def test_NewFromFileOfFiles( self ):
"""Pulls in the lymphoma eosin histology 5x6 tiled featureset via .sig files."""
# Types of files containing features:
# FIT: contains an entire FeatureSpace definition including features.
# FOF: "File Of Files" containing a FeatureSpace structure definition only,
# listing paths to files of pre-calculated features (.sig) or the
# tiff images themselves so features can be calculated
# SIG: A text file containing pre-calculated features for a single sample.
# Test dataset: subset of the IICBU2008 lymphoma dataset. 2 channels (H+E),
# 3 classes ('CLL', 'FL', 'MCL'), 10 images per class per channel,
# 5x6 tiling grid = 30 samples per image resulting in
# 2 x 3 x 10 X 30 = 1800 total samples available
# Files containing features included in this test suite:
# 1. lymphoma_iicbu2008_subset_EOSIN_ONLY_t5x6_v3.2features.fit.zip:
# A zip archive containing a single FIT file with features pre-calculated.
# 2. lymphoma_iicbu2008_subset_HE_t5x6_v3.2features_SIGFILES.zip:
# Contains 1800 SIG files, plus 4 FOF files (items 2-5 below):
# "lymphoma_iicbu2008_subset_EOSIN_ONLY_images.fof.tsv"
# "lymphoma_iicbu2008_subset_EOSIN_ONLY_sigfiles_t5x6-l.fof.tsv"
# "lymphoma_iicbu2008_subset_2CHAN_HE_images.fof.tsv"
# "lymphoma_iicbu2008_subset_2CHAN_HE_sigfiles_t5x6-l.fof.tsv"
# List of possible feature sources:
# 1. Single channel FIT (Eosin only)
# 2. Single channel FOF (Eosin only) referencing to 30 tiffs (requires global sampling options -t5x6 -l to grab sigs)
# 3. Single channel FOF (Eosin only) referencing 900 sig files
# 4. Double channel FOF (Eosin+Haemotoxylin) referencing 60 tiffs (requires global sampling options -t5x6 -l to grab sigs)
# 5. Double channel FOF (Eosin+Haemotoxylin) referencing 1800 sig files.
#=============================================
# BEGIN CODE TO CREATE TESTDATA ZIP PACKAGE
#import zipfile
#import zlib
#path = '/Users/chris/src/wnd-charm/tests/pywndcharm_tests/TESTDATA_lymphoma_iicbu2008_subset_HE_t5x6_v3.2features_SIGFILES.zip'
#zf = zipfile.ZipFile( path, mode='w' )
#import os
#classes = 'CLL', 'FL', 'MCL',
#channels = 'haemotoxylin', 'eosin'
#from collections import defaultdict
#sig_tracker = defaultdict(int)
#samplegroupid_tracker = {}
#samplegroup_counter = 0
#
#eosin_tif_fof = [] # 30 lines
#eosin_sig_fof = [] # 900 lines
#double_tif_fof = [] # 30 lines, 2 feature set columns
#double_sig_fof = [] # 900 lines, 2 feature set columns
#
#for _channel in channels:
# zf.write( './' + _channel, compress_type=zipfile.ZIP_DEFLATED )
# for _class in classes:
# zf.write( './' + _channel + '/' + _class, compress_type=zipfile.ZIP_DEFLATED )
# for root, dirs, files in os.walk( _channel + '/' + _class ):
# for _file in files:
# if _file.endswith( '.tif' ):
# # Strip off the _H.tif or _E.tif
# samplename = _file[:-6]
# eosinpath = './eosin/' + _class + '/' + samplename + '_E.tif'
# haemopath = './haemotoxylin/' + _class + '/' + samplename + '_H.tif'
# if _channel == 'eosin':
