def run(samples,
channel,
era,
use,
train,
short,
datacard=False,
add_nominal=False):
# import model
if use == "xgb":
from XGBModel import XGBObject as modelObject
parameters = "conf/parameters_xgb.json"
if use == "keras":
from KerasModel import KerasObject as modelObject
parameters = "conf/parameters_keras.json"
# create instance of Reader
read = Reader(channel=channel, config_file=samples, folds=2, era=era)
target_names = read.config["target_names"]
variables = read.config["variables"]
models_folder = era + "/models"
if not os.path.exists(models_folder):
os.makedirs(models_folder)
modelname = "{0}/{1}.{2}".format(models_folder, channel, use)
scaler = None
if train:
print "Training new model"
print "Loading Training set"
# load samples for training. This returns the input files merged (ggH+qqH+...), randomized and split into two folds
trainSet = read.getSamplesForTraining()
# use StandardScaler from sklearn and "train" it on the training set. Then pickle it store it for later and finaly apply it to the training set.
print "Fit Scaler to training set...",
scaler = trainScaler(trainSet, variables)
print " done. Dumping for later."
with open("{0}/StandardScaler.{1}.pkl".format(models_folder, channel),
'wb') as FSO:
cPickle.dump(scaler, FSO, 2)
scaler = [scaler, scaler] # Hotfix since KIT uses 2 scalers
trainSet = applyScaler(scaler, trainSet, variables)
# load model and start training
model = modelObject(parameter_file=parameters,
variables=variables,
target_names=target_names)
model.train(trainSet) # done in KerasModel.py
model.save(modelname)
# prediction starts
#load scaler and trained model
elif not datacard:
# TODO: Maybe not needed to check. Just load what is there
if os.path.exists("{0}/StandardScaler.{1}.pkl".format(
models_folder, channel)):
print "Loading Scaler"
scaler = []
if glob("{0}/{1}_*_keras_preprocessing.pickle".format(
models_folder, channel)):
with open(
"{0}/{1}_fold0_keras_preprocessing.pickle".format(
models_folder, channel), "rb") as FSO:
scaler.append(cPickle.load(FSO))
with open(
"{0}/{1}_fold1_keras_preprocessing.pickle".format(
models_folder, channel), "rb") as FSO:
scaler.append(cPickle.load(FSO))
else:
with open(
"{0}/StandardScaler.{1}.pkl".format(
models_folder, channel), "rb") as FSO:
tmp = cPickle.load(FSO)
scaler = [tmp, tmp]
print "Loading model and predicting."
model = modelObject(filename=modelname)
read.variables = model.variables
variables = model.variables
if not datacard:
outpath = read.config["outpath"] + "/predictions_" + era
predictions = {}
print "Predicting samples"
# only used by DESY
if add_nominal:
print "Predicting Nominal"
for sample, sampleConfig in read.get(what="nominal",
for_prediction=True):
sandbox(channel, model, scaler, sample, variables,
"nom_" + sampleConfig["histname"], outpath,
sampleConfig, read.modifyDF)
# Iterate over nominal samples
for sample, sampleConfig in read.get(what="full",
add_jec=not short,
for_prediction=True):
if "data" in sampleConfig["histname"]:
sandbox(channel, model, scaler, sample, variables,
"NOMINAL_ntuple_Data", outpath, sampleConfig,
read.modifyDF)
elif "full" in sampleConfig["histname"]:
sandbox(
channel, model, scaler, sample, variables,
"NOMINAL_ntuple_" + sampleConfig["histname"].split("_")[0],
outpath, sampleConfig, read.modifyDF)
else:
splName = sampleConfig["histname"].split("_")
sandbox(
channel, model, scaler, sample, variables,
"_".join(splName[1:]) + "_ntuple_" +
sampleConfig["histname"].split("_")[0], outpath,
sampleConfig, read.modifyDF)
# shape files
if not short:
print "Predicting shapes"
for sample, sampleConfig in read.get(what="tes",
for_prediction=True):
sandbox(channel, model, scaler, sample, variables,
sampleConfig["histname"], outpath, sampleConfig,
read.modifyDF)
if "hephy.at" in os.environ["HOME"]:
from Tools.Datacard.produce import Datacard, makePlot
from Tools.CutObject.CutObject import Cut
from Tools.FakeFactor.FakeFactor import FakeFactor
Datacard.use_config = era + "/datacard_conf"
D = Datacard(channel=channel,
variable="predicted_prob",
era=era,
real_est="mc",
add_systematics=not short,
debug=True,
use_cutfile="conf/cuts_{0}.json".format(era))
FakeFactor.fractions = "{0}/datacard_conf/fractions/htt_ff_fractions_{0}.root".format(
era)
D.create(era + "/" + use)
makePlot(channel, "ML", era + "/" + use, era, era + "/plots")
def run(samples,channel, use, train,short, preprocess_chain = []):
if use == "xgb":
from XGBModel import XGBObject as modelObject
parameters = "conf/parameters_xgb.json"
if use == "keras":
from KerasModel import KerasObject as modelObject
parameters = "conf/parameters_keras.json"
read = Reader(channel = channel,
config_file = samples,
folds=2)
target_names = read.config["target_names"]
variables = read.config["variables"]
if not os.path.exists("models"):
os.mkdir("models")
modelname = "models/{0}.{1}".format(channel,use)
scaler = None
if train:
print "Training new model"
print "Loading Training set"
trainSet = read.getSamplesForTraining()
print "Fit Scaler to training set...",
scaler = trainScaler(trainSet, variables )
print " done. Dumping for later."
with open("models/StandardScaler.{0}.pkl".format(channel), 'wb') as FSO:
cPickle.dump(scaler, FSO , 2)
trainSet = applyScaler(scaler, trainSet, variables)
model = modelObject( parameter_file = parameters,
variables=variables,
target_names = target_names )
model.train( trainSet )
model.save(modelname)
else:
if os.path.exists("models/StandardScaler.{0}.pkl".format(channel) ):
print "Loading Scaler"
with open( "models/StandardScaler.{0}.pkl".format(channel), "rb" ) as FSO:
scaler = cPickle.load( FSO )
print "Loading model and predicting."
model = modelObject( filename = modelname )
where = ""
coll = Collector( channel = channel,
var_name = "pred_prob",
target_names = target_names,
path = use,
recreate = True,
rebin = False )
print "Predicting simulation"
for sample, sampleName in read.get(what = "nominal"):
pred = model.predict( applyScaler(scaler, sample, variables), where )
coll.addPrediction(pred, sample, sampleName)
print "Adding looser samples to predictions"
for sample, sampleName in read.get(what = "more"):
pred = model.predict( applyScaler(scaler, sample, variables), where )
coll.addPrediction(pred, sample, sampleName)
print "Predicting data"
for sample, sampleName in read.get(what = "data"):
pred = model.predict( applyScaler(scaler, sample, variables), where )
coll.addPrediction(pred, sample, sampleName)
if not short:
print "Predicting TES shapes"
for sample, sampleName in read.get(what = "tes"):
pred = model.predict( applyScaler(scaler, sample, variables), where )
coll.addPrediction(pred, sample, sampleName)
print "Predicting JES shapes"
for sample, sampleName in read.get(what = "jec"):
pred = model.predict( applyScaler(scaler, sample, variables), where )
coll.addPrediction(pred, sample, sampleName)
coll.createDC(writeAll = True)
plot = Plotter( channel= channel,
naming = read.processes,
path = use )
plot.makePlots()
