def allFeatures_random_neg(features, labels, n_neg):
j=0
for i in range(0,len(features)-1):
for k in labels[i]:
if j == 0:
x = getFeatures(features[i],features[i+1],k[0],k[1])
j+=1
else:
x = np.vstack((x,getFeatures(features[i],features[i+1],k[0],k[1])))
#negative examples
count_negative = 0
while(count_negative < n_neg):
m = np.random.randint(1, max(labels[i][0])-10,size=2)
if m not in labels[i]:
count_negative+=1
x = np.vstack((x,getFeatures(features[i],features[i+1],m[0],m[1])))
return x
def allFeatures(features, labels, neg_labels):
j=0
lab=[]
for i in range(0,len(features)-1):
for k in labels[i]:
if j == 0:
x = getFeatures(features[i],features[i+1],k[0],k[1])
j+=1
else:
x = np.vstack((x,getFeatures(features[i],features[i+1],k[0],k[1])))
lab.append(1)
for k in neg_labels[i]:
if k not in labels[i].tolist():
x = np.vstack((x,getFeatures(features[i],features[i+1],k[0],k[1])))
lab.append(0)
x = x[:,~np.isnan(x).any(axis=0)] #now removing the nans
return x,np.asarray(lab)
def addSample(self, f1, f2, label, pluginManager):
# if self.labels == []:
self.labels.append(label)
# else:
# self.labels = np.concatenate((np.array(self.labels),label)) # for adding batches of features
features = self.constructSampleFeatureVector(f1, f2, pluginManager)
if self._numSamples is None:
# use vstack
if self.mydata is None:
self.mydata = features
else:
self.mydata = np.vstack((self.mydata, features))
else:
# allocate full array once, then fill in row by row
if self.mydata is None:
self.mydata = np.zeros((self._numSamples, features.shape[0]))
assert(self._nextIdx < self._numSamples)
self.mydata[self._nextIdx, :] = features
self._nextIdx += 1
def addSample(self, f1, f2, label, pluginManager):
# if self.labels == []:
self.labels.append(label)
# else:
# self.labels = np.concatenate((np.array(self.labels),label)) # for adding batches of features
features = self.constructSampleFeatureVector(f1, f2, pluginManager)
if self._numSamples is None:
# use vstack
if self.mydata is None:
self.mydata = features
else:
self.mydata = np.vstack((self.mydata, features))
else:
# allocate full array once, then fill in row by row
if self.mydata is None:
self.mydata = np.zeros((self._numSamples, features.shape[0]))
assert(self._nextIdx < self._numSamples)
self.mydata[self._nextIdx, :] = features
self._nextIdx += 1
def addSample(self, f1, f2, label):
#if self.labels == []:
self.labels.append(label)
#else:
# self.labels = np.concatenate((np.array(self.labels),label)) # for adding batches of features
res=[]
res2=[]
for key in selectedFeatures:
if key == "Global<Maximum >" or key=="Global<Minimum >":
# the global min/max intensity is not interesting
continue
elif key == 'RegionCenter':
res.append(np.linalg.norm(f1[key]-f2[key])) #difference of features
res2.append(np.linalg.norm(f1[key]*f2[key])) #product of features
elif key == 'Histogram': #contains only zeros, so trying to see what the prediction is without it
continue
elif key == 'Polygon': #vect has always another length for different objects, so center would be relevant
continue
else:
if not isinstance(f1[key], np.ndarray):
res.append(float(f1[key]) - float(f2[key]) ) #prepare for flattening
res2.append(float(f1[key]) * float(f2[key]) ) #prepare for flattening
else:
res.append((f1[key]-f2[key]).tolist() ) #prepare for flattening
res2.append((f1[key]*f2[key]).tolist() ) #prepare for flattening
x= np.asarray(flatten(res)) #flatten
x2= np.asarray(flatten(res2)) #flatten
assert(np.any(np.isnan(x)) == False)
assert(np.any(np.isnan(x2)) == False)
assert(np.any(np.isinf(x)) == False)
assert(np.any(np.isinf(x2)) == False)
#x= x[~np.isnan(x)]
#x2= x2[~np.isnan(x2)] #not getting the nans out YET
features = np.concatenate((x,x2))
if self.mydata is None:
self.mydata = features
else:
self.mydata = np.vstack((self.mydata, features))
endFrame = 20
#read in raw images - here ALL
filepath = '/net/hciserver03/storage/lparcala/mitocheck_006--01--06/manual_tracking2/'
gt_rawimage_filename = '/net/hciserver03/storage/lparcala/mitocheck_006--01--06/mitocheck_94570_2D+t_00-92.h5'
gt_rawimage = vigra.impex.readHDF5(gt_rawimage_filename, 'volume/data')
#this are the features for the first 5 time frames
features = compute_features(gt_rawimage,read_in_images(initFrame,endFrame, filepath),initFrame,endFrame)
mylabels = read_positiveLabels(initFrame,endFrame,filepath)
neg_labels = negativeLabels(features,mylabels)
mydata, endlabels = allFeatures(features, mylabels, neg_labels)
rf = vigra.learning.RandomForest()
rf.learnRF(mydata.astype("float32"), (np.asarray(endlabels)).astype("uint32").reshape(-1,1))
# Cross Validation
X, Y = allFeatures(features, mylabels, neg_labels)
total_number_of_samples = Y.shape[0]
kf = KFold(total_number_of_samples, 4, shuffle=True)
print "Starting cross validation"
final_measure = []
for train, test in kf:
rf = vigra.learning.RandomForest()
print "oob=",rf.learnRF(X[train].astype("float32"),Y[train].astype("uint32").reshape(-1,1))
test_error = precision_recall_fscore_support(Y[test],rf.predictLabels(X[test].astype("float32")),average='weighted')
print "test error=",test_error
final_measure.append(test_error[:3])
print np.vstack(tuple(final_measure))
print np.mean(np.vstack(tuple(final_measure)),axis=0)
