def gettingSolu(plate):
global monOutput
global loadingFolder
print "current directory ", os.getcwd()
#print os.getcwd()
newFrameLot = None
print plate
listW = os.listdir('/media/lalil0u/New/workspace2/Tracking/data/raw/'+plate)
for well in listW:
well=well[:-5]
print well
filename = '/media/lalil0u/New/workspace2/Tracking/data/raw/'+plate+"/"+well+".hdf5"
filenameT = '/media/lalil0u/New/workspace2/Tracking/data/TSinclMD/PL'+plate+"___P"+well+"___T00000.xml"
monOutput+="plate = "+plate+",well = "+well+"\n"
#ajout du frameLot et du tabF
frameLotC, tabFC = test.gettingRaw(filename, filenameT, plate, well)
if newFrameLot == None:
newFrameLot = frameLotC
else: newFrameLot.addFrameLot(frameLotC)
predictions = {}
for well in listW:
well=well[:-5]
print well
filenameD = '/media/lalil0u/New/workspace2/Tracking/data/CecogPredictions/'+plate+'/tracking_graph___P'+well+'.dot'
predictions.update({well: lireDot(filenameD)})
return newFrameLot, predictions
def gettingSolu(plate, well):
global loadingFolder
newFrameLot = None
print "Loading data from ", plate, well
filename = '/media/lalil0u/New/workspace2/Tracking/data/raw/'+plate+"/"+well+".hdf5"
filenameT = '/media/lalil0u/New/workspace2/Tracking/data/TSinclMD/PL'+plate+"___P"+well+"___T00000.xml"
#ajout du frameLot et du tabF
frameLotC, tabFC = test.gettingRaw(filename, filenameT, plate, well)
if newFrameLot == None:
newFrameLot = frameLotC
else: newFrameLot.addFrameLot(frameLotC)
#
return newFrameLot
def gettingSolu(plate, phenoOnly=False):
global monOutput
global loadingFolder
print "current directory ", os.getcwd()
# print os.getcwd()
newFrameLot = None
print plate
listW = os.listdir("/media/lalil0u/New/workspace2/Tracking/data/raw/" + plate)
for well in listW:
well = well[:-5]
print well
if phenoOnly:
if well not in d_ctrl[plate]:
print "------------------------PAS PRIS------------------------"
continue
else:
print "CONTROL"
filename = "/media/lalil0u/New/workspace2/Tracking/data/raw/" + plate + "/" + well + ".hdf5"
filenameT = "/media/lalil0u/New/workspace2/Tracking/data/TSinclMD/PL" + plate + "___P" + well + "___T00000.xml"
monOutput += "plate = " + plate + ",well = " + well + "\n"
# ajout du frameLot et du tabF
frameLotC, tabFC = test.gettingRaw(filename, filenameT, plate, well)
if newFrameLot == None:
newFrameLot = frameLotC
else:
newFrameLot.addFrameLot(frameLotC)
predictions = {}
return newFrameLot, predictions
def gettingSolu(plate, pheno_only=False):
global monOutput
global FEATURE_NUMBER
global loadingFolder
global first
global ctrl; global pheno
#tableau qui contiendra toutes les features de tlm pr voir lesquelles contiennent des NaN
tabF= None
print "current directory ", os.getcwd()
fichier = open(loadingFolder+"featuresToDelete.pkl", 'r')
f = pickle.load(fichier)
fichier.close()
#print os.getcwd()
newFrameLot = None
print plate
listW = os.listdir('/media/lalil0u/New/workspace2/Tracking/data/raw/'+plate)
for well in listW:
well=well[:-5]
print well
if pheno_only:
if well not in d_ctrl[plate]:
if pheno>0:
print "------------------------PAS PRIS------------------------"
pheno-=1
continue
else:
print "PHENO"
else:
if ctrl>0:
print "------------------------PAS PRIS------------------------"
ctrl-=1
continue
else:
print "CONTROL"
filename = '/media/lalil0u/New/workspace2/Tracking/data/raw/'+plate+"/"+well+".hdf5"
filenameT = '/media/lalil0u/New/workspace2/Tracking/data/TSinclMD/PL'+plate+"___P"+well+"___T00000.xml"
monOutput+="plate = "+plate+",well = "+well+"\n"
#ajout du frameLot et du tabF
frameLotC, tabFC = test.gettingRaw(filename, filenameT, plate, well)
if newFrameLot == None:
newFrameLot = frameLotC
else: newFrameLot.addFrameLot(frameLotC)
tabF = tabFC if tabF == None else np.vstack((tabF, tabFC))
# print "final training set content :"
# count, total= newFrameLot.statisticsTraining2()
# print count, total
if newFrameLot is None:
return None, None
c, f2 = treatments.whichAreNan(tabF)
#print len(f2.keys()), len(f)
