DEV: ADD NaiveBayes CODE

src/python/04.NaiveBayes/bayes.py

@@ -0,0 +1,166 @@
+#!/usr/bin/env python
+# -*- coding:utf-8 -*-
+from numpy import *
+
+
+def loadDataSet():
+    """
+    创建数据集
+    :return: 单词列表postingList, 所属类别classVec
+    """
+    postingList = [['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],
+                   ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],
+                   ['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],
+                   ['stop', 'posting', 'stupid', 'worthless', 'garbage'],
+                   ['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],
+                   ['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']]
+    classVec = [0, 1, 0, 1, 0, 1]  # 1 is abusive, 0 not
+    return postingList, classVec
+
+
+def createVocabList(dataSet):
+    """
+    获取所有单词的集合
+    :param dataSet: 数据集
+    :return: 所有单词的集合(即不含重复元素的单词列表)
+    """
+    vocabSet = set([])  # create empty set
+    for document in dataSet:
+        vocabSet = vocabSet | set(document)  # union of the two sets
+    return list(vocabSet)
+
+
+def setOfWords2Vec(vocabList, inputSet):
+    """
+    遍历查看该单词属否出现，出现该单词则将该单词置1
+    :param vocabList: 所有单词集合列表
+    :param inputSet: 输入数据集
+    :return: 匹配列表[0,1,0,1...]
+    """
+    returnVec = [0] * len(vocabList)
+    for word in inputSet:
+        if word in vocabList:
+            returnVec[vocabList.index(word)] = 1
+        else:
+            print "the word: %s is not in my Vocabulary!" % word
+    return returnVec
+
+
+def _trainNB0(trainMatrix, trainCategory):
+    """
+    训练数据原版
+    :param trainMatrix: 文件单词矩阵
+    :param trainCategory: 文件对应的类别
+    :return:
+    """
+    # 文件数
+    numTrainDocs = len(trainMatrix)
+    # 单词数
+    numWords = len(trainMatrix[0])
+    # 侮辱性文件的出现概率
+    pAbusive = sum(trainCategory) / float(numTrainDocs)
+    # 构造单词出现次数列表
+    p0Num = zeros(numWords)
+    p1Num = zeros(numWords)
+
+    # 整个数据集单词出现总数
+    p0Denom = 0.0
+    p1Denom = 0.0
+    for i in range(numTrainDocs):
+        if trainCategory[i] == 1:
+            p1Num += trainMatrix[i]
+            p1Denom += sum(trainMatrix[i])
+        else:
+            p0Num += trainMatrix[i]
+            p0Denom += sum(trainMatrix[i])
+    # 类别1，即侮辱性文档的[P(F1|C1),P(F2|C1),P(F3|C1),P(F4|C1),P(F5|C1)....]列表
+    p1Vect = p1Num / p1Denom
+    # 类别0，即正常文档的[P(F1|C0),P(F2|C0),P(F3|C0),P(F4|C0),P(F5|C0)....]列表
+    p0Vect = p0Num / p0Denom
+    return p0Vect, p1Vect, pAbusive
+
+
+def trainNB0(trainMatrix, trainCategory):
+    """
+    训练数据优化版本
+    :param trainMatrix: 文件单词矩阵
+    :param trainCategory: 文件对应的类别
+    :return:
+    """
+    # 文件数
+    numTrainDocs = len(trainMatrix)
+    # 单词数
+    numWords = len(trainMatrix[0])
+    # 侮辱性文件的出现概率
+    pAbusive = sum(trainCategory) / float(numTrainDocs)
+    # 构造单词出现次数列表
+    p0Num = ones(numWords)
+    p1Num = ones(numWords)
+
+    # 整个数据集单词出现总数，2.0根据样本/实际调查结果调整分母的值
+    p0Denom = 2.0
+    p1Denom = 2.0
+    for i in range(numTrainDocs):
+        if trainCategory[i] == 1:
+            p1Num += trainMatrix[i]
+            p1Denom += sum(trainMatrix[i])
+        else:
+            p0Num += trainMatrix[i]
+            p0Denom += sum(trainMatrix[i])
+    # 类别1，即侮辱性文档的[log(P(F1|C1)),log(P(F2|C1)),log(P(F3|C1)),log(P(F4|C1)),log(P(F5|C1))....]列表
+    p1Vect = log(p1Num / p1Denom)
+    # 类别0，即正常文档的[log(P(F1|C0)),log(P(F2|C0)),log(P(F3|C0)),log(P(F4|C0)),log(P(F5|C0))....]列表
+    p0Vect = log(p0Num / p0Denom)
+    return p0Vect, p1Vect, pAbusive
+
+
+def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
+    """
+    使用算法
+    :param vec2Classify: 待测数据
+    :param p0Vec: 类别1，即侮辱性文档的[log(P(F1|C1)),log(P(F2|C1)),log(P(F3|C1)),log(P(F4|C1)),log(P(F5|C1))....]列表
+    :param p1Vec: 类别0，即正常文档的[log(P(F1|C0)),log(P(F2|C0)),log(P(F3|C0)),log(P(F4|C0)),log(P(F5|C0))....]列表
+    :param pClass1: 类别1，侮辱性文件的出现概率
+    :return: 类别1 or 0
+    """
+    # 计算公式  log(P(F1|C))+log(P(F2|C))+....+log(P(Fn|C))+log(P(C))
+    p1 = sum(vec2Classify * p1Vec) + log(pClass1)
+    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
+    if p1 > p0:
+        return 1
+    else:
+        return 0
+
+
+def bagOfWords2VecMN(vocabList, inputSet):
+    returnVec = [0] * len(vocabList)
+    for word in inputSet:
+        if word in vocabList:
+            returnVec[vocabList.index(word)] += 1
+    return returnVec
+
+
+def testingNB():
+    """
+    测试朴素贝叶斯算法
+    """
+    # 1. 加载数据集
+    listOPosts, listClasses = loadDataSet()
+    # 2. 创建单词集合
+    myVocabList = createVocabList(listOPosts)
+    # 3. 计算单词是否出现并创建数据矩阵
+    trainMat = []
+    for postinDoc in listOPosts:
+        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
+    # 4. 训练数据
+    p0V, p1V, pAb = trainNB0(array(trainMat), array(listClasses))
+    # 5. 测试数据
+    testEntry = ['love', 'my', 'dalmation']
+    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
+    print testEntry, 'classified as: ', classifyNB(thisDoc, p0V, p1V, pAb)
+    testEntry = ['stupid', 'garbage']
+    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
+    print testEntry, 'classified as: ', classifyNB(thisDoc, p0V, p1V, pAb)
+
+
+testingNB()