def main():
import input
logging.basicConfig(level=logging.INFO, stream=sys.stdout)
np.set_printoptions(precision=3, edgeitems=3, threshold=20)
random.seed(5108) # used by the GA
randSample = random.Random(input.SAMPLE_SEED) # used for data set sampling
inp = input.Input("train3-std.tsv", randSample)
print "Train set:",
inp.trainSet.show()
print "Test set:",
inp.testSet.show()
n = inp.trainSet.size * 20/100
a = ANN()
a.prepare(inp.trainSet, POPSIZE)
tester = SampleTester()
tester.prepare(inp.testSet, randSample)
tester.showSampleSets()
params = []
generatePop(params)
mutateValue = 6.0
for genIndex in range(5000):
print "Generation", genIndex, "starting."
logFP("Population", params)
outputValues = a.evaluate(params, returnOutputs=True)
logFP("Outputs", outputValues)
thresholds = a.nlargest(n)
logFP("Thresholds", thresholds)
lifts = a.lift(n)
logFP("Lifts", lifts)
taggedParams = sorted(zip(lifts, params, range(len(params))),
key=lambda (l, p, i): l,
reverse=True)
sortedParams = [p for l, p, i in taggedParams]
logFP("Sorted pop", sortedParams)
testLift, _ = tester.test(sortedParams[0])
genplot.addGeneration(lifts, testLift, genIndex)
params = generateGeneration(sortedParams, mutateValue)
if genIndex%500 == 499:
mutateValue -= 0.5
args = sys.argv[1:]
if len(args) == 1:
open(args[0], "w").write(repr(sortedParams[0]))
genplot.plot()
#!/usr/bin/python
import genops
import genplot
def fitnessTest(generation):
fitList = []
for i in generation:
fitList.append(i.ih[3][2] - i.c[1][15])
zippedGen = zip(fitList, generation)
zippedGen.sort()
zippedGen.reverse()
return zippedGen
currGen = genops.generatePop(500)
currFit = []
zippedGen = fitnessTest(currGen)
currFit, currGen = zip(*zippedGen)
genplot.addGeneration(currFit, 0)
for i in range(1,100):
print "Generation", i
nextGen = genops.generateGeneration(currGen)
zippedGen = fitnessTest(nextGen)
currFit, currGen = zip(*zippedGen)
genplot.addGeneration(currFit, i)
genplot.plot()
