def test_convert_all_variable_data():
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],
'latlong': [np.nan, (10, 4), (np.nan, 4)]
})
variable_types = {
'id': vtypes.Numeric,
'category': vtypes.Categorical,
'ints': vtypes.Numeric,
'boolean': vtypes.Boolean,
'date': vtypes.Datetime,
'integers': vtypes.Numeric,
'latlong': vtypes.LatLong
}
df = convert_all_variable_data(df, variable_types)
assert df['id'].dtype.name in vtypes.PandasTypes._pandas_numerics
assert df['category'].dtype.name == 'object'
assert df['ints'].dtype.name in vtypes.PandasTypes._pandas_numerics
assert df['boolean'].dtype.name == 'bool'
assert df['date'].dtype.name in vtypes.PandasTypes._pandas_datetimes
assert df['integers'].dtype.name in vtypes.PandasTypes._pandas_numerics
# confirm `nan` value in latlong is replaced by `(nan, nan)`
assert df['latlong'][0] == (np.nan, np.nan)
def test_convert_all_variable_data():
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]
})
variable_types = {
'id': vtypes.Numeric,
'category': vtypes.Categorical,
'ints': vtypes.Numeric,
'boolean': vtypes.Boolean,
'date': vtypes.Datetime,
'integers': vtypes.Numeric
}
df = convert_all_variable_data(df, variable_types)
assert df['id'].dtype.name in vtypes.PandasTypes._pandas_numerics
assert df['category'].dtype.name == 'object'
assert df['ints'].dtype.name in vtypes.PandasTypes._pandas_numerics
assert df['boolean'].dtype.name == 'bool'
assert df['date'].dtype.name in vtypes.PandasTypes._pandas_datetimes
assert df['integers'].dtype.name in vtypes.PandasTypes._pandas_numerics
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]