基本理論

鑒于網(wǎng)上有很多好的文章理論部分我就不寫了仙畦，放出下面的參考态坦。可以先看理論埂淮。再看代碼了解細(xì)節(jié)姑隅。
詳細(xì)的理論可參考博文;
具體的sklearn使用方式和調(diào)參可參考博文

思維導(dǎo)圖

Goodnotes

python 實(shí)現(xiàn)

import numpy as np

class Bayes(object):
    def __init__(self, model = "multinomial",alpha = 1, log = False):
        """
        :param model: "multinomial" :  Naive Bayes classifier for multinomial models
                      "gaussian" :Naive Bayes classifier for gaussian model
                      "bernoulli" : Naive Bayes classifier for bernoulli model
        :param alpha: smoothing
                      if alpha = 0 is no smoothing,
                      if 0 < alpha < 1 is Lidstone smoothing
                      if alpha = 1 is Laplace smoothing
        :param log: is True
                    x1 * x2 * x3  to log(x1 * x2 * x3)
        """
        self.model = model
        self.alpha = alpha
        self.log = log

    def _probabilities_for_feature(self, feature):
        if self.model == "multinomial" or "bernoulli":
            feature_class_list = np.unique(feature)
            total_mum = len(feature)
            feature_value_prob = {}
            for value in feature_class_list:
                feature_value_prob[value] = (np.sum(np.equal(feature, value)) + self.alpha) / \
                                            (total_mum + len(feature_class_list) * self.alpha)

            feature_value_prob['error'] = self.alpha / (len(feature_class_list) * self.alpha)
            return feature_value_prob


        if self.model == "gaussian":
            _meam = np.mean(feature)
            _std = np.std(feature)
            return (_meam, _std)

    def fit(self, X, y, threshold = None):
        X_ = X.copy()
        self.feature_len = X_.shape[1]
        self.threshold = threshold
        if self.model == "bernoulli":
            X_ = self._bernoulli_transform(X_)
        self.classes_list = np.unique(y)
        total_mum = len(y)
        self.classes_prior = {}
        # P(y = Ck )
        for value in self.classes_list:
            self.classes_prior[value] = (np.sum(np.equal(y, value)) + self.alpha) / (total_mum + len(self.classes_list) * self.alpha)

        # P( xj | y= Ck )
        self.conditional_prob = {}
        for c in self.classes_list:
            self.conditional_prob[c] = {}

            # Traversal features
            for i in range(len(X_[0])):
                feature_value = self._probabilities_for_feature(X_[np.equal(y, c)][:, i])
                self.conditional_prob[c][i] = feature_value

        return self

    def _get_xj_prob(self, values_probs,target_value):
        if self.model == "multinomial" or "bernoulli":
            if target_value not in values_probs.keys():
                return values_probs['error']
            else:
                return values_probs[target_value]
        elif self.model == "gaussian":
            target_prob = (1 / np.sqrt(2 * np.pi * np.square(values_probs[1]))) * \
                          np.exp(-np.square(target_value - values_probs[0]) / (2*np.square(values_probs[1])))

            return target_prob

    def _bernoulli_transform(self, X):
        assert len(X[0]) == len(self.threshold)
        for index in range(len(X[0])):
            X[:, index] = np.where(X[:, index] >= self.threshold[index], 1, 0)
        return X


    def predict(self, X):
        X_ = X.copy()
        if self.model == "bernoulli":
            X_ = self._bernoulli_transform(X_)
        assert len(X_.shape) == self.feature_len
        result = np.zeros([len(X_)])
        for r in range(len(X_)):
            result_list = []
            for index in range(len(self.classes_list)):
                c_prior = self.classes_prior[self.classes_list[index]]
                if self.log == False:
                    current_conditional_prob = 1.0
                    for i in range(len(X_[0])):
                        current_conditional_prob *= self._get_xj_prob(self.conditional_prob[self.classes_list[index]][i], X_[r,i])
                    current_conditional_prob *= c_prior

                    result_list.append(current_conditional_prob)


                else:
                    current_conditional_prob = 0
                    for i in range(len(X[0])):
                        current_conditional_prob += np.log(self._get_xj_prob(self.conditional_prob[self.classes_list[index]][i], X[r,i]))
                    current_conditional_prob += np.log(c_prior)
                    result_list.append(current_conditional_prob)

            result[r] = self.classes_list[np.argmax(np.array(result_list))]

        return result