实验三 朴素贝叶斯算法及应用

实验三 朴素贝叶斯算法及应用

博客班级	机器学习18级
作业要求	https://edu.cnblogs.com/campus/ahgc/machinelearning/homework/12085
学号	3180701315

实验目的
理解朴素贝叶斯算法原理，掌握朴素贝叶斯算法框架；
掌握常见的高斯模型，多项式模型和伯努利模型；
能根据不同的数据类型，选择不同的概率模型实现朴素贝叶斯算法；
针对特定应用场景及数据，能应用朴素贝叶斯解决实际问题。

实验内容
实现高斯朴素贝叶斯算法。
熟悉sklearn库中的朴素贝叶斯算法；
针对iris数据集，应用sklearn的朴素贝叶斯算法进行类别预测。
针对iris数据集，利用自编朴素贝叶斯算法进行类别预测。

实验报告要求
对照实验内容，撰写实验过程、算法及测试结果；
代码规范化：命名规则、注释；
分析核心算法的复杂度；
查阅文献，讨论各种朴素贝叶斯算法的应用场景；
讨论朴素贝叶斯算法的优缺点。

实验代码

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from collections import Counter
import math
data
def create_data():
    iris = load_iris()
    df = pd.DataFrame(iris.data, columns=iris.feature_names)
    df['label'] = iris.target
    df.columns = [
        'sepal length', 'sepal width', 'petal length', 'petal width', 'label'
    ]
    data = np.array(df.iloc[:100, :])
    # print(data)
    return data[:, :-1], data[:, -1]
X, y = create_data()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
X_test[0], y_test[0]
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()
        }
        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))
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)
from sklearn.naive_bayes import GaussianNB
clf = GaussianNB()
clf.fit(X_train, y_train)
clf.score(X_test, y_test)
clf.predict([[4.4, 3.2, 1.3, 0.2]])
from sklearn.naive_bayes import BernoulliNB, MultinomialNB # 伯努利模型和多项式模型

运行结果

#GaussianNB 高斯朴素贝叶斯,特征的可能性被假设为高斯
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()}
        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))
model = NaiveBayes()#生成一个算法对象
model.fit(X_train, y_train)#将训练数据代入算法中

#生成scikit-learn结果与上面手写函数的结果对比
from sklearn.naive_bayes import GaussianNB  #导入模型
clf = GaussianNB()
clf.fit(X_train, y_train)#训练数据

clf.score(X_test, y_test)

clf.predict([[4.4, 3.2, 1.3, 0.2]])

运行结果

实验小结
朴素贝叶斯算法逻辑简单,易于实现，分类过程中时空开销小。理论上，朴素贝叶斯模型与其他分类方法相比具有最小的误差率。但是实际上并非总是如此，这是因为朴素贝叶斯模型假设属性之间相互独立，这个假设在实际应用中往往是不成立的，在属性个数比较多或者属性之间相关性较大时，分类效果不好。 而在属性相关性较小时，朴素贝叶斯性能最为良好。