Python3.x实现感知器

版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/github_39611196/article/details/83116958

在进行代码实现时,下面的代码无法再python3.x中运行:

reduce(lambda a, b: a + b,
                   map(lambda (x, w): x * w,  
                       zip(input_vec, self.weights))
                , 0.0) + self.bias

将上述代码修改为:

reduce(lambda a, b: a + b,
                   [x * w for x, w in zip(input_vec, self.weights)],
                   0.0) + self.bias

完整代码:

from functools import reduce
class Perseptron(object):
    def __init__(self, input_num, activator):
        '''
        初始化感知器,设置输输入参数的个数以及激活函数
        :param input_num:
        :param activator:
        '''
        self.activator = activator
        # 权重向量初始化为0
        self.weights = [0.0 for _ in range(input_num)]
        # 初始化偏置项为0
        self.bias = 0

    def __str__(self):
        '''
        打印学习到的权重、偏置项
        :return:
        '''
        return 'weights\t:%s\nbias\t:%f\n' % (self.weights, self.bias)

    def predict(self, input_vec):
        '''
        输入向量,输出感知器的计算结果
        :param input_vec:
        :return:
        '''
        # 把input_vec[x1, x2,x3...]和weights[w1, w2, w3..]打包在一起
        # 变成[(x1, w1), (x2, w2), (x3, w3),..]
        # 然后利用map函数计算[x1*w1, x2*w2, x3* w3]
        # 最后利用reduce求和
        return self.activator(
            reduce(lambda a, b: a + b,
                   [x * w for x, w in zip(input_vec, self.weights)],
                   0.0) + self.bias)

    def train(self, input_vecs, labels, iteration, rate):
        '''
        输入训练数据:一组向量、与每个向量对应的label,以及训练轮数、学习率
        :param input_vec:
        :param labels:
        :param iteration:
        :param rate:
        :return:
        '''
        for i in range(iteration):
            self._one_iteration(input_vecs, labels, rate)

    def _one_iteration(self, input_vecs, labels, rate):
        '''
        一次迭代, 把所有的训练数据过一遍
        :param input_vecs:
        :param labels:
        :param rate:
        :return:
        '''
        # 把输入和输出打包在一起,成为样本的列表[(input_vec, label),..]
        # 每个训练样本是(input_vec, label)
        samples = zip(input_vecs, labels)
        # 对每个样本,按照感知器规则更新权重
        for (input_vec, label) in samples:
            # 计算服务器在当前权重下的输出
            output = self.predict(input_vec)
            # 更新权重
            self._update_weights(input_vec, output, label, rate)

    def _update_weights(self, input_vec, output, label, rate):
        '''
        按照感知器啊规则更新权重
        :param input_vec:
        :param output:
        :param label:
        :param rate:
        :return:
        '''
        # 把input_vec[x1,x2,x3,...]和weights[w1,w2,w3,...]打包在一起
        # 变成[(x1,w1),(x2,w2),(x3,w3),...]
        # 然后利用感知器规则更新权重
        delta = label - output
        self.weights = [ w + rate * delta * x
                         for x, w in zip(input_vec, self.weights)]
        # 更新权重
        self.bias += rate * delta


def f(x):
    '''
    定义激活函数f
    :param x:
    :return:
    '''
    return 1 if x > 0 else 0


def get_training_dataset():
    '''
    基于and真值表构建训练数据
    :return:
    '''
    # 构建训练数据
    input_vecs = [[1, 1], [0, 0], [1, 0], [0, 1]]
    # 期望的输出列表,注意要与输入一一对应
    # [1,1] -> 1, [0,0] -> 0, [1,0] -> 0, [0,1] -> 0
    labels = [1, 0, 0, 0]
    return input_vecs, labels

def train_and_perceptron():
    '''
    使用and真值表训练感知器
    :return:
    '''
    # 构建感知器,输入参数个数为2(因为and是二元函数),激活函数为f
    p = Perseptron(2, f)
    # 训练,迭代10轮,学习速率为0.1
    input_vecs, labels = get_training_dataset()
    p.train(input_vecs, labels, 10, 0.1)
    # 返回训练好的感知器
    return p

if __name__ == '__main__':
    # 训练and感知器
    and_perceptron = train_and_perceptron()
    # 打印训练获得的权值
    print(and_perceptron)
    # 测试
    print(
    '1 and 1 = %d' % and_perceptron.predict([1, 1]))
    print(
    '0 and 0 = %d' % and_perceptron.predict([0, 0]))
    print(
    '1 and 0 = %d' % and_perceptron.predict([1, 0]))
    print(
    '0 and 1 = %d' % and_perceptron.predict([0, 1]))

运行结果:

weights	:[0.1, 0.2]
bias	:-0.200000

1 and 1 = 1
0 and 0 = 0
1 and 0 = 0
0 and 1 = 0

猜你喜欢

转载自blog.csdn.net/github_39611196/article/details/83116958