public async void TrainAndFilter()
{
var trainer1 = new BayesTrain
{
Class = "Spam"
};
foreach (var s in spam)
{
await trainer1.HandleMessage(new StringMessage
{
Value = s
});
}
var trainer2 = new BayesTrain
{
Class = "Ham"
};
foreach (var h in ham)
{
await trainer2.HandleMessage(new StringMessage
{
Value = h
});
}
var bayes1 = new Bayes
{
Class = "Spam"
};
var msg1 = new StringMessage
{
Value = spamSample
};
//var likelySpam1 = Bayes.Prediction(msg1.Tokens, "Spam");
//var likelyHam1 = Bayes.Prediction(msg1.Tokens, "Ham");
//Assert.True(likelySpam1 > 0);
//Assert.True(likelyHam1 > 0);
//Assert.True(likelySpam1 > likelyHam1);
//var msg2 = new StringMessage
//{
// Value = hamSample
//};
//var likelySpam2 = Bayes.Prediction(msg2.Tokens, "Spam");
//var likelyHam2 = Bayes.Prediction(msg2.Tokens, "Ham");
//Assert.True(likelySpam2 > 0);
//Assert.True(likelyHam2 > 0);
//Assert.True(likelySpam2 < likelyHam2);
}
static void Main(string[] args)
{
var bayes = new Bayes();
bayes.LoadData(@"D:\Politechnika\Semestr4\ArtificialIntelligencePOLSL\BayesAndKeyPoints\BayesAndKeyPoints\GoForAWalk.txt");
bayes.Learn();
bayes.Predict("Sunny", "Cool", "Weak");
bayes.Predict("Rainy", "Hot", "Strong");
var keyPoints = new KeyPoints();
keyPoints.AddMask();
keyPoints.PotencialPoints(5000);
Console.ReadKey();
}
public Parlogike()
{
corrector = new SymSpell();
BayesClassifiers = new Bayes(ref corrector);
externFunctors = new Dictionary <string, Func <Parlogike, string, List <Variable>, char, bool, Pattern, string, string, Result> >();
internFunctors = new Dictionary <string, Func <Parlogike, List <Variable>, int, bool> >();
MarkovGenerators = new Dictionary <string, Markov>();
GlobalVariables = new Dictionary <string, Dictionary <string, Variable> >();
LocalStack = new List <string>();
Residues = new List <string>();
Groups = new Dictionary <string, List <string> >();
knowledge = new List <Pattern>();
GlobalVariables[""] = new Dictionary <string, Variable>();
if (!init)
{
Functors.populate();
init = true;
}
}
public void CrossValidation(int howManyValidationFolds)
{
var dataCount = youtubeChannel.Count;
var range = dataCount / howManyValidationFolds;
var values = youtubeChannel.Values.ToList();
Console.WriteLine("Full Data: " + dataCount + " inputs. For testing we take 1/" + howManyValidationFolds + " of data. That is: " + range + "\n");
int start = 0;
Bayes bayes = new Bayes();
List <string> knnResults = new List <string>();
List <string> bayesResults = new List <string>();
for (int i = 0; i < howManyValidationFolds; i++)
{
var testData = values.GetRange(start, range).ToDictionary(x => x.channelName); //paimamas range kiekis duomeų - testavimui
var trainData = values.GetRange(0, start).Concat(values.GetRange(start + range, dataCount - start - range)).ToDictionary(x => x.channelName); //paimami likusieji duomenys mokymuisi
start += range;
var fullData = DivideData(youtubeChannel, howManyValidationFolds);
var dividedData = DivideData(trainData, howManyValidationFolds);
//čia kviečiam algoritmo magijas
KNN knn = new KNN(fullData, dividedData, howManyValidationFolds);
bayes.Train(dividedData);
bayesResults.Add(bayes.Test(fullData, testData));
knnResults.Add(knn.Test(testData));
}
Console.WriteLine(new string('-', 40));
foreach (var item in knnResults)
{
Console.WriteLine(item);
}
Console.WriteLine(new string('-', 40));
foreach (var item in bayesResults)
{
Console.WriteLine(item);
}
Console.WriteLine(new string('-', 40));
}
// 分类运算
private void classifyButton_Click(object sender, EventArgs e)
{
//前提检验
if (SelectedPCXHelper.GetSelPCXFromLB().Count == 0 || SelectedPCXHelper.GetUnselPCXList().Count == 0)
{
MessageBox.Show(this, "您还未提取样本特征，或者还未设置测试样本集！", "提示信息", MessageBoxButtons.OK);
}
else
{
string correctRate = null; //正确率
string myfilepath = filepathText.Text.ToString();
Features feature;
#region 这里做一个文件名为unknown.pcx的判断
string filename = FeatureHelper.GetUnknownName(myfilepath);
if (filename.ToLower().Equals("unknown"))
{
feature = new Features(myfilepath);
}
else
{
int classID = Convert.ToInt32(FeatureHelper.GetUpperFoldername(myfilepath));
feature = new Features(myfilepath, classID);
}
#endregion
#region Bayes分类法
if (rbBayes.Checked)
{
#region 数据初始化
CheckInit();
double correctCount = 0.0;
#endregion
IList sampleList = FeatureHelper.GetFeaturesList(); //获取原始训练样本
//从降维器获取降维后的新样本
IList newSampleList = MDAHelper.GetMDSampleList();
MVHelper.SetSampleList((ArrayList)newSampleList);
Bayes bayes = Bayes.GetInstance();
bayes.TrainSampleList = newSampleList; //向贝叶斯分类器注入降维后的训练样本
//int classID = Convert.ToInt32(FeatureHelper.GetUpperFoldername(myfilepath));
//Features feature = new Features(myfilepath, classID);
feature = MDAHelper.MDSample(feature); //测试样本降维
int testClassID = bayes.DecisionFunction(feature); //用贝叶斯决策进行测试样本分类
//结果显示
lblunknownclassify.Text = testClassID.ToString("000");
if (feature.classID == testClassID)
{
lblerrorinfo.Text = "Bayes分类法分类正确";
lblerrorinfo.ForeColor = Color.Green;
}
//unknown.pcx处理
else if (feature.classID == -1)
{
}
else
{
lblerrorinfo.Text = "Bayes分类法分类失败";
lblerrorinfo.ForeColor = Color.Green;
}
}
#endregion
#region Kn近邻法
if (rbKn.Checked)
{
#region 相关数据初始化
CheckInit();
int testResult = -1;
double correctCount = 0.0;
int kvalue = Constant.kvalue;
#endregion
#region 效的情况下进行计算
if (KCheck(kvalue))
{
KnNear my_knearest = new KnNear();
//int classID = Convert.ToInt32(FeatureHelper.GetUpperFoldername(myfilepath));
//Features currfeature = new Features(myfilepath, classID);
testResult = my_knearest.DoK_nearest(feature, FeatureHelper.GetFeaturesList(), kvalue);
//testResult为K近邻的分类结果
// 其实testResult的结果直接就是result求的值
string result = testResult.ToString("000");
lblunknownclassify.Text = result;
result = ResultConvert(result);
int testID = Convert.ToInt32(result);
if (testID > 0 && testID == feature.classID)
{
//correctRate = "分类正确率： " + Constant.kn_Rate;
lblerrorinfo.Text = "Kn近邻法分类正确";
lblerrorinfo.ForeColor = Color.Green;
}
//unknown.pcx处理
else if (feature.classID == -1)
{
}
else
{
lblerrorinfo.Text = "Kn近邻法分类失败！";
lblerrorinfo.ForeColor = Color.Green;
}
}
#endregion
}
#endregion
#region 最近邻法
if (rbnearest.Checked)
{
#region 初始化
CheckInit();
int testResult = -1;
double correctCount = 0.0;
#endregion
#region 最近邻分类
if (NearestCheck())
{
Nearest nearest = new Nearest();
//int classID = Convert.ToInt32(FeatureHelper.GetUpperFoldername(myfilepath));
//Features currfeature = new Features(myfilepath, classID);
testResult = nearest.Do_Nearest(feature, FeatureHelper.GetFeaturesList());
string result = testResult.ToString("000");
lblunknownclassify.Text = result;
if (testResult > 0 && testResult == feature.classID)
{
lblerrorinfo.Text = "最近邻法分类正确";
lblerrorinfo.ForeColor = Color.Green;
}
//unknown.pcx处理
else if (feature.classID == -1)
{
}
else
{
lblerrorinfo.Text = "最近邻法分类失败！";
lblerrorinfo.ForeColor = Color.Green;
}
}
#endregion
}
#endregion
}
}
private void testButton_Click(object sender, EventArgs e)
{
#region 数据初始化
double correctCount = 0.0;
double correctRate = 0.0;
IList sampleList = FeatureHelper.GetFeaturesList(); //获取原始训练样本
//从降维器获取降维后的新样本
IList newSampleList = MDAHelper.GetMDSampleList();
MVHelper.SetSampleList((ArrayList)newSampleList);
Bayes bayes = Bayes.GetInstance();
bayes.TrainSampleList = newSampleList; //向贝叶斯分类器注入降维后的训练样本
IList testSampleList = FeatureHelper.GetTestFeaturesList(); //获取测试样本
#endregion
#region DataGridView操作
bayesDataGridView.DataSource = null;
bayesDataGridView.Rows.Clear();
bayesDataGridView.Refresh();
DataSet ds = new DataSet();
DataTable dt = new DataTable();
// 或者直接将arr作为参数传入
//FeatureHelper.GetSamplesFeatures(); //初始化训练和测试样本
dt.Columns.Add("文件夹", typeof(string));
dt.Columns.Add("所属类别", typeof(string));
dt.Columns.Add("测试类别", typeof(string));
dt.Columns.Add("正误判断", typeof(string));
for (int i = 0; i < testSampleList.Count; i++)
{
DataRow row = dt.NewRow();
string rightOrWrong = "×";
Features feature = (Features)testSampleList[i];
row[0] = feature.Filepath;
row[1] = feature.classID;
feature = MDAHelper.MDSample(feature); //测试样本降维
int testClassID = bayes.DecisionFunction(feature); //用贝叶斯决策进行测试样本分类
// 用StringBuilder加快字符串处理速度。【值类型和堆类型】
StringBuilder sb = new StringBuilder();
sb.Append("类");
sb.Append(testClassID.ToString());
sb.ToString();
row[2] = sb;
if (feature.classID == testClassID)
{
correctCount++;
row[3] = " ";
}
else
{
row[3] = rightOrWrong;
//this.bayesDataGridView.DefaultCellStyle.ForeColor = Color.Red;
}
dt.Rows.Add(row);
}
ds.Tables.Add(dt);
this.bayesDataGridView.DataSource = ds.Tables[0];
#endregion
#region Bayes分类性能显示
correctRate = (correctCount / Convert.ToDouble(testSampleList.Count)) * 100.0;
Constant.bayes_Rate = correctRate.ToString("0.000") + "%";
dataShowLabel.Text = "测试样本总数 " + testSampleList.Count + " ，Bayes判断正确 " + correctCount + " 个，正确率为：" + Constant.bayes_Rate;
#endregion
}
private void UpdateText()
{
TextBox_BPM.Text = Bayes.ToString();
}
