Data Converter (drive, bike, walk)

dataConverter.py

@@ -1,3 +1,10 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Oct 30 12:45:06 2020
+
+@author: ma076216
+"""
+
 # Read a csv file with source, target, and length and generate a standard graph
 import csv
 import json
@@ -8,8 +15,9 @@
 dFile = []
 
 # loading the graph from the json file located in .\graph folder
-dirName = path.dirname(__file__)
-fileName = path.join(dirName, 'graph/TestData.csv')
+#dirName = path.dirname(__file__)
+dirName = "C:/Users/ma076216/Desktop/PhD/research paper/python_code"
+fileName = path.join(dirName, 'graph/graph_avg.csv')
 
 # open the CSV input file
 with open(fileName, newline='') as csvfile:
@@ -26,7 +34,7 @@
     index = 0
     while index < len(nodes):
         graph.append({'id': index, 'gid': nodes[index],
-                      'lat': 0, 'lon': 0, 'nbrs': [], 'dists': []})
+                      'lat': 0, 'lon': 0, 'nbrs': [], 'dists': [],'TT':[],'bike':[],'walk':[]})
         index += 1
 
     # update the neighbor nodes in the graph
@@ -40,12 +48,15 @@
         if (t != s):  # edges starting and ending at the same node are useless
             if (t not in graph[s]['nbrs']):
                 graph[s]['nbrs'].append(t)
-                graph[s]['dists'].append(float(row['dist']))
+                graph[s]['dists'].append(float(row['length_m']))
             if (s not in graph[t]['nbrs']):
                 graph[t]['nbrs'].append(s)
-                graph[t]['dists'].append(float(row['dist']))
+                graph[t]['dists'].append(float(row['length_m']))
+                graph[t]['TT'].append(float(row['tt_thodaysec']))
+                graph[t]['bike'].append(float(row['Biking travel time']))
+                graph[t]['walk'].append(float(row['walking travel time_sec']))
 
 # stroing graph.json file in the graph folder. It will overwrite existing files
-fileName = path.join(dirName, 'graph/graph.json')
+fileName = path.join(dirName, 'graph/graph1.json')
 with open(fileName, 'w') as fp:
-    json.dump(graph, fp)
+    json.dump(graph, fp)

hybalg.py

@@ -0,0 +1,80 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Nov 12 11:03:56 2020
+
+@author: ma076216
+"""
+import math
+import random
+demand_points_rnd = random.sample(range(1,19835),500)
+demand_levels =[]
+for i in range (len(demand_points_rnd)):
+
+    demand_levels.append(random.randint(1,100))
+
+demand_set = list(zip(demand_points_rnd,demand_levels))
+
+number_clusters = 5
+capacity = 100
+from clusalg import *
+
+
+clusters_f = findCluster(demand_points_rnd, demand_levels, number_clusters, .5)
+clusters_list = []
+for i in range (number_clusters):
+    clusters_list.append(clusters_f[0][i]['dps']) 
+
+total_demand_clusters = []
+number_modules = []
+utilization = []
+for i in range (number_clusters):
+    demand_sum = 0
+
+    j=0
+    for j in range(len(clusters_list[i])):
+
+        demand_sum = demand_sum+clusters_list[i][j][1]
+
+    total_demand_clusters.append(demand_sum)
+    number_modules.append(demand_sum/capacity)
+    utilization.append (number_modules[i]- math.floor(number_modules[i]))
+
+uti_sort = sorted(utilization,reverse=True)
+sim_thrishold = 7000
+i = 0
+dedicated_mod = []
+shared_mod = []
+remainder_mod=[]
+
+while len(uti_sort)>0:
+    if uti_sort[i]== 1:
+        dedicated_mod.append(utilization.index(uti_sort[i],0, number_clusters-1))
+        uti_sort.pop(0)
+        continue
+    if uti_sort[i]>=0.50:
+        uti_shared = uti_sort[i]
+        sh_l = []
+        sh_l.append(utilization.index(uti_sort[i])) # get index of module with utilization >0.5 store it in shl
+        j=i+1
+        while j in range (1,len(uti_sort)-1): # iterate through remainng elements to find shared modules 
+            uti_shared = uti_shared + uti_sort[j]
+            if uti_shared > 1: # if a combination is greater than 100 utilization do not combine them and move on
+                uti_shared = uti_shared - uti_sort[j]
+                j+=1
+                continue
+            sh_l.append(utilization.index(uti_sort[j])) # if two modules can be combined, do it and get their indecies
+            uti_sort.pop(j) # reomve the item combined from sorted utilization list  
+        if len(sh_l)>1: #if 2 or more modules combined add them to the shared modules list, otherwise to dedicated list
+            shared_mod.append(sh_l)
+            uti_sort.pop(i)
+            continue
+        else:
+            dedicated_mod.append(sh_l)
+            uti_sort.pop(i)
+            continue
+    if uti_sort[i]<0.50:
+        remainder_mod.append(utilization.index(uti_sort[i]))
+        uti_sort.pop(i)
+
+
+

pMedian.py

@@ -1,4 +1,19 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Feb 25 18:09:26 2021
+
+@author: ma076216
+"""
+
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Oct 30 12:45:49 2020
+
+@author: ma076216
+"""
+
 # Multi Threaded Dijkstra's (MTD) algorithm
+import random 
 import heapq
 from os import path
 from operator import itemgetter
@@ -8,13 +23,15 @@
 