# eosin_tif_fof.append( eosinpath + '\t' + _class )
# double_tif_fof.append( samplename + '\t' + _class + '\t' + eosinpath + '\t{\tchannel\t=\teosin\t}\t' + haemopath + '\t{\tchannel\t=\thaemotoxylin\t}')
# elif _file.endswith( '.sig' ):
# zf.write( './' + _channel + '/' + _class + '/' + _file, compress_type=zipfile.ZIP_DEFLATED )
# if _channel == 'eosin':
# # Strip off the _H-t5x6_0_0-l.sig
# samplename = _file[:-17] + '.tif'
# eosinpath = './eosin/' + _class + '/' + _file
# haemopath = './haemotoxylin/' + _class + '/' + _file.replace( '_E-t5x6_', '_H-t5x6_' )
# # count samples from 0:
# samplesequenceid = str( sig_tracker[ samplename ] )
# sig_tracker[ samplename ] += 1
# if samplename not in samplegroupid_tracker:
# samplegroupid_tracker[ samplename ] = samplegroup_counter
# samplegroup_counter += 1
# samplegroupid = str( samplegroupid_tracker[ samplename ] )
# eosin_sig_fof.append( eosinpath + '\t' + _class )
# double_sig_fof.append( samplename + '\t' + _class + '\t' + eosinpath + '\t{\tchannel\t=\teosin\t;\tsamplegroupid\t=\t' + samplegroupid + '\t;\tsamplesequenceid\t=\t' + samplesequenceid + '\t}\t' + haemopath + '\t{\tchannel\t=\thaemotoxylin\t;\tsamplegroupid\t=\t' + samplegroupid + '\t;\tsamplesequenceid\t=\t' + samplesequenceid + '\t}\t')
#
#fof_dir = '/Users/chris/src/wnd-charm/tests/pywndcharm_tests/'
#with open( 'lymphoma_iicbu2008_subset_EOSIN_ONLY_images.fof.tsv', 'w') as out:
# for _ in eosin_tif_fof:
# out.write( _ + '\n')
#with open( 'lymphoma_iicbu2008_subset_EOSIN_ONLY_sigfiles_t5x6-l.fof.tsv', 'w') as out:
# for _ in eosin_sig_fof:
# out.write( _ + '\n')
#with open( 'lymphoma_iicbu2008_subset_2CHAN_HE_images.fof.tsv', 'w') as out:
# for _ in double_tif_fof:
# out.write( _ + '\n')
#with open( 'lymphoma_iicbu2008_subset_2CHAN_HE_sigfiles_t5x6-l.fof.tsv', 'w') as out:
# for _ in double_sig_fof:
# out.write( _ + '\n')
#zf.write( './' + 'lymphoma_iicbu2008_subset_EOSIN_ONLY_images.fof.tsv', compress_type=zipfile.ZIP_DEFLATED )
#zf.write( './' + 'lymphoma_iicbu2008_subset_EOSIN_ONLY_sigfiles_t5x6-l.fof.tsv', compress_type=zipfile.ZIP_DEFLATED )
#zf.write( './' + 'lymphoma_iicbu2008_subset_2CHAN_HE_images.fof.tsv', compress_type=zipfile.ZIP_DEFLATED )
#zf.write( './' + 'lymphoma_iicbu2008_subset_2CHAN_HE_sigfiles_t5x6-l.fof.tsv', compress_type=zipfile.ZIP_DEFLATED )
#zf.printdir()
#zf.close()
# END CODE TO CREATE TESTDATA ZIP PACKAGE
#=============================================
# Inflate the zipped test fit into a temp file
import zipfile
zipped_file_path = pychrm_test_dir + sep + 'lymphoma_iicbu2008_subset_HE_t5x6_v3.2features_SIGFILES.zip'
zf1 = zipfile.ZipFile( zipped_file_path, mode='r' )
tempdir = mkdtemp()
zf1.extractall( tempdir )
# for comparison:
zf2 = zipfile.ZipFile( pychrm_test_dir + sep + 'lymphoma_iicbu2008_subset_EOSIN_ONLY_t5x6_v3.2features.fit.zip', mode='r')
zf2.extractall( tempdir )
try:
kwargs = {}
kwargs['pathname'] = tempdir + sep + 'lymphoma_iicbu2008_subset_EOSIN_ONLY_sigfiles_t5x6-l.fof.tsv'
