1、摘要
本文主要讲解：使用地铁客流业务逻辑来计算重庆地铁断面客流量
主要思路：
- 使用Floyd佛洛依德算法找到重庆地铁的最短路径；
- 计算每个段面的客流量（算某个时间段重庆所有断面的客流量）
- 把断面客流量加到json里面去，利用累加的方式去计算
2、数据介绍
重庆各站点间的区间长度，18年的数据，共8条线142个站点
某个时间段的OD客流量，采用矩阵的方式进行存储
3、相关技术
1、panda读取文件后的数据为Dataframe，关于Dataframe的遍历方法itertuples
2、Json数据的key，value格式，适合存储与计算断面客流量
4、完整代码
代码输出如下：
Json格式的如下：
步骤1：根据每个站点的距离计算各个站点间的最短路径
from itertools import permutations
import pandas as pd
from my_utils.read_write import writeOneCsv, writeOneJson
subway_dict = []
transfer_dict = []
src = r'D:\项目\重庆地铁断面客流量计算\\'
try:
yearStop = pd.read_excel(src + '区间长度.xlsx', encoding='gbk')
except Exception as e:
yearStop = pd.read_excel(src + '区间长度.xlsx', encoding='utf-8')
def getRoute():
for feature in yearStop.itertuples(index=False):
line = str(getattr(feature, '线路名称'))
SStation = str(getattr(feature, 'SStation'))
EStation = str(getattr(feature, 'EStation'))
Length_Dow = getattr(feature, 'Length_Dow')
start = line + '-' + SStation
end = line + '-' + EStation
subway_dict.append([start, end, Length_Dow])
transfer = {}
def getTransfer():
'''SStation EStation Length_Dow 线路名称'''
features = yearStop.groupby('SStation')
for name, feature in features:
if feature.shape[0] > 0:
for one in feature.itertuples():
linename = getattr(one, '线路名称')
line_station = str(linename) + '-' + str(name)
if name not in transfer.keys():
transfer[name] = []
transfer[name].append(line_station)
# 列举排列结果[(1, 2), (1, 3), (2, 1), (2, 3), (3, 1), (3, 2)]
data4 = list(permutations([i for i in range(0, 4)], 2))
for key in transfer.keys():
data = transfer[key]
if len(data) == 2:
transfer_dict.append([data[1], data[0], 120])
transfer_dict.append([data[0], data[1], 120])
elif len(data) == 3:
transfer_dict.append([data[1], data[0], 180])
transfer_dict.append([data[0], data[1], 180])
transfer_dict.append([data[0], data[2], 180])
transfer_dict.append([data[2], data[0], 180])
transfer_dict.append([data[1], data[2], 180])
transfer_dict.append([data[2], data[1], 180])
elif len(data) == 4:
for one in data4:
transfer_dict.append([data[one[0]], data[one[1]], 240])
# getTransfer()
'''
弗洛伊德算法（Floyd算法）
'''
class Vertex:
def __init__(self, key):
self.id = key
self.connectedTo = {}
def addNeighbor(self, nbr, weight=0):
self.connectedTo[nbr] = weight
def __str__(self):
return str(self.id) + ' connectedTo: ' + str([x.id for x in self.connectedTo])
def getConnections(self):
return self.connectedTo.keys()
def getId(self):
return self.id
def getWeight(self, nbr):
return self.connectedTo[nbr]
class Graph:
def __init__(self):
self.vertList = {}
self.numVertices = 0
def addVertex(self, key):
self.numVertices = self.numVertices + 1
newVertex = Vertex(key)
self.vertList[key] = newVertex
return newVertex
def getVertex(self, n):
if n in self.vertList:
return self.vertList[n]
else:
return None
def __contains__(self, n):
return n in self.vertList
def addEdge(self, f, t, cost=0):
if f not in self.vertList:
nv = self.addVertex(f)
if t not in self.vertList:
nv = self.addVertex(t)
self.vertList[f].addNeighbor(self.vertList[t], cost)
def getVertices(self):
return self.vertList.keys()
def __iter__(self):
return iter(self.vertList.values())
def Floyd(Graph, ShortestPath):
global path
NodeNum = len(Graph)
lastShortestDistance = [[0 for i in range(NodeNum)] for j in range(NodeNum)]
currentShortestDistance = [[0 for i in range(NodeNum)] for j in range(NodeNum)]
