Esempio n. 1
0
    def evaluate(self, bi, wallet_key, sample_seed_set, ss_time):
        ss_time = 0.001 if ss_time == 0.0 else ss_time
        eva_start_time = time.time()
        ini = Initialization(self.data_key, self.prod_key, self.cas_key, wallet_key)

        seed_cost_dict = ini.constructSeedCostDict()
        graph_dict = ini.constructGraphDict()
        product_list = ini.constructProductList()[0]
        num_product = len(product_list)
        wallet_dict = ini.constructWalletDict()
        total_cost = sum(seed_cost_dict[i] for i in seed_cost_dict)
        total_budget = round(total_cost / 2 ** bi, 4)

        eva = Evaluation(graph_dict, product_list, wallet_dict)
        print('@ evaluation @ ' + self.data_name + '_' + self.cas_name +
              '\t' + self.model_name +
              '\t' + wallet_distribution_type_dict[wallet_key] + '_' + self.prod_name + '_bi' + str(bi))

        for times in range(self.times):
            model_name = self.model_name + '_' + str(times) if self.times == 10 else self.model_name

            sample_pnn_k, seed_diffusion_dict_k = eva.getSeedSetProfit(sample_seed_set)
            sample_pro_k = [round(sample_pnn_k[k] * product_list[k][0], 4) for k in range(num_product)]
            sample_sn_k = [len(sample_sn_k) for sample_sn_k in sample_seed_set]
            sample_bud_k = [round(sum(seed_cost_dict[i] for i in sample_seed_set[k]), 4) for k in range(num_product)]
            sample_bud = round(sum(sample_bud_k), 4)
            sample_pro = round(sum(sample_pro_k), 4)
            seed_diffusion_list = [(seed_diffusion_flag, seed_diffusion_dict_k[seed_diffusion_flag]) for seed_diffusion_flag in seed_diffusion_dict_k]
            seed_diffusion_list = [(round(sd_item[1] * product_list[sd_item[0][0]][0], 4), sd_item[0], sd_item[1]) for sd_item in seed_diffusion_list]
            seed_diffusion_list = sorted(seed_diffusion_list, reverse=True)

            result = [sample_pro, sample_bud, sample_sn_k, sample_pnn_k, sample_pro_k, sample_bud_k, sample_seed_set]
            print('eva_time = ' + str(round(time.time() - eva_start_time, 2)) + 'sec')
            print(result)
            print('------------------------------------------')

            path0 = 'result/' + self.data_name + '_' + self.cas_name
            if not os.path.isdir(path0):
                os.mkdir(path0)
            path = path0 + '/' + wallet_distribution_type_dict[wallet_key] + '_' + self.prod_name + '_bi' + str(bi)
            if not os.path.isdir(path):
                os.mkdir(path)
            result_name = path + '/' + model_name + '.txt'

            fw = open(result_name, 'w')
            fw.write(self.data_name + '_' + self.cas_name + '\t' +
                     model_name + '\t' +
                     wallet_distribution_type_dict[wallet_key] + '_' + self.prod_name + '_bi' + str(bi) + '\n' +
                     'budget_limit = ' + str(total_budget) + '\n' +
                     'time = ' + str(ss_time) + '\n\n' +
                     'profit = ' + str(sample_pro) + '\n' +
                     'budget = ' + str(sample_bud) + '\n')
            fw.write('\nprofit_ratio = ')
            for kk in range(num_product):
                fw.write(str(sample_pro_k[kk]) + '\t')
            fw.write('\nbudget_ratio = ')
            for kk in range(num_product):
                fw.write(str(sample_bud_k[kk]) + '\t')
            fw.write('\nseed_number = ')
            for kk in range(num_product):
                fw.write(str(sample_sn_k[kk]) + '\t')
            fw.write('\ncustomer_number = ')
            for kk in range(num_product):
                fw.write(str(sample_pnn_k[kk]) + '\t')
            fw.write('\n\n')

