Public Member Functions
	__init__ (self, X, Y, Z)

	next_batch (self, batch_size)

Public Attributes
	X = X
	Input Features.

	Y = Y
	Label Data.

	Z = Z
	Spectators.

	len = len(Y)
	Number of events.

	index_array = np.arange(self.len)
	Index array, which will be shuffled.

int	pointer = 0
	Pointer for index array.

Detailed Description

Class to create batches for training the Adversary Network.
See mva/examples/keras/adversary_network.py for details.

Definition at line 54 of file B2A714-DeepContinuumSuppression_MVAModel.py.

Constructor & Destructor Documentation

◆ init()

__init__	(	self,
		X,
		Y,
		Z )

Init the class
:param X: Input Features
:param Y: Label Data
:param Z: Spectaters/Qunatity to be uncorrelated to

Definition at line 60 of file B2A714-DeepContinuumSuppression_MVAModel.py.

    def __init__(self, X, Y, Z):
        """
        Init the class
        :param X: Input Features
        :param Y: Label Data
        :param Z: Spectaters/Qunatity to be uncorrelated to
        """
        
        self.X = X
        
        self.Y = Y
        
        self.Z = Z
        
        self.len = len(Y)
        
        self.index_array = np.arange(self.len)
        np.random.shuffle(self.index_array)
        
        self.pointer = 0
 

Member Function Documentation

◆ next_batch()

next_batch	(		self,
			batch_size )

Getting next batch of training data

Definition at line 81 of file B2A714-DeepContinuumSuppression_MVAModel.py.

    def next_batch(self, batch_size):
        """
        Getting next batch of training data
        """
        if self.pointer + batch_size >= self.len:
            np.random.shuffle(self.index_array)
            self.pointer = 0
 
        batch_index = self.index_array[self.pointer:self.pointer + batch_size]
        self.pointer += batch_size
 
        return self.X[batch_index], self.Y[batch_index], self.Z[batch_index]
 
 