kwargs['quiet'] = True
# sampling opts: -l -t5x6 implies 5 columns and 6 rows ... I know it's weird.
kwargs['long'] = True
kwargs['tile_num_rows'] = 6
kwargs['tile_num_cols'] = 5
fs_fof = FeatureSpace.NewFromFileOfFiles( **kwargs )
kwargs['pathname'] = tempdir + sep + 'lymphoma_iicbu2008_subset_eosin_t5x6_v3.2features.fit'
fs_fit = FeatureSpace.NewFromFitFile( **kwargs )
# Fit file has less significant figures than Signature files, and it's not
# consistent how many there are. Seems like fit file just lops off numbers
# at the end. Example: (signatures on top, fit on bottom)
#
# Example:
# - 17.232246, # sig
# ? --
#
# + 17.2322, # fit
# - -63.549056, # sig
# ? ^^^
#
# + -63.5491, # fit
# ? ^
#
# - 223.786977, # sig
# ? ---
#
# + 223.787, # fit
# More of the same:
#(Pdb) fs_fof.data_matrix[0,-5:]
#array([ 0.935442, 14.005003, -43.562076, 127.394914, 0.628772])
#(Pdb) fs_fit.data_matrix[0,-5:]
#array([ 0.935442, 14.005 , -43.5621 , 127.395 , 0.628772])
# default is rtol=1e-07, atol=0
#np.testing.assert_allclose( actual=fs_fit.data_matrix, desired=fs_fof.data_matrix,
# rtol=1e-03, atol=0 )
#np.testing.assert_array_almost_equal_nulp( fs_fit.data_matrix, fs_fof.data_matrix )
for row_num, (fit_row, fof_row) in enumerate( zip( fs_fit.data_matrix, fs_fof.data_matrix )):
retval = compare( fit_row, fof_row )
if retval == False:
print "error in sample row", row_num
print "FIT: ", fs_fit._contiguous_sample_names[row_num], "FOF", fs_fof._contiguous_sample_names[row_num]
self.assertTrue( retval )
# Test sorting; scramble the FOF then load and check:
sorted_fof = tempdir + sep + \
'lymphoma_iicbu2008_subset_EOSIN_ONLY_sigfiles_t5x6-l.fof.tsv'
with open( sorted_fof) as fof:
lines = fof.readlines()
from random import shuffle
shuffle(lines)
unsorted_fof = tempdir + sep + \
'lymphoma_iicbu2008_subset_EOSIN_ONLY_sigfiles_t5x6-l_UNSORTED.fof.tsv'
with open( unsorted_fof, 'w' ) as fof:
for line in lines:
fof.write( line )
kwargs = {}
kwargs['pathname'] = unsorted_fof
kwargs['quiet'] = True
# sampling opts: -l -t5x6 implies 5 columns and 6 rows ... I know it's weird.
kwargs['long'] = True
kwargs['tile_num_rows'] = 6
kwargs['tile_num_cols'] = 5
fs_fof = FeatureSpace.NewFromFileOfFiles( **kwargs )
# Check again
for row_num, (fit_row, fof_row) in enumerate( zip( fs_fit.data_matrix, fs_fof.data_matrix )):
retval = compare( fit_row, fof_row )
if retval == False:
print "error in sample row", row_num
print "FIT: ", fs_fit._contiguous_sample_names[row_num], "FOF", fs_fof._contiguous_sample_names[row_num]
self.assertTrue( retval )
# TESTING TAKE TILES:
self.assertRaises( ValueError, fs_fof.TakeTiles, tuple() )
self.assertRaises( ValueError, fs_fof.TakeTiles, (45, 46, 47,) )
self.assertRaises( TypeError, fs_fof.TakeTiles, 'crap' )
# take middle 4
wanted_tiles = ( 14, 15, 20, 21 )
took = fs_fof.TakeTiles( wanted_tiles, inplace=False )
num_sample_groups = len( set( fs_fof._contiguous_sample_group_ids ) )
self.assertEqual( took.num_samples_per_group, len( wanted_tiles ) )
self.assertEqual( took.num_samples, len( wanted_tiles ) * num_sample_groups )
