<Machine Learning in Action >之二 樸素貝葉斯 C#實現文章分類
def trainNB0(trainMatrix,trainCategory):
numTrainDocs = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCategory)/float(numTrainDocs)
p0Num = ones(numWords); p1Num = ones(numWords) #change to ones()
p0Denom = 2.0; p1Denom = 2.0 #change to 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])
p1Vect = log(p1Num/p1Denom) #change to log()
p0Vect = log(p0Num/p0Denom) #change to log()
return p0Vect,p1Vect,pAbusivedef classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
p1 = sum(vec2Classify * p1Vec) + log(pClass1) #element-wise mult *提示一
p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
if p1 > p0:
return 1
else:
return 0
*提示一
p(Ci|w)=p(w|Ci)p(Ci)/p(w) 對乘積取自然對數 ln(p(w|Ci)p(Ci))=ln(p(w|Ci))+ln(p(Ci))
在以下樣例中。由於每一個分類在樣本中的比例都一樣的，這樣不用再加上log(p(Ci))也不會影響最後的分類效果
用C#隨便做個樣例，實現文章類型的分類 隨機詞不如有針對性的詞來的有效，所以這裏都是從全部三個分類裏找到的詞匯
1、創建詞向量：中超/亞冠/國足/足協/英超/西甲/歐冠/意甲/德甲/籃球/NBA/CBA/高爾夫/乒乓/排球/網球/羽毛球/跑步/賽車/棋牌/臺球/遊泳/馬術/拳擊/田徑/功夫/撲克/體育/球隊/球員/訓練/國家隊/聯賽/俱樂部/場地/翻盤/絕殺/熱身/隊友/冠軍/亞軍/季軍/犯規/賽季/加時/反超/半場/爭奪/戰術/陣容/比賽/德比/恢復/進球/失球/奧斯卡/娛樂/影迷/電影/電視/音樂/戲劇/視頻/演員/導演/明星/經紀人/歌手/連續劇/展映/粉絲/寫真/演技/作秀/節目/藝人/超模/女星/模特/男星/性感/主創/院線/影業/拍攝/編劇/情節/影像/劇情/主演/上映/票房/開機/劇集/表演/收視/預告片/主持人/艾美獎/角色/劇院/樂迷/影迷/演出/專輯/樂壇/劇場/文藝/芭蕾/戲曲/舞蹈/軍事/軍隊/軍機/炸彈/軍方/坦克/軍艦/炸死/軍演/戰備/部隊/軍區/國防/士兵/艦船/潛艇/飛機/直升機/艦隊/保衛/演習/武器/反擊/打擊/閱兵/對抗/防衛/海軍/空軍/陸軍/武裝/戰略/空襲/沖突/裝甲/步兵/作戰/導彈/邊防/偵察/戰鬥機/雷達/轟炸/防禦/據點/火力/航空母艦/進攻/彈藥/軍營/包圍/攻占/俘虜/參戰/戰友/戰鬥/入侵
2、搜狐上下載三類文章各10篇組成訓練樣本，計算出每篇文章的文檔矩陣。標註每篇文章的類別標簽
樣本文件名稱格式： 編號_類別標簽.txt
文檔矩陣：
000000000000000000100000000000000000001100010001001010000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000010000000000000100000000000000011110001010000000000000000011000000110000000000100000000000000000010000000000000000000000000000000000000000000000
000000000000000000000000000011000000000000000000000001001000001001000000001000000000000000000000010000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000001001000000000000000001000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000010000000000000000000000000000010010000100000000000000010010000001000000000100000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000010000000010000010000010100000000111111111110000000100000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000110000000000000011010000001000010000000000001100001110000000000000000000000000000000000000000000000000000000000000000000000000000
000000000100000000000000000000000000000000000000000000001010000110000000000000000100000001101000000100000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000010000010000000000000001000000001100000100000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000001010000110000000000000000000001011000010000110000000000000000000000000000000000000000000000000000000000000000000
000000010000000000000000000011100000001000010110001001000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000100000000000000000000000
000000000000000000000000000000000000000000000000000000001001000100000000000000000000000010000100000100000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000011110000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000110000000111111111111100000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000001100000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000100000000000000000000100000000000000000000000000000000000
000000000000000000000000000000000000000000000001000000000001000000000000000000000000100000000000000000000000000100100000010010000000000000000100000000000100000000000010
000000000000000000000000000000100000000000000000000000000001000000000000000000000000000000000000000000000000000100010000010000000000000000000100000100000000000000000000
000000000000000000000000000000000000000000000000100000000000000000000000000000000000000000000000000000000000000000000000110010000000001001010000000010000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000000000100000000000000000000000000000010100000000000100000000010000000000000001000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000001000010000000000100000000100010000000000001000000000
000000010000000000000000000111001100000000010000001001000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000100000000000100000000000000100000000110000010000000000000
110000000000000000000000000100001000100000010000000001000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000001000000000
