def test_nanmode(self):
X = np.array([[np.nan, np.nan, 1, 1], [2, np.nan, 1, 1]])
mode, count = nanmode(X, 0)
np.testing.assert_array_equal(mode, [[2, np.nan, 1, 1]])
np.testing.assert_array_equal(count, [[1, np.nan, 2, 2]])
mode, count = nanmode(X, 1)
np.testing.assert_array_equal(mode, [[1], [1]])
np.testing.assert_array_equal(count, [[2], [2]])
def test_nanmode(self):
X = np.array([[np.nan, np.nan, 1, 1],
[2, np.nan, 1, 1]])
mode, count = nanmode(X, 0)
np.testing.assert_array_equal(mode, [[2, np.nan, 1, 1]])
np.testing.assert_array_equal(count, [[1, np.nan, 2, 2]])
mode, count = nanmode(X, 1)
np.testing.assert_array_equal(mode, [[1], [1]])
np.testing.assert_array_equal(count, [[2], [2]])
def __mode(x, *args, **kwargs):
if sp.issparse(x):
x = x.todense(order="C")
# return ss.mode(x, *args, **kwargs)[0]
return ut.nanmode(
x, *args,
**kwargs)[0] # Temporary replacement for scipy < 1.2.0
def aggregate(
var: Variable,
data: np.ndarray,
groupindices: Sequence[Sequence[int]],
) -> np.ndarray:
if var.is_string:
join = lambda values: (join_elided(", ", 42, values, " ({} more)"))
# collect all original labels for every merged row
values = [data[indices] for indices in groupindices]
data = [join(list(map(var.str_val, vals))) for vals in values]
return np.array(data, dtype=object)
elif var.is_continuous:
data = [
np.nanmean(data[indices]) if len(indices) else np.nan
for indices in groupindices
]
return np.array(data, dtype=float)
elif var.is_discrete:
from Orange.statistics.util import nanmode
data = [
nanmode(data[indices])[0] if len(indices) else np.nan
for indices in groupindices
]
return np.asarray(data, dtype=float)
else:
raise TypeError(type(var))
def __mode(x, *args, **kwargs):
if sp.issparse(x):
x = x.todense(order="C")
# return ss.mode(x, *args, **kwargs)[0]
return ut.nanmode(x, *args, **kwargs)[0] # Temporary replacement for scipy
