def get_information(file_path): # using target_MDG and a benchmark, create result
"""
Execute Each algorithm for given file and return TurboMQ, cohesion, and coupling
:param file_path: A path of dot file
:return: Clustering result - value of TurboMQ, A list of [Cohesion, Coupling], A list of result clusters
"""
targetMDG = make_target_MDG(file_path)
methods = ['WCA', 'HC', 'WCA_HC', 'SA', 'WCA_SA', 'PSO', 'WCA_PSO']
clusters_set = []
TMQ = []
cohe_coup = []
print("====WCA start====\n")
clusters_set.append(WCA(targetMDG))
print("====WCA end====\n\n")
print("====HC start====\n")
clusters_set.append(HC.HC(targetMDG))
print("====HC end====\n\n")
print("====WCA_HC start====\n")
clusters_set.append(HC.WCA_HC(targetMDG, WCA(targetMDG)))
print("====WCA_HC end====\n\n")
print("====SA start====\n")
clusters_set.append(SA.SA(targetMDG))
print("====SA end====\n\n")
print("====WCA_SA start====\n")
clusters_set.append(SA.WCA_SA(targetMDG, WCA(targetMDG)))
print("====WCA_SA end====\n\n")
print("====PSO start====\n\n")
clusters_set.append(PSO.PSO(targetMDG))
print("====PSO end====\n\n")
print("====WCA_PSO start====\n\n")
clusters_set.append(PSO.WCA_PSO(targetMDG, WCA(targetMDG)))
print("====WCA_PSO end====\n\n")
# get TMQ data
for clusters in clusters_set:
TMQ.append(TurboMQ.calculate_fitness(clusters, targetMDG))
cohe_coup.append(TurboMQ.get_cohesion_coupling(clusters, targetMDG))
# write result files
for i in range(len(methods)):
DotParser.write_file(file_path, methods[i], clusters_set[i], targetMDG)
return TMQ, cohe_coup, clusters_set
def TSP(stops, Alg, steps, param, seed=None, coordfile='xycoords.txt'):
'''A wrapper function that attempts to optimize the traveling
salesperson problem using a specified algorithm. If coordfile
exists, a preexisting set of coordinates will be used. Otherwise,
a new set of "stops" coordinates will be generated for the person to
traverse, and will be written to the specified file.'''
# Create the distance matrix, which will be used to calculate
# the fitness of a given path
if os.path.isfile(coordfile):
coords = scipy.genfromtxt(coordfile)
distMat = DistanceMatrix(coords)
else:
distMat = GenerateMap(stops, fname=coordfile, seed=seed)
if Alg == 'HC':
# param is the number of solutions to try per step
bestSol, fitHistory = hc.HillClimber(steps, param, distMat, seed)
elif Alg == 'SA':
# param is a placeholder
bestSol, fitHistory = sa.SimulatedAnnealing(steps, param, distMat,
seed)
elif Alg == 'MC3':
# param is the number of chains
bestSol, fitHistory = mc3.MCMCMC(steps, param, distMat, seed)
elif Alg == 'GA':
# param is the population size
bestSol, fitHistory = ga.GeneticAlgorithm(steps, param, distMat, seed)
else:
raise ValueError('Algorithm must be "HC", "SA", "MC3", or "GA".')
