isotrackTrainRegressor Namespace Reference

Functions
def	fac0
def	fac1
def	fac2
def	propweights

Variables
tuple	_ = plt.plot(lims, lims)
list	a0 = [0.973, 0.998, 0.992, 0.965 ]
	marinas correction form More...
list	a1 = [0, -0.318, -0.261, -0.406]
list	a2 = [0, 0, 0.047, 0.089]
list	cols_to_minmax = ['t_delta', 't_hmaxNearP','t_emaxNearP', 't_hAnnular', 't_eAnnular','t_pt','t_nVtx','t_ieta','t_eHcal10', 't_eHcal30','t_rhoh','t_eHcal_x']
	data = df.values
tuple	df = pd.read_pickle(fName)
tuple	dop = (X_test[:,16]/X_test[:,13])
tuple	eop = (X_test[:,15]/X_test[:,13])
tuple	fName = parser.parse_args()
tuple	history = model.fit(X_train,Y_train , batch_size=5000, epochs=100, validation_split=0.2, verbose=1,sample_weight=propweights(Y_train))
list	keya = []
list	lims = [0, 200]
list	marinascorr = X_test[:,15]
list	maxa = []
tuple	mcorrval = vec0(abs(X_test[:,17]))
tuple	meany = np.mean(Y_train)
list	mina = []
tuple	model = Sequential()
tuple	modv = parser.parse_args()
int	ntest = 20000
tuple	parser = argparse.ArgumentParser()
list	pmom = X_test[:,13]
tuple	preds = model.predict(X_test[:,0:12])
tuple	RMS = keras.optimizers.RMSprop(lr=0.001, rho=0.9)
tuple	stdy = np.std(Y_train)
list	targets = data[:,12]
list	testindx = data.shape[0]
list	uncorrected = X_test[:,15]
tuple	vec0 = np.vectorize(fac0)
tuple	vec1 = np.vectorize(fac1)
tuple	vec2 = np.vectorize(fac2)
list	X_test = data[testindx:,:]
list	X_train = data[:testindx,0:12]
list	Y_train = data[:testindx,12]

Function Documentation

def isotrackTrainRegressor.fac0

(

jeta

)

Definition at line 101 of file isotrackTrainRegressor.py.

Referenced by MonopoleSteppingAction.update().

def fac0(jeta):
    PU_IETA_1 = 9
    PU_IETA_2 = 16
    PU_IETA_3 = 25
    idx = (int(jeta >= PU_IETA_1) + int(jeta >= PU_IETA_2) + int(jeta >= PU_IETA_3))