def test_selects_percentage_of_features(self):
N = self.labels.size
p = 5. / N
selector = fs.OutlierAbundanceAndVarianceSelector(p=p).fit(self.data)
self.assertAlmostEqual(selector.selected_.mean(), p, places=2)
p = 20. / N
selector = fs.OutlierAbundanceAndVarianceSelector(p=p).fit(self.data)
self.assertAlmostEqual(selector.selected_.mean(), p, places=2)
def test_selects_percentage_of_features(self):
N = self.labels.size
p = 5.0 / N
selector = fs.OutlierAbundanceAndVarianceSelector(p=p).fit(self.data)
assert round(abs(selector.selected_.mean() - p), 2) == 0
p = 20.0 / N
selector = fs.OutlierAbundanceAndVarianceSelector(p=p).fit(self.data)
assert round(abs(selector.selected_.mean() - p), 2) == 0
def test_discards_outlier_variance(self):
selector = fs.OutlierAbundanceAndVarianceSelector().fit(self.data)
TNR = (selector.selected_[self.high_var] == False).mean()
self.assertGreaterEqual(TNR, 0.95)
def test_discards_outlier_abundance(self):
selector = fs.OutlierAbundanceAndVarianceSelector().fit(self.data)
TNR = (selector.selected_[self.outlier_mean] == False).mean()
assert TNR >= 0.95