            fw.write(str(sample_seed_set))
            for sd_item in seed_diffusion_list:
                fw.write('\n' + str(sd_item[1]) + '\t' + str(sd_item[0]) + '\t' + str(sd_item[2]))
            fw.close()
    ## data_name: (str) the dataset ##
    ## product_name: (str) the product ##
    ## total_budget: (int) the seed budget ##
    ## num_price: (int) the kinds of generated price ##
    ## num_ratio: (int) the kinds of generated ratio ##
    ## ctrlexpect: (str) the controller for which expected function is used ##
    data_name = "email"
    product_name = "prod_ratio_similar_n3p1"
    total_budget = 1
    num_price, num_ratio = 3, 1
    num_product = num_price * num_ratio
    ctrlexpect = "p"

    ini = Initialization(data_name)

    graph_dict = ini.constructGraphDict()
    seedcost_dict = ini.constructSeedCostDict()

    ### product_list: (list) [profit, cost, price]
    product_list = []
    with open("product/" + product_name + ".txt") as f:
        for line in f:
            (p, c, r, pr) = line.split()
            product_list.append(
                [float(p), float(c),
                 round(float(p) + float(c), 2)])

    ### current_profit: (float4) the profit currently
    ### current_budget: (float4) the used budget currently
    ### seed_set: (list) the set of seeds for all products
    ### seed_set[k]: (set) the set of seeds for k-product
Esempio n. 3
0
    def evaluate(self, bi, wallet_distribution_type, ppp, seed_set_sequence,
                 ss_time_sequence):
        eva_start_time = time.time()
        ini = Initialization(self.dataset_name, self.product_name)
        iniW = IniWallet(self.dataset_name, self.product_name,
                         wallet_distribution_type)

        seed_cost_dict = ini.constructSeedCostDict()
        graph_dict = ini.constructGraphDict(self.cascade_model)
        product_list = ini.constructProductList()
        num_product = len(product_list)
        wallet_dict = iniW.constructWalletDict()
        total_cost = sum(seed_cost_dict[k][i] for i in seed_cost_dict[0]
                         for k in range(num_product))
        total_budget = round(total_cost / 2**bi, 4)

        ppp_strategy = 'random' * (ppp == 1) + 'expensive' * (
            ppp == 2) + 'cheap' * (ppp == 3)
        result = []

        eva = Evaluation(graph_dict, product_list, ppp_strategy, self.wpiwp)
        personal_prob_dict = eva.setPersonalPurchasingProbDict(wallet_dict)
        for sample_count, sample_seed_set in enumerate(seed_set_sequence):
            print('@ ' + self.model_name + ' evaluation @ dataset_name = ' +
                  self.dataset_name + '_' + self.cascade_model +
                  ', product_name = ' + self.product_name + ', wd = ' +
                  wallet_distribution_type + ', ppp = ' + ppp_strategy +
                  ', sample_count = ' + str(sample_count))
            sample_pro_k_acc, sample_pnn_k_acc = [
                0.0 for _ in range(num_product)
            ], [0 for _ in range(num_product)]

            for _ in range(self.eva_monte_carlo):
                pro, pro_k_list, pnn_k_list = eva.getSeedSetProfit(
                    sample_seed_set, copy.deepcopy(wallet_dict),
                    copy.deepcopy(personal_prob_dict))
                sample_pro_k_acc = [(pro_k + sample_pro_k)
                                    for pro_k, sample_pro_k in zip(
                                        pro_k_list, sample_pro_k_acc)]
                sample_pnn_k_acc = [(pnn_k + sample_pnn_k)
                                    for pnn_k, sample_pnn_k in zip(
                                        pnn_k_list, sample_pnn_k_acc)]
            sample_pro_k_acc = [
                round(sample_pro_k / self.eva_monte_carlo, 4)
                for sample_pro_k in sample_pro_k_acc
            ]
            sample_pnn_k_acc = [
                round(sample_pnn_k / self.eva_monte_carlo, 4)
                for sample_pnn_k in sample_pnn_k_acc
            ]
            sample_bud_k_acc = [
                round(
                    sum(seed_cost_dict[sample_seed_set.index(sample_bud_k)][i]
                        for i in sample_bud_k), 4)
                for sample_bud_k in sample_seed_set
            ]
            sample_sn_k_acc = [
                len(sample_sn_k) for sample_sn_k in sample_seed_set
            ]
            sample_pro_acc = round(sum(sample_pro_k_acc), 4)
            sample_bud_acc = round(sum(sample_bud_k_acc), 4)

