def step()

in Bin Packing/src/bin_packing_environment.py [0:0]

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

    def step(self, action):
        done = False
        self.step_count += 1
        if action >= self.bag_capacity:
            print("Error: Invalid Action")
            raise
        elif action > (self.bag_capacity - self.item_size):
            # can't insert item because bin overflow
            reward = BIG_NEG_REWARD - self.waste
            done = True
        elif action == 0:  # new bag
            self.num_bins_levels[self.item_size] += 1
            # waste = sum of empty spaces in all bags
            self.waste = self.bag_capacity - self.item_size
            # reward is negative waste
            reward = -1 * self.waste
            self.__update_bin_type_distribution_map(0)
        elif self.num_bins_levels[action] == 0:
            # can't insert item because bin of this level doesn't exist
            print('cannot insert item because bin of this level does not exist')
            reward = BIG_NEG_REWARD - self.waste
            done = True
        else:
            if action + self.item_size == self.bag_capacity:
                self.num_full_bags += 1
            else:
                self.num_bins_levels[action + self.item_size] += 1
            # waste = empty space in the bag
            self.waste = -self.item_size
            # reward is negative waste
            reward = -1 * self.waste
            self.__update_bin_type_distribution_map(action)
            if self.num_bins_levels[action] < 0:
                print(self.num_bins_levels[action])
            self.num_bins_levels[action] -= 1

        self.total_reward += reward

        self.time_remaining -= 1
        if self.time_remaining == 0:
            done = True

        # get the next item
        self.item_size = self.__get_item()
        # state is the number of bins at each level and the item size
        state = self.num_bins_levels + [self.item_size]
        info = self.bin_type_distribution_map

        return state, reward, done, info