outfname = coordfile + '-' + Alg + '-' + \
str(steps) + '-' + str(param) + '.txt'
scipy.savetxt(outfname, scipy.array(bestSol), fmt='%i')
return bestSol, fitHistory
def main():
parser = argparse.ArgumentParser(description='Modularize given dot file')
parser.add_argument('file_path',
metavar='F',
type=str,
nargs='+',
help='File path for dot file')
parser.add_argument(
'-a',
help=
'Algorithm for modularization. All, WCA, HC, WCA_HC, SA, WCA_SA, PSO, WCA_PSO'
)
args = parser.parse_args()
file_path = args.file_path
if args.a:
modularizeMethod = args.a
else:
modularizeMethod = 'All'
for single_file in file_path:
targetMDG = MakeResult.make_target_MDG(single_file)
clusters = None
if modularizeMethod == 'WCA':
clusters = WCA(targetMDG)
elif modularizeMethod == 'HC':
clusters = HC.HC(targetMDG)
elif modularizeMethod == 'WCA_HC':
clusters = HC.WCA_HC(targetMDG, WCA(targetMDG))
elif modularizeMethod == 'SA':
clusters = SA.SA(targetMDG)
elif modularizeMethod == 'WCA_SA':
clusters = SA.WCA_SA(targetMDG, WCA(targetMDG))
elif modularizeMethod == 'PSO':
clusters = PSO.PSO(targetMDG)
elif modularizeMethod == 'WCA_PSO':
clusters = PSO.WCA_PSO(targetMDG, WCA(targetMDG))
elif modularizeMethod == 'All':
MakeResult.print_result(single_file)
if modularizeMethod != 'All':
DotParser.write_file(single_file, modularizeMethod, clusters,
targetMDG)
def index():
Caster = request.args.get("Caster")
Defense = (request.args.get("Defense"))
if Defense:
Defense = int(Defense)
Armor = (request.args.get("Armor"))
if Armor:
Armor = int(Armor)
Boxes = (request.args.get("Boxes"))
if Boxes:
Boxes = int(Boxes)
Focus = (request.args.get("Focus"))
if Focus:
Focus = int(Focus)
if Caster and Defense and Armor and Boxes and Focus:
percent = HC.survive_options(Caster, Defense, Armor, Boxes, Focus)
else:
percent = " "
response = make_response(render_template("index.html", death=percent))
return response
x = phi[i]
means_cost += (((c[x][0] - cluster[i][0])**2 +
(c[x][1] - cluster[i][1])**2)**0.5)**2
#means_cost=means_cost/ float(len(cluster))
print '3-means cost is :', means_cost
print '\n Indexes are :'
print '******************************'
print 'Cluster 1:', indexes1
print '******************************'
print 'Cluster 2:', indexes2
print '******************************'
print 'Cluster 3:', indexes3
print '******************************'
""" Plotting the data """
title = "Clustering using Gonzalez algorithm "
HC.lloyds_plot(cluster, phi, c, title)
"""
print '\n Subsets are :'
print '******************************'
print 'Subset 1:', subset1
print '******************************'
print 'Subset 2:', subset2
print '******************************'
print 'Subset 3:', subset3
print '******************************'
"""
print 'The set c now is :', b #print 'c[0][0] is :', c[0][0] #print 'c[1][0] is :', c[1][0] #print 'c[2][0] is :', c[2][1] for j in range(0, len(cluster)): dist1=((cluster[j][0]- c[0][0])**2 + (cluster[j][1] - c[0][1])**2)**0.5 dist2=((cluster[j][0]- c[1][0])**2 + (cluster[j][1] - c[1][1])**2)**0.5 dist3=((cluster[j][0]- c[2][0])**2 + (cluster[j][1] - c[2][1])**2)**0.5 #print 'Dist1 is :', dist1 #print 'Dist2 is :', dist2 #print 'Dist3 is :', dist3 min_dist=HC.my_min(dist1,dist2,dist3) #print 'Minimum is :', min_dist if min_dist==dist1: phi[j]=0 c0_x+=cluster[j][0] c0_y+=cluster[j][1] c0_center+=1 elif min_dist==dist2: phi[j]=1 c1_x+=cluster[j][0] c1_y+=cluster[j][1] c1_center+=1 elif min_dist==dist3: phi[j]=2 c2_x+=cluster[j][0]
