def test_get_linked_vars(mock_customer):
transactions_linked_vars = get_linked_vars(mock_customer['transactions'])
assert transactions_linked_vars == ['product_id', 'session_id']
products_linked_vars = get_linked_vars(mock_customer['products'])
assert products_linked_vars == ['product_id']
sessions_linked_vars = get_linked_vars(mock_customer['sessions'])
assert sessions_linked_vars == ['session_id', 'customer_id']
customers_linked_vars = get_linked_vars(mock_customer['customers'])
assert customers_linked_vars == ['customer_id']
def test_get_linked_vars():
es = ft.demo.load_mock_customer(return_entityset=True)
transactions_linked_vars = get_linked_vars(es['transactions'])
assert transactions_linked_vars == ['product_id', 'session_id']
products_linked_vars = get_linked_vars(es['products'])
assert products_linked_vars == ['product_id']
sessions_linked_vars = get_linked_vars(es['sessions'])
assert sessions_linked_vars == ['session_id', 'customer_id']
customers_linked_vars = get_linked_vars(es['customers'])
assert customers_linked_vars == ['customer_id']
def _create_variables(self, variable_types, index, time_index, secondary_time_index):
"""Extracts the variables from a dataframe
Args:
variable_types (dict[str -> types/str/dict[str -> type]]) : An entity's
variable_types dict maps string variable ids to types (:class:`.Variable`)
or type_strings (str) or (type, kwargs) to pass keyword arguments to the Variable.
index (str): Name of index column
time_index (str or None): Name of time_index column
secondary_time_index (dict[str: [str]]): Dictionary of secondary time columns
that each map to a list of columns that depend on that secondary time
"""
variables = []
variable_types = variable_types.copy() or {}
string_to_class_map = find_variable_types()
# TODO: Remove once Text has been removed from variable types
string_to_class_map[Text.type_string] = Text
for vid in variable_types.copy():
vtype = variable_types[vid]
if isinstance(vtype, str):
if vtype in string_to_class_map:
variable_types[vid] = string_to_class_map[vtype]
else:
variable_types[vid] = string_to_class_map['unknown']
warnings.warn("Variable type {} was unrecognized, Unknown variable type was used instead".format(vtype))
if index not in variable_types:
variable_types[index] = vtypes.Index
link_vars = get_linked_vars(self)
inferred_variable_types = infer_variable_types(self.df,
link_vars,
variable_types,
time_index,
secondary_time_index)
inferred_variable_types.update(variable_types)
for v in inferred_variable_types:
# TODO document how vtype can be tuple
vtype = inferred_variable_types[v]
if isinstance(vtype, tuple):
# vtype is (ft.Variable, dict_of_kwargs)
_v = vtype[0](v, self, **vtype[1])
else:
_v = inferred_variable_types[v](v, self)
variables += [_v]
# convert data once we've inferred
self.df = convert_all_variable_data(df=self.df,
variable_types=inferred_variable_types)
# make sure index is at the beginning
index_variable = [v for v in variables
if v.id == index][0]
self.variables = [index_variable] + [v for v in variables
if v.id != index]
def _create_variables(self, variable_types, index, time_index, secondary_time_index):
"""Extracts the variables from a dataframe
Args:
variable_types (dict[str -> dict[str -> type]]) : An entity's
variable_types dict maps string variable ids to types (:class:`.Variable`)
or (type, kwargs) to pass keyword arguments to the Variable.
index (str): Name of index column
time_index (str or None): Name of time_index column
secondary_time_index (dict[str: [str]]): Dictionary of secondary time columns
that each map to a list of columns that depend on that secondary time
"""
variables = []
variable_types = variable_types or {}
if index not in variable_types:
variable_types[index] = vtypes.Index
link_vars = get_linked_vars(self)
inferred_variable_types = infer_variable_types(self.df,
link_vars,
variable_types,
time_index,
secondary_time_index)
inferred_variable_types.update(variable_types)
for v in inferred_variable_types:
# TODO document how vtype can be tuple
vtype = inferred_variable_types[v]
if isinstance(vtype, tuple):
# vtype is (ft.Variable, dict_of_kwargs)
_v = vtype[0](v, self, **vtype[1])
else:
_v = inferred_variable_types[v](v, self)
variables += [_v]
# convert data once we've inferred
self.df = convert_all_variable_data(df=self.df,
variable_types=inferred_variable_types)
# make sure index is at the beginning
index_variable = [v for v in variables
if v.id == index][0]
self.variables = [index_variable] + [v for v in variables
if v.id != index]
