零基础深度学习：感知器实现(map lambda在py3与py2使用的不同)

from functools import reduce
class Perceptron:
    def __init__(self, input_num, activator):
        '''
        initialize the perceptron
        :param input_num: the number of parameters
        :param activator: sctivator function
        '''
        self.activator = activator
        self.weights = [0.0 for _ in range(input_num)]
        self.bias = 0.0

    def __str__(self):
        return 'weight\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
        把input_vec[x1,x2,x3...]和weights[w1,w2,w3...]打包在一起
        变成[(x1,w1),(x2,w2),(x3,w3)...]
        利用map函数计算[x1*w1,x2*w2,...]
        最后利用reduce求和
        :param input_vec: 输入向量
        :return:
        '''
        #python3
        return self.activator(reduce(lambda a, b: a + b,
                              list(map(lambda x: x[0] * x[1], zip(input_vec, self.weights)))) + self.bias)
        #or
        #return self.activator(reduce(lambda a, b: a + b, [x*w for x, w in zip(input_vec, self.weights)]) + self.bias)


        ##python2
        #samples = zip(input_vec, self.weights)
        #return self.activator(
        #    reduce(lambda a, b: a + b,
        #           map(lambda x, w: x * w, samples)
        #           , 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labels；以及训练轮数、学习率
        :param input_vecs:
        :param labels:
        :param interation:
        :param rate:
        :return:
        '''
        for i in range(iteration):
            self._one_iteration(input_vecs, labels, rate)

    def _one_iteration(self, input_vecs, labels, rate):
        for (input_vec, label) in zip(input_vecs, labels):
            output = self.predict(input_vec)
            self._update_weights(input_vec, output, label, rate)

    def _update_weights(self, input_vec, output, label, rate):
        '''
        按照感知器规则更新权重
        :param input_vec:
        :param output:
        :param label:
        :param rate:
        :return:
        '''
        delta = label - output
        #self.weights = map(lambda x, w: w+rate*delta*x, zip(input_vec,self.weights))##python2
        self.weights = list(map(
            lambda x: x[1] + rate * delta * x[0],
            zip(input_vec, self.weights)))

        self.bias+=rate*delta

 

 

#####用感知器实现and函数
from perceptron import Perceptron
def f(x):
    '''
    定义激活函数
    :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:
    '''
    input_vecs = [[1, 1], [0, 0], [1, 0], [0, 1]]
    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:
    '''
    # 创建感知器，输入参数个数为2，激活函数为f
    p = Perceptron(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)
    return p


if __name__ == '__main__':
    and_perceptron = train_and_perceptron()
    print(and_perceptron)
    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]))

 

py2与py3中lambda的写法不同 ，3中要用x[0],x[1]....

py2的map函数直接返回列表  ，而python3返回map对象