def readFromRootFile(self,filename,TupleMeanStd, weighter):
# this function defines how to convert the root ntuple to the training format
# options are not yet described here
import numpy as np
import ROOT
fileTimeOut(filename,120) #give eos a minute to recover
rfile = ROOT.TFile(filename)
tree = rfile.Get("tree")
self.nsamples=tree.GetEntries()
# user code, example works with the example 2D images in root format generated by make_example_data
from DeepJetCore.preprocessing import read2DArray
print(filename)
feature_array = read2DArray(filename,"tree","image2d",self.nsamples,32,32)
reg_truth = read2DArray(filename,"tree","sigfrac2d",self.nsamples,32,32)
bgfrac = 1 - reg_truth
truth = np.concatenate([reg_truth, bgfrac, feature_array], axis=-1)
#notremoves=weighter.createNotRemoveIndices(Tuple)
# this removes parts of the dataset for weighting the events
#feature_array = feature_array[notremoves > 0]
# call this in the end
self.nsamples=len(feature_array)
self.x=[feature_array] # list of feature numpy arrays
self.y=[truth] # list of target numpy arrays (truth)
self.w=[] # list of weight arrays. One for each truth target, not used
def convertFromSourceFile(self, filename, weighterobjects, istraining):
# This is the only really mandatory function (unless writeFromSourceFile is defined).
# It defines the conversion rule from an input source file to the lists of training
# arrays self.x, self.y, self.w
# self.x is a list of input feature arrays
# self.y is a list of truth arrays
# self.w is optional and can contain a weight array
# (needs to have same number of entries as truth array)
# If no weights are needed, this can be left completely empty
#
# The conversion should convert finally to numpy arrays. In the future,
# also tensorflow tensors will be supported.
#
# In this example, differnt ways of reading files are deliberatly mixed
#
print('reading ' + filename)
import ROOT
fileTimeOut(filename, 120) #give eos a minute to recover
rfile = ROOT.TFile(filename)
tree = rfile.Get("tree")
nsamples = tree.GetEntries()
# user code, example works with the example 2D images in root format generated by make_example_data
from DeepJetCore.preprocessing import read2DArray
feature_array = read2DArray(filename, "tree", "image2d", nsamples, 32,
32)
print('feature_array', feature_array.shape)
import uproot
urfile = uproot.open(filename)["tree"]
truth = np.concatenate([
np.expand_dims(urfile.array("isA"), axis=1),
np.expand_dims(urfile.array("isB"), axis=1),
np.expand_dims(urfile.array("isC"), axis=1)
],
axis=1)
truth = truth.astype(dtype='float32',
order='C') #important, float32 and C-type!
self.nsamples = len(feature_array)
#returns a list of feature arrays, a list of truth arrays and a list of weight arrays
return [feature_array], [truth], []
def readFromRootFile(self,filename,TupleMeanStd, weighter):
# this function defines how to convert the root ntuple to the training format
# options are not yet described here
import numpy as np
import ROOT
fileTimeOut(filename,120) #give eos a minute to recover
rfile = ROOT.TFile(filename)
tree = rfile.Get("tree")
self.nsamples=tree.GetEntries()
# user code, example works with the example 2D images in root format generated by make_example_data
from DeepJetCore.preprocessing import read2DArray,readListArray
print(filename)
feature_image = read2DArray(filename,"tree","image2d",self.nsamples,24,24)
npy_array = self.readTreeFromRootToTuple(filename)
scale = np.expand_dims(npy_array['scale'],axis=1)
xcenter = np.expand_dims(npy_array['xcenter'],axis=1)
ycenter = np.expand_dims(npy_array['ycenter'],axis=1)
ptype = np.expand_dims(npy_array['type'],axis=1)
print('ycenter',ycenter.shape)
add_features = np.concatenate([scale,xcenter,ycenter,ptype],axis=1)
xcoords = numpy.expand_dims( numpy.array(list(npy_array['xcoords']),dtype='float32'), axis=2)
ycoords = numpy.expand_dims( numpy.array(list(npy_array['ycoords']),dtype='float32'), axis=2)
xcoords = numpy.reshape(xcoords, newshape=[xcoords.shape[0],24,24,1])
ycoords = numpy.reshape(ycoords, newshape=[xcoords.shape[0],24,24,1])
print('xcoords',xcoords.shape)
all_coords = numpy.concatenate([xcoords,ycoords],axis=-1)
#readListArray(filename,"tree","frac_at_idxs",self.nsamples,4,1)
alltruth = numpy.zeros(self.nsamples)+1. #this is real data
self.x = [feature_image,all_coords,add_features]
self.y = [alltruth]
self.w=[]