# def partition_diversity(partition): import numpy as np import pandas as pd from Code import Code from variancediy import variancediy from TOPSIS import TOPSIS from adregionf import adregionf from select import select from crossnew import crossnew from mutationnew import mutationnew from hui_fun import liziqunfun from hui_xfun import xfun import os import time from three_dimensional_TOPSIS import three_dimensional_TOPSIS from boundary_adjustment_fitness import boundary_fitness from boundary_adjustment import boundary_adjustment_fitness import concurrent.futures import multiprocessing from hui_fun import liziqunfun import pickle from luanlai import multi_huifun from sklearn.cluster import KMeans from distance_to_origin import distance_to_origin import random for _ in range(0,1): # for Initial_partitions in [60]:#[40, 50, 60, 70, 80]: for final_partitions in range(3,4): try: Initial_partitions=3 print(f'times is {_}') print(f'Initial_partitions is {Initial_partitions}') print(f'final_partitions is {final_partitions}') # bus_info = pd.DataFrame() # file_range = range(242, 248) # file_directory = "E:\\分方向MFD\\数据\\处理后的数据\\公交匹配到路网\\03_pcross" # for file_number in file_range: # file_name = f"20190903_{file_number:03d}.csv" # 根据文件名模式构造文件名 # file_path = os.path.join(file_directory, file_name) # 构造完整的文件路径 # temp_dataframe = pd.read_csv(file_path) # 使用 pandas 读取 CSV 文件 # bus_info = pd.concat([bus_info, temp_dataframe], ignore_index=True) # 将 temp_dataframe 追加到 merged_dataframe 中 # links = pd.read_csv('links_niu22.csv') # # 计算第16列相同值的第7列的平均值 # average_values = bus_info.groupby(bus_info.columns[9])[bus_info.columns[5]].mean() # # 在links_osm的第六列找到average_values，将平均值放在该值所在行第五列的位置 # for index, value in average_values.items(): # links.loc[links[links.columns[5]] == index, links.columns[4]] = value # # links = links[links[links.columns[5]].isin(average_values.index)] # # 将结果保存到新的CSV文件 # links.to_csv('links_processed03.csv', index=False) links = pd.read_csv('links_processed.csv') links = pd.read_excel('cheche.xlsx',header=None) # links = pd.read_csv('links.csv') # folder_name = f"{Initial_partitions}_to_{final_partitions}" folder_name = f"{_}_to_{final_partitions}" OUTPUT_DIR = os.path.join('output', folder_name) # 如果文件夹不存在，则创建 if not os.path.exists(OUTPUT_DIR): os.makedirs(OUTPUT_DIR) # links = pd.read_csv('links_1.csv') links = links.to_numpy() # for chuu in range(1, 17): # for dic in range(1): # tic() # chu = 10 # zhong = 2 # 给道路起点和终点标注序列，eg从1到500， # 因为一个路口可以是好几个道路的起点或终点，所以同一路口就会有同样的标记 node = np.concatenate((links[:, :2], links[:, 2:4]), axis=0) # np.concatenate 函数会将这两个子数组沿着轴 0 连接起来; # axis 是指在数组操作时沿着哪个轴进行操作。当axis=0时，表示在第一个维度上进行拼接操作。