def test_NewFromDirectory( self ):
""""""
ref_sig_path = 'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E-t6x5_5_4-l.sig'
ref_fv = FeatureVector.NewFromSigFile( pychrm_test_dir + sep + ref_sig_path )
from shutil import copy
tempdir = mkdtemp()
img_filename = "lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E-t6x5_5_4-l.tiff"
orig_img_filepath = pychrm_test_dir + sep + img_filename
copy( orig_img_filepath, tempdir )
try:
fs = FeatureSpace.NewFromDirectory( tempdir, quiet=False )
self.assertTrue( compare( fs.data_matrix[0], ref_fv.values ) )
#from numpy.testing import assert_allclose
#assert_allclose( ref_fv.values, fs.data_matrix[0], rtol=1e-05 )
finally:
rmtree( tempdir )
from os import mkdir
toptempdir = mkdtemp()
try:
class_names = []
for letter in 'CBA':
dirname = toptempdir + sep + letter
mkdir( dirname )
copy( orig_img_filepath, dirname )
fs = FeatureSpace.NewFromDirectory( toptempdir, quiet=False, )
self.assertEqual( fs.class_names, ['A', 'B', 'C' ] )
for row_of_features in fs.data_matrix:
self.assertTrue( compare( row_of_features, ref_fv.values ) )
finally:
rmtree( toptempdir )
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 )
def test_LargeFeatureSetGrayscale( self ):
"""Large feature set, grayscale image"""
reference_sample = FeatureVector.NewFromSigFile( self.sig_file_path,
image_path=self.test_tif_path )
target_sample = FeatureVector( source_filepath=self.test_tif_path,
long=True).GenerateFeatures( write_to_disk=False )
# This doesn't work since the ranges of features are so wide
# Tried using relative tolerance, but no dice:
# from numpy.testing import assert_allclose
# assert_allclose( reference_sample.values, target_sample.values, rtol=1e-3 )
# Remember we're reading these values in from strings. and the ranges are so wide
# you only have 6 sig figs. Better apples to apples comparison is to
# compare strings.
self.assertTrue( compare( target_sample.values, reference_sample.values ) )
def test_LargeFeatureSetGrayscale( self ):
"""Large feature set, grayscale image"""
reference_sample = FeatureVector.NewFromSigFile( self.sig_file_path,
image_path=self.test_tif_path )
target_sample = FeatureVector( source_filepath=self.test_tif_path,
long=True).GenerateFeatures( write_to_disk=False )
# This doesn't work since the ranges of features are so wide
# Tried using relative tolerance, but no dice:
# from numpy.testing import assert_allclose
# assert_allclose( reference_sample.values, target_sample.values, rtol=1e-3 )
# Remember we're reading these values in from strings. and the ranges are so wide
# you only have 6 sig figs. Better apples to apples comparison is to
# compare strings.
self.assertTrue( compare( target_sample.values, reference_sample.values ) )
def test_HeatMap_w_FeatureComputationPlan( self ):
"""Classification results using SampleImageTiles method and FOF should be the same.
"""
# chris@NIA-LG-01778617 ~/src/wnd-charm/tests/pywndcharm_tests
# $ tiffinfo lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E.tif
# TIFF Directory at offset 0x18ea9c (1632924)
# Image Width: 1388 Image Length: 1040
# Bits/Sample: 8
# Compression Scheme: LZW
# Photometric Interpretation: min-is-black
# Samples/Pixel: 1
# Rows/Strip: 5
# Planar Configuration: single image plane
# 5x6 tiling scheme => tile dims 208 x 231.33 each
scan_x = 231
scan_y = 208
#num_features = 200
# Inflate the zipped test fit into a temp file
tempdir = mkdtemp()
try:
import zipfile
reference_sigs = pychrm_test_dir + sep + 'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E_REFERENCE_SIGFILES.zip'
zf = zipfile.ZipFile( reference_sigs, mode='r' )
zf.extractall( tempdir )
img_filename = "lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E.tif"
orig_img_filepath = pychrm_test_dir + sep + img_filename
from shutil import copy
# copy the tiff to the tempdir so the .sig files end up there too
copy( orig_img_filepath, tempdir )
input_image_path = tempdir + sep + img_filename
# create the tile image iterator
image_iter = SampleImageTiles( input_image_path, scan_x, scan_y, True)
print "Number of samples = " + str( image_iter.samples )
base, ext = splitext( input_image_path )
# Just grab the first tile:
import pdb; pdb.set_trace()
tile_cropped_px_plane = image_iter.sample()
kwargs = {}
kwargs[ 'name' ] = input_image_path
kwargs[ 'source_filepath' ] = tile_cropped_px_plane
#kwargs[ 'feature_names' ] = fw.feature_names
#kwargs[ 'feature_computation_plan' ] = comp_plan
kwargs[ 'long' ] = True
kwargs[ 'tile_num_cols' ] = image_iter.tiles_x
kwargs[ 'tile_num_rows' ] = image_iter.tiles_y
kwargs[ 'tiling_scheme' ] = '{0}x{1}'.format( image_iter.tiles_x, image_iter.tiles_y )
kwargs[ 'tile_col_index' ] = image_iter.current_col
kwargs[ 'tile_row_index' ] = image_iter.current_row
kwargs[ 'sample_group_id' ] = 0
top_left_tile_feats = FeatureVector( **kwargs ).GenerateFeatures( quiet=False, write_to_disk=False )
top_left_tile_reference_feats = FeatureVector.NewFromSigFile( tempdir + sep + 'sj-05-3362-R2_001_E-t5x6_0_0-l.sig' )
