def test_Normalize(self):
"""FIXME: THIS TEST BELONGS IN TEST_FEATURESET.PY"""
from numpy.testing import assert_allclose
result_fs = FeatureSet_Discrete.NewFromFitFile(self.test_fit_path)
result_fs.Normalize()
target_fs = FeatureSet_Discrete.NewFromFitFile(
self.test_normalized_fit_path)
assert_allclose(result_fs.data_matrix,
target_fs.data_matrix,
rtol=self.epsilon)
def test_IfNotInterpolatable(self):
"""You can't graph predicted values if the classes aren't interpolatable."""
testfilename = 'ShouldntBeGraphable.png'
fitfilepath = wndchrm_test_dir + sep + 'test-l.fit'
fs = FeatureSet_Discrete.NewFromFitFile(fitfilepath)
train_set, test_set = fs.Split(randomize=False, quiet=True)
train_set.Normalize()
fw = FisherFeatureWeights.NewFromFeatureSet(train_set).Threshold()
reduced_train_set = train_set.FeatureReduce(fw.names)
reduced_test_set = test_set.FeatureReduce(fw.names)
test_set.Normalize(train_set, quiet=True)
batch_result = DiscreteBatchClassificationResult.New(reduced_train_set,
reduced_test_set,
fw,
quiet=True)
graph = PredictedValuesGraph(batch_result)
tempfile = self.tempdir + sep + testfilename
with self.assertRaises(ValueError):
graph.RankOrderedPredictedValuesGraph()
graph.SaveToFile(tempfile)
def test_PerSampleStatisticsWITHOUTPredictedValue(self):
"""DISCRETE ShuffleSplit/PerSampleStatistics w/ mini binucleate test set (no predicted value)"""
fs = FeatureSet_Discrete.NewFromFitFile('../wndchrm_tests/test-l.fit')
exp = DiscreteClassificationExperimentResult.NewShuffleSplit(
fs, quiet=True)
exp.PerSampleStatistics()
self.assertTrue(True)
def test_NewFromFeatureSet(self):
"""Fisher score calculation"""
feature_set = FeatureSet_Discrete.NewFromFitFile(self.test_fit_path)
feature_set.Normalize()
result_weights = FisherFeatureWeights.NewFromFeatureSet(feature_set)
# test weights generated from test-l.fit:
# wndchrm classify -l -f1.0 -vtest_fit-l.weights test-l.fit test-l.fit
target_weights = FisherFeatureWeights.NewFromFile(
self.test_feat_weight_path)
for target_val, res_val in zip(target_weights.values,
result_weights.values):
self.assertAlmostEqual(target_val, res_val, delta=self.epsilon)
class TestWND5Classification(unittest.TestCase):
"""WND5 Classification"""
epsilon = 0.00001
# Define paths to original files
test_sig_path = join(test_dir, 't1_s01_c05_ij-l_precalculated.sig')
test_fit_path = join(test_dir, 'test-l.fit')
test_feat_wght_path = join(test_dir, 'test_fit-l.weights')
test_tif_path = join(test_dir, 't1_s01_c05_ij.tif')
# Here are the correct values that Python API needs to return:
# wndchrm classify -l -f1.0 test-l.fit t1_s01_c05_ij.tif
# t1_s01_c05_ij.tif 1.6e-27 0.083 0.917 * 4cell 3.835
# wndchrm classify -l -f0.14765 test-l.fit t1_s01_c05_ij.tif
# t1_s01_c05_ij.tif 3.23e-27 0.076 0.924 * 4cell 3.848
# wndchrm classify -l -f0.0685 test-l.fit t1_s01_c05_ij.tif
# t1_s01_c05_ij.tif 7.05e-27 0.069 0.931 * 4cell 3.862
correct_marg_probs = {}
correct_marg_probs[2919] = [0.083, 0.917]
correct_marg_probs[431] = [0.076, 0.924]
#correct_marg_probs[200] = [0.044, 0.956]
# slight difference in marg probs due to my use of round() below
correct_marg_probs[200] = [0.069, 0.931]
# Load the original files once and only once for all this class's tests
feature_set = FeatureSet_Discrete.NewFromFitFile(test_fit_path)
feature_set.Normalize()
test_sample = Signatures.NewFromSigFile(test_sig_path, test_tif_path)
test_sample.Normalize(feature_set)
all_weights = FisherFeatureWeights.NewFromFile(test_feat_wght_path)
# --------------------------------------------------------------------------
def Check(self, num_feats=None):
weights = self.all_weights.Threshold(num_feats)
feat_set = self.feature_set.FeatureReduce(weights.names)
sample = self.test_sample.FeatureReduce(weights.names)
result = DiscreteImageClassificationResult.NewWND5(
feat_set, weights, sample)
result_marg_probs = [ round( val, 3 ) \
for val in result.marginal_probabilities ]
self.assertSequenceEqual(self.correct_marg_probs[num_feats],
result_marg_probs)
# --------------------------------------------------------------------------
def test_WND5_all_features(self):
"""WND5 classification with entire large feature set (2919 features)"""
self.Check(2919)
# --------------------------------------------------------------------------
def test_WND5_15percent_threshold(self):
"""WND5 classification with large feature set 15% threshold (431 features)"""
self.Check(431)
# --------------------------------------------------------------------------
def test_WND5_200_feat_threshold(self):
"""WND5 classification with large feature set & 200 feature threshold"""
self.Check(200)
