机器学习代码笔记-朴素贝叶斯

主题：朴素贝叶斯
类别：个人机器学习笔记（数学推导见上传的手写PDF）
书籍参考：《机器学习实战》、《统计学习》、《机器学习》

import numpy as np
import pandas as pd
import math 

创建数据集：

def createDataXG20():
    data = np.array([['青绿', '蜷缩', '浊响', '清晰', '凹陷', '硬滑']
                    , ['乌黑', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑']
                    , ['乌黑', '蜷缩', '浊响', '清晰', '凹陷', '硬滑']
                    , ['青绿', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑']
                    , ['浅白', '蜷缩', '浊响', '清晰', '凹陷', '硬滑']
                    , ['青绿', '稍蜷', '浊响', '清晰', '稍凹', '软粘']
                    , ['乌黑', '稍蜷', '浊响', '稍糊', '稍凹', '软粘']
                    , ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '硬滑']
                    , ['乌黑', '稍蜷', '沉闷', '稍糊', '稍凹', '硬滑']
                    , ['青绿', '硬挺', '清脆', '清晰', '平坦', '软粘']
                    , ['浅白', '硬挺', '清脆', '模糊', '平坦', '硬滑']
                    , ['浅白', '蜷缩', '浊响', '模糊', '平坦', '软粘']
                    , ['青绿', '稍蜷', '浊响', '稍糊', '凹陷', '硬滑']
                    , ['浅白', '稍蜷', '沉闷', '稍糊', '凹陷', '硬滑']
                    , ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '软粘']
                    , ['浅白', '蜷缩', '浊响', '模糊', '平坦', '硬滑']
                    , ['青绿', '蜷缩', '沉闷', '稍糊', '稍凹', '硬滑']])
    label = np.array(['是', '是', '是', '是', '是', '是', '是', '是', '否', '否', '否', '否', '否', '否', '否', '否', '否'])
    feature = np.array(['色泽', '根蒂', '敲声', '纹理', '脐部', '触感'])
    return data,label,feature
    

testdata = ['青绿','蜷缩','浊响','清晰','凹陷','硬滑']
data,label,feature = createDataXG20() 
len_feature = len(feature); len_data = len(label)

# 离散数据NB函数定义
def discreteFunction(data,label,features,testdata):
    classification = np.unique(label).tolist()
    Plist = list(0 for i in range(len(classification)))   #指定生成一个长度为len(classification)的列表，节省空间
    for i in classification:
        Pclassification = len(label[label==i])/len(label)
        multi = 1
        temp_data = data[label==i]
        for j in testdata:
            c = len(temp_data[temp_data==j])/len(temp_data) # 在label为是（否）的条件下，某个特征满足测试数据集的概率
            multi *= c
        multi *= Pclassification
        ind = classification.index(i)
        Plist[ind] = multi      
    return Plist,classification

discreteFunction(data,label,feature,testdata)

([0.0008607009333225744, 0.03392836626838235], [‘否’, ‘是’])
可以看到是好瓜的概率远远超出坏瓜的概率，所以预测为好瓜。

def createDataXG():
    data = np.array([['青绿', '蜷缩', '浊响', '清晰', '凹陷', '硬滑',0.697,0.460],
                     ['乌黑', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑',0.774,0.376],
                     ['乌黑', '蜷缩', '浊响', '清晰', '凹陷', '硬滑',0.634,0.264],
                     ['青绿', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑',0.608,0.318],
                     ['浅白', '蜷缩', '浊响', '清晰', '凹陷', '硬滑',0.556,0.215],
                     ['青绿', '稍蜷', '浊响', '清晰', '稍凹', '软粘',0.403,0.237],
                     ['乌黑', '稍蜷', '浊响', '稍糊', '稍凹', '软粘',0.481,0.149],
                     ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '硬滑',0.437,0.211],
                     ['乌黑', '稍蜷', '沉闷', '稍糊', '稍凹', '硬滑',0.666,0.091],
                     ['青绿', '硬挺', '清脆', '清晰', '平坦', '软粘',0.243,0.267],
                     ['浅白', '硬挺', '清脆', '模糊', '平坦', '硬滑',0.245,0.057],
                     ['浅白', '蜷缩', '浊响', '模糊', '平坦', '软粘',0.343,0.099],
                     ['青绿', '稍蜷', '浊响', '稍糊', '凹陷', '硬滑',0.639,0.161],
                     ['浅白', '稍蜷', '沉闷', '稍糊', '凹陷', '硬滑',0.657,0.198],
                     ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '软粘',0.360,0.370],
                     ['浅白', '蜷缩', '浊响', '模糊', '平坦', '硬滑',0.593,0.042],
                     ['青绿', '蜷缩', '沉闷', '稍糊', '稍凹', '硬滑',0.719,0.103]])
    label = np.array(['好瓜','好瓜','好瓜','好瓜','好瓜','好瓜','好瓜','好瓜','坏瓜','坏瓜','坏瓜','坏瓜','坏瓜','坏瓜','坏瓜','坏瓜','坏瓜'])
    feature = np.array(['色泽', '根蒂', '敲声', '纹理', '脐部', '触感','密度', '含糖量'])
    return data,label,feature

testdata = ['青绿','蜷缩','浊响','清晰','凹陷','硬滑',0.697,0.460]
data,label,feature = createDataXG() 
len_feature = len(feature); len_data = len(label)

def NFunction(m,x,miu,sigma):   # 连续数据的概率计算用N(\miu,\sigma^{2})计算
    return (1/math.sqrt(2)/math.sqrt(math.pi)/sigma) * math.exp(-(miu-x)**2/2/(sigma**2))    

def continuousFunction(data,label,features,testdata):
    classification = np.unique(label).tolist()
    Plist = list(0 for i in range(len(classification)))   #指定生成一个长度为len(classification)的列表，节省空间
    for i in classification:
        Pclassification = len(label[label==i])/len(label)
        multi = 1
        temp_data = data[label==i]
        for j in testdata:
            if type(j) == str:
                c = len(temp_data[temp_data==j])/len(temp_data) # 在label为是（否）的条件下，某个特征满足测试数据集的概率
                print(c)
                multi *= c
            else:
                jindex = testdata.index(j)
                jdata = np.array([float(k) for k in temp_data[:,jindex]])
                m = len(jdata)
                miu = np.mean(jdata)
                sum = 0
                sigma = np.std(jdata)
                Np = NFunction(m,j,miu,sigma)
                print(Np)
                multi *= Np          
        multi *= Pclassification
        ind = classification.index(i)
        Plist[ind] = multi      
    return Plist,classification
    

continuousFunction(data,label,feature,testdata)

([4.365876684002464e-05, 0.044552310283477066], [‘坏瓜’, ‘好瓜’])
好瓜！