def test_cosine_disc(self):
assert_almost_equal = np.testing.assert_almost_equal
data = self.disc_data
data.X = np.array([[1, 0, 0], [0, 1, 1], [1, 3, 0]], dtype=float)
model = distance.Cosine().fit(data)
assert_almost_equal(model.means, [2 / 3, 2 / 3, 1 / 3])
dist = model(data)
assert_almost_equal(
dist, 1 - np.array([[1, 0, 1 / sqrt(2)], [0, 1, 0.5],
[1 / sqrt(2), 0.5, 1]]))
data.X[1, 1] = np.nan
model = distance.Cosine().fit(data)
assert_almost_equal(model.means, [2 / 3, 1 / 2, 1 / 3])
dist = model(data)
assert_almost_equal(
dist, 1 -
np.array([[1, 0, 1 / sqrt(2)], [0, 1, 0.5 / sqrt(1.25) / sqrt(2)],
[1 / sqrt(2), 0.5 / sqrt(1.25) / sqrt(2), 1]]))
data.X = np.array([[1, 0, 0], [0, np.nan, 1], [1, np.nan, 1],
[1, 3, 1]])
model = distance.Cosine().fit(data)
dist = model(data)
assert_almost_equal(model.means, [0.75, 0.5, 0.75])
assert_almost_equal(dist, [[0, 1, 0.333333333, 0.422649731],
[1, 0, 0.254644008, 0.225403331],
[0.333333333, 0.254644008, 0, 0.037749551],
[0.422649731, 0.225403331, 0.037749551, 0]])
def test_cosine_cont(self):
assert_almost_equal = np.testing.assert_almost_equal
data = self.cont_data
dist = distance.Cosine(data, axis=1)
assert_almost_equal(dist, [[0, 0.266200614, 0.0741799, 0.355097978],
[0.266200614, 0, 0.547089186, 0.925279678],
[0.0741799, 0.547089186, 0, 0.12011731],
[0.355097978, 0.925279678, 0.12011731, 0]])
with data.unlocked():
data.X[1, 0] = np.nan
dist = distance.Cosine(data, axis=1)
assert_almost_equal(dist, [[0, 0.174971353, 0.0741799, 0.355097978],
[0.174971353, 0, 0.207881966, 0.324809395],
[0.0741799, 0.207881966, 0, 0.12011731],
[0.355097978, 0.324809395, 0.12011731, 0]])
with data.unlocked():
data.X[0, 0] = np.nan
dist = distance.Cosine(data, axis=1)
assert_almost_equal(dist, [[0, 0.100977075, 0.035098719, 0.056666739],
[0.100977075, 0, 0.188497329, 0.246304671],
[0.035098719, 0.188497329, 0, 0.12011731],
[0.056666739, 0.246304671, 0.12011731, 0]])
def test_cosine_cols(self):
assert_almost_equal = np.testing.assert_almost_equal
data = self.cont_data
dist = distance.Cosine(data, axis=0, normalize=False)
assert_almost_equal(
dist,
[[0, 0.711324865, 0.11050082],
[0.711324865, 0, 0.44365136],
[0.11050082, 0.44365136, 0]])
with data.unlocked():
data.X[1, 1] = np.nan
dist = distance.Cosine(data, axis=0, normalize=False)
assert_almost_equal(
dist,
[[0, 0.47702364, 0.11050082],
[0.47702364, 0, 0.181076975],
[0.11050082, 0.181076975, 0]])
with data.unlocked():
data.X[1, 0] = np.nan
data.X[1, 2] = 2
dist = distance.Cosine(data, axis=0, normalize=False)
assert_almost_equal(
dist,
[[0, 0.269703257, 0.087129071],
[0.269703257, 0, 0.055555556],
[0.087129071, 0.055555556, 0]])
def test_two_tables(self):
assert_almost_equal = np.testing.assert_almost_equal
with self.cont_data.unlocked(), self.cont_data2.unlocked():
self.cont_data.X[1, 0] = np.nan
self.cont_data2.X[1, 0] = np.nan
dist = distance.Cosine(self.cont_data, self.cont_data2)
assert_almost_equal(
dist,
[[0.2142857, 0.1573352],
[0.4958158, 0.2097042],
[0.0741799, 0.0198039],
[0.1514447, 0.0451363]])
model = distance.Cosine().fit(self.cont_data)
dist = model(self.cont_data, self.cont_data2)
assert_almost_equal(
dist,
[[0.2142857, 0.1573352],
[0.4958158, 0.2097042],
[0.0741799, 0.0198039],
[0.1514447, 0.0451363]])
dist = model(self.cont_data2)
assert_almost_equal(dist, [[0, 0.092514787], [0.092514787, 0]])
def test_cosine_mixed(self):
assert_almost_equal = np.testing.assert_almost_equal
data = self.mixed_data
data.X = np.array(
[[1, 3, 2, 1, 0, 0], [-1, 5, 0, 0, 1, 1], [1, 1, 1, 1, 3, 0]],
dtype=float)
model = distance.Cosine(axis=1).fit(data)
assert_almost_equal(model.means, [1 / 3, 3, 1, 2 / 3, 2 / 3, 1 / 3])
dist = model(data)
assert_almost_equal(
dist,
[[0, 0.316869949, 0.191709623], [0.316869949, 0, 0.577422873],
[0.191709623, 0.577422873, 0]])
import Orange.data
import Orange.misc
from Orange.widgets import widget, gui, settings
from Orange import distance
_METRICS = [
("Euclidean", distance.Euclidean()),
("Manhattan", distance.Manhattan()),
("Cosine", distance.Cosine()),
("Jaccard", distance.Jaccard()),
("Mahalanobis", distance.Mahalanobis()),
("Spearman", distance.SpearmanR()),
("Spearman absolute", distance.SpearmanRAbsolute()),
("Pearson", distance.PearsonR()),
("Pearson absolute", distance.PearsonRAbsolute()),
]
class OWDistances(widget.OWWidget):
name = "Distances"
description = "Compute a matrix of pairwise distances."
icon = "icons/Distance.svg"
inputs = [("Data", Orange.data.Table, "set_data")]
outputs = [("Distances", Orange.misc.DistMatrix)]
axis = settings.Setting(0)
metric_idx = settings.Setting(0)
autocommit = settings.Setting(False)
want_main_area = False
