Question

我正在寻找一个关于如何使用Encog Framework创建简单的垃圾邮件过滤/分类或群集应用程序的示例。我一直无法在谷歌上找到任何东西。

我还购买了Jeff Heaton的书，用C＃编写了带有Encog3的神经网络，但我找不到这样一个应用程序的例子。

任何人都可以提供有关简单应用程序的任何信息，如何根据主题和正文将电子邮件归类为垃圾邮件？

编辑：我已经看过如何在Python中执行此操作的方法，但我要问，是否有人可以提供任何Encog + C＃具体示例，了解如何创建垃圾邮件过滤/分类应用程序？

Answer 1

大多数垃圾邮件过滤器使用一种贝叶斯分类，这是最流行的，朴素的贝叶斯分类。以下是一些可以在没有任何其他框架的情况下使用的代码。

public void TrainClassifier(DataTable table)
{
dataSet.Tables.Add(table);

//table
DataTable GaussianDistribution = dataSet.Tables.Add("Gaussian");
GaussianDistribution.Columns.Add(table.Columns[0].ColumnName);

//columns
for (int i = 1; i < table.Columns.Count; i++)
{
    GaussianDistribution.Columns.Add(table.Columns[i].ColumnName + "Mean");
    GaussianDistribution.Columns.Add(table.Columns[i].ColumnName + "Variance");
}

//calc data
var results = (from myRow in table.AsEnumerable()
               group myRow by myRow.Field<string>(table.Columns[0].ColumnName) into g
               select new { Name = g.Key, Count = g.Count() }).ToList();

for (int j = 0; j < results.Count; j++)
{
    DataRow row = GaussianDistribution.Rows.Add();
    row[0] = results[j].Name;

    int a = 1;
    for (int i = 1; i < table.Columns.Count; i++)
    {
        row[a] = Helper.Mean(SelectRows(table, i, string.Format("{0} = '{1}'", 
                             table.Columns[0].ColumnName, results[j].Name)));
        row[++a] = Helper.Variance(SelectRows(table, i, 
                   string.Format("{0} = '{1}'", 
                   table.Columns[0].ColumnName, results[j].Name)));
        a++;
    }
}

}

public string Classify(double[] obj)
{
Dictionary<string,> score = new Dictionary<string,>();

var results = (from myRow in dataSet.Tables[0].AsEnumerable()
               group myRow by myRow.Field<string>(
                     dataSet.Tables[0].Columns[0].ColumnName) into g
               select new { Name = g.Key, Count = g.Count() }).ToList();

for (int i = 0; i < results.Count; i++)
{
    List<double> subScoreList = new List<double>();
    int a = 1, b = 1;
    for (int k = 1; k < dataSet.Tables["Gaussian"].Columns.Count; k = k + 2)
    {
        double mean = Convert.ToDouble(dataSet.Tables["Gaussian"].Rows[i][a]);
        double variance = Convert.ToDouble(dataSet.Tables["Gaussian"].Rows[i][++a]);
        double result = Helper.NormalDist(obj[b - 1], mean, Helper.SquareRoot(variance));
        subScoreList.Add(result);
        a++; b++;
    }

    double finalScore = 0;
    for (int z = 0; z < subScoreList.Count; z++)
    {
        if (finalScore == 0)
        {
            finalScore = subScoreList[z];
            continue;
        }

        finalScore = finalScore * subScoreList[z];
    }

    score.Add(results[i].Name, finalScore * 0.5);
}

double maxOne = score.Max(c => c.Value);
var name = (from c in score
            where c.Value == maxOne
            select c.Key).First();

return name;
}

编辑：以下是你如何使用它！

    DataTable table = new DataTable(); 
    table.Columns.Add("Sex"); 
    table.Columns.Add("Height", typeof(double)); 
    table.Columns.Add("Weight", typeof(double)); 
    table.Columns.Add("FootSize", typeof(double)); 

    //training data. 
    table.Rows.Add("male", 6, 180, 12); 
    table.Rows.Add("male", 5.92, 190, 11); 
    table.Rows.Add("male", 5.58, 170, 12); 
    table.Rows.Add("male", 5.92, 165, 10); 
    table.Rows.Add("female", 5, 100, 6); 
    table.Rows.Add("female", 5.5, 150, 8); 
    table.Rows.Add("female", 5.42, 130, 7); 
    table.Rows.Add("female", 5.75, 150, 9); 
    table.Rows.Add("transgender", 4, 200, 5); 
    table.Rows.Add("transgender", 4.10, 150, 8); 
    table.Rows.Add("transgender", 5.42, 190, 7); 
    table.Rows.Add("transgender", 5.50, 150, 9);

    Classifier classifier = new Classifier(); 
    classifier.TrainClassifier(table);
    //output would be transgender.
    Console.WriteLine(classifier.Classify(new double[] { 4, 150, 12 }));
    Console.Read();

使用Encog框架的垃圾邮件过滤示例

1 个答案: