Example #1
0
        public static void Main(string[] args)
        {
            Process p = Process.GetCurrentProcess();

            ShowWindow(p.MainWindowHandle, 3); //SW_MAXIMIZE = 3

            Console.WriteLine("reading train data...");
            StarterClass s = new StarterClass();

            DataTable dt = s.readCSVFile("zoo.data");

            List <string> autompg_data = new List <string>();

            Console.WriteLine("Reading and cleaning train data\n...");

            DataHolder dh = new DataHolder(dt, null);

            Console.WriteLine("finished reading and cleaning data\nBuilding tree...");
            SimpleNode node = s.buildtree(null, dh, null, null);

            Console.WriteLine("built tree\nreading test data...");
            // validation begins
            DataTable autompg_test = s.readCSVFile("zoo.test");

            //object classifiedNode = null;
            Console.WriteLine("finished reading and cleaning test\nstarting classification...");
            Dictionary <int, string> testingNodesList    = new Dictionary <int, string>();
            Dictionary <int, string> classifiedNodesList = new Dictionary <int, string>();

            int i = 0;

            foreach (DataRow datarow in autompg_test.Rows)
            {
                testingNodesList[i] = (string)datarow[datarow.ItemArray.Length - 1];
                var classifiedNode = s.classify(datarow, node);
                classifiedNodesList[i] = classifiedNode is SimpleNode ? (((SimpleNode)classifiedNode).Name) : (string)classifiedNode;
                Console.WriteLine(string.Join(",", datarow.ItemArray) + " " + classifiedNodesList[i]);
                i++;
            }
            Console.Write("\nfinished classifying\ncalculating accuracy...");

            int predictedCorrectValues = 0;

            for (int m = 0; m < testingNodesList.Count; m++)
            {
                if (testingNodesList[m] == classifiedNodesList[m])
                {
                    predictedCorrectValues += 1;
                }
            }

            double accuracy = 0;

            if (testingNodesList.Count != 0)
            {
                accuracy = (float)(predictedCorrectValues) / testingNodesList.Count * 100;
            }
            Console.Write("Found Accuracy:" + accuracy + " %");
            Console.ReadKey();
        }
Example #2
0
        public double set_gains(string inp_feature)
        {
            double sum_of_entropies_weighted_by_proportion = 0;
            int    s_dataset = Dataset.Rows.Count;

            foreach (string unique_feature_value in Feature_uniqueValues[inp_feature])
            {
                DataTable temp_newds = getSubset(unique_feature_value, inp_feature);
                int       s_newds    = temp_newds.Rows.Count;
                double    e_of_newds = 0.0;
                double    proportion = 0;
                if (s_newds != 0)
                {
                    proportion = (double)(s_newds) / s_dataset;
                    e_of_newds = StarterClass.get_entropy(temp_newds, null);
                }
                sum_of_entropies_weighted_by_proportion += proportion * e_of_newds;
            }
            double infogain = Entropy - sum_of_entropies_weighted_by_proportion;

            return(infogain);
        }