这里就是纵轴 # 这里是给道路起点和终点标注序列，也就是路口表注序列，因为一个路口可以是好几个道路的起点或终点，所以同一路口就会有同样的标记 noi = 1 node = np.hstack((node, np.zeros((len(node), 1)))) for i in range(node.shape[0]): # node.shape[0] 是指 node 数组的第一维大小，即 node 数组的行数 # node[:i, 0] 表示从 node 数组的第一行到第 i-1 行的所有行的第一列构成的数组 # np.where() 函数返回一个包含下标的元组，后面的[0]就代表返回第一个元素的下标 a = np.where(node[:i, 0] == node[i, 0])[0] b = np.where(node[:i, 1] == node[i, 1])[0] c = np.intersect1d(a, b) # intersect1d 返回两个数组的交集 if c.size > 0: x = c.shape[0] y = 1 else: x, y = 0, 1 # 在 node 数组的最后添加一列全为0的列，并将添加后的新数组重新赋值给 node if x > 0 and y > 0: node[i, 2] = node[min(c), 2] # 如果c是矩阵，则min(A)是包含每一列的最小值的行向量 else: node[i, 2] = noi noi += 1 node = np.concatenate((node[:int(len(node) / 2), 2].reshape(-1, 1), node[int(len(node) / 2):, 2].reshape(-1, 1)), axis=1) np.save('node.npy', node) # 这里的links多加了一行才能yanlinks，但这样yanlinks就不对了 links = np.hstack((links, np.zeros((len(links), 1)))) links = np.hstack((links, np.zeros((len(links), 1)))) links = np.hstack((links, np.zeros((len(links), 1)))) yanlinks = np.concatenate((node, links[:, [5, 6, 7, 4, 0, 1, 2, 3]], np.zeros((len(links), 4))), axis=1) yanlinks[:, 4] = np.arange(1, len(yanlinks) + 1) road = np.arange(1, node.shape[0] + 1) adjacency = np.zeros((len(road), len(road))) # 初始化分区 for i in range(len(road)): temp1 = np.where(node[:, 0] == node[i, 0])[0] # 找出第一列每个数字在第一列出现的位置 temp2 = np.where(node[:, 1] == node[i, 0])[0] # 找出第一列每个数字在第二列出现的位置 temp3 = np.where(node[:, 0] == node[i, 1])[0] # 找出第二列每个数字在第一列出现的位置 temp4 = np.where(node[:, 1] == node[i, 1])[0] # 找出第二列每个数字在第二列出现的位置 temp = np.unique(np.intersect1d(np.arange(i + 1, node.shape[0]), np.concatenate((temp1, temp2, temp3, temp4)))) if len(temp) > 0: adjacency[i, temp] = 1 adjacency[temp, i] = 1 row_sums = np.sum(adjacency, axis=1) # 找到全零行的索引 zero_row_indices = np.where(row_sums == 0)[0] N = Initial_partitions # 设置聚类数目 # 利用 K-Means 算法对 yanlinks 矩阵的第 7 列和第 8 列（即经度和纬度）进行聚类， # 将样本分成 N 类，idx是一个N x 2的矩阵，其中N是聚类数目。 # idx的每一行就是一个聚类中心，其中第一列是该中心的经度，第二列是该中心的纬度。 # 在计算每个点到聚类中心的距离时，就需要用到idx的值。 Cluster_Label, idx = KMeans(n_clusters=N, n_init=10).fit(yanlinks[:, [6, 7]]).labels_, KMeans(n_clusters=N, n_init=10).fit( yanlinks[:, [6, 7]]).cluster_centers_ # df = pd.read_csv('idx.csv',header=None) # idx = df.to_numpy() # 计算每个点到聚类中心的距离 dis = 111000 * np.sqrt( (yanlinks[:, 6] - idx[:, 0].reshape(N, 1)) ** 2 + (yanlinks[:, 7] - idx[:, 1].reshape(N, 1)) ** 2) # 找到每个点最近的聚类中心，mm是最小值，nn是最小值在向量的索引 mm, nn = np.min(dis, axis=1, keepdims=True), np.argmin(dis, axis=1) data = links[:, 4] # links第五行是路的长度 if data.size > 0: m = data.shape[0] n = 1 else: m, n = 0, 1 pattern = np.zeros((m, n)) # zeros(m,n+1)返回由零组成的m×(n+1)数组 pattern[:, 0] = data # 前n列为data中的数据 pattern = np.hstack((pattern, np.zeros((len(pattern), 1)))) pattern[:, 1] = -1 center = np.zeros((N, n)) # 初始化聚类中心 pattern[:, :n] = data.reshape(-1, n) center = np.hstack((center, np.zeros((len(center), 1)))) # 初始化聚类中心 for x in range(0, N): center[x, 1] = nn[x] center[x, 0] = data[int(center[x, 1])] pattern[int(center[x, 1]), 1] = x # 初始化距离和计数 distance = np.zeros(N) num = np.zeros(N) # 初始化新的聚类中心 new_center = np.zeros((N, n)) unassigned_links = 2 while unassigned_links > 0: print(unassigned_links) x=random.randint(0, 59) # for x in range(0,Initial_partitions): try: selected_links = adjacency[pattern[:, 1] == x, :] unassigned_roads = np.where(np.sum(selected_links, axis=0) > 0)[0] selected_links = np.where(pattern[:, 1] > -1)[0] unassigned_roads = np.setdiff1d(unassigned_roads, selected_links) # bound 是一个向量，表示与聚类 x 相关的未被分配到聚类中的道路的编号。 selected_links = np.where(pattern[:, 1] == x)[0] # 这里的yisou表示已经被分配到的道路编号 bus = [] road_evaluation = np.zeros((len(unassigned_roads), 2)) for unassigned_road_index in range(len(unassigned_roads)): selected_links_lengths_float = (pattern[selected_links, 0]).tolist() unassigned_road_length_array = (pattern[unassigned_roads[unassigned_road_index], 0]) unassigned_road_length_array = [unassigned_road_length_array] abrr = selected_links_lengths_float + unassigned_road_length_array road_evaluation[unassigned_road_index, 0] = np.var(abrr, ddof=1) aas = yanlinks[yanlinks[:, 4] == unassigned_roads[unassigned_road_index] + 1, 6:8] road_evaluation[unassigned_road_index, 1] = 111000 * np.sqrt(np.sum( (yanlinks[yanlinks[:, 4] == unassigned_roads[unassigned_road_index] + 1, 6:8] - idx[x, :]) ** 2)) if road_evaluation.shape[0] > 1: m, n = TOPSIS(road_evaluation) # bestxuhao最优方案的序号，bestgoal最优得分 else: n = 0 # pattern[unassigned_roads[n - 1], 1] = x pattern[unassigned_roads[n], 1] = x except: continue unassigned_links = np.sum(pattern[:, 1] == -1) # 因为我的pattern是从0到39的编号，所以要变成1到40 pattern[:, 1] = pattern[:, 1] + 1 # # np.save('pattern60.npy', pattern) # filename = f'pattern{Initial_partitions}.npy' pattern = np.load(filename) # np.save(os.path.join(OUTPUT_DIR, 'pattern.npy'), pattern) # pattern_path = os.path.join(OUTPUT_DIR, 'pattern.npy') # pattern = np.load(pattern_path) yanlinks[:, 3] = links[:, 9] yanlinks[:, 10] = pattern[:, 1] data_path = r'' df2 = pd.read_csv(data_path + 'links_processed.csv') zero_rows = yanlinks[:, 10] == 0 # 获取已删除行的索引 deleted_rows_indices = np.where(zero_rows)[0] # 从 links 中删除 deleted_rows_indices 中指定的行 df2 = df2.drop(deleted_rows_indices, errors='ignore') df2.to_csv(data_path + 'links_test1.csv', index=False) yanlinks = yanlinks[yanlinks[:, 10] != 0] yanlinks = yanlinks[yanlinks[:, 10] != -1, :] road = np.unique(np.concatenate((yanlinks[:, 1], yanlinks[:, 0]), axis=0)) adjacency = np.zeros((len(road), len(road))) adregion = np.zeros((int(np.max(yanlinks[:, 4])), int(np.max(yanlinks[:, 4])))) for i in range(len(yanlinks[:, 0])): temp1 = np.where(node[:, 0] == node[i, 0])[0] temp2 = np.where(node[:, 1] == node[i, 0])[0] temp3 = np.where(node[:, 0] == node[i, 1])[0] temp4 = np.where(node[:, 1] == node[i, 1])[0] temp = np.unique(np.intersect1d(np.arange(i + 1, node.shape[0]), np.concatenate((temp1, temp2, temp3, temp4)))) if len(temp) > 0: adregion[i, temp] = 1 adregion[temp, i] = 1 # adregion矩阵表示路段之间的邻接关系 np.save('adregion.npy', adregion) # 给adregion矩阵乘上权重（道路的分组编号） for i in range(len(yanlinks[:, 1])): # print(adregion[:, int(yanlinks[i, 4])]) # print(int(yanlinks[i, 10])) adregion[:, int(yanlinks[i, 4]) - 1] = adregion[:, int(yanlinks[i, 4]) - 1] * int(yanlinks[i, 10]) subregion_adj = np.zeros((Initial_partitions, Initial_partitions)) # 计算adregion中的每个元素出现的频率(判断是强相关还是弱相关） for i in range(len(adregion[:, 1])): a = adregion[i, :] a = np.unique(a) a = a[a != 0] if a.size > 0: x = 1 y = a.shape[0] else: x, y = 0, 1 if y > 1: for j in range(len(a)): for u in range(len(a)): if j != u: # subregion_adj表示子区域的邻接关系，其中数值的大小表示区域之间的相关程度 subregion_adj[int(a[j])-1, int(a[u])-1] += 1 subregion_adj[int(a[u])-1, int(a[j])-1] += 1 # 计算后存到directed_adjacency_matrix里 directed_adjacency_matrix = subregion_adj.copy() # 对于子区域相关程度处于弱相关的邻接关系进行忽略 min_value = np.min(np.max(subregion_adj, axis=0)) - 2 subregion_adj[subregion_adj < min_value] = 0 subregion_adj[subregion_adj > 1] = 1 directed_adjacency_matrix[directed_adjacency_matrix > 1] = 1 np.save('adr.npy', subregion_adj) pd.DataFrame(subregion_adj).to_csv(os.path.join(OUTPUT_DIR, 'subregion_adj.csv'), index=False, header=False) np.save('dadr.npy', directed_adjacency_matrix) np.save('yanlinks.npy', yanlinks) Asb = 0 # 计算平均相似性 # unique_values, unique_indices = np.unique(yanlinks[:, 10], return_index=True) # for i in unique_values: # wu = np.where(subregion_adj[int(i) - 1, :] == 1) # wu是元组 # smrjj_divide_smrjj_ = 0 # # 0726 # # wu_1 = wu[0] # # for j in wu_1: # selected_values_list = [yanlinks[yanlinks[:, 10] == j + 1][:, 5]] # # # 主区域邻接的一个区域速度均值与方差 # selected_values = np.array(selected_values_list) # average = np.mean(selected_values) # variance = np.var(selected_values) # # # 计算主区域的速度均值与方差 # selected_values1 = yanlinks[yanlinks[:, 10] == i][:, 5] # average1 = np.mean(selected_values1) # variance1 = np.var(selected_values1) # # smrjj = 2 * variance1 # jj情况下的smrjj # smrjj_ = variance + variance1 + (average - average1) ** 2 # smrjj_divide_smrjj_one = smrjj / smrjj_ # smrjj_divide_smrjj_ += smrjj_divide_smrjj_one # # num_elements = len(wu[0]) # 计算分母NE # Asb_one = smrjj_divide_smrjj_ / num_elements # Asb += Asb_one # Asb = Asb / Initial_partitions # print('Asb=', Asb) # # Tvb = 0 # for i in unique_values: # selected_values = yanlinks[yanlinks[:, 10] == i][:, 5] # variance = np.var(selected_values) # Tvb += variance # # print('Tvb=', Tvb) #################################################################################################################### start = time.time() # 组合优化 print('step2 combinatorial optimization') maxgen = 100 # 进化代数 sizepop = 30 # 种群规模 pcross = 0.8 # 交叉概率 pmutation = 0.8 # 变异概率 lenchrom = [1] * Initial_partitions # 变量字串长度 unassigned_roads = np.tile([[1, final_partitions]], (Initial_partitions, 1)) individuals = {'fitness': np.zeros((sizepop, 1)), 'chrom': []} bestfitness = [] # 种群最佳适应度 bestchrom = None # 种群最佳染色体 lixiangjie = {} every_generation_best_chromosome_san={} every_generation_best_chromosome={} for