def testIrisReplacement(trainfile, testfile, attrfile):
iris_train = pd.read_csv(trainfile, header=None)
iris_test = pd.read_csv(testfile, header=None)
iris_attr = pd.read_csv(attrfile, header=None)
input, output, input_test, output_test = digitalize(iris_train, iris_test, iris_attr,"iris")
input = input.astype(np.float)
input = np.concatenate((input, output), axis=1)
test_input = np.concatenate((input_test, output_test), axis=1)
replaceRate = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
strategies = ['fitness-proportional', 'tournament', 'rank']
cor_list = []
strategy_list = []
for j in range (len(strategies)):
print ('Strategy: ' + strategies[j])
for i10 in range(1, 10, 1):
i = i10 / 10
print('Replacement rate: ' + str(i))
ga = GA(100, 6, 48, 3, i, 0.1, 1, 1, 30, strategies[j], 'iris')
cor, bestHypo = ga.fit(input)
testAcc = ga.predict(bestHypo, test_input)
print("Accuracy: " + str(testAcc) +"\n" )
cor_list.append(testAcc)
cor_array = np.array(cor_list)
strategy_list.append(cor_array)
cor_list = []
print ('correct rate for fitness-proportional, tournament, rank strategy at vary replacement rate are')
print (strategy_list)
def testTennis(trainFile, testFile, attrFile):
tennis_train = pd.read_csv(trainFile, sep=" ", header=None)
tennis_test = pd.read_csv(testFile, sep=" ", header=None)
tennis_attr = pd.read_csv(attrFile, sep=" ", header=None)
input, output, input_test, output_test = digitalize(tennis_train, tennis_test, tennis_attr,"tennis")
input = np.concatenate((input, output), axis=1)
test_input = np.concatenate((input_test, output_test), axis=1)
# p, numOfRulesPerHypo, numofattr, numofoutput, r, m, fit_threshold, stopGeneration, strategy, dataType):
ga = GA(100, 4, 10, 2, 0.3, 0.1, 1, 1, 30, 'fitness-proportional', 'tennis')
trainAcc, bestHypo = ga.fit(input)
print ('Training data accuracy is: ' + str(trainAcc[0]))
testAcc = ga.predict(bestHypo, test_input)
print ('Test data accuracy is: ' + str(testAcc[0]))
ga.printRules(bestHypo)
def testIris(trainfile, testfile, attrfile):
iris_train = pd.read_csv(trainfile, header=None)
iris_test = pd.read_csv(testfile, header=None)
iris_attr = pd.read_csv(attrfile, header=None)
input, output, input_test, output_test = digitalize(iris_train, iris_test, iris_attr,"iris")
input = input.astype(np.float)
input = np.concatenate((input, output), axis=1)
test_input = np.concatenate((input_test, output_test), axis=1)
# p, numOfRulesPerHypo, numofattr, numofoutput, r, m, numOfChangeBitsPerRule, fit_threshold, stopGeneration, strategy, dataType): tournament fitness-proportional rank
# ga = GA(100, 6, 28, 3, 0.4, 0.2, 1, 0.8, 100, 'rank', 'iris')
# (6*2*4+3)*4 *4
ga = GA(400, 6, 48, 3, 0.3, 0.1, 1, 1, 50, 'tournament', 'iris')
correct, bestHypo = ga.fit(input)
print ('correct rate on traning data' + str(correct))
ga.printRules(bestHypo)
cor = ga.predict(bestHypo, test_input)
def testIrisSelection(trainfile, testfile, attrfile):
iris_train = pd.read_csv(trainfile, header=None)
iris_test = pd.read_csv(testfile, header=None)
iris_attr = pd.read_csv(attrfile, header=None)
input, output, input_test, output_test = digitalize(iris_train, iris_test, iris_attr,"iris")
input = input.astype(np.float)
input = np.concatenate((input, output), axis=1)
test_input = np.concatenate((input_test, output_test), axis=1)
# stopGen = [10, 20, 30, 40, 50, 60, 70, 80, 90, 100]
strategies = ['fitness-proportional', 'tournament', 'rank']
cor_list = []
strategy_list = []
for j in range (len(strategies)):
ga = GA(100, 6, 48, 3, 0.3, 0.1, 1, 1, 50, strategies[j], 'iris')
print ('Strategy: ' + strategies[j])
cor, bestHypo = ga.fit(input, outputGen=True)
for i in range (len(cor)):
cor2 = ga.predict(bestHypo[i], test_input)
cor_list.append(cor2)
cor_array = np.array(cor_list)
strategy_list.append(cor_array)
cor_list = []
print ('correct rate for fitness-proportional, tournament, rank strategy at vary generations are')
print (strategy_list)
def demo_func(x):
x1, x2, x3 = x
return x1 ** 2 + (x2 - 0.05) ** 2 + x3 ** 2
from ga import GA
ga = GA(func=demo_func, lb=[-1, -10, -5], ub=[2, 10, 2], max_iter=500)
best_x, best_y = ga.fit()
import pandas as pd
import matplotlib.pyplot as plt
FitV_history = pd.DataFrame(ga.FitV_history)
fig, ax = plt.subplots(2, 1)
ax[0].plot(FitV_history.index, FitV_history.values, '.', color='red')
plt_max = FitV_history.max(axis=1)
ax[1].plot(plt_max.index, plt_max, label='max')
ax[1].plot(plt_max.index, plt_max.cummax())
plt.show()
