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_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)
reduced_fisher_weights = full_fisher_weights.Threshold( num_features )
# 6. Reduce the training set feature space to contain only those top 200 features
reduced_training_set = full_training_set.FeatureReduce( reduced_fisher_weights.names )
# 7. Save your work:
reduced_training_set.PickleMe( os.path.splitext(input_filename)[0] + ".fit.pickled" )
reduced_fisher_weights.PickleMe( os.path.splitext(input_filename)[0] + "_w"+str(num_features)+".weights.pickled" )
else:
# I've already done all that, just proceed from here:
reduced_training_set = FeatureSet_Discrete.NewFromPickleFile( pickled_features )
reduced_fisher_weights = FisherFeatureWeights.NewFromPickleFile( pickled_weights )
# create the tile image iterator
image_iter = SampleImageTiles (input_image, scan_x, scan_y, True)
print "Number of samples = "+str (image_iter.samples)
# Create a list of zero'd out, image-sized, 2-D byte numpys
masks = []
for i in range( reduced_training_set.num_classes ):
masks.append ( np.zeros (shape=(image_iter.image.height,image_iter.image.width), dtype='uint8') )
# iterate over the image, classifying each tile
for sample in image_iter.sample():
try:
test_image_signatures = Signatures.NewFromFeatureNameList( sample, reduced_fisher_weights.names )
test_image_signatures.Normalize( reduced_training_set )
result = DiscreteImageClassificationResult.NewWND5( reduced_training_set, reduced_fisher_weights, test_image_signatures )
for i in range( reduced_training_set.num_classes ):
# 7. Save your work:
reduced_training_set.PickleMe(
os.path.splitext(input_filename)[0] + ".fit.pickled")
reduced_fisher_weights.PickleMe(
os.path.splitext(input_filename)[0] + "_w" + str(num_features) +
".weights.pickled")
else:
# I've already done all that, just proceed from here:
reduced_training_set = FeatureSet_Discrete.NewFromPickleFile(
pickled_features)
reduced_fisher_weights = FisherFeatureWeights.NewFromPickleFile(
pickled_weights)
# create the tile image iterator
image_iter = SampleImageTiles(input_image, scan_x, scan_y, True)
print "Number of samples = " + str(image_iter.samples)
# Create a list of zero'd out, image-sized, 2-D byte numpys
masks = []
for i in range(reduced_training_set.num_classes):
masks.append(
np.zeros(shape=(image_iter.image.height, image_iter.image.width),
dtype='uint8'))
# iterate over the image, classifying each tile
for sample in image_iter.sample():
try:
test_image_signatures = Signatures.NewFromFeatureNameList(
sample, reduced_fisher_weights.names)
test_image_signatures.Normalize(reduced_training_set)