slink_cluster=cluster clink_cluster=cluster meanlink_cluster=cluster """ Single-link Hierarchical clustering """ while len(slink_cluster)!=4: for i in range(0,len(slink_cluster)): print 'Len is now :', len(slink_cluster) for j in range(0,len(slink_cluster)): if slink_cluster[i]==slink_cluster[j]: continue else: tdist=HC.single_link(slink_cluster[i],slink_cluster[j]) print 'tdist here is:', tdist if tdist <= min: min=tdist print 'min at this point is :', min index=j c_cluster1=slink_cluster[i] c_cluster2=slink_cluster[j] print' Points are :', c_cluster1 ,'and :', c_cluster2 print 'Cluster 1 going to be removed is :', c_cluster1 print 'Cluster 2 going to be removed is :', c_cluster2 slink_cluster.remove(c_cluster1) slink_cluster.remove(c_cluster2) #slink_cluster.insert(index,c_cluster1 + c_cluster2) slink_cluster.append(c_cluster1 + c_cluster2)
print 'The set c now is :', b #print 'c[0][0] is :', c[0][0] #print 'c[1][0] is :', c[1][0] #print 'c[2][0] is :', c[2][1] for j in range(0, len(cluster)): dist1=((cluster[j][0]- c[0][0])**2 + (cluster[j][1] - c[0][1])**2)**0.5 dist2=((cluster[j][0]- c[1][0])**2 + (cluster[j][1] - c[1][1])**2)**0.5 dist3=((cluster[j][0]- c[2][0])**2 + (cluster[j][1] - c[2][1])**2)**0.5 #print 'Dist1 is :', dist1 #print 'Dist2 is :', dist2 #print 'Dist3 is :', dist3 min_dist=HC.my_min(dist1,dist2,dist3) #print 'Minimum is :', min_dist if min_dist==dist1: phi[j]=0 c0_x+=cluster[j][0] c0_y+=cluster[j][1] c0_center+=1 elif min_dist==dist2: phi[j]=1 c1_x+=cluster[j][0] c1_y+=cluster[j][1] c1_center+=1 elif min_dist==dist3: phi[j]=2 c2_x+=cluster[j][0]
clink_cluster=cluster """ Complete-link hierarchical clustering """ while len(clink_cluster)!=4: for i in range(0,len(clink_cluster)): for j in range(0,len(clink_cluster)): if clink_cluster[i]==clink_cluster[j]: continue else: tdist=HC.complete_link(clink_cluster[i],clink_cluster[j]) if tdist <= min: min=tdist #print 'min at this point is :', min c_cluster1=clink_cluster[i] c_cluster2=clink_cluster[j] #print 'Cluster 1 going to be removed is :', c_cluster1 #print 'Cluster 2 going to be removed is :', c_cluster2 clink_cluster.remove(c_cluster1) clink_cluster.remove(c_cluster2) clink_cluster.append(c_cluster1 + c_cluster2) #print 'Clusters at this stage are :', clink_cluster min=99999
def hierarchical_clustering():
G = load_data_by_networkx(email_path, type='U')
#HC.HierarchicalClustering(G,42)
result = HC.HierarchicalClustering(G)
return result
print '******************************'
print 'Cluster 2:', indexes2
print '******************************'
print 'Cluster 3:', indexes3
print '******************************'
print 'Centers calculated are :', c
print '3-means cost is :', new_cost
indexes1=[]
indexes2=[]
indexes3=[]
""" Plotting the data """
title="Clustering using k-Means++ algorithm "
HC.kmeansplusplus_plot(cluster,phi,c,title)
val1=str(new_cost)
val2=str(c)
f = open( 'k_means+.txt', 'a' )
#headers='3-means cost'
#f.write(''.join(headers) + '\n')
#f.write ( '3 means cost =' +'\n')
f.write (val1 + '\t'+ val2 +'\n' )
f.close()
new_cost=0