            result.append([
                sample_pro_acc, sample_bud_acc, sample_sn_k_acc,
                sample_pnn_k_acc, sample_pro_k_acc, sample_bud_k_acc,
                sample_seed_set
            ])

            print('eva_time = ' + str(round(time.time() - eva_start_time, 2)) +
                  'sec')
            print(result[sample_count])
            print('------------------------------------------')

        avg_pro = round(sum(r[0] for r in result) / len(seed_set_sequence), 4)
        avg_bud = round(sum(r[1] for r in result) / len(seed_set_sequence), 4)
        avg_sn_k = [
            round(sum(r[2][kk] for r in result) / len(seed_set_sequence), 4)
            for kk in range(num_product)
        ]
        avg_pnn_k = [
            round(sum(r[3][kk] for r in result) / len(seed_set_sequence), 4)
            for kk in range(num_product)
        ]
        avg_pro_k = [
            round(sum(r[4][kk] for r in result) / len(seed_set_sequence), 4)
            for kk in range(num_product)
        ]
        avg_bud_k = [
            round(sum(r[5][kk] for r in result) / len(seed_set_sequence), 4)
            for kk in range(num_product)
        ]

        path = 'sample_result/' + \
               self.model_name + '_' + wallet_distribution_type + '_ppp' + str(ppp) + '_wpiwp' * self.wpiwp
        if not os.path.isdir(path):
            os.mkdir(path)
        fw = open(
            path + '/' + self.dataset_name + '_' + self.cascade_model + '_' +
            self.product_name + '_bi' + str(bi) + '.txt', 'w')
        fw.write(self.model_name + ', ' + self.dataset_name + '_' +
                 self.cascade_model + ', ' + self.product_name + '\n' +
                 'ppp = ' + str(ppp) + ', wd = ' + wallet_distribution_type +
                 ', wpiwp = ' + str(self.wpiwp) + '\n' + 'total_budget = ' +
                 str(total_budget) + ', sample_number = ' +
                 str(len(seed_set_sequence)) + '\n' + 'avg_profit = ' +
                 str(avg_pro) + ', avg_budget = ' + str(avg_bud) + '\n' +
                 'total_time = ' + str(round(sum(ss_time_sequence), 4)) +
                 ', avg_time = ' +
                 str(round(sum(ss_time_sequence) / len(ss_time_sequence), 4)) +
                 '\n')
        fw.write('\nprofit_ratio =')
        for kk in range(num_product):
            fw.write(' ' + str(avg_pro_k[kk]))
        fw.write('\nbudget_ratio =')
        for kk in range(num_product):
            fw.write(' ' + str(avg_bud_k[kk]))
        fw.write('\nseed_number =')
        for kk in range(num_product):
            fw.write(' ' + str(avg_sn_k[kk]))
        fw.write('\ncustomer_number =')
        for kk in range(num_product):
            fw.write(' ' + str(avg_pnn_k[kk]))
        fw.write('\n')

        for t, r in enumerate(result):
            fw.write('\n' + str(t) + '\t' + str(round(r[0], 4)) + '\t' +
                     str(round(r[1], 4)) + '\t' + str(r[2]) + '\t' +
                     str(r[3]) + '\t' + str(r[4]) + '\t' + str(r[5]) + '\t' +
                     str(r[6]))
        fw.close()
Esempio n. 4
0
    def evaluate(self, bi, wallet_distribution_type, sample_seed_set, ss_time):
        eva_start_time = time.time()
        ini = Initialization(self.dataset_name, self.product_name, wallet_distribution_type)