i in range(sizepop): individuals['chrom'].append([Code(lenchrom, unassigned_roads,final_partitions)]) # 给第一个个体随机产生染色体 print('code ended') repeated_row1= np.array([[0]]) inff = np.repeat([repeated_row1], sizepop, axis=0) inff_np = np.array(inff, dtype=np.int64) # with open('individuals_chrom.pkl', 'wb') as file: # pickle.dump(individuals['chrom'], file) road_velocity = yanlinks[:, [4, 5]] # if __name__ == "__main__": dadr = np.load('dadr.npy') bus_line_sequence = pd.read_csv('bus_road_sequence_processed.csv', header=None, encoding='gbk') bus_line_sequence = bus_line_sequence.replace(' ', np.nan) # 替换空格为NaN bus_line_sequence = bus_line_sequence.drop(bus_line_sequence.columns[0], axis=1) bus_line_sequence = bus_line_sequence.fillna(0) bus_line_sequence = bus_line_sequence.astype(int) bus_line_sequence = bus_line_sequence.values chromosome_results = np.array(multi_huifun(individuals['chrom'],yanlinks,road_velocity,dadr,bus_line_sequence)) # 读取 # with open('individuals_chrom.pkl', 'rb') as file: # individuals['chrom'] = pickle.load(file) # chromosome_results = np.zeros((sizepop, 3)) # for j in range(sizepop): # chromosome_results[j,:] = liziqunfun(individuals['chrom'][j],yanlinks,road_velocity,dadr,bus_line_sequence) inff_np = three_dimensional_TOPSIS(chromosome_results,None) inff_np[inff_np == 0] = 0.1 print('The fitness calculation for Code is complete') # isnan函数是判断输入是否为NaN（not a number）的函数，而inff是表示正无穷大的特殊值。 # 在这段代码中，如果inff是无限值，则将其值设为1000000 inff[np.isnan(inff_np)] = 1000000 for j in range(sizepop): individuals['fitness'][j] = inff_np[j] # 找最好的染色体 lixiangjie[0] = np.amin(chromosome_results, axis=0) every_generation_best_chromosome[0] = individuals['chrom'][np.argmin(individuals['fitness'])][0] every_generation_best_chromosome_san[0] = chromosome_results[np.argmin(individuals['fitness'])] individuals['chrom'] = np.array(individuals['chrom'])#select,crossnew,mutationnew有用到 # 记录最好适应度和平均适应度 trace = {'avgfitness': [], 'bestfitness': []} chromosome_results1 = np.zeros((sizepop, 3)) for i in range(1, maxgen + 1): print(i) individuals = select(individuals, sizepop) individuals['chrom'] = crossnew(pcross, lenchrom, individuals['chrom'], sizepop, unassigned_roads,final_partitions) individuals['chrom'] = mutationnew(pmutation, lenchrom, individuals['chrom'], sizepop, unassigned_roads,final_partitions) inff = np.zeros(sizepop) # for j in range(sizepop): # chromosome_results1[j, :] = liziqunfun(individuals['chrom'][j, :]) chromosome_results1 = np.array(multi_huifun(individuals['chrom'],yanlinks,road_velocity,dadr,bus_line_sequence)) inff = three_dimensional_TOPSIS(chromosome_results1,lixiangjie[i-1]) inff[inff == 0] = 0.1 inff[np.isnan(inff)] = 1000000 result = np.vstack((chromosome_results, chromosome_results1)) chromosome_results = np.amin(result, axis=0) for j in range(sizepop): individuals['fitness'][j] = inff[j] newbestindex = np.argmin(individuals['fitness']) worstindex = np.argmax(individuals['fitness']) # Replace the worst chromosome with the best chromosome individuals['chrom'][worstindex] = individuals['chrom'][newbestindex] individuals['fitness'][worstindex] = individuals['fitness'][newbestindex] lixiangjie[i] = chromosome_results every_generation_best_chromosome[i] = individuals['chrom'][newbestindex] every_generation_best_chromosome_san[i] = chromosome_results1[newbestindex] all_generation_bestchrom_san = three_dimensional_TOPSIS(np.array(list(every_generation_best_chromosome_san.values())),lixiangjie[maxgen]) min_index = np.argmin(all_generation_bestchrom_san) fitness = np.minimum.accumulate(all_generation_bestchrom_san) values = np.array(list(every_generation_best_chromosome_san.values())) # 追踪当前的最小值 current_min = float('inf') corresponding_values_list = [] for idx, val in enumerate(all_generation_bestchrom_san): if val < current_min: current_min = val min_index = np.argmin(all_generation_bestchrom_san[:idx + 1]) corresponding_values_list.append(values[min_index]) else: corresponding_values_list.append(corresponding_values_list[-1]) corresponding_values = np.array(corresponding_values_list) bestchrom = list(every_generation_best_chromosome.values())[min_index] pd.DataFrame({'Fitness': fitness}).to_excel(os.path.join(OUTPUT_DIR, 'all_generation_bestchrom_fitness_directionless.xlsx'), index=True) df = pd.DataFrame.from_dict(lixiangjie, orient='index', columns=['var', 'cut', 'linknumber']) df_original_values = pd.DataFrame(corresponding_values, columns=['var', 'cut', 'linknumber']) merged_df = pd.concat([df, df_original_values], axis=1) # 将合并后的DataFrame保存为xlsx文件 merged_df.to_excel(os.path.join(OUTPUT_DIR, 'lixiangjie_and_best_chromosome.xlsx'), index=False) df2 = pd.DataFrame.from_dict(every_generation_best_chromosome, orient='index') df2.to_excel(os.path.join(OUTPUT_DIR, 'every_generation_best_chromosome.xlsx'), index=False) end = time.time() start1 = time.time() # print('Step 3 boundary adjustment') for i in range(len(yanlinks)): yanlinks[i, 11] = bestchrom[int(yanlinks[i, 10])-1] data_path = r'' df2 = pd.read_csv(data_path + 'links_test1.csv') df2['L'] = yanlinks[:, 11] df1 = pd.read_csv(data_path + 'bus_road_sequence_processed.csv', header=None, encoding='gbk') replace_dict = df2.set_index(df2.columns[5])[df2.columns[11]].to_dict() df1.iloc[:, 1:] = df1.iloc[:, 1:].applymap(replace_dict.get) df1.to_csv(os.path.join(OUTPUT_DIR, 'bus_line_partition.csv'), header=None, index=False) # yanlinks = boundary_adjustment_fitness(yanlinks,bestchrom) pd.DataFrame(yanlinks).to_csv(os.path.join(OUTPUT_DIR, 'yanlinks_boundary_adjustment.csv'), index=False, header=False) pd.DataFrame(bestchrom).to_csv(os.path.join(OUTPUT_DIR, "bestchrom.csv"), index=False, header=False) end1 = time.time() # print('Partition Merge:', end - start, 'seconds') # print('Boundary Adjustment:', end1 - start1, 'seconds') except: continue