path = [[0 for i in range(NodeNum)] for j in range(NodeNum)]
for i in range(NodeNum):
for j in range(NodeNum):
path[i][j] = j
for i in range(NodeNum):
for j in range(NodeNum):
lastShortestDistance[i][j] = Graph[i][j]
currentShortestDistance[i][j] = lastShortestDistance[i][j]
for k in range(NodeNum):
for i in range(NodeNum):
for j in range(NodeNum):
if lastShortestDistance[i][j] > lastShortestDistance[i][k] + lastShortestDistance[k][j]:
currentShortestDistance[i][j] = lastShortestDistance[i][k] + lastShortestDistance[k][j]
path[i][j] = path[i][k]
lastShortestDistance = currentShortestDistance
for i in range(NodeNum):
for j in range(NodeNum):
# if i==j:
# ShortestPath[i][j]=0
# else:
ShortestPath[i][j] = currentShortestDistance[i][j]
print("path is: ", path)
print("shortestPath is: ", ShortestPath)
# print(currentShortestDistance)
return None
def printPath(i, j, shortestPath, path):
print(zhandian[i] + "----" + zhandian[j] + "\n最短时间:" + str(shortestPath[i][j]) + "s\n路径:\n" + zhandian[i])
temp = path[i][j]
odName = zhandian[i] + "_" + zhandian[j]
JsonData = {}
routeSplitData = [zhandian[i]]
while (temp != j):
routeSplitData.append(zhandian[temp])
print("-->" + zhandian[temp])
temp = path[temp][j]
routeSplitData.append(zhandian[j])
JsonData[odName] = routeSplitData
mainJson.append(JsonData)
print("-->" + zhandian[j])
'''SStation EStation Length_Dow 线路名称'''
def splitTime(i, j, shortestPath, path):
temp = path[i][j]
routeSplitData = [zhandian[i]]
time = shortestPath[i][j]
while (temp != j):
routeSplitData.append(zhandian[temp])
temp = path[temp][j]
routeSplitData.append(zhandian[j])
start = zhandian[i]
SStation = routeSplitData[len(routeSplitData) - 2].split('-')[1]
EStation = zhandian[j].split('-')[1]
if SStation != EStation:
save = [start, SStation, EStation, time]
print(save)
writeOneCsv(save, src+r'all.csv')
def writeOneCsv(relate_record, src):
with open(src, 'a', newline='\n') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(relate_record)
# 写Json文件,一个数据一个文件
def writeOneJson(relate_record, src):
Json_str = json.dumps(relate_record, ensure_ascii=False)
with open(src, 'w', encoding='utf-8') as Json_file:
Json_file.write(Json_str)
Json_file.close()
if
__name__ == "__main__":
mainJson = []
getRoute()
getTransfer()
g = Graph()
# vel = 10 # 地铁的速度 m/s
vel = 10 # 地铁的速度 m/s
for x in subway_dict:
g.addEdge(x[0], x[1], int(float(x[2]) / vel)) # 由距离得到时间
g.addEdge(x[1], x[0], int(float(x[2]) / vel)) # 双向都有
for x in transfer_dict:
g.addEdge(x[0], x[1], int(float(x[2]))) # 换站给的直接就是时间
print(len(g.getVertices())) # 打印图中顶点数
print(g.getVertices()) # 打印图中所有的顶()点
zhandian = []
for i in g.getVertices():
zhandian.append(i)
zhandian = tuple(list(zhandian))
x = float('inf')
matrix = [[x for i in range(338)] for i in range(338)]
for i in range(338):
matrix[i][i] = 0
for v in g: # 对图中的每一个顶点，获取与它有连接关系的顶点
for w in v.getConnections():
time = v.getWeight(w)
matrix[zhandian.index(v.getId())][zhandian.index(w.getId())] = time
graph = matrix
nodeNum = len(graph)
shortestPath = [[0 for i in range(nodeNum)] for j in range(nodeNum)]
print("计算时间比较长，请耐心等待几分钟！")
Floyd(graph, shortestPath)
allStation = []
'''SStation EStation Length_Dow 线路名称'''
for one_s in yearStop.itertuples():
line = str(getattr(one_s, '线路名称'))
start = line + '-' + str(getattr(one_s, 'SStation'))
end = line + '-' + str(getattr(one_s, 'EStation'))
if start not in allStation:
allStation.append(start)
