try to get name and calculate
instance.get_name()
ft.calculate_feature_matrix([instance], entityset=es)
def test_init_and_name(es):
from featuretools import calculate_feature_matrix
log = es['log']
features = [Feature(v) for v in log.variables] +\
[GreaterThan(Feature(es["products"]["rating"], es["log"]), 2.5)]
# Add Timedelta feature
features.append(pd.Timestamp.now() - Feature(log['datetime']))
for transform_prim in get_transform_primitives().values():
# use the input_types matching function from DFS
input_types = transform_prim.input_types
if type(input_types[0]) == list:
matching_inputs = match(input_types[0], features)
else:
matching_inputs = match(input_types, features)
if len(matching_inputs) == 0:
raise Exception("Transform Primitive %s not tested" %
transform_prim.name)
for s in matching_inputs:
instance = transform_prim(*s)
# try to get name and calculate
instance.get_name()
calculate_feature_matrix([instance], entityset=es).head(5)
def test_init_and_name(es):
from featuretools import calculate_feature_matrix
log = es['log']
features = [Feature(v) for v in log.variables] +\
[GreaterThan(Feature(es["products"]["rating"], es["log"]), 2.5)]
# Add Timedelta feature
features.append(pd.Timestamp.now() - Feature(log['datetime']))
for transform_prim in get_transform_primitives().values():
# use the input_types matching function from DFS
input_types = transform_prim.input_types
if type(input_types[0]) == list:
matching_inputs = match(input_types[0], features)
else:
matching_inputs = match(input_types, features)
if len(matching_inputs) == 0:
raise Exception(
"Transform Primitive %s not tested" % transform_prim.name)
for s in matching_inputs:
instance = transform_prim(*s)
# try to get name and calculate
instance.get_name()
calculate_feature_matrix([instance], entityset=es).head(5)
def test_init_and_name(es):
session = es['sessions']
log = es['log']
features = [Feature(v) for v in log.variables]
for agg_prim in get_aggregation_primitives().values():
input_types = agg_prim.input_types
if type(input_types[0]) != list:
input_types = [input_types]
# test each allowed input_types for this primitive
for it in input_types:
# use the input_types matching function from DFS
matching_types = match(it, features)
if len(matching_types) == 0:
raise Exception("Agg Primitive %s not tested" % agg_prim.name)
for t in matching_types:
instance = agg_prim(t, parent_entity=session)
# try to get name and calculate
instance.get_name()
ft.calculate_feature_matrix([instance], entityset=es).head(5)
def test_init_and_name(es):
session = es['sessions']
log = es['log']
features = [ft.Feature(v) for v in log.variables]
agg_primitives = get_aggregation_primitives().values()
# If Dask EntitySet use only Dask compatible primitives
if isinstance(es['sessions'].df, dd.DataFrame):
agg_primitives = [
prim for prim in agg_primitives
if Library.DASK in prim.compatibility
]
if ks and isinstance(es['sessions'].df, ks.DataFrame):
agg_primitives = [
prim for prim in agg_primitives
if Library.KOALAS in prim.compatibility
]
for agg_prim in agg_primitives:
input_types = agg_prim.input_types
if type(input_types[0]) != list:
input_types = [input_types]
# test each allowed input_types for this primitive
for it in input_types:
# use the input_types matching function from DFS
matching_types = match(it, features)
if len(matching_types) == 0:
raise Exception("Agg Primitive %s not tested" % agg_prim.name)
for t in matching_types:
instance = ft.Feature(t,
parent_entity=session,
primitive=agg_prim)
# try to get name and calculate
instance.get_name()
ft.calculate_feature_matrix([instance], entityset=es)
