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 remove_unused_values(var, data):
column_data = Orange.data.Table.from_table(
Orange.data.Domain([var]),
data
)
array = column_data.X.ravel()
mask = numpy.isfinite(array)
unique = numpy.array(numpy.unique(array[mask]), dtype=int)
if len(unique) == len(var.values):
return var
used_values = [var.values[i] for i in unique]
new_var = Orange.data.DiscreteVariable(
"R_{}".format(var.name),
values=used_values
)
translation_table = numpy.array([numpy.NaN] * len(var.values))
translation_table[unique] = range(len(new_var.values))
if 0 >= var.base_value < len(var.values):
base = translation_table[var.base_value]
if numpy.isfinite(base):
new_var.base_value = int(base)
new_var.get_value_from = Lookup(var, translation_table)
return new_var
def merge_lookup(A, B):
"""
Merge two consecutive Lookup transforms into one.
"""
lookup_table = numpy.array(A.lookup_table)
mask = numpy.isfinite(lookup_table)
indices = numpy.array(lookup_table[mask], dtype=int)
lookup_table[mask] = B.lookup_table[indices]
return Lookup(A.variable, lookup_table)
def sort_var_values(var):
newvalues = list(sorted(var.values))
if newvalues == list(var.values):
return var
translation_table = numpy.array(
[float(newvalues.index(value)) for value in var.values])
newvar = Orange.data.DiscreteVariable(var.name, values=newvalues)
newvar.compute_value = Lookup(var, translation_table)
return newvar