def test_thresholdWeights(self):
w = FisherFeatureWeights()
w.names = ['a', 'b', 'c']
w.values = [1.0, 2.0, 4.0]
w1 = w.Threshold(2)
self.assertEqual(w1.names, ['c', 'b'])
self.assertAlmostEqual(w1.values, [4.0, 2.0])
def test_thresholdWeights(self):
w = FisherFeatureWeights()
w.names = ["a", "b", "c"]
w.values = [1.0, 2.0, 4.0]
w1 = w.Threshold(2)
self.assertEqual(w1.names, ["c", "b"])
self.assertAlmostEqual(w1.values, [4.0, 2.0])
def test_thresholdWeights(self):
w = FisherFeatureWeights()
w.names = ['a', 'b', 'c']
w.values = [1.0, 2.0, 4.0]
w1 = w.Threshold(2)
self.assertEqual(w1.names, ['c', 'b'])
self.assertAlmostEqual(w1.values, [4.0, 2.0])
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)
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_predictDiscrete(self):
s1 = self.createSignature(1, -1)
s2 = self.createSignature(2, -2)
s3 = self.createSignature(3, -3)
s4 = self.createSignature(4, -4)
trainFts = FeatureSet_Discrete()
trainFts.AddSignature(s1, 0)
trainFts.AddSignature(s2, 0)
trainFts.AddSignature(s3, 1)
trainFts.AddSignature(s4, 1)
tmp = trainFts.ContiguousDataMatrix()
# Values are chosen so that different weights give different predictions
s5 = self.createSignature(0, -5)
s6 = self.createSignature(5, 0)
testFts = FeatureSet_Discrete()
testFts.AddSignature(s5, 0)
testFts.AddSignature(s6, 0)
tmp = testFts.ContiguousDataMatrix()
weights = FisherFeatureWeights()
weights.names = ['ft [0]', 'ft [1]']
weights.values = [2.0, 1.0]
pred = DiscreteBatchClassificationResult.New(trainFts, testFts,
weights)
self.assertEqual(len(pred.individual_results), 2)
r1, r2 = pred.individual_results
np.testing.assert_almost_equal(r1.marginal_probabilities,
[0.975, 0.025],
decimal=3)
np.testing.assert_almost_equal(r2.marginal_probabilities,
[0.025, 0.975],
decimal=3)
weights = FisherFeatureWeights()
weights.names = ['ft [0]', 'ft [1]']
weights.values = [1.0, 2.0]
pred = DiscreteBatchClassificationResult.New(trainFts, testFts,
weights)
self.assertEqual(len(pred.individual_results), 2)
r1, r2 = pred.individual_results
np.testing.assert_almost_equal(r1.marginal_probabilities,
[0.025, 0.975],
decimal=3)
np.testing.assert_almost_equal(r2.marginal_probabilities,
[0.975, 0.025],
decimal=3)
def test_fisherFeatureWeights(self):
sig1, sig2, sig3, sig4 = self.createSignatures()
fts = FeatureSet_Discrete()
fts.AddSignature(sig1, 0)
fts.AddSignature(sig2, 0)
fts.AddSignature(sig3, 1)
fts.AddSignature(sig4, 1)
tmp = fts.ContiguousDataMatrix()
# TODO: weight[1]==0, presumably because the intra-class variance=0,
# even though feature[1] is a perfect discriminator?
fts.Normalize()
wts = FisherFeatureWeights.NewFromFeatureSet(fts)
np.testing.assert_almost_equal(wts.values, [4.0, 0.0])
self.assertEqual(wts.names, ['ft [0]', 'ft [1]'])
def test_predictDiscrete(self):
s1 = self.createSignature(1, -1)
s2 = self.createSignature(2, -2)
s3 = self.createSignature(3, -3)
s4 = self.createSignature(4, -4)
trainFts = FeatureSet_Discrete()
trainFts.AddSignature(s1, 0)
trainFts.AddSignature(s2, 0)
trainFts.AddSignature(s3, 1)
trainFts.AddSignature(s4, 1)
tmp = trainFts.ContiguousDataMatrix()
# Values are chosen so that different weights give different predictions
s5 = self.createSignature(0, -5)
s6 = self.createSignature(5, 0)
testFts = FeatureSet_Discrete()
testFts.AddSignature(s5, 0)
testFts.AddSignature(s6, 0)
tmp = testFts.ContiguousDataMatrix()
weights = FisherFeatureWeights()
weights.names = ['ft [0]', 'ft [1]']
weights.values = [2.0, 1.0]
pred = DiscreteBatchClassificationResult.New(trainFts, testFts, weights)
self.assertEqual(len(pred.individual_results), 2)
r1, r2 = pred.individual_results
np.testing.assert_almost_equal(
r1.marginal_probabilities, [0.975, 0.025], decimal=3)
np.testing.assert_almost_equal(
r2.marginal_probabilities, [0.025, 0.975], decimal=3)
weights = FisherFeatureWeights()
weights.names = ['ft [0]', 'ft [1]']
weights.values = [1.0, 2.0]
pred = DiscreteBatchClassificationResult.New(trainFts, testFts, weights)
self.assertEqual(len(pred.individual_results), 2)
r1, r2 = pred.individual_results
np.testing.assert_almost_equal(
r1.marginal_probabilities, [0.025, 0.975], decimal=3)
np.testing.assert_almost_equal(
r2.marginal_probabilities, [0.975, 0.025], decimal=3)
class TestGraphs(unittest.TestCase):
"""Test WND-CHARM's graph-making functionality."""