print '\n Indexes are :' print '******************************' print 'Cluster 1:', indexes1 print '******************************' print 'Cluster 2:', indexes2 print '******************************' print 'Cluster 3:', indexes3 print '******************************' """ Plotting the data """ title="Clustering using Gonzalez algorithm " HC.lloyds_plot(cluster,phi,c,title) """ print '\n Subsets are :' print '******************************' print 'Subset 1:', subset1 print '******************************' print 'Subset 2:', subset2 print '******************************' print 'Subset 3:', subset3 print '******************************' """
dist4 = (
(cluster[j][0] - c[3][0]) ** 2
+ (cluster[j][1] - c[3][1]) ** 2
+ (cluster[j][2] - c[3][2]) ** 2
+ (cluster[j][3] - c[3][3]) ** 2
+ (cluster[j][4] - c[3][4]) ** 2
) * 0.5
dist5 = (
(cluster[j][0] - c[4][0]) ** 2
+ (cluster[j][1] - c[4][1]) ** 2
+ (cluster[j][2] - c[4][2]) ** 2
+ (cluster[j][3] - c[4][3]) ** 2
+ (cluster[j][4] - c[4][4]) ** 2
) * 0.5
min_dist = HC.median5_min(dist1, dist2, dist3, dist4, dist5)
# print 'Minimum is :', min_dist
if min_dist == dist1:
phi[j] = 0
cluster1.append(cluster[j])
elif min_dist == dist2:
phi[j] = 1
cluster2.append(cluster[j])
elif min_dist == dist3:
phi[j] = 2
cluster3.append(cluster[j])
elif min_dist == dist4:
phi[j] = 3
cluster4.append(cluster[j])
elif min_dist == dist5:
for i in range(0, len(point)):
cluster += [[(x_coord[i], y_coord[i])]]
""" Making copies of the cluster list for the 3 variants """
slink_cluster = cluster
clink_cluster = cluster
meanlink_cluster = cluster
""" Mean-link Hierarchical clustering """
while len(meanlink_cluster) != 4:
for i in range(0, len(meanlink_cluster)):
for j in range(0, len(meanlink_cluster)):
if meanlink_cluster[i] == meanlink_cluster[j]:
continue
else:
tdist = HC.mean_link(meanlink_cluster[i], meanlink_cluster[j])
if tdist <= mean:
mean = tdist
#print 'min at this point is :', min
c_cluster1 = meanlink_cluster[i]
c_cluster2 = meanlink_cluster[j]
meanlink_cluster.remove(c_cluster1)
meanlink_cluster.remove(c_cluster2)
meanlink_cluster.append(c_cluster1 + c_cluster2)
mean = 999
meanlink_cluster1 = meanlink_cluster[0]
meanlink_cluster2 = meanlink_cluster[1]
meanlink_cluster3 = meanlink_cluster[2]
meanlink_cluster4 = meanlink_cluster[3]
for his in cost_his:
if len(his) > i:
tmp.append(his[i])
cost_his_t.append(tmp)
cost_std = list(map(np.std, cost_his_t))
cost_avg = list(map(np.average, cost_his_t))
return np.array(cost_avg), np.array(cost_std)
# Problem (1): 8-queen problem (n = 8)
hc_cost = []
aver_cost, aver_runtime, num_succ = [], [], 0
for i in range(num_trails):
prob = problem.N_QueenProblem(8)
hc = HC.HC(prob, max_iter=30)
hc.loop()
sol, runtime, final_cost, cost_his = hc.result()
aver_runtime.append(runtime)
aver_cost.append(final_cost)
if final_cost == 0:
num_succ += 1
del prob, hc
hc_cost.append(cost_his)
print('Problem (1): 8-queen problem (n = 8)')
print(' Hill Climbing')
print('\tAverage Runtime :', np.average(aver_runtime))
print('\tAverage Number of Attacks :', np.average(aver_cost))
print('\tSuccess Rate :', num_succ / num_trails)
hc_avg, hc_std = statics(hc_cost)
