'''returns a float which is the populations average score'''
total = sum(pop)
return float(total) / float(len(pop))
def bestScore(pop, minmax='max'):
'''returns the Gen with the highest score in a population'''
if minmax == 'max':
return sorted(pop, key=attrgetter('rawScore'))[len(pop) - 1]
else:
return sorted(pop, key=attrgetter('rawScore'))[0]
lower = 0 # bounds for Gen parameters
upper = 100
rpop = initialPop(20, lower, upper, 5) # initializes pops
ypop = initialPop(20, lower, upper, 5)
for i in range(1000):
testFitFunc2(rpop, ypop) # sets pop scores
if i % 100 == 0: # prints every 100th generation
print('Generation', i)
print(str('r ') + str(averageScore(rpop)) + ' ' + str(bestScore(rpop)))
print(str('y ') + str(averageScore(ypop)) + ' ' + str(bestScore(ypop)))
#Evolves! (gets the new pop)
rpop = nextpop(rpop, .05, lower, upper, 'max')
ypop = nextpop(ypop, .05, lower, upper, 'max')
def averageScore(pop):
'''returns a float which is the populations average score'''
total = sum(pop)
return float(total)/float(len(pop))
def bestScore(pop,minmax='max'):
'''returns the Gen with the highest score in a population'''
if minmax == 'max':
return sorted(pop,key=attrgetter('rawScore'))[len(pop)-1]
else:
return sorted(pop,key=attrgetter('rawScore'))[0]
lower = 0 # bounds for Gen parameters
upper = 100
rpop = initialPop(20,lower,upper,5) # initializes pops
ypop = initialPop(20,lower,upper,5)
for i in range(1000):
testFitFunc2(rpop,ypop) # sets pop scores
if i%100 == 0: # prints every 100th generation
print('Generation',i)
print(str('r ')+str(averageScore(rpop))+' '+str(bestScore(rpop)))
print(str('y ')+str(averageScore(ypop))+' '+str(bestScore(ypop)))
#Evolves! (gets the new pop)
rpop = nextpop(rpop,.05,lower,upper,'max')
ypop = nextpop(ypop,.05,lower,upper,'max')
sort = sorted(pop, key=attrgetter('rawScore'))
return sort[0], sort[10]
def bestScore(pop, minmax='max'):
'''returns the Gen with the highest score in a population'''
if minmax == 'max':
return sorted(pop, key=attrgetter('rawScore'))[len(pop) - 1]
else:
return sorted(pop, key=attrgetter('rawScore'))[0]
#Initial parameters
lower = -10 #lower and upper are bounds for the Gen parameters
upper = 10
rpop = initialPop(20, lower, upper,
8) #Initializes predator and prey populations
ypop = initialPop(20, lower, upper, 8)
#Set up log to collect data
log = open("6BestCoEvolveLog.txt", 'a')
log.write('NewTest\n')
for i in range(5): #Runs this number of generations
#Calculates the population scores
fitFunc(rpop, ypop)
#Log relevant data
print 'Generation ' + str(i)
br, ar = bestAverageScore(rpop, 'min')
by, ay = bestAverageScore(ypop)
aSr = averageScore(rpop)
aSy = averageScore(ypop)
sort = sorted(pop,key=attrgetter('rawScore'))
return sort[len(pop)-1], sort[11]
else:
sort = sorted(pop,key=attrgetter('rawScore'))
return sort[0], sort[10]
def bestScore(pop,minmax='max'):
'''returns the Gen with the highest score in a population'''
if minmax == 'max':
return sorted(pop,key=attrgetter('rawScore'))[len(pop)-1]
else:
return sorted(pop,key=attrgetter('rawScore'))[0]
#Initial parameters
lower = -10 #lower and upper are bounds for the Gen parameters
upper = 10
rpop = initialPop(20,lower,upper,8) #Initializes predator and prey populations
ypop = initialPop(20,lower,upper,8)
#Set up log to collect data
log = open("6BestCoEvolveLog.txt",'a')
log.write('NewTest\n')
for i in range(5): #Runs this number of generations
#Calculates the population scores
fitFunc(rpop,ypop)
#Log relevant data
print 'Generation '+str(i)
br,ar = bestAverageScore(rpop,'min')
by,ay = bestAverageScore(ypop)
aSr = averageScore(rpop)
aSy = averageScore(ypop)