342 lines
13 KiB
Python
342 lines
13 KiB
Python
|
# 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 deap import base, creator, tools, algorithms
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
bus_info = pd.DataFrame()
|
|||
|
|
file_range = range(211, 236)
|
|||
|
|
file_directory = "E:\\分方向MFD\\数据\\处理后的数据\\公交匹配到路网\\08_pcross"
|
|||
|
|
for file_number in file_range:
|
|||
|
|
file_name = f"20190908_{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_niu.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_processed.csv', index=False)
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
# final_partitions是最终分区的数量 Initial_partitions是初始分区的数量
|
|||
|
|
final_partitions = 5
|
|||
|
|
Initial_partitions = 40
|
|||
|
|
|
|||
|
|
# links = pd.read_csv('links.csv')
|
|||
|
|
|
|||
|
|
# links = pd.read_csv('links_1.csv')
|
|||
|
|
links = links.to_numpy()
|
|||
|
|
|
|||
|
|
df = pd.read_excel('stationidwan.xls')
|
|||
|
|
stationid = df.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))))
|
|||
|
|
print(node.shape[0])
|
|||
|
|
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
|
|||
|
|
print(i)
|
|||
|
|
# 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]
|
|||
|
|
from sklearn.cluster import KMeans
|
|||
|
|
|
|||
|
|
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).fit(yanlinks[:, [6, 7]]).labels_, KMeans(n_clusters=N).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)
|
|||
|
|
#
|
|||
|
|
#
|
|||
|
|
#
|
|||
|
|
# for x in range(0, N): # x表示当前聚类的编号
|
|||
|
|
# 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('pattern.npy', pattern)
|
|||
|
|
pattern = np.load('pattern.npy')
|
|||
|
|
|
|||
|
|
|
|||
|
|
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('output/subregion_adj.csv', index=False, header=False)
|
|||
|
|
np.save('dadr.npy', directed_adjacency_matrix)
|
|||
|
|
np.save('yanlinks.npy', yanlinks)
|
|||
|
|
df = pd.DataFrame(yanlinks)
|
|||
|
|
df.to_csv('output/yanlinks_initial_partition.csv', index=False, header=False)
|
|||
|
|
|
|||
|
|
sizepop=2
|
|||
|
|
generations=3
|
|||
|
|
# 初始化
|
|||
|
|
lenchrom = [1] * Initial_partitions
|
|||
|
|
unassigned_roads = np.tile([[1, final_partitions]], (Initial_partitions, 1))
|
|||
|
|
individuals = {'fitness': np.zeros((sizepop, 1)), 'chrom': []}
|
|||
|
|
for i in range(sizepop):
|
|||
|
|
chromosome = Code(lenchrom, unassigned_roads, final_partitions)
|
|||
|
|
individuals['chrom'].append(chromosome)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def nsga2(func, individuals, sizepop, generations, pcross, pmutation, lenchrom, unassigned_roads, final_partitions):
|
|||
|
|
for generation in range(generations):
|
|||
|
|
# 计算适应度
|
|||
|
|
for i in range(sizepop):
|
|||
|
|
chrom = individuals['chrom'][i]
|
|||
|
|
individuals['fitness'][i] = func(chrom)
|
|||
|
|
|
|||
|
|
# 选择
|
|||
|
|
individuals = select(individuals, sizepop)
|
|||
|
|
|
|||
|
|
# 交叉
|
|||
|
|
individuals['chrom'] = crossnew(pcross, lenchrom, individuals['chrom'], sizepop, unassigned_roads,
|
|||
|
|
final_partitions)
|
|||
|
|
|
|||
|
|
# 变异
|
|||
|
|
individuals['chrom'] = mutationnew(pmutation, lenchrom, individuals['chrom'], sizepop, unassigned_roads,
|
|||
|
|
final_partitions)
|
|||
|
|
|
|||
|
|
return individuals
|
|||
|
|
|
|||
|
|
|
|||
|
|
# 执行 NSGA-II
|
|||
|
|
result = nsga2(liziqunfun, individuals, sizepop=sizepop, generations=generations, pcross=0.8, pmutation=0.2, lenchrom=lenchrom,
|
|||
|
|
unassigned_roads=unassigned_roads, final_partitions=final_partitions)
|
|||
|
|
|
|||
|
|
for chrom in result['chrom']:
|
|||
|
|
print(chrom)
|
|||
|
|
|