def test_inference_by_sample():
period = pd.period_range(start=1970, periods=2, freq='T')
duplicate = pd.PeriodIndex([period[0]] * 48)
period = period.append(duplicate)
df = pd.DataFrame({'id': range(period.size), 'period': period})
inferred_variable_types = infer_variable_types(
df=df,
link_vars=["link_var"],
variable_types={},
time_index=None,
secondary_time_index={},
)
vtype = inferred_variable_types['period']
info = 'inference by sample must return categorical'
assert vtype == vtypes.Categorical, info
period = pd.period_range(start=1970, periods=5, freq='T')
df = pd.DataFrame({'id': range(period.size), 'period': period})
inferred_variable_types = infer_variable_types(
df=df,
link_vars=["link_var"],
variable_types={},
time_index=None,
secondary_time_index={},
)
vtype = inferred_variable_types['period']
info = 'inference by sample must return numeric'
assert vtype == vtypes.Numeric, info
def test_infer_variable_types():
df = pd.DataFrame({
'id': [0, 1, 2],
'category': ['a', 'b', 'a'],
'ints': ['1', '2', '1'],
'boolean': [True, False, True],
'date': ['3/11/2000', '3/12/2000', '3/13/2000'],
'integers': [1, 2, 1],
'integers_category': [1, 2, 1]
})
df['integers_category'] = df['integers_category'].astype('category')
variable_types = ['id']
inferred_variable_types = infer_variable_types(
df=df,
link_vars=[],
variable_types=variable_types,
time_index=None,
secondary_time_index={})
# Check columns' number
assert len(variable_types) + len(inferred_variable_types) == len(
df.columns)
# Check columns' types
assert inferred_variable_types['category'] == vtypes.Categorical
assert inferred_variable_types['ints'] == vtypes.Categorical
assert inferred_variable_types['boolean'] == vtypes.Boolean
assert inferred_variable_types['date'] == vtypes.Datetime
assert inferred_variable_types['integers'] == vtypes.Numeric
assert inferred_variable_types['integers_category'] == vtypes.Categorical
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]
def test_infer_variable_types_empty_df():
# test empty dataframe
empty_df = pd.DataFrame({
"id": [],
"empty_int": [],
"empty_category": [],
"empty_object": [],
"empty_date": [],
"empty_boolean": [],
})
empty_df['empty_int'] = empty_df['empty_int'].astype('int')
empty_df['empty_category'] = empty_df['empty_category'].astype('category')
empty_df['empty_object'] = empty_df['empty_object'].astype('object')
empty_df['empty_date'] = empty_df['empty_date'].astype('datetime64[ns]')
empty_df['empty_boolean'] = empty_df['empty_boolean'].astype(bool)
variable_types = {'id': vtypes.Index}
inferred_variable_types = infer_variable_types(
df=empty_df,
variable_types=variable_types,
link_vars=[],
time_index=None,
secondary_time_index={})
# Check columns' types
assert "id" not in inferred_variable_types
assert inferred_variable_types['empty_int'] == vtypes.Numeric
assert inferred_variable_types['empty_category'] == vtypes.Categorical
assert inferred_variable_types['empty_object'] == vtypes.Categorical
assert inferred_variable_types['empty_boolean'] == vtypes.Boolean
assert inferred_variable_types['empty_date'] == vtypes.Datetime
# Check columns' number
assert len(variable_types) + len(inferred_variable_types) == len(
empty_df.columns)