if end not in allStation:
allStation.append(end)
for start in allStation:
for end in allStation:
if start != end:
s = zhandian.index(start)
e = zhandian.index(end)
printPath(s, e, shortestPath, path)
# splitTime(s, e, shortestPath, path)
writeOneJson(mainJson, src + '最短路径.json')
主运行程序入口
import pandas as pd
from my_utils.read_write import writeOneJson, readJson, writeOneCsv
'''
此文件用于计算重庆地铁线路断面客流量
计算步骤：1、找到最短路径；
2、计算每个段面的客流量（算0这个时间段所有深圳所有断面的客流量）
'''
src = r'D:\项目\重庆地铁断面客流量计算\\'
try:
od_people = pd.read_excel(src + 'OD客流量.xlsx', encoding='gbk')
except Exception as e:
od_people = pd.read_excel(src + 'OD客流量.xlsx', encoding='utf-8')
try:
yearStop = pd.read_excel(src + '区间长度.xlsx', encoding='gbk')
except Exception as e:
yearStop = pd.read_excel(src + '区间长度.xlsx', encoding='utf-8')
all_split = []
for one_s in yearStop.itertuples():
line = str(getattr(one_s, '线路名称'))
start = line + '-' + str(getattr(one_s, 'SStation'))
end = line + '-' + str(getattr(one_s, 'EStation'))
all_split.append(start + '_' + end)
all_split.append(end + '_' + start)
def add_count(split, od_count, routeSplitJson):
if split not in routeSplitJson.keys():
routeSplitJson[split] = 0
# 某个断面某个时间加入od的数量
routeSplitJson[split] = routeSplitJson[split] + od_count
def readJson(filepath):
try:
with open(filepath, 'r', encoding='GBK') as file_open:
data = json.load(file_open)
file_open.close()
return data
except:
try:
with open(filepath, 'r', encoding='utf-8') as file_open:
data = json.load(file_open)
file_open.close()
return data
except:
with open(filepath, 'r', encoding="unicode_escape") as file_open:
data = json.load(file_open)
file_open.close()
return data
def routeSplit(df, routeSplitJson):
minWays = readJson(src + '最短路径.json')
min_ways = {}
for one in minWays:
keys = one.keys()
for i in keys:
if i not in min_ways.keys():
min_ways[i] = {}
# 某个断面某个时间加入od的数量
min_ways[i] = one[i]
allStation = []
for one_s in yearStop.itertuples():
line = str(getattr(one_s, '线路名称'))
start = line + '-' + str(getattr(one_s, 'SStation'))
end = line + '-' + str(getattr(one_s, 'EStation'))
if start not in allStation:
allStation.append(start)
if end not in allStation:
allStation.append(end)
# o_station,d_station,tw,od
for row in df.itertuples(index=False):
line = str(getattr(row, '线路'))
start = line + '-' + str(getattr(row, '车站编号'))
for n in range(len(allStation)):
if start != allStation[n]:
od_count = row[n + 2]
od_name = start + '_' + allStation[n]
# 获取到最短路径的数据
minStations = min_ways[od_name]
for m in range(0, len(minStations)):
if m + 1 < len(minStations):
split = minStations[m] + '_' + minStations[m + 1]
if split in all_split:
# 把断面客流量加到json里面去
add_count(split, od_count, routeSplitJson)
def final():
routeSplitJson = {}
routeSplit(od_people, routeSplitJson)
writeOneJson(routeSplitJson, src + '重庆断面客流量.json')
def deal_json():
data = readJson(src + '重庆断面客流量.json')
# 上行客流量,断面,下行客流量
alr = []
one = []
for key in data.keys():
if key not in alr:
split_data = key.split('_')
add = split_data[0].split('-')[1] + '-' + split_data[1].split('-')[1]
down_key = split_data[1] + '_' + split_data[0]
alr.append(down_key)
alr.append(key)
if down_key in data.keys():
writeOneCsv([data[key], add, data[down_key]], src + '重庆地铁断面客流量.csv')
else:
writeOneCsv([data[key], add, 0], src + '重庆地铁断面客流量.csv')
if __name__ == '__main__':
deal_json()
final()
read_write文件在我的下载里有，请自行搜索
如需数据示例请私聊我，有偿