def update_whole()

in datasets/ClassPrioritySampler.py [0:0]

• 11 lines of code
• 7 McCabe index (conditional complexity)

    def update_whole(self, total_weights):
        """ Update the whole tree based on per-example sampling weights """
        if self.alpha != 1:
            total_weights = np.power(total_weights, self.alpha)
        lefti = self.pointer_to_treeidx(0)
        righti = self.pointer_to_treeidx(self.capacity-1)
        self.tree[lefti:righti+1] = total_weights

        # Iteratively find a parent layer
        while lefti != 0 and righti != 0:
            lefti = (lefti - 1) // 2 if lefti != 0 else 0
            righti = (righti - 1) // 2 if righti != 0 else 0
            
            # Assign paraent weights from right to left
            for i in range(righti, lefti-1, -1):
                self.tree[i] = self.tree[2*i+1] + self.tree[2*i+2]