# mid4 = 'lymphoma_iicbu2008_subset_EOSIN_ONLY_sigfiles_MIDDLE_4_TILES_t5x6-l.fof.tsv'
# # fake out wndcharm by putting empty tiffs in the temp dir
# # we don't need them, the sigs are in there already.
# with open( mid4) as fof:
# lines = fof.readlines()
# names, classes, paths, opts = zip( *[ _.split('\t') for _ in lines ] )
# for _path in paths:
# with open( tempdir + sep + _path, 'w' ):
# pass
# took_via_fof = FeatureSpace.NewFromFileOfFiles( mid4, num_samples_per_group=4 )
#
# for row_num, (fit_row, fof_row) in enumerate( zip( took.data_matrix, took_via_fof.data_matrix )):
# retval = compare( fit_row, fof_row )
# if retval == False:
# print "error in sample row", row_num
# print "FIT: ", took._contiguous_sample_names[row_num], "FOF", took_via_fof._contiguous_sample_names[row_num]
# self.assertTrue( retval )
finally:
rmtree( tempdir )
args = parser.parse_args()
num_splits = args.n
num_bins = args.b
input_filename = args.classifier_file_path[0]
outpath = args.output_filepath
dump_pickle = args.D
if input_filename.endswith( ".fit" ):
full_set = FeatureSpace.NewFromFitFile( input_filename )
elif input_filename.endswith( ".fit.pickled" ):
full_set = FeatureSpace.NewFromPickleFile( input_filename )
elif input_filename.endswith( ".fof" ):
full_set = FeatureSpace.NewFromFileOfFiles( input_filename )
else:
raise Exception( 'The classifier must either end in .fit, .fit.pickled, or .fof' )
if not dump_pickle == 'unset':
if dump_pickle:
# user used -D to specify a name for their training set pickle
full_set.PickleMe( dump_pickle )
else:
# user used -D as a flag, use default pickle name pattern
full_set.PickleMe()
num_features_per_bin = int( float( len( full_set.feature_names ) ) / float( num_bins ) )
bin_offset = 0
def test_ParallelTiling(self):
"""Specify bounding box to FeatureVector, calc features, then compare
with C++ implementation-calculated feats."""
import zipfile
from shutil import copy
from tempfile import NamedTemporaryFile
refdir = mkdtemp(prefix='ref')
targetdir = mkdtemp(prefix='target')
try:
reference_feats = pychrm_test_dir + sep + 'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E_t6x5_REFERENCE_SIGFILES.zip'
zf = zipfile.ZipFile(reference_feats, mode='r')
zf.extractall(refdir)
img_filename = "lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E.tif"
orig_img_filepath = pychrm_test_dir + sep + img_filename
# copy the tiff to the tempdir so the .sig files end up there too
copy(orig_img_filepath, targetdir)
copy(orig_img_filepath, refdir)
input_image_path = targetdir + sep + img_filename
with NamedTemporaryFile(mode='w',
dir=refdir,
prefix='ref',
delete=False) as temp:
ref_fof = temp.name
temp.write('reference_samp\ttest_class\t{}\t{{}}\n'.format(
refdir + sep + img_filename))
with NamedTemporaryFile(mode='w',
dir=targetdir,
prefix='target',
delete=False) as temp:
target_fof = temp.name
temp.write(
'test_samp\ttest_class\t{}\t{{}}\n'.format(targetdir +
sep +
img_filename))
global_sampling_options = \
FeatureVector( long=True, tile_num_cols=6, tile_num_rows=5 )
# Should just load reference sigs
ref_fs = FeatureSpace.NewFromFileOfFiles(
ref_fof,
quiet=False,
global_sampling_options=global_sampling_options)
target_fs = FeatureSpace.NewFromFileOfFiles(
target_fof,
n_jobs=True,
quiet=False,
global_sampling_options=global_sampling_options)
#from numpy.testing import assert_allclose
#self.assertTrue( assert_allclose( ref_fs.data_matrix, target_fs.data_matrix ) )
from wndcharm.utils import compare
for row_num, (ref_row, test_row) in enumerate(
zip(ref_fs.data_matrix, target_fs.data_matrix)):
retval = compare(ref_row, test_row)
if retval == False:
print "error in sample row", row_num
print "FIT: ", ref_fs._contiguous_sample_names[
row_num], "FOF", target_fs._contiguous_sample_names[
row_num]
self.assertTrue(retval)
finally:
rmtree(refdir)
rmtree(targetdir)