        seed_cost_dict = ini.constructSeedCostDict(self.seed_cost_option)
        graph_dict = ini.constructGraphDict(self.cascade_model)
        product_list = ini.constructProductList()[0]
        num_product = len(product_list)
        wallet_dict = ini.constructWalletDict()
        total_cost = sum(seed_cost_dict[k][i] for i in seed_cost_dict[0] for k in range(num_product))
        total_budget = round(total_cost / 2 ** bi, 4)

        eva = Evaluation(graph_dict, product_list, wallet_dict)
        print('@ ' + self.model_name + ' evaluation @ dataset_name = ' + self.dataset_name + '_' + self.cascade_model + ', product_name = ' + self.product_name +
              ', seed_cost_option = ' + self.seed_cost_option + ', wd = ' + wallet_distribution_type)
        sample_pro_k, sample_pnn_k = [0.0 for _ in range(num_product)], [0 for _ in range(num_product)]

        for _ in range(self.eva_monte_carlo):
            pro_k_list, pnn_k_list = eva.getSeedSetProfit(sample_seed_set)
            sample_pro_k = [(pro_k + sample_pro_k) for pro_k, sample_pro_k in zip(pro_k_list, sample_pro_k)]
            sample_pnn_k = [(pnn_k + sample_pnn_k) for pnn_k, sample_pnn_k in zip(pnn_k_list, sample_pnn_k)]
        sample_pro_k = [round(sample_pro_k / self.eva_monte_carlo, 4) for sample_pro_k in sample_pro_k]
        sample_pnn_k = [round(sample_pnn_k / self.eva_monte_carlo, 4) for sample_pnn_k in sample_pnn_k]
        sample_bud_k = [round(sum(seed_cost_dict[sample_seed_set.index(sample_bud_k)][i] for i in sample_bud_k), 4) for sample_bud_k in sample_seed_set]
        sample_sn_k = [len(sample_sn_k) for sample_sn_k in sample_seed_set]
        sample_pro = round(sum(sample_pro_k), 4)
        sample_bud = round(sum(sample_bud_k), 4)

        result = [sample_pro, sample_bud, sample_sn_k, sample_pnn_k, sample_pro_k, sample_bud_k, sample_seed_set]
        print('eva_time = ' + str(round(time.time() - eva_start_time, 2)) + 'sec')
        print(result)
        print('------------------------------------------')

        path = 'result/' + self.model_name + '_' + wallet_distribution_type
        if not os.path.isdir(path):
            os.mkdir(path)
        fw = open(path + '/' + self.dataset_name + '_' + self.cascade_model + '_' + self.product_name + '_' + self.seed_cost_option +
                  '_ds' * self.diff_seed_option + '_bi' + str(bi) + '.txt', 'w')
        fw.write(self.model_name + ', ' + wallet_distribution_type + ', ' + self.dataset_name + '_' + self.cascade_model + ', ' + self.product_name +
                 ', seed_cost_option = ' + self.seed_cost_option + '\n\n' +
                 'total_budget = ' + str(total_budget) + '\n' +
                 'profit = ' + str(sample_pro) + '\n' +
                 'budget = ' + str(sample_bud) + '\n' +
                 'time = ' + str(ss_time) + '\n')
        fw.write('\nprofit_ratio =')
        for kk in range(num_product):
            fw.write(' ' + str(sample_pro_k[kk]))
        fw.write('\nbudget_ratio =')
        for kk in range(num_product):
            fw.write(' ' + str(sample_bud_k[kk]))
        fw.write('\nseed_number =')
        for kk in range(num_product):
            fw.write(' ' + str(sample_sn_k[kk]))
        fw.write('\ncustomer_number =')
        for kk in range(num_product):
            fw.write(' ' + str(sample_pnn_k[kk]))
        fw.write('\n\n')

        for r in result:
            # -- pro, bud, sn_k, pnn_k, pro_k, bud_k, seed_set --
            fw.write(str(r) + '\t')
        fw.close()