fs = CreateArtificialFeatureSet_Discrete(n_samples=1000,
n_classes=10,
initial_noise_sigma=100,
noise_gradient=10,
random_state=43)
train_set, test_set = fs.Split(randomize=False, quiet=True)
train_set.Normalize(quiet=True)
fw = FisherFeatureWeights.NewFromFeatureSet(train_set).Threshold()
reduced_train_set = train_set.FeatureReduce(fw.names)
reduced_test_set = test_set.FeatureReduce(fw.names)
reduced_test_set.Normalize(reduced_train_set, quiet=True)
batch_result = DiscreteBatchClassificationResult.New(reduced_train_set,
reduced_test_set,
fw,
quiet=True)
def setUp(self):
self.tempdir = mkdtemp()
def tearDown(self):
rmtree(self.tempdir)
def CompareGraphs(self, graph, testfilename):
"""Helper function to check output graphs"""
tempfile = self.tempdir + sep + testfilename
graph.SaveToFile(tempfile)
try:
self.assertTrue(filecmp.cmp(testfilename, tempfile))
except AssertionError:
print "Files not equal: {0} and {1}".format(testfilename, tempfile)
raise
@unittest.skipIf(HasMatplotlib, "Skipped if matplotlib IS installed")
def test_ErrMsgIfMatplotibNotInstalled(self):
"""Fail gracefully with informative message if matplotlib"""
graph = PredictedValuesGraph(self.batch_result)
with self.assertRaises(ImportError):
graph.RankOrderedPredictedValuesGraph()
with self.assertRaises(ImportError):
graph.KernelSmoothedDensityGraph()
@unittest.skipUnless(HasMatplotlib,
"Skipped if matplotlib IS NOT installed")
def test_RankOrderedFromBatchClassificationResult(self):
"""Rank Ordered Predicted values graph from a single split"""
testfilename = 'test_graph_rank_ordered.png'
graph = PredictedValuesGraph(self.batch_result)
graph.RankOrderedPredictedValuesGraph()
self.CompareGraphs(graph, testfilename)
@unittest.skipUnless(HasMatplotlib,
"Skipped if matplotlib IS NOT installed")
def test_KernelSmoothedFromBatchClassificationResult(self):
"""Kernel Smoothed Probability density graph from a single split"""
testfilename = 'test_graph_kernel_smoothed.png'
graph = PredictedValuesGraph(self.batch_result)
graph.KernelSmoothedDensityGraph()
self.CompareGraphs(graph, testfilename)
@unittest.skip("Skip until ShuffleSplit has a RandomState param to pass in"
)
def test_FromDiscreteClassificationExperimentResults(self):
"""Rank Ordered Predicted values graph from an experiment result (multiple splits)"""
testfilename = 'test_graph_rank_ordered_experiment.png'
small_fs = CreateArtificialFeatureSet_Discrete(n_samples=100,
n_classes=5,
initial_noise_sigma=100,
noise_gradient=10,
random_state=42)
experiment = DiscreteClassificationExperimentResult.NewShuffleSplit(
small_fs, quiet=True)
graph = PredictedValuesGraph(self.batch_result)
graph.RankOrderedPredictedValuesGraph()
# graph.SaveToFile( tempfile ) # remove after RandomState for ShuffleSplit is implemented
self.CompareGraphs(graph, testfilename)
@unittest.skipUnless(HasMatplotlib,
"Skipped if matplotlib IS NOT installed")
def test_FromHTML(self):
"""Rank Ordered Predicted values graph from an experiment result (multiple splits)"""
testfilename = 'test_graph_fromHTML.png'
# Inflate the zipped html file into a temp file
import zipfile
#zipped_file_path = pychrm_test_dir + sep + 'c_elegans_terminal_bulb.html'
#import zlib
#zf = zipfile.ZipFile( zipped_file_path + '.zip', mode='w' )
#zf.write( zipped_file_path, compress_type=zipfile.ZIP_DEFLATED )
#zf.close()
zipped_file_path = pychrm_test_dir + sep + 'c_elegans_terminal_bulb.html.zip'
zf = zipfile.ZipFile(zipped_file_path, mode='r')
zf.extractall(self.tempdir)
tempfile = self.tempdir + sep + testfilename
htmlfilepath = self.tempdir + sep + zf.namelist()[0]
exp_result = DiscreteClassificationExperimentResult.NewFromHTMLReport(
htmlfilepath)
graph = PredictedValuesGraph(exp_result)
graph.RankOrderedPredictedValuesGraph()
graph.SaveToFile(tempfile)
try:
self.assertTrue(filecmp.cmp(testfilename, tempfile))
except AssertionError:
print "Files not equal: {0} and {1}".format(testfilename, tempfile)
raise
@unittest.skip(
"Skip until test training set w/ uninterpolatable class lables is made avail."
)
#@unittest.skipUnless( HasMatplotlib, "Skipped if matplotlib IS NOTinstalled" )
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)
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)
