def Get_feat_test(ind,h,w, M_mean,nb_features):
img=np.empty([h,w,3])
GRAY_IM=np.empty([h,w])
img=M_mean[:,:,:][ind]
gray_img = rgb2gray(img)
gray_img = (gray_img * 255 ).astype( np.uint8 )
GRAY_IM[:,:]=gray_img-np.mean(gray_img)
GRAY_IM
FV=np.empty([nb_features])
matrix = PyImageMatrix()
matrix.allocate(h, w)
numpy_matrix = matrix.as_ndarray()
numpy_matrix[:] = GRAY_IM[:,:]
fv = FeatureVector( name='stufff', long=True, original_px_plane=matrix )
t1 = time.time()
fv.GenerateFeatures(quiet=True, write_to_disk=False)
t2 = time.time()
FV[:]=fv.values
Names=fv.feature_names
FV
FV=FV.astype(float)
return(FV)
def get_image_matrix(img_array):
if len(img_array.shape) != 2:
raise ValueError("array must be two-dimensional")
image_matrix = PyImageMatrix()
image_matrix.allocate(img_array.shape[1], img_array.shape[0])
numpy_matrix = image_matrix.as_ndarray()
numpy_matrix[:] = img_array
return image_matrix
def get_image_matrix(img_array):
if len(img_array.shape) != 2:
raise ValueError("array must be two-dimensional")
image_matrix = PyImageMatrix()
image_matrix.allocate(img_array.shape[1], img_array.shape[0])
numpy_matrix = image_matrix.as_ndarray()
numpy_matrix[:] = img_array
return image_matrix
def calc_features(img_arr, plane_tag, long=False):
assert len(img_arr.shape) == 2
pychrm_matrix = PyImageMatrix()
pychrm_matrix.allocate(img_arr.shape[1], img_arr.shape[0])
numpy_matrix = pychrm_matrix.as_ndarray()
numpy_matrix[:] = img_arr
signatures = FeatureVector(basename=plane_tag, long=long)
signatures.original_px_plane = pychrm_matrix
signatures.GenerateFeatures(write_to_disk=False)
return signatures
def Features_calcul_np_GrayscaleIm_WND(ind, nb_features, w, h, GRAY):
" calculate WND Charm Features from grayscale images (2919 features)"
FV = np.empty([nb_features])
matrix = PyImageMatrix()
matrix.allocate(h, w)
numpy_matrix = matrix.as_ndarray()
numpy_matrix[:] = GRAY[:, :][ind]
fv = FeatureVector(name='stufff', long=True, original_px_plane=matrix)
t1 = time.time()
fv.GenerateFeatures(quiet=True, write_to_disk=False)
t2 = time.time()
FV[:] = fv.values
Names = fv.feature_names
FV
return (FV, Names)
def Get_proba(ind, h, w, M_mean, nb_features):
img = np.empty([h, w, 3])
GRAY_IM = np.empty([h, w])
img = M_mean[:, :, :][ind]
gray_img = rgb2gray(img)
gray_img = (gray_img * 255).astype(np.uint8)
GRAY_IM[:, :] = gray_img - np.mean(gray_img)
GRAY_IM
FV = np.empty([nb_features])
matrix = PyImageMatrix()
matrix.allocate(h, w)
numpy_matrix = matrix.as_ndarray()
numpy_matrix[:] = GRAY_IM[:, :]
fv = FeatureVector(name='stufff', long=True, original_px_plane=matrix)
t1 = time.time()
fv.GenerateFeatures(quiet=True, write_to_disk=False)
t2 = time.time()
FV[:] = fv.values
Names = fv.feature_names
FV
FV = FV.astype(float)
pca = decomposition.PCA()
RFC = RandomForestClassifier()
estimators = [('reduce_dim', pca), ('Random_Forest', RFC)]
pipe = Pipeline(estimators)
params = dict(reduce_dim__n_components=90,
Random_Forest__n_estimators=200,
Random_Forest__random_state=0)
filename_Features_two_blocs = projectpath + 'io/Output/Features_two_blocs.npy'
FV_N = np.load(filename_Features_two_blocs)
X = FV_N
Data_FRAMES = pd.read_pickle(projectpath + 'io/Output/Dataframe_.pkl')
yr = Get_true_y(Data_FRAMES)
filename_yr = projectpath + 'io/Output/yr.npy'
np.save(filename_yr, yr)
yr = np.load(filename_yr)
RFC = RandomForestClassifier(n_estimators=200, random_state=0)
predictedVAL = cross_val_predict(RFC, X, yr, n_jobs=-1)
metrics.accuracy_score(yr, predictedVAL)
Conf_Mat = confusion_matrix(yr, predictedVAL)
RFC.fit(X, yr)
predict_probab = np.ones([M_mean.shape[0], 3])
predict_proba = RFC.predict_proba(FV)
predict_probab[ind, 0] = predict_proba[:, 0]
predict_probab[ind, 1] = predict_proba[:, 1]
predict_probab[ind, 2] = predict_proba[:, 2]
return (predict_probab)
def extractFeatures(ftb, ds, newOnly, chNames, imageId = None, im = None):
message = ''
tc = ftb.tc
# dataset must be explicitly provided because an image can be linked to
# multiple datasets in which case im.getDataset() doesn't work
if not im:
if not imageId:
#raise Exception('No input image')
raise omero.ServerError('No input image')
im = ftb.conn.getObject('Image', imageId)
if not im:
return 'Image id:%d not found\n' % imageId
else:
imageId = im.getId()
tid = WndcharmStorage.getAttachedTableFile(ftb.tc, ds)
if tid:
if not ftb.openTable(tid):
return message + '\nERROR: Table not opened\n'
version = unwrap(ftb.versiontag.getTextValue())
# version seems to be in unicode
message += 'Opened table id:%d version:%s\n' % (tid, str(version))
if newOnly and ftb.tableContainsId(imageId):
return message + 'Image id:%d features already in table' % imageId
# FIXME: default is convert multichannel to greyscale unless user input
# Calculate features for an image channel
# Optionally prepend the channel label to each feature name and combine
ftall = None
for c in xrange( len( chNames ) ):
wndcharm_matrix = PyImageMatrix()
wndcharm_matrix.allocate( im.getSizeX(), im.getSizeY() )
numpy_matrix = wndcharm_matrix.as_ndarray()
numpy_matrix[:] = im.getPrimaryPixels().getPlane(theZ=0,theC=c,theT=0)
feature_plan = wndcharm.StdFeatureComputationPlans.getFeatureSet();
options = "" # This is where you can tell wnd-charm to normalize pixel intensities,
# take ROIs etc. ... leave blank for now.
ft = Signatures.NewFromFeatureComputationPlan( wndcharm_matrix, feature_plan, options )
ft.names = [WndcharmStorage.insert_channel_name(
n, chNames[c]) for n in ft.names]
ft.source_path = im.getName()
if not ftall:
ftall = ft
else:
ftall.names += ft.names
ftall.values += ft.values
# Save the features to a table
if not tid:
ftb.createTable(ftall.names, ft.version)
version = unwrap(ftb.versiontag.getTextValue())
message += 'Created new table id:%d version:%s\n' % (
ftb.tc.tableId, version)
message += WndcharmStorage.addFileAnnotationTo(tc, ds)
if version != ft.version:
return message + 'Incompatible version: Stored=%s Calculated=%s' % (
version, ft.version)
ftb.saveFeatures(imageId, ftall)
return message + 'Extracted features from Image id:%d\n' % imageId
