樸素bayes實現

樸素貝葉斯理解

• 參考：https://www.cnblogs.com/marc01in/p/4775440.html

實驗流程

代碼實現

main.py

#coding:utf-8
#樸素貝葉斯算法   貝葉斯估計， λ=1  K=2， S=3； λ=1 拉普拉斯平滑
import pandas as pd
import numpy as np

class NavieBayesB(object):
    def __init__(self):
        self.A = 1    # 即λ=1
        self.K = 2
        self.S = 3

    def getTrainSet(self):
        trainSet = pd.read_csv('naivebayes_data.csv')
        trainSetNP = np.array(trainSet)     #由dataframe類型轉換爲數組類型
        trainData = trainSetNP[:,0:trainSetNP.shape[1]-1]     #訓練數據x1,x2
        labels = trainSetNP[:,trainSetNP.shape[1]-1]          #訓練數據所對應的所屬類型Y
        return trainData, labels

    def classify(self, trainData, labels, features):
        labels = list(labels)    #轉換爲list類型
        #求先驗概率
        P_y = {}
        for label in labels:
            P_y[label] = (labels.count(label) + self.A) / float(len(labels) + self.K*self.A)

        #求條件概率
        P = {}
        for y in P_y.keys():
            y_index = [i for i, label in enumerate(labels) if label == y]   # y在labels中的所有下標
            y_count = labels.count(y)     # y在labels中出現的次數
            for j in range(len(features)):
                pkey = str(features[j]) + '|' + str(y)
                x_index = [i for i, x in enumerate(trainData[:,j]) if x == features[j]]   # x在trainData[:,j]中的所有下標
                xy_count = len(set(x_index) & set(y_index))   #x y同時出現的次數
                P[pkey] = (xy_count + self.A) / float(y_count + self.S*self.A)   #條件概率

        #features所屬類
        F = {}
        for y in P_y.keys():
            F[y] = P_y[y]
            for x in features:
                F[y] = F[y] * P[str(x)+'|'+str(y)]

        features_y = max(F, key=F.get)   #概率最大值對應的類別
        return features_y


if __name__ == '__main__':
    nb = NavieBayesB()
    # 訓練數據
    trainData, labels = nb.getTrainSet()
    # x1,x2
    features = [2,'S']
    # 該特徵應屬於哪一類
    result = nb.classify(trainData, labels, features)
    print (features,'屬於',result)

naivebayes_data.csv

x1,x2,Y
1,S,-1
1,M,-1
1,M,1
1,S,1
1,S,-1
2,S,-1
2,M,-1
2,M,1
2,L,1
2,L,1
3,L,1
3,M,1
3,M,1
3,L,1
3,L,-1

測試結果

[2, 'S'] 屬於 -1