# if len(f)<len(f2.keys()):
# pdb.set_trace()
#
#if there are features with NaN entries in the predict data but not in the training data
toZeros = filter(lambda x: x not in f, f2.keys())
#pdb.set_trace()
if toZeros !=[]:
msg="WARNING WARNING WARNING, some features here have NaN entries, and this was not the case in the training set. They are put to 0"
warnings.warn(msg)
newFrameLot.zeros(toZeros)
newFrameLot.clean(f)
if first:
FEATURE_NUMBER -=len(f)
print "Feature number", FEATURE_NUMBER
print "Getting all uplets now"
print "TIME TIME TIME", time.clock()
#ICI ON RECUPERE DONC LES SINGLETS ET DOUBLETS AVEC LA VALEUR DU TRAINING DANS CELL.TO SI ILS Y SONT, NONE SINON
#POUR LE CENTRE ET LES FEATURES C'EST LA MOYENNE DES OBJETS DU SINGLET
singlets, doublets = newFrameLot.getAllUplets()
#pour l'instant je ne garde que le passage de l'image 0 a 1
print "TIME TIME TIME after getting all uplets", time.clock()
print "Joining uplets now"
solutions = joining.j(singlets, doublets, FEATURE_NUMBER, training = False)
print "TIME TIME TIME after joining", time.clock()
return solutions, newFrameLot
def gettingSolu(loadingFolder, hdf5Folder = '/media/lalil0u/New/workspace2/Tracking/data/predict/', plate=None, wellL=None, training = False, first=True, xb_screen=False):
global monOutput
global FEATURE_NUMBER
tabF = None
#var pour indiquer si on prend un toy example ou pas
#tableau qui contiendra toutes les features de tlm pr voir lesquelles contiennent des NaN
# print "current directory ", os.getcwd()
fichier = open(loadingFolder+"featuresToDelete.pkl", 'r')
f = pickle.load(fichier)
fichier.close()
newFrameLot = None
listP = os.listdir(hdf5Folder)
if plate is not None:
listP=[plate]
for plate in listP:
print plate
listW = sorted(os.listdir(os.path.join(hdf5Folder, plate, 'hdf5')))
if wellL is not None:
listW = wellL
for well in listW[:18]:
well=well.split('_')[0]+'_'+well.split('_')[1][:2]
if not xb_screen:
filename = os.path.join(hdf5Folder, plate, 'hdf5', well+".hdf5")
else:
filename = os.path.join(hdf5Folder, plate, 'hdf5', well+".ch5")
print well
if training:
filenameT = '/media/lalil0u/New/workspace2/Tracking/data/trainingset/PL'+plate+"___P"+well+"___T00000.xml"
else:
filenameT = None
monOutput+="plate = "+plate+",well = "+well+"\n"
#ajout du frameLot et du tabF
frameLotC, tabFC = gettingRaw(filename, filenameT, plate, well, name_primary_channel='primary__primary3')
if newFrameLot == None:
newFrameLot = frameLotC
else: newFrameLot.addFrameLot(frameLotC)
tabF = tabFC if tabF == None else np.vstack((tabF, tabFC))
#en ce qui concerne le nettoyage des NaN
c, f2 = treatments.whichAreNan(tabF)
print len(f2.keys()), len(f)
#if there are features with NaN entries in the predict data but not in the training data
toZeros = filter(lambda x: x not in f, f2.keys())
if toZeros !=[]:
print "Attention attention, some features here have NaN entries, and this was not the case in the training set. They are put to 0"
newFrameLot.zeros(toZeros)
# if f!= f2.keys():
# featuresNames = imp.importFeaturesNames(filename)
# print filter(lambda x: x not in f, f2.keys())
# pdb.set_trace()
newFrameLot.clean(f) ##np.delete(X, f, 1)
if first:
FEATURE_NUMBER -=len(f)
#FEATURE_NUMBER -=len(bou)
print FEATURE_NUMBER
print "Getting all uplets now"
print "TIME TIME TIME", time.clock()
#ICI ON RECUPERE DONC LES SINGLETS ET DOUBLETS AVEC LA VALEUR DU TRAINING DANS CELL.TO SI ILS Y SONT, NONE SINON
#POUR LE CENTRE ET LES FEATURES C'EST LA MOYENNE DES OBJETS DU SINGLET
if training == False:
singlets, doublets = newFrameLot.getAllUplets(loadingFolder)
else:
singlets, doublets = newFrameLot.getTrainingUplets()
print "TIME TIME TIME after getting all uplets", time.clock()
print "joining uplets now"
solutions = j(singlets, doublets, FEATURE_NUMBER, training)
print "TIME TIME TIME after joining", time.clock()
print "normalization"
fichier = open(loadingFolder+"minMax_data_all.pkl", "r")
minMax = pickle.load(fichier)
fichier.close()
solutions.normalisation(minMax)
print "TIME TIME TIME after normalization", time.clock()
return solutions