""" Making copies of the cluster list for the 3 variants """ slink_cluster=cluster clink_cluster=cluster meanlink_cluster=cluster """ Mean-link Hierarchical clustering """ while len(meanlink_cluster)!=4: for i in range(0,len(meanlink_cluster)): for j in range(0,len(meanlink_cluster)): if meanlink_cluster[i]==meanlink_cluster[j]: continue else: tdist=HC.mean_link(meanlink_cluster[i],meanlink_cluster[j]) if tdist <= mean: mean=tdist #print 'min at this point is :', min c_cluster1=meanlink_cluster[i] c_cluster2=meanlink_cluster[j] meanlink_cluster.remove(c_cluster1) meanlink_cluster.remove(c_cluster2) meanlink_cluster.append(c_cluster1 + c_cluster2) mean=999 meanlink_cluster1=meanlink_cluster[0] meanlink_cluster2=meanlink_cluster[1] meanlink_cluster3=meanlink_cluster[2]
"""
Created on Thu Jan 16 23:33:44 2020
@author: Nicolai
----------------
"""
from __future__ import absolute_import
from __future__ import print_function
import sys
import pickle
import numpy as np
sys.path.append('../../Modules')
import HC
import Cross_3_3_day as c33
if __name__ == "__main__":
# calculating
print("start init random")
x = np.array([90, 0, 5, 10, 15, 20, 25, 30, 35, 40])
# print("read old pop")
# with open('NSGA2_SaveList.pkl', 'rb') as pickle_file:
# backup = pickle.load(pickle_file)
# x = backup[-1][0]
print("finished init")
opt4, fD4 = HC.hillClimbing(x, c33.function_Cross_3_3)
for j in range(0, len(cluster)):
dist1 = ((cluster[j][0] - c[0][0])**2 + (cluster[j][1] - c[0][1])**2 +
(cluster[j][2] - c[0][2])**2 + (cluster[j][3] - c[0][3])**2 +
(cluster[j][4] - c[0][4])**2) * 0.5
dist2 = ((cluster[j][0] - c[1][0])**2 + (cluster[j][1] - c[1][1])**2 +
(cluster[j][2] - c[1][2])**2 + (cluster[j][3] - c[1][3])**2 +
(cluster[j][4] - c[1][4])**2) * 0.5
dist3 = ((cluster[j][0] - c[2][0])**2 + (cluster[j][1] - c[2][1])**2 +
(cluster[j][2] - c[2][2])**2 + (cluster[j][3] - c[2][3])**2 +
(cluster[j][4] - c[2][4])**2) * 0.5
dist4 = ((cluster[j][0] - c[3][0])**2 + (cluster[j][1] - c[3][1])**2 +
(cluster[j][2] - c[3][2])**2 + (cluster[j][3] - c[3][3])**2 +
(cluster[j][4] - c[3][4])**2) * 0.5
min_dist = HC.median_min(dist1, dist2, dist3, dist4)
#print 'Minimum is :', min_dist
if min_dist == dist1:
phi[j] = 0
cluster1.append(cluster[j])
elif min_dist == dist2:
phi[j] = 1
cluster2.append(cluster[j])
elif min_dist == dist3:
phi[j] = 2
cluster3.append(cluster[j])
elif min_dist == dist4:
phi[j] = 3
cluster4.append(cluster[j])
cluster += [[(x_coord[i], y_coord[i])]]
""" Making copies of the cluster list for the 3 variants """
slink_cluster = cluster
clink_cluster = cluster
meanlink_cluster = cluster
""" Single-link Hierarchical clustering """
while len(slink_cluster) != 4:
for i in range(0, len(slink_cluster)):
print 'Len is now :', len(slink_cluster)
for j in range(0, len(slink_cluster)):
if slink_cluster[i] == slink_cluster[j]:
continue
else:
tdist = HC.single_link(slink_cluster[i], slink_cluster[j])
print 'tdist here is:', tdist
if tdist <= min:
min = tdist
print 'min at this point is :', min
index = j
c_cluster1 = slink_cluster[i]
c_cluster2 = slink_cluster[j]
print ' Points are :', c_cluster1, 'and :', c_cluster2
print 'Cluster 1 going to be removed is :', c_cluster1
print 'Cluster 2 going to be removed is :', c_cluster2
slink_cluster.remove(c_cluster1)
slink_cluster.remove(c_cluster2)
#slink_cluster.insert(index,c_cluster1 + c_cluster2)
slink_cluster.append(c_cluster1 + c_cluster2)