# Remember we're reading these values in from strings. and the ranges are so wide
# you only have 6 sig figs. Better apples to apples comparison is to
# compare strings.
self.assertTrue( compare( top_left_tile_feats.values, top_left_tile_reference_feats.values ) )
# Setting feature_names initiates the feature reduce from
# the larger set of features that comes back from computation
#kwargs[ 'feature_names' ] = fw.feature_names
# if these are set, then the code will try to take a ROI of a ROI:
#kwargs[ 'x' ] = image_iter.current_x
#kwargs[ 'y' ] = image_iter.current_y
#kwargs[ 'w' ] = image_iter.tile_width
#kwargs[ 'h' ] = image_iter.tile_height
finally:
rmtree( tempdir )
def test_FeatureComputationFromROI( self ):
"""Specify bounding box to FeatureVector, calc features, then compare
with C++ implementation-calculated feats."""
# orig image lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E.tif
# has size=1388x1040
# WND-CHARM command line specifies via -tCxR param
# where C is columns and R is rows, ergo 5 rows, 6 cols = -t6x5
# tile dims => w=1388/6 cols = 231.33px wide, h=1040/5 rows = 208 px tall
ROI_width = 231
ROI_height = 208
# Inflate the zipped test fit into a temp file
tempdir = mkdtemp()
try:
import zipfile
reference_sigs = pychrm_test_dir + sep + 'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E_t6x5_REFERENCE_SIGFILES.zip'
zf = zipfile.ZipFile( reference_sigs, mode='r' )
zf.extractall( tempdir )
img_filename = "lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E.tif"
orig_img_filepath = pychrm_test_dir + sep + img_filename
from shutil import copy
# copy the tiff to the tempdir so the .sig files end up there too
copy( orig_img_filepath, tempdir )
input_image_path = tempdir + sep + img_filename
kwargs = {}
kwargs[ 'name' ] = img_filename
kwargs[ 'source_filepath' ] = input_image_path
#kwargs[ 'feature_names' ] = fw.feature_names
#kwargs[ 'feature_computation_plan' ] = comp_plan
kwargs[ 'long' ] = True
kwargs[ 'x' ] = 0
kwargs[ 'y' ] = 0
kwargs[ 'w' ] = ROI_width
kwargs[ 'h' ] = ROI_height
kwargs[ 'sample_group_id' ] = 0
top_left_tile_feats = FeatureVector( **kwargs ).GenerateFeatures( quiet=False, write_to_disk=False )
top_left_tile_reference_feats = FeatureVector.NewFromSigFile( tempdir + sep + 'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E-t6x5_0_0-l.sig' )
# Remember we're reading these values in from strings. and the ranges are so wide
# you only have 6 sig figs. Better apples to apples comparison is to
# compare strings.
self.assertEqual( top_left_tile_feats.feature_names, top_left_tile_reference_feats.feature_names )
self.assertTrue( compare( top_left_tile_feats.values, top_left_tile_reference_feats.values ) )
kwargs[ 'x' ] = 1155
kwargs[ 'y' ] = 832
bot_right_tile_feats = FeatureVector( **kwargs ).GenerateFeatures( quiet=False, write_to_disk=False )
bot_right_tile_reference_feats = FeatureVector.NewFromSigFile( tempdir + sep + 'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E-t6x5_5_4-l.sig' )
self.assertEqual( bot_right_tile_feats.feature_names, bot_right_tile_reference_feats.feature_names )
self.assertTrue( compare( bot_right_tile_feats.values, bot_right_tile_reference_feats.values ) )
finally:
rmtree( tempdir )
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 )
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)
def test_HeatMap_w_FeatureComputationPlan(self):
"""Classification results using SampleImageTiles method and FOF should be the same.
