def createSignature(self, a, b):
s = Signatures()
s.names = ['ft [0]', 'ft [1]']
s.values = [a, b]
s.source_file = '%s %s' % (a, b)
s.version = self.feature_vector_version
return s
def createSignature(self, a, b):
s = Signatures()
s.names = ["ft [0]", "ft [1]"]
s.values = [a, b]
s.source_file = "%s %s" % (a, b)
s.version = self.feature_vector_version
return s
def test_LargeFeatureSetGrayscale(self):
"""Large feature set, grayscale image"""
reference_sample = Signatures.NewFromSigFile(
self.sig_file_path, image_path=self.test_tif_path)
target_sample = Signatures.LargeFeatureSet(self.test_tif_path)
for target_val, res_val in zip(reference_sample.values,
target_sample.values):
self.assertAlmostEqual(target_val, res_val, delta=self.epsilon)
def test_reduceFeatures(self):
ftnames = ["c", "b"]
s = Signatures()
s.names = ["a", "b", "c"]
s.values = [1.0, 2.0, 3.0]
s.source_file = ""
s1 = s.FeatureReduce(ftnames)
self.assertEqual(s1.names, ftnames)
self.assertAlmostEqual(s1.values, [3.0, 2.0])
def test_reduceFeatures(self):
ftnames = ['c', 'b']
s = Signatures()
s.names = ['a', 'b', 'c']
s.values = [1.0, 2.0, 3.0]
s.source_file = ''
s1 = s.FeatureReduce(ftnames)
self.assertEqual(s1.names, ftnames)
self.assertAlmostEqual(s1.values, [3.0, 2.0])
def test_calculateLargeFeatureSet(self):
ft1 = Signatures.LargeFeatureSet(self.image1)
self.assertEqual(len(ft1.names), self.LargeFSexpectedLen)
self.assertTrue(all([re.match('^.+ \[\d+\]$', n) for n in ft1.names]))
self.assertEqual(len(set(ft1.names)), self.LargeFSexpectedLen)
self.assertEqual(len(ft1.values), self.LargeFSexpectedLen)
self.assertFalse(any(np.isinf(ft1.values)))
self.assertFalse(any(np.isnan(ft1.values)))
ft2 = Signatures.LargeFeatureSet(self.image2)
self.assertEqual(ft1.names, ft2.names)
self.assertEqual(len(ft2.values), self.LargeFSexpectedLen)
self.assertFalse(any(np.isinf(ft2.values)))
self.assertFalse(any(np.isnan(ft2.values)))
def createSignature(self, a, b):
s = Signatures()
s.names = ['ft [0]', 'ft [1]']
s.values = [a, b]
s.source_file = '%s %s' % (a, b)
s.version = self.feature_vector_version
return s
def test_reduceFeatures(self):
ftnames = ['c', 'b']
s = Signatures()
s.names = ['a', 'b', 'c']
s.values = [1.0, 2.0, 3.0]
s.source_file = ''
s1 = s.FeatureReduce(ftnames)
self.assertEqual(s1.names, ftnames)
self.assertAlmostEqual(s1.values, [3.0, 2.0])
def addToFeatureSet(ftb, ds, fts, classId, imagesOnly):
message = ''
tid = WndcharmStorage.getAttachedTableFile(ftb.tc, ds)
if tid:
if not ftb.openTable(tid):
return message + '\nERROR: Table not opened'
version = unwrap(ftb.versiontag.getTextValue())
message += 'Opened table id:%d version:%s\n' % (tid, version)
else:
message += 'ERROR: Table not found for Dataset id:%d' % ds.getId()
return message
if imagesOnly:
for image in ds.listChildren():
imId = image.getId()
message += '\tProcessing features for image id:%d\n' % imId
sig = Signatures()
(sig.names, sig.values) = ftb.loadFeatures(imId)
sig.source_file = str(imId)
sig.version = version
fts.AddSignature(sig, classId)
else:
names, values, ids = ftb.bulkLoadFeatures()
message += '\tProcessing all features for dataset id:%d\n' % ds.getId()
for imId, vals in izip(ids, values):
sig = Signatures()
sig.names = names
sig.values = vals
sig.source_file = str(imId)
sig.version = version
fts.AddSignature(sig, classId)
fts.classnames_list[classId] = ds.getName()
return message
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)