110000000000000000000000000111001100100100010001111011000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000001000000000
000000000001000000000000000001000000101000100110001000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000001000000000
000000000000010000000000000000000000001101000001001000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000010000000000000000010000000000000010010001000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000001000000000000000111100000101000110100001000100000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000001000000000
000000000000000000000000000100000000000110010100000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
類別標簽向量：
122222222212333333333131111111
using System;
using System.Text;
using System.Windows.Forms;
using System.IO;
namespace NaiveBayes
{
public partial class Form1 : Form
{
private string[] vocabArray;
private double[] p0Num, p1Num, p2Num;
public Form1()
{
InitializeComponent();
label2.Text = "體育1、娛樂2、軍事3\r\n每一個類型10個訓練樣本\r\n文章所有出自搜狐新聞\r\n詞向量從各類文章中分詞獲得";
StreamReader sr = new StreamReader("vocabList.txt", Encoding.Default);
string line, all = "";
while ((line = sr.ReadLine()) != null)
{
all += line;
}
vocabArray = all.Split(new string[] { "/" }, StringSplitOptions.RemoveEmptyEntries);
}
private void Form1_Resize(object sender, EventArgs e)
{
this.Width = 800;
this.Height = 600;
}
private void button1_Click(object sender, EventArgs e)
{
//生成文檔矩陣和分類標簽向量
DirectoryInfo di = new DirectoryInfo("train");
FileInfo[] fi = di.GetFiles("*.txt");
string[] trainMatrix = new string[fi.Length];
p0Num = new double[vocabArray.Length];
p1Num = new double[vocabArray.Length];
p2Num = new double[vocabArray.Length];
double p0Denom = 2.0;
double p1Denom = 2.0;
double p2Denom = 2.0;
for (int i = 0; i < vocabArray.Length; i++)
{
p0Num[i] = p1Num[i] = p2Num[i] = 1.0;
}
string trainCategory = "";
int m = 0;
foreach (FileInfo i in fi)
{
StreamReader sr = new StreamReader(i.FullName, Encoding.Default);
string line, all = "";
while ((line = sr.ReadLine()) != null)
{
all += line;
}
string strVec = "";
foreach (string j in vocabArray)
{
if (all.Contains(j))
strVec += "1";
else
strVec += "0";
}
trainMatrix[m] = strVec;
m++;
trainCategory += i.Name.Substring(i.Name.LastIndexOf("_") + 1, 1);
}
StreamWriter sw = new StreamWriter(".\\trainV\\trainMatrix.txt", true);
foreach (string i in trainMatrix)
{
sw.WriteLine(i);
sw.Flush();
}
sw.Close();
sw = new StreamWriter(".\\trainV\\trainCategory.txt", true);
sw.WriteLine(trainCategory);
sw.Close();
for (int i = 0; i < trainMatrix.Length; i++)
{
if (trainCategory.Substring(i, 1) == "1")
{
double tmp = 0;
for (int j = 0; j < vocabArray.Length; j++)
{
p0Num[j] += double.Parse(trainMatrix[i].Substring(j, 1));
tmp += double.Parse(trainMatrix[i].Substring(j, 1));
}
p0Denom += tmp;
}
else if (trainCategory.Substring(i, 1) == "2")
{
double tmp = 0;
for (int j = 0; j < vocabArray.Length; j++)
{
p1Num[j] += double.Parse(trainMatrix[i].Substring(j, 1));
tmp += double.Parse(trainMatrix[i].Substring(j, 1));
}
p1Denom += tmp;
}
else if (trainCategory.Substring(i, 1) == "3")
{
double tmp = 0;
for (int j = 0; j < vocabArray.Length; j++)
{
p2Num[j] += double.Parse(trainMatrix[i].Substring(j, 1));
tmp += double.Parse(trainMatrix[i].Substring(j, 1));
}
p2Denom += tmp;
}
else
{
//Undo
}
}
for (int j = 0; j < vocabArray.Length; j++)
{
p0Num[j] = Math.Log(p0Num[j] / p0Denom);
p1Num[j] = Math.Log(p1Num[j] / p1Denom);
p2Num[j] = Math.Log(p2Num[j] / p2Denom);
}
label4.Text = "處理樣本數據完畢";
}
private void button2_Click(object sender, EventArgs e)
{
if (textBox1.Text.Trim() != "")
{
string strVec = "";
foreach (string i in vocabArray)
{
if (textBox1.Text.Contains(i))
strVec += "1";
else
strVec += "0";
}
double p0 = 0;
double p1 = 0;
double p2 = 0;
for (int j = 0; j < vocabArray.Length; j++)
{
p0 += p0Num[j] * double.Parse(strVec.Substring(j, 1));
p1 += p1Num[j] * double.Parse(strVec.Substring(j, 1));
p2 += p2Num[j] * double.Parse(strVec.Substring(j, 1));
}
string catelog = "";
if (p0 > p1 && p0 > p2)
catelog = "體育";
else if (p1 > p0 && p1 > p2)
catelog = "娛樂";
else if (p2 > p0 && p2 > p1)
catelog = "軍事";
else
catelog = "無法推斷";
label3.Text = "體育：" + p0.ToString() + "\r\n娛樂：" + p1.ToString() + "\r\n軍事：" + p2.ToString();
label1.Text = "所屬類型是：" + catelog;
}
}
}
}
<Machine Learning in Action >之二 樸素貝葉斯 C#實現文章分類