import math
classNaiveBayes:
def__init__(self):
self.model = None# 数学期望 @staticmethoddefmean(X):
"""计算均值
Param: X : list or np.ndarray
Return:
avg : float
"""
avg = 0.0# ========= show me your code ==================
avg = sum(X) / float(len(X))
# ========= show me your code ==================return avg
# 标准差(方差)defstdev(self, X):
"""计算标准差
Param: X : list or np.ndarray
Return:
res : float
"""
res = 0.0# ========= show me your code ==================
avg = self.mean(X)
res = math.sqrt(sum([pow(x - avg, 2) for x in X]) / float(len(X)))
# ========= show me your code ==================return res
# 概率密度函数defgaussian_probability(self, x, mean, stdev):
"""根据均值和标注差计算x符号该高斯分布的概率
Parameters:
----------
x : 输入
mean : 均值
stdev : 标准差
Return:
res : float, x符合的概率值
"""
res = 0.0# ========= show me your code ==================
exponent = math.exp(-(math.pow(x - mean, 2) /
(2 * math.pow(stdev, 2))))
res = (1 / (math.sqrt(2 * math.pi) * stdev)) * exponent
# ========= show me your code ==================return res
# 处理X_traindefsummarize(self, train_data):
"""计算每个类目下对应数据的均值和标准差
Param: train_data : list
Return : [mean, stdev]
"""
summaries = [0.0, 0.0]
# ========= show me your code ==================
summaries = [(self.mean(i), self.stdev(i)) for i inzip(*train_data)]
# ========= show me your code ==================return summaries
# 分类别求出数学期望和标准差deffit(self, X, y):
labels = list(set(y))
data = {label: [] for label in labels}
for f, label inzip(X, y):
data[label].append(f)
self.model = {
label: self.summarize(value) for label, value in data.items()
}
return'gaussianNB train done!'# 计算概率defcalculate_probabilities(self, input_data):
"""计算数据在各个高斯分布下的概率
Paramter:
input_data : 输入数据
Return:
probabilities : {label : p}
"""# 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 = {}
# ========= show me your code ==================for label, value in self.model.items():
probabilities[label] = 1for i inrange(len(value)):
mean, stdev = value[i]
probabilities[label] *= self.gaussian_probability(
input_data[i], mean, stdev)
# ========= show me your code ==================return probabilities
# 类别defpredict(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
# 计算得分defscore(self, X_test, y_test):
right = 0for X, y inzip(X_test, y_test):
label = self.predict(X)
if label == y:
right += 1return right / float(len(X_test))
from sklearn.naive_bayes import GaussianNB
from sklearn.datasets import load_iris
import pandas as pd
from sklearn.model_selection import train_test_split
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2)
clf = GaussianNB().fit(X_train, y_train)
print ("Classifier Score:", clf.score(X_test, y_test))
model = NaiveBayes()
model.fit(X_train, y_train)
print(model.predict([4.4, 3.2, 1.3, 0.2]))
model.score(X_test, y_test)
【推荐】编程新体验,更懂你的AI,立即体验豆包MarsCode编程助手
【推荐】凌霞软件回馈社区,博客园 & 1Panel & Halo 联合会员上线
【推荐】抖音旗下AI助手豆包,你的智能百科全书,全免费不限次数
【推荐】博客园社区专享云产品让利特惠,阿里云新客6.5折上折
【推荐】轻量又高性能的 SSH 工具 IShell:AI 加持,快人一步
· 用 C# 插值字符串处理器写一个 sscanf
· Java 中堆内存和栈内存上的数据分布和特点
· 开发中对象命名的一点思考
· .NET Core内存结构体系(Windows环境)底层原理浅谈
· C# 深度学习:对抗生成网络(GAN)训练头像生成模型
· 为什么说在企业级应用开发中,后端往往是效率杀手?
· 本地部署DeepSeek后,没有好看的交互界面怎么行!
· 趁着过年的时候手搓了一个低代码框架
· 用 C# 插值字符串处理器写一个 sscanf
· 推荐一个DeepSeek 大模型的免费 API 项目!兼容OpenAI接口!