 # loading the graph from the json file located in .\graph folder
 dirName = path.dirname(__file__)
+dirName = "C:/Users/ma076216/Desktop/PhD/research paper/python_code"
+
 fileName = path.join(dirName, 'graph/graph.json')
 graph = pd.read_json(fileName)
 print('Graph has '+str(len(graph))+' nodes.')
 graph = graph[['id', 'nbrs', 'dists', 'lat', 'lon']]
 
 
-def findCluster(nodes, weights, p, pec, maxItr=1000):
+def findCluster(nodes, weights, p, pec, maxItr=10):
     pec = int(pec*p)
     dps = list(zip(nodes, weights))  # make a tuple from the demand points
     dps.sort(key=itemgetter(1), reverse=False)  # sorting the demand points in ascending order
@@ -28,16 +45,17 @@ def findCluster(nodes, weights, p, pec, maxItr=1000):
         bestDist = float('inf')
         bestId = -1
         src = dps.pop()
-        for cluster in clusters:
-            dist = findSDist((graph['lon'][src[0]], graph['lon'][src[0]]), cluster['median'])
+        for cluster in clusters: #this loop iterates through all clusters to find the closet cluster for point src
+         # first modification
+            dist = findSDist((graph['lon'][src[0]], graph['lat'][src[0]]), cluster['median'])
             if dist < bestDist:
                 bestDist = dist
                 bestId = cluster['id']
         clusters[bestId]['dps'].append(src)  # add the node to the closest cluster
         clusters[bestId]['median'] = findCOM(clusters[bestId]['dps'])  # update the center of mass
 
         distMat = [[0 for i in range(p)] for j in range(p)]  # initialize the distance matrix
-        for (i, j) in [(i, j) for i in range(3) for j in range(3)]:
+        for (i, j) in [(i, j) for i in range(p) for j in range(p)]:
             if i < j:
                 distMat[i][j] = distMat[j][i] = findSDist(
                     clusters[i]['median'], clusters[j]['median'])
@@ -49,27 +67,36 @@ def findCluster(nodes, weights, p, pec, maxItr=1000):
             for cluster in clusters:
                 if len(cluster['dps']) < 2:  # skip clusters with one point
                     continue
-                pq = []  # create a list of nearby clusters
-                for j in range(p):
-                    if cluster['id'] != j:
-                        heapq.heappush(pq, (distMat[cluster['id']][j], j))
-                bestMove = {'src': -1, 'dst': -1, 'dp': -1, 'costDiff': 0}
+
                 for i in range(len(cluster['dps'])):
+                    #5th modification reini
+                    bestMove = {'src': -1, 'dst': -1, 'dp': -1, 'costDiff': 0}
+                    pq = []  # create a list of nearby clusters
+                    for j in range(p):
+                        if cluster['id'] != j:
+                            heapq.heappush(pq, (distMat[cluster['id']][j], j))
+
+                    # second modification j=0 
+                    j=0
                     while j < pec:
                         tmpSrc = (graph['lon'][cluster['dps'][i][0]],
                                   graph['lat'][cluster['dps'][i][0]])
                         tmpDst = heapq.heappop(pq)
                         # weighted distance between the demand point and new cluster median
-                        newCost = findDist(
+                        #third modification FindSdistance
+                        newCost = findSDist(
                             tmpSrc, clusters[tmpDst[1]]['median']) * cluster['dps'][i][1]
+
                         # weighted distance between the demand point and curretn cluster median
-                        curCost = findDist(tmpSrc, cluster['median']) * cluster['dps'][i][1]
+                        curCost = findSDist(tmpSrc, cluster['median']) * cluster['dps'][i][1]
+
                         # update bestMove if we have a cost saving move
                         if bestMove['costDiff'] < curCost - newCost:
                             bestMove = {'src': cluster['id'], 'dst': tmpDst[1],
                                         'dp': cluster['dps'][i], 'costDiff': curCost - newCost}
                         j += 1
                 if bestMove['costDiff'] > 0:  # if we have a cost saving move, do it!
+
                     exchange = True
                     clusters[bestMove['src']]['dps'].remove(
                         bestMove['dp'])  # remove the dp from the src cluster
@@ -80,6 +107,7 @@ def findCluster(nodes, weights, p, pec, maxItr=1000):
                     # update the center of mass of the dst cluster
                     clusters[bestMove['dst']]['median'] = findCOM(clusters[bestMove['dst']]['dps'])
             Itr += 1
+
     return (clusters, Itr)
 
 
@@ -99,6 +127,13 @@ def findCOM(nodes):  # finds the geometric center of mas of a set of graph nodes
         w += j
     return (x/w, y/w)
 
+#select demand points randomly and assign weight 1 to all points 
+demand_points_rnd = random.sample(range(1,19835),500)
+demand_levels =[1]*500 # intialize a list of demand levels for all demand points
 
 # this is how to call the clustering algorithm
-print(findCluster([1453, 10, 456, 178, 876, 8743], [1, 2, 3, 4, 5, 6], 3, .5))
+print(findCluster([1453, 10, 456, 178, 876, 8743], [1, 2, 3, 4, 5, 6], 3, .8))
+
+print(findCluster(demand_points_rnd, demand_levels , 6, .7))
+
+