def __call__(self, data, variable):
variable = data.domain[variable]
if variable.is_discrete:
fmt = "{var.name}"
value = "N/A"
var = Orange.data.DiscreteVariable(
fmt.format(var=variable),
values=variable.values + (value, ),
compute_value=Lookup(variable,
np.arange(len(variable.values),
dtype=int),
unknown=len(variable.values)),
sparse=variable.sparse,
)
return var
elif variable.is_continuous:
fmt = "{var.name}_def"
indicator_var = Orange.data.DiscreteVariable(
fmt.format(var=variable),
values=("undef", "def"),
compute_value=IsDefined(variable),
sparse=variable.sparse,
)
stats = basic_stats.BasicStats(data, variable)
return (variable.copy(
compute_value=ReplaceUnknowns(variable, stats.mean)),
indicator_var)
else:
raise TypeError(type(variable))
def column_imputer_as_value(variable, table):
if isinstance(variable, Orange.data.DiscreteVariable):
fmt = "{var.name}"
value = "N/A"
var = Orange.data.DiscreteVariable(
fmt.format(var=variable),
values=variable.values + [value],
base_value=variable.base_value
)
var.get_value_from = Lookup(
variable,
numpy.arange(len(variable.values), dtype=int),
unknown=len(variable.values)
)
codomain = [var]
transformers = [var.get_value_from]
elif isinstance(variable, Orange.data.ContinuousVariable):
fmt = "{var.name}_def"
var = Orange.data.DiscreteVariable(
fmt.format(var=variable),
values=("undef", "def"),
)
var.get_value_from = IsDefined(variable)
codomain = [variable, var]
stats = basic_stats.BasicStats(table, variable)
transformers = [ReplaceUnknowns(variable, stats.mean),
var.get_value_from]
else:
raise TypeError(type(variable))
return ColumnImputerAsValue(
table.domain, Orange.data.Domain(codomain), transformers)
def __call__(self, data, variable, value=None):
variable = data.domain[variable]
if value is None:
if variable.is_continuous:
stats = basic_stats.BasicStats(data, variable)
value = stats.mean
elif variable.is_discrete:
dist = distribution.get_distribution(data, variable)
value = dist.modus()
else:
raise TypeError("Variable must be continuous or discrete")
return variable.copy(compute_value=ReplaceUnknowns(variable, value))
def __call__(self, data, variable):
if is_continuous(variable):
stats = basic_stats.BasicStats(data, variable)
value = stats.mean
elif is_discrete(variable):
dist = distribution.get_distribution(data, variable)
value = dist.modus()
else:
raise TypeError
var = copy.copy(variable)
var.compute_value = ReplaceUnknowns(variable, value)
return var
def column_imputer_average(variable, table):
stats = basic_stats.BasicStats(table, variable)
return column_imputer_defaults(variable, table, stats.mean)
def column_imputer_minimal(variable, table):
stats = basic_stats.BasicStats(table, variable)
return column_imputer_defaults(variable, table, stats.min)
