def test_FitOnFitClassification(self):
fitfile_path = wndchrm_test_dir + sep + 'test-l.fit'
#fs = FeatureSet.NewFromFitFile( fitfile_path )
fs = FeatureSpace.NewFromFitFile(fitfile_path)
fs.Normalize(inplace=True, quiet=True)
fw = FisherFeatureWeights.NewFromFeatureSpace(fs).Threshold(438)
fw.Print(50)
fs.FeatureReduce(fw, inplace=True)
pychrm_split = FeatureSpaceClassification.NewWND5(fs,
fs,
fw,
quiet=False)
from wndcharm.FeatureSpacePredictionExperiment import FeatureSpaceClassificationExperiment
html_path = pychrm_test_dir + sep + 'test-l_training_error_result.html'
html_exp = FeatureSpaceClassificationExperiment.NewFromHTMLReport(
html_path, quiet=False)
# single split in this html
html_split = html_exp.individual_results[0]
for i, (html_result, pychrm_result) in enumerate( zip( html_split.individual_results,\
pychrm_split.individual_results ) ):
try:
self.assertEqual(html_result, pychrm_result)
except:
outstr = "Error in comparison # {0}:\n".format(i)
outstr += "HTML result:\n{0}\n Python API res:\n{1}".format(
html_result, pychrm_result)
raise
def test_FitOnFit(self):
"""Uses a curated subset of the IICBU 2008 Lymphoma dataset, preprocessed as follows:
auto-deconvolved, eosin channel only, tiled 5x6, 3 classes, 10 imgs per class,
300 samples per class.
"""
# Inflate the zipped test fit into a temp file
import zipfile
zipped_file_path = pychrm_test_dir + sep + 'lymphoma_iicbu2008_subset_EOSIN_ONLY_t5x6_v3.2features.fit.zip'
zf = zipfile.ZipFile(zipped_file_path, mode='r')
tempdir = mkdtemp()
zf.extractall(tempdir)
try:
fitfilepath = tempdir + sep + zf.namelist()[0]
# Do fit on fit WITHOUT tiling and compare with fit on fit results
# generated with wndchrm 1.60
fs = FeatureSpace.NewFromFitFile(fitfilepath).Normalize(
inplace=True, quiet=True)
#fs = FeatureSpace.NewFromFitFile( wndchrm_test_dir + sep + 'test-l.fit' )
#fs.ToFitFile( 'temp.fit' )
fw = FisherFeatureWeights.NewFromFeatureSpace(fs).Threshold()
fs.FeatureReduce(fw, inplace=True)
# #fw.Print()
# #fs.Print(verbose=True)
pychrm_res = FeatureSpaceClassification.NewWND5(fs, fs, fw)
pychrm_res.Print()
#
# import cProfile as pr
# #import profile as pr
# import tempfile
# import pstats
# prof = tempfile.NamedTemporaryFile()
# cmd = 'no_tile_pychrm_result = DiscreteBatchClassificationResult.New( reduced_fs, reduced_fs, fw )'
# pr.runctx( cmd, globals(), locals(), prof.name)
# p = pstats.Stats(prof.name)
# p.sort_stats('time').print_stats(20)
# prof.close()
self.maxDiff = None
html_path = pychrm_test_dir + sep + 'lymphoma_iicbu2008_subset_eosin_t5x6_v3.2feats_REFERENCE_RESULTS_900_samples_TRAINING_ERROR.html'
wres = FeatureSpaceClassificationExperiment.NewFromHTMLReport(
html_path)
wres.Print()
wc_batch_result = wres.individual_results[
0] # only 1 split in fit-on-fit
# This takes WAY too long:
#self.assertSequenceEqual( wc_batch_result.individual_results, pychrm_res.individual_results )
wc_result = np.empty((3 * len(wc_batch_result.individual_results)))
for i, single_result in enumerate(
wc_batch_result.individual_results):
wc_result[i * 3:(i + 1) *
3] = single_result.marginal_probabilities
pc_result = np.empty((3 * len(pychrm_res.individual_results)))
for i, single_result in enumerate(pychrm_res.individual_results):
# HTML report only has 3 decimal places
pc_result[ i*3 : (i+1)*3 ] = \
[ float( "{0:0.3f}".format( val ) ) for val in single_result.marginal_probabilities ]
from numpy.testing import assert_allclose
assert_allclose(actual=pc_result, desired=wc_result, atol=0.003)
#wc_batch_result.Print()
#pres.Print()
# ==========================================================
# Now do the same with tiling, reusing fs from before:
num_samples_per_group = 30
n_groups = fs.num_samples / num_samples_per_group
new_sg_ids = [
i for i in xrange(n_groups)
for j in xrange(num_samples_per_group)
]
fs.Update( tile_num_rows=5, tile_num_cols=6, num_samples_per_group=30,\
_contiguous_sample_group_ids=new_sg_ids )._RebuildViews()
with_tile_pychrm_result = FeatureSpaceClassification.NewWND5(
fs, fs, fw)
html_path = pychrm_test_dir + sep + 'lymphoma_iicbu2008_subset_eosin_t5x6_v3.2feats_REFERENCE_RESULTS_30_samples_tiled_TRAINING_ERROR.html'
with_tile_wndchrm_result = \
FeatureSpaceClassificationExperiment.NewFromHTMLReport( html_path ).individual_results[0]
#self.assertSequenceEqual( with_tile_pychrm_result.averaged_results, with_tile_wndchrm_result.individual_results )
wc_result = np.empty(
(3 * len(with_tile_wndchrm_result.individual_results)))
for i, single_result in enumerate(
with_tile_wndchrm_result.individual_results):
wc_result[i * 3:(i + 1) *
3] = single_result.marginal_probabilities
pc_result = np.empty(
(3 * len(with_tile_pychrm_result.averaged_results)))
for i, single_result in enumerate(
with_tile_pychrm_result.averaged_results):
# HTML report only has 3 decimal places
pc_result[ i*3 : (i+1)*3 ] = \
[ float( "{0:0.3f}".format( val ) ) for val in single_result.marginal_probabilities ]
assert_allclose(actual=pc_result, desired=wc_result, atol=0.003)
finally:
rmtree(tempdir)