【统计学习笔记】朴素贝叶斯法

在连续分布情形下，需要假设先验分布（如高斯分布），由测试数据得到具体的先验分布。这样根据先验分布计算出的后验概率为概率密度。

class NaiveBayes:
    def __init__(self):
        self.model = None

    # 数学期望
    @staticmethod
    def mean(X):
        return sum(X) / float(len(X))

    # 标准差（方差）
    def stdev(self, X):
        avg = self.mean(X)
        return math.sqrt(sum([pow(x-avg, 2) for x in X]) / float(len(X)))

    # 概率密度函数
    def gaussian_probability(self, x, mean, stdev):
        exponent = math.exp(-(math.pow(x-mean,2)/(2*math.pow(stdev,2))))
        return (1 / (math.sqrt(2*math.pi) * stdev)) * exponent

    # 处理X_train
    def summarize(self, train_data):
        summaries = [(self.mean(i), self.stdev(i)) for i in zip(*train_data)]
        return summaries

    # 分类别求出数学期望和标准差
    def fit(self, X, y):
        labels = list(set(y))
        data = {
    
    label:[] for label in labels}
        for f, label in zip(X, y):
            data[label].append(f)
        self.model = {
    
    label: self.summarize(value) for label, value in data.items()}
        print(self.model)
        return 'gaussianNB train done!'

    # 计算概率
    def calculate_probabilities(self, input_data):
        # summaries:{0.0: [(5.0, 0.37),(3.42, 0.40)], 1.0: [(5.8, 0.449),(2.7, 0.27)]}
        # input_data:[1.1, 2.2]
        probabilities = {
    
    }
        for label, value in self.model.items():
            probabilities[label] = 1
            for i in range(len(value)):
                mean, stdev = value[i]
                probabilities[label] *= self.gaussian_probability(input_data[i], mean, stdev)
        return probabilities

    # 类别
    def predict(self, X_test):
        # {0.0: 2.9680340789325763e-27, 1.0: 3.5749783019849535e-26}
        label = sorted(self.calculate_probabilities(X_test).items(), key=lambda x: x[-1])[-1][0]
        return label

    def score(self, X_test, y_test):
        right = 0
        for X, y in zip(X_test, y_test):
            label = self.predict(X)
            if label == y:
                right += 1

        return right / float(len(X_test))

先验分布