"""
# chris@NIA-LG-01778617 ~/src/wnd-charm/tests/pywndcharm_tests
# $ tiffinfo lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E.tif
# TIFF Directory at offset 0x18ea9c (1632924)
# Image Width: 1388 Image Length: 1040
# Bits/Sample: 8
# Compression Scheme: LZW
# Photometric Interpretation: min-is-black
# Samples/Pixel: 1
# Rows/Strip: 5
# Planar Configuration: single image plane
# 5x6 tiling scheme => tile dims 208 x 231.33 each
scan_x = 231
scan_y = 208
#num_features = 200
# Inflate the zipped test fit into a temp file
tempdir = mkdtemp()
try:
import zipfile
reference_sigs = pychrm_test_dir + sep + 'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E_REFERENCE_SIGFILES.zip'
zf = zipfile.ZipFile(reference_sigs, mode='r')
zf.extractall(tempdir)
img_filename = "lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E.tif"
orig_img_filepath = pychrm_test_dir + sep + img_filename
from shutil import copy
# copy the tiff to the tempdir so the .sig files end up there too
copy(orig_img_filepath, tempdir)
input_image_path = tempdir + sep + img_filename
# create the tile image iterator
image_iter = SampleImageTiles(input_image_path, scan_x, scan_y,
True)
print "Number of samples = " + str(image_iter.samples)
base, ext = splitext(input_image_path)
# Just grab the first tile:
import pdb
pdb.set_trace()
tile_cropped_px_plane = image_iter.sample()
kwargs = {}
kwargs['name'] = input_image_path
kwargs['source_filepath'] = tile_cropped_px_plane
#kwargs[ 'feature_names' ] = fw.feature_names
#kwargs[ 'feature_computation_plan' ] = comp_plan
kwargs['long'] = True
kwargs['tile_num_cols'] = image_iter.tiles_x
kwargs['tile_num_rows'] = image_iter.tiles_y
kwargs['tiling_scheme'] = '{0}x{1}'.format(image_iter.tiles_x,
image_iter.tiles_y)
kwargs['tile_col_index'] = image_iter.current_col
kwargs['tile_row_index'] = image_iter.current_row
kwargs['sample_group_id'] = 0
top_left_tile_feats = FeatureVector(**kwargs).GenerateFeatures(
quiet=False, write_to_disk=False)
top_left_tile_reference_feats = FeatureVector.NewFromSigFile(
tempdir + sep + 'sj-05-3362-R2_001_E-t5x6_0_0-l.sig')
# Remember we're reading these values in from strings. and the ranges are so wide
# you only have 6 sig figs. Better apples to apples comparison is to
# compare strings.
self.assertTrue(
compare(top_left_tile_feats.values,
top_left_tile_reference_feats.values))
# Setting feature_names initiates the feature reduce from
# the larger set of features that comes back from computation
#kwargs[ 'feature_names' ] = fw.feature_names
# if these are set, then the code will try to take a ROI of a ROI:
#kwargs[ 'x' ] = image_iter.current_x
#kwargs[ 'y' ] = image_iter.current_y
#kwargs[ 'w' ] = image_iter.tile_width
#kwargs[ 'h' ] = image_iter.tile_height
finally:
rmtree(tempdir)
def test_FeatureComputationFromROI(self):
"""Specify bounding box to FeatureVector, calc features, then compare
with C++ implementation-calculated feats."""
# orig image lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E.tif
# has size=1388x1040
# WND-CHARM command line specifies via -tCxR param
# where C is columns and R is rows, ergo 5 rows, 6 cols = -t6x5
# tile dims => w=1388/6 cols = 231.33px wide, h=1040/5 rows = 208 px tall
ROI_width = 231
ROI_height = 208
# Inflate the zipped test fit into a temp file
tempdir = mkdtemp()
try:
import zipfile
reference_sigs = pychrm_test_dir + sep + 'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E_t6x5_REFERENCE_SIGFILES.zip'
zf = zipfile.ZipFile(reference_sigs, mode='r')
zf.extractall(tempdir)
img_filename = "lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E.tif"
orig_img_filepath = pychrm_test_dir + sep + img_filename
from shutil import copy
# copy the tiff to the tempdir so the .sig files end up there too
copy(orig_img_filepath, tempdir)
input_image_path = tempdir + sep + img_filename
kwargs = {}
kwargs['name'] = img_filename
kwargs['source_filepath'] = input_image_path
#kwargs[ 'feature_names' ] = fw.feature_names
#kwargs[ 'feature_computation_plan' ] = comp_plan
kwargs['long'] = True
kwargs['x'] = 0
kwargs['y'] = 0
kwargs['w'] = ROI_width
kwargs['h'] = ROI_height
kwargs['sample_group_id'] = 0
top_left_tile_feats = FeatureVector(**kwargs).GenerateFeatures(
quiet=False, write_to_disk=False)
top_left_tile_reference_feats = FeatureVector.NewFromSigFile(
tempdir + sep +
'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E-t6x5_0_0-l.sig'
)
