GA-SVM算法python实现

最近在学习如何用遗传算法对SVM的超参数进行优化，参考了一些其他博主的文章，实现了这一方法。

遗传算法程序

首先定义SVM和MSE的函数：

def msefunc(predictval, realval):
    squaredError = []
    # absError = []
    for i in range(len(predictval)):
        val = predictval[i] - realval[i]
        squaredError.append(val * val)  # 预测值与真实值之差的平方

    print("Square Error: ", squaredError)
    print("MSE = ", sum(squaredError) / len(squaredError))  # 均方误差MSE
    return sum(squaredError) / len(squaredError)


def SVMResult(vardim, x, bound):
    X_train = [[0, 0], [2, 2], [1, 4], [3, 7], [3, 6]]
    y_train = [0.5, 2.5, 3.0, 4.0, 5]
    X_valid = [[1, 1], [3, 5]]
    y_valid = [3, 4]
    c = x[0]
    e = x[1]
    g = x[2]
    clf = svm.SVR(C=c, epsilon=e, gamma=g, kernel='rbf')
    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_valid)
    print("y_pred is", y_pred , "y_true is" , y_valid)
    # 返回svm的mse作为适应度值
    return msefunc(y_pred, y_valid)

遗传算法种群个体计算：

class GAIndividual:
    '''
    individual of genetic algorithm
    创建pop中的单个个体
    '''
    def __init__(self, vardim, bound):
        '''
        vardim: dimension of variables
        bound: boundaries of variables
        '''
        self.vardim = vardim
        self.bound = bound
        self.fitness = 0.

    def generate(self):
        '''
        generate a random chromsome for genetic algorithm
        '''
        len = self.vardim
        rnd = np.random.random(size=len)
        self.chrom = np.zeros(len)
        for i in range(0, len):
            self.chrom[i] = self.bound[0, i] + \
                (self.bound[1, i] - self.bound[0, i]) * rnd[i]

    def calculateFitness(self):
        '''
        calculate the fitness of the chromsome
        '''
        self.fitness = SVMResult(self.vardim, self.chrom, self.bound)

建立种群衍变的类，其中种群选择、交叉、变异的方法可以根据需要重新定义。

class GeneticAlgorithm:
    '''
    The class for genetic algorithm
    '''
    def __init__(self, sizepop, vardim, bound, MAXGEN, params):
        '''
        sizepop: population sizepop
        vardim: dimension of variables
        bound: boundaries of variables
        MAXGEN: termination condition
        param: algorithm required parameters, it is a list which is consisting 
               of crossover rate, mutation rate, alpha
        '''
        self.sizepop = sizepop
        self.MAXGEN = MAXGEN
        self.vardim = vardim
        self.bound = bound
        self.population = []
        self.fitness = np.zeros((self.sizepop, 1))
        self.trace = np.zeros((self.MAXGEN, 2))
        self.params = params

    def initialize(self):
        '''
        initialize the population
        '''
        for i in range(0, self.sizepop):
            ind = GAIndividual(self.vardim, self.bound)
            ind.generate()
            self.population.append(ind)

    def evaluate(self):
        '''
        evaluation of the population fitnesses
        '''
        for i in range(0, self.sizepop):
            self.population[i].calculateFitness()
            self.fitness[i] = self.population[i].fitness

    def solve(self):
        '''
        evolution process of genetic algorithm
        '''
        self.t = 0 # 迭代次数
        self.initialize() # 初始化种群
        self.evaluate() # 计算适应度
        best = np.max(self.fitness) #选出适应度最大的个体
        bestIndex = np.argmax(self.fitness) # 最大适应度的索引
        self.best = copy.deepcopy(self.population[bestIndex]) 
        self.avefitness = np.mean(self.fitness) # 平均适应度
        self.trace[self.t, 0] = (1 - self.best.fitness) / self.best.fitness
        self.trace[self.t, 1] = (1 - self.avefitness) / self.avefitness
        print(
            "Generation %d: optimal function value is: %f; average function value is %f"
            % (self.t, self.trace[self.t, 0], self.trace[self.t, 1]))
        while (self.t < self.MAXGEN - 1):
            self.t += 1
            self.selectionOperation() # 选择
            self.crossoverOperation() # 交叉
            self.mutationOperation()  # 变异
            self.evaluate()           # 重新计算新种群适应度
            best = np.max(self.fitness)
            bestIndex = np.argmax(self.fitness)
            if best > self.best.fitness:
                self.best = copy.deepcopy(self.population[bestIndex])
            self.avefitness = np.mean(self.fitness)
            # 种群中表现最好的个体的适应度变化
            self.trace[self.t, 0] = (1 - self.best.fitness) / self.best.fitness 
            # 种群平均适应度变化
            self.trace[self.t, 1] = (1 - self.avefitness) / self.avefitness
            print(
                "Generation %d: optimal function value is: %f; average function value is %f"
                % (self.t, self.trace[self.t, 0], self.trace[self.t, 1]))
        print("Optimal function value is: %f; " % self.trace[self.t, 0])
        print("Optimal solution is:",self.best.chrom)
        self.printResult()

    def selectionOperation(self):
        '''
        selection operation for Genetic Algorithm
        '''
        newpop = []
        totalFitness = np.sum(self.fitness)
        accuFitness = np.zeros((self.sizepop, 1))

        # 适应度的累进占比
        sum1 = 0.
        for i in range(0, self.sizepop):
            accuFitness[i] = sum1 + self.fitness[i] / totalFitness
            sum1 = accuFitness[i]

        # 随机选出新种群的索引
        for i in range(0, self.sizepop):
            r = random.random()
            idx = 0
            for j in range(0, self.sizepop - 1):
                if j == 0 and r < accuFitness[j]:
                    idx = 0
                    break
                elif r >= accuFitness[j] and r < accuFitness[j + 1]:
                    idx = j + 1
                    break
            newpop.append(self.population[idx])
        self.population = newpop

    def crossoverOperation(self):
        '''
        crossover operation for genetic algorithm
        '''
        newpop = []
        # 选出两个个体进行交换
        for i