def test_replacement(self):
nan = np.nan
X = [
[1.0, nan, 0.0],
[2.0, 1.0, 3.0],
[nan, nan, nan]
]
unknowns = np.isnan(X)
domain = data.Domain(
(data.DiscreteVariable("A", values=["0", "1", "2"]),
data.ContinuousVariable("B"),
data.ContinuousVariable("C"))
)
table = data.Table.from_numpy(domain, np.array(X))
v1 = impute.Random()(table, domain[0])
v2 = impute.Random()(table, domain[1])
v3 = impute.Random()(table, domain[2])
self.assertTrue(np.all(np.isfinite(v1.compute_value(table))))
self.assertTrue(np.all(np.isfinite(v2.compute_value(table))))
self.assertTrue(np.all(np.isfinite(v3.compute_value(table))))
imputer = preprocess.Impute(method=impute.Random())
itable = imputer(table)
self.assertTrue(np.all(np.isfinite(itable.X)))
# Original data should keep unknowns
self.assertTrue(np.all(unknowns == np.isnan(table.X)))
self.assertTrue(np.all(itable.X[~unknowns] == table.X[~unknowns]))
def createinstance(params):
params = dict(params)
method = params.pop("method", ImputeEditor.Average)
if method == ImputeEditor.NoImputation:
return None
elif method == ImputeEditor.Average:
return preprocess.Impute()
elif method == ImputeEditor.Model:
return preprocess.Impute(method=preprocess.impute.Model())
elif method == ImputeEditor.DropRows:
return RemoveNaNRows()
elif method == ImputeEditor.DropColumns:
return preprocess.RemoveNaNColumns()
else:
method, defaults = ImputeEditor.Imputers[method]
defaults = dict(defaults)
defaults.update(params)
return preprocess.Impute(method=method)
def test_replacement(self):
nan = np.nan
X = [[1.0, nan, 0.0], [2.0, 1.0, 3.0], [nan, nan, nan]]
table = Table.from_numpy(None, np.array(X))
var1 = impute.Default(0.0)(table, 0)
self.assertTrue(np.all(np.isfinite(var1.compute_value(table))))
self.assertTrue(all(var1.compute_value(table) == [1.0, 2.0, 0.0]))
imputer = preprocess.Impute(method=impute.Default(42))
idata = imputer(table)
np.testing.assert_allclose(
idata.X, [[1.0, 42., 0.0], [2.0, 1.0, 3.0], [42., 42., 42.]])
def test_replacement(self):
from Orange.classification import MajorityLearner, SimpleTreeLearner
from Orange.regression import MeanLearner
nan = np.nan
X = [
[1.0, nan, 0.0],
[2.0, 1.0, 3.0],
[nan, nan, nan]
]
unknowns = np.isnan(X)
domain = data.Domain(
(data.DiscreteVariable("A", values=["0", "1", "2"]),
data.ContinuousVariable("B"),
data.ContinuousVariable("C"))
)
table = data.Table.from_numpy(domain, np.array(X))
v = impute.Model(MajorityLearner())(table, domain[0])
self.assertTrue(np.all(np.isfinite(v.compute_value(table))))
self.assertTrue(np.all(v.compute_value(table) == [1., 2., 1.])
or np.all(v.compute_value(table) == [1., 2., 2.]))
v = impute.Model(MeanLearner())(table, domain[1])
self.assertTrue(np.all(np.isfinite(v.compute_value(table))))
self.assertTrue(np.all(v.compute_value(table) == [1., 1., 1.]))
imputer = preprocess.Impute(impute.Model(SimpleTreeLearner()))
itable = imputer(table)
# Original data should keep unknowns
self.assertTrue(np.all(np.isnan(table.X) == unknowns))
self.assertTrue(np.all(itable.X[~unknowns] == table.X[~unknowns]))
Aimp = itable.domain["A"].compute_value
self.assertIsInstance(Aimp, impute.ReplaceUnknownsModel)
col = Aimp(table)
self.assertEqual(col.shape, (len(table),))
self.assertTrue(np.all(np.isfinite(col)))
v = Aimp(table[-1])
self.assertEqual(v.shape, (1,))
self.assertTrue(np.all(np.isfinite(v)))
def test_replacement(self):
nan = np.nan
X = [[1.0, nan, 0.0], [2.0, 1.0, 3.0], [nan, nan, nan]]
unknowns = np.isnan(X)
domain = data.Domain(
(data.DiscreteVariable("A", values=("0", "1", "2")),
data.ContinuousVariable("B"), data.ContinuousVariable("C")),
# the class is here to ensure the backmapper in model does not
# run and raise exception
data.DiscreteVariable("Z", values=("P", "M")))
table = data.Table.from_numpy(domain, np.array(X), [
0,
] * 3)
v = impute.Model(MajorityLearner())(table, domain[0])
self.assertTrue(np.all(np.isfinite(v.compute_value(table))))
self.assertTrue(
np.all(v.compute_value(table) == [1., 2., 1.])
or np.all(v.compute_value(table) == [1., 2., 2.]))
v = impute.Model(MeanLearner())(table, domain[1])
self.assertTrue(np.all(np.isfinite(v.compute_value(table))))
self.assertTrue(np.all(v.compute_value(table) == [1., 1., 1.]))
imputer = preprocess.Impute(impute.Model(SimpleTreeLearner()))
itable = imputer(table)
# Original data should keep unknowns
self.assertTrue(np.all(np.isnan(table.X) == unknowns))
self.assertTrue(np.all(itable.X[~unknowns] == table.X[~unknowns]))
Aimp = itable.domain["A"].compute_value
self.assertIsInstance(Aimp, impute.ReplaceUnknownsModel)
col = Aimp(table)
self.assertEqual(col.shape, (len(table), ))
self.assertTrue(np.all(np.isfinite(col)))
v = Aimp(table[-1])
self.assertEqual(v.shape, (1, ))
self.assertTrue(np.all(np.isfinite(v)))
def test_imputer(self):
auto = data.Table(test_filename('datasets/imports-85.tab'))
auto2 = preprocess.Impute()(auto)
self.assertFalse(np.isnan(auto2.X).any())
def test_imputer(self):
auto = data.Table('auto-mpg')
auto2 = preprocess.Impute()(auto)
self.assertFalse(np.isnan(auto2.X).any())