# Remember we're reading these values in from strings. and the ranges are so wide
# you only have 6 sig figs. Better apples to apples comparison is to
# compare strings.
self.assertEqual(top_left_tile_feats.feature_names,
top_left_tile_reference_feats.feature_names)
self.assertTrue(
compare(top_left_tile_feats.values,
top_left_tile_reference_feats.values))
kwargs['x'] = 1155
kwargs['y'] = 832
bot_right_tile_feats = FeatureVector(**kwargs).GenerateFeatures(
quiet=False, write_to_disk=False)
bot_right_tile_reference_feats = FeatureVector.NewFromSigFile(
tempdir + sep +
'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E-t6x5_5_4-l.sig'
)
self.assertEqual(bot_right_tile_feats.feature_names,
bot_right_tile_reference_feats.feature_names)
self.assertTrue(
compare(bot_right_tile_feats.values,
bot_right_tile_reference_feats.values))
finally:
rmtree(tempdir)
def test_HeatMap_w_FeatureComputationPlan( self ):
"""Classification results using SampleImageTiles method and FOF
should be the same."""
# chris@NIA-LG-01778617 ~/src/wnd-charm/tests/pywndcharm_tests
# $ tiffinfo lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E.tif
# TIFF Directory at offset 0x18ea9c (1632924)
# Image Width: 1388 Image Length: 1040
# Bits/Sample: 8
# Compression Scheme: LZW
# Photometric Interpretation: min-is-black
# Samples/Pixel: 1
# Rows/Strip: 5
# Planar Configuration: single image plane
# WND-CHARM command line specifies via -tCxR param
# where C is columns and R is rows, ergo 5 rows, 6 cols = -t6x5
# tile dims => w=1388/6 cols = 231.33px wide, h=1040/5 rows = 208 px tall
#scan_x = 231
#scan_y = 208
#num_features = 200
# Inflate the zipped test fit into a temp file
sourcedir = mkdtemp()
targetdir = mkdtemp()
try:
import zipfile
reference_sigs = pychrm_test_dir + sep + 'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E_t6x5_REFERENCE_SIGFILES.zip'
zf = zipfile.ZipFile( reference_sigs, mode='r' )
zf.extractall( targetdir )
img_filename = "lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E.tif"
orig_img_filepath = pychrm_test_dir + sep + img_filename
from shutil import copy
# copy the tiff to the tempdir so the .sig files end up there too
copy( orig_img_filepath, sourcedir )
input_image_path = sourcedir + sep + img_filename
# Create sliding window that emulates 6x5 tiling:
kwargs = {}
kwargs[ 'source_filepath' ] = input_image_path
kwargs[ 'tile_num_cols' ] = 6
kwargs[ 'tile_num_rows' ] = 5
kwargs[ 'long' ] = True
window = SlidingWindow( **kwargs )
print "Number of samples = " + str( window.num_positions )
base, ext = splitext( input_image_path )
ref_file = 'lymphoma_eosin_channel_MCL_test_img_sj-05-3362-R2_001_E-t6x5_{}_{}-l.sig'
# top left:
for test_feats in window.sample():
test_feats.GenerateFeatures( quiet=False, write_to_disk=False, cache=True )
reference_feats = FeatureVector.NewFromSigFile( targetdir + sep + ref_file.format(0,0) )
self.assertTrue( compare( test_feats.values, reference_feats.values ) )
break
# below top left:
#window.GenerateFeatures( quiet=False, write_to_disk=False, cache=True )
#reference_feats = FeatureVector.NewFromSigFile( targetdir + sep + ref_file.format(0,1) )
#self.assertTrue( compare( window.values, reference_feats.values ) )
# Setting feature_names initiates the feature reduce from
# the larger set of features that comes back from computation
#kwargs[ 'feature_names' ] = fw.feature_names
finally:
rmtree( sourcedir )
rmtree( targetdir )
