def test_simple(self):
data = Orange.data.Table("iris")
f = SavitzkyGolayFiltering()
data = data[:1]
fdata = f(data)
np.testing.assert_almost_equal(
fdata.X, [[4.86857143, 3.47428571, 1.49428571, 0.32857143]])
def test_predict_savgol_another_interpolate(self):
train, test = separate_learn_test(self.collagen)
train = SavitzkyGolayFiltering(window=9, polyorder=2, deriv=2)(train)
auc = AUC(TestOnTestData()(train, test, [LogisticRegressionLearner()]))
train = Interpolate(points=getx(train))(train)
aucai = AUC(TestOnTestData()(train, test, [LogisticRegressionLearner()]))
self.assertAlmostEqual(auc, aucai, delta=0.02)
def test_unknown_no_propagate(self):
data = Orange.data.Table("iris")
f = SavitzkyGolayFiltering()
data = data[:5]
for i in range(4):
data.X[i, i] = np.nan
data.X[4] = np.nan
fdata = f(data)
np.testing.assert_equal(np.sum(np.isnan(fdata.X), axis=1), [1, 1, 1, 1, 4])
def preprocessor_data(preproc):
"""
Rerturn appropriate test file for a preprocessor.
Very slow preprocessors should get smaller files.
"""
if isinstance(preproc, ME_EMSC):
return SMALLER_COLLAGEN
return SMALL_COLLAGEN
# Preprocessors that work per sample and should return the same
# result for a sample independent of the other samples
PREPROCESSORS_INDEPENDENT_SAMPLES = [
Interpolate(np.linspace(1000, 1700, 100)),
SavitzkyGolayFiltering(window=9, polyorder=2, deriv=2),
Cut(lowlim=1000, highlim=1800),
GaussianSmoothing(sd=3.),
Absorbance(),
Transmittance(),
Integrate(limits=[[900, 100], [1100, 1200], [1200, 1300]]),
Integrate(methods=Integrate.Simple, limits=[[1100, 1200]]),
Integrate(methods=Integrate.Baseline, limits=[[1100, 1200]]),
Integrate(methods=Integrate.PeakMax, limits=[[1100, 1200]]),
Integrate(methods=Integrate.PeakBaseline, limits=[[1100, 1200]]),
Integrate(methods=Integrate.PeakAt, limits=[[1100]]),
Integrate(methods=Integrate.PeakX, limits=[[1100, 1200]]),
Integrate(methods=Integrate.PeakXBaseline, limits=[[1100, 1200]]),
RubberbandBaseline(),
LinearBaseline(),
Normalize(method=Normalize.Vector),
def test_predict_savgov_same_domain(self):
data = SavitzkyGolayFiltering(window=9, polyorder=2, deriv=2)(self.collagen)
train, test = separate_learn_test(data)
auc = AUC(TestOnTestData()(train, test, [LogisticRegressionLearner()]))
self.assertGreater(auc, 0.85)
