文章目录
1.课本习题-符号太多了2.视频作业1.课本习题-符号太多了
2.视频作业
与课本P63-64页差不多
#!usr/bin/env python# -*- coding:utf-8 _*-"""@author: liujie@software: PyCharm@file: naives 自编程实现.py@time: /10/22 10:03"""import numpy as npimport pandas as pd# 定义朴素贝叶斯类class NaiveBayes():# 所有参数初始化def __init__(self,lambda_):self.lambda_ = lambda_ # 贝叶斯系数，取0时即为极大似然估计self.y_types_count = None# y的数量self.y_types_proba = None# y的概率self.x_types_prob = dict()# (xi 的编号,xi的取值，y的类型)条件概率#def fit(self,x_train,y_train):# y的所有取值类型[-1,1]self.y_types = np.unique(y_train)# 转化为DataFrame数据格式,方便后续计算x = pd.DataFrame(x_train)y = pd.DataFrame(y_train)# y的数量统计# 利用value_counts()对y进行统计self.y_types_count = y[0].value_counts()# y的概率的计算self.y_types_proba = (self.y_types_count + self.lambda_) / (y.shape[0] + len(self.y_types) * self.lambda_)# 条件概率的计算# 遍历xi- 特征for idx in x.columns:# 遍历每一个y的类型for j in self.y_types:# 选择y==j为真的数据点的第idx个特征的值，并进行统计p_x_y = x[(y == j).values][idx].value_counts()print(p_x_y)for i in p_x_y.index:print(i)# 字典-xi 的编号,xi的取值，y的类型self.x_types_prob[(idx,i,j)] = (p_x_y[i] + self.lambda_) / (self.y_types_count[j] + p_x_y.shape[0] * self.lambda_)def predict(self,x_new):res = []# 遍历y的可能取值for y in self.y_types:p_y = self.y_types_proba[y]p_xy =1for idx,x in enumerate(x_new):p_xy *= self.x_types_prob[idx,x,y]res.append(p_y*p_xy)for i in range(len(self.y_types)):print('[{}]对应的概率 : {:.2%}'.format(self.y_types[i],res[i]))# 返回最大后验概率对应的y值return self.y_types[np.argmax(res)]def main():X_train = np.array([[1, "S"],[1, "M"],[1, "M"],[1, "S"],[1, "S"],[2, "S"],[2, "M"],[2, "M"],[2, "L"],[2, "L"],[3, "L"],[3, "M"],[3, "M"],[3, "L"],[3, "L"]])y_train = np.array([-1, -1, 1, 1, -1, -1, -1, 1, 1, 1, 1, 1, 1, 1, -1])clf = NaiveBayes(lambda_=0.2)clf.fit(X_train, y_train)X_new = np.array([2, "S"])y_predict = clf.predict(X_new)print("{}被分类为:{}".format(X_new, y_predict))if __name__ == '__main__':main()
[-1]对应的概率 : 6.51%[1]对应的概率 : 2.49%['2' 'S']被分类为:-1
import numpy as npfrom sklearn.naive_bayes import GaussianNB,BernoulliNB,MultinomialNBfrom sklearn import preprocessing #预处理def main():X_train=np.array([[1,"S"],[1,"M"],[1,"M"],[1,"S"],[1,"S"],[2,"S"],[2,"M"],[2,"M"],[2,"L"],[2,"L"],[3,"L"],[3,"M"],[3,"M"],[3,"L"],[3,"L"]])y_train=np.array([-1,-1,1,1,-1,-1,-1,1,1,1,1,1,1,1,-1])# 数据预处理enc = preprocessing.OneHotEncoder(categories='auto')enc.fit(X_train)# toarray()变成数组的形式X_train = enc.transform(X_train).toarray()print(X_train)clf=MultinomialNB(alpha=0.0000001)clf.fit(X_train,y_train)X_new=np.array([[2,"S"]])X_new=enc.transform(X_new).toarray()y_predict=clf.predict(X_new)print("{}被分类为:{}".format(X_new,y_predict))print(clf.predict_proba(X_new))if __name__=="__main__":main()
