Question

我试图按类别对一系列文本示例进行分类。我有大量数据集的新闻文本与数据库中的类别。机器应该经过培训并决定新闻类别。

    public static string[] Tokenize(string text)
    {
        StringBuilder sb = new StringBuilder(text);

        char[] invalid = "!-;':'\",.?\n\r\t".ToCharArray();

        for (int i = 0; i < invalid.Length; i++)
            sb.Replace(invalid[i], ' ');

        return sb.ToString().Split(new[] { ' ' }, System.StringSplitOptions.RemoveEmptyEntries);
    }
    private void Form1_Load(object sender, EventArgs e)
    {
        string strDSN = "Provider=Microsoft.ACE.OLEDB.12.0;Data Source = c:\\users\\158820\\Documents\\Database4.accdb";
        string strSQL = "SELECT * FROM NewsRepository";
        // create Objects of ADOConnection and ADOCommand  
        OleDbConnection myConn = new OleDbConnection(strDSN);
        OleDbDataAdapter myCmd = new OleDbDataAdapter(strSQL, myConn);
        myConn.Open();
        DataSet dtSet = new DataSet();
        myCmd.Fill(dtSet, "NewsRepository");
        DataTable dTable = dtSet.Tables[0];
        myConn.Close();

        StringBuilder sWords = new StringBuilder();
        string[][] swords = new string[dTable.Rows.Count][];
        int i = 0;

        foreach (DataRowView dr in dTable.DefaultView)
        {
            swords[i] = Tokenize(dr[1].ToString());
            i++;
        }

        Codification codebook = new Codification(dTable, new string[] { "NewsTitle", "Category" });
        DataTable symbols = codebook.Apply(dTable);
        int[][] inputs = symbols.ToJagged<int>(new string[] { "NewsTitle" });
        int[] outputs = symbols.ToArray<int>("Category");

        bagOfWords(inputs, outputs);
    }


    private static void bagOfWords(int[][] inputs, int[] outputs)
    {
        var bow = new BagOfWords<int>();
        var quantizer = bow.Learn(inputs);
        string filenamebow = Path.Combine(Application.StartupPath, "News_BOW.accord");
        Serializer.Save(obj: bow, path: filenamebow);
        double[][] histograms = quantizer.Transform(inputs);

        // One way to perform sequence classification with an SVM is to use
        // a kernel defined over sequences, such as DynamicTimeWarping.

        // Create the multi-class learning algorithm as one-vs-one with DTW:
        var teacher = new MulticlassSupportVectorLearning<ChiSquare, double[]>()
        {
            Learner = (p) => new SequentialMinimalOptimization<ChiSquare, double[]>()
            {
               // Complexity = 100 // Create a hard SVM
            }
        };

        // Learn a multi-label SVM using the teacher
        var svm = teacher.Learn(histograms, outputs);

        // Get the predictions for the inputs
        int[] predicted = svm.Decide(histograms);

        // Create a confusion matrix to check the quality of the predictions:
        var cm = new GeneralConfusionMatrix(predicted: predicted, expected: outputs);

        // Check the accuracy measure:
        double accuracy = cm.Accuracy;

        string filename = Path.Combine(Application.StartupPath, "News_SVM.accord");
        Serializer.Save(obj: svm, path: filename);
    }

我对如何训练accord.net对象感到困惑。我能够序列化经过训练的模型（对于9个类别中的3600个独特新闻大约为106 MB）

如何使用该模型预测一组新的新闻文本的类别？

Answer 1

在不在训练集中的数据上使用您的模型就像调用您的svm做出另一个决定一样简单：

svm.Decide(outofSampleData)

由于您已经对已训练的模型进行了序列化，因此您可以使用Serializer.Load<T> \build\generated来实例化svm对象。

文本分类NaiveBayes

1 个答案: