private static void write_about_Estimates(XmlWriter writer, c_Fuzzy_System Classifier)
{
writer.WriteStartElement("Estimates");
if (Classifier.Test_Samples_set != null)
{
writer.WriteAttributeString("Count", XmlConvert.ToString(2));
writer.WriteStartElement("Estimate");
writer.WriteAttributeString("Table", Classifier.Learn_Samples_set.File_Name.Remove(Classifier.Learn_Samples_set.File_Name.Length - 4, 4));
writer.WriteAttributeString("Type", "PrecisionPercent");
writer.WriteAttributeString("Value", XmlConvert.ToString(Classifier.Classify_Learn_Samples()));
writer.WriteEndElement();
writer.WriteStartElement("Estimate");
writer.WriteAttributeString("Table", Classifier.Test_Samples_set.File_Name.Remove(Classifier.Learn_Samples_set.File_Name.Length - 4, 4));
writer.WriteAttributeString("Type", "PrecisionPercent");
writer.WriteAttributeString("Value", XmlConvert.ToString(Classifier.Classify_Test_Samples()));
writer.WriteEndElement();
}
else
{
writer.WriteAttributeString("Count", XmlConvert.ToString(1));
writer.WriteStartElement("Estimate");
writer.WriteAttributeString("Table", Classifier.Learn_Samples_set.File_Name.Remove(Classifier.Learn_Samples_set.File_Name.Length - 4, 4));
writer.WriteAttributeString("Type", "PrecisionPercent");
writer.WriteAttributeString("Value", XmlConvert.ToString(Classifier.Classify_Learn_Samples()));
writer.WriteEndElement();
}
writer.WriteEndElement();
}
private static void write_about_varibles_and_terms(XmlWriter writer, c_Fuzzy_System Classifier)
{
writer.WriteStartElement("Variables");
writer.WriteAttributeString("Count", XmlConvert.ToString(Classifier.Count_Vars));
for (int i = 0; i < Classifier.Count_Vars; i++)
{
writer.WriteStartElement("Variable");
writer.WriteAttributeString("Name", Classifier.Learn_Samples_set.Input_Attribute(i).Name);
writer.WriteAttributeString("Min",
XmlConvert.ToString(Classifier.Learn_Samples_set.Input_Attribute(i).Min));
writer.WriteAttributeString("Max",
XmlConvert.ToString(Classifier.Learn_Samples_set.Input_Attribute(i).Max));
List <Term> terms_for_varrible =
Classifier.Rulles_Database_Set[0].Terms_Set.Where(x => x.Number_of_Input_Var == i).ToList();
writer.WriteStartElement("Terms");
writer.WriteAttributeString("Count", XmlConvert.ToString(terms_for_varrible.Count));
foreach (var term in terms_for_varrible)
{
write_about_term(writer, Classifier, term);
}
writer.WriteEndElement();
writer.WriteEndElement();
}
writer.WriteEndElement();
}
public static bool save_to_UFS(c_Fuzzy_System Classifier, string file_name)
{
XmlWriterSettings settings = new XmlWriterSettings();
settings.Encoding = Encoding.UTF8;
settings.Indent = true;
settings.IndentChars = "\t";
settings.NewLineChars = Environment.NewLine;
settings.NewLineHandling = NewLineHandling.None;
settings.OmitXmlDeclaration = false;
XmlWriter writer = XmlTextWriter.Create(file_name, settings);
writer.WriteStartElement("FuzzySystem");
writer.WriteAttributeString("Type", "ClassifierPittsburgh");
write_about_varibles_and_terms(writer, Classifier);
write_about_rules(writer, Classifier);
write_about_observation(writer, Classifier);
write_about_Estimates(writer, Classifier);
writer.WriteEndElement();
// writer.Flush();
writer.Close();
return(false);
}
private static void write_about_rules(XmlWriter writer, c_Fuzzy_System Classifier)
{
writer.WriteStartElement("Rules");
writer.WriteAttributeString("Count", XmlConvert.ToString(Classifier.Rulles_Database_Set[0].Rules_Database.Count));
foreach (CRule rule in Classifier.Rulles_Database_Set[0].Rules_Database)
{
writer.WriteStartElement("Rule");
writer.WriteStartElement("Antecedent");
writer.WriteAttributeString("Count", XmlConvert.ToString(rule.Term_of_Rule_Set.Count));
foreach (Term term in rule.Term_of_Rule_Set)
{
writer.WriteStartElement("Pair");
writer.WriteAttributeString("Variable", Classifier.Learn_Samples_set.Input_Attribute(term.Number_of_Input_Var).Name);
writer.WriteAttributeString("Term", XmlConvert.ToString(Classifier.Rulles_Database_Set[0].Terms_Set.IndexOf(term)));
writer.WriteEndElement();
}
writer.WriteEndElement();
writer.WriteStartElement("Consequent");
writer.WriteAttributeString("Class", rule.Label_of_Class);
writer.WriteAttributeString("CF", XmlConvert.ToString(rule.CF));
writer.WriteEndElement();
writer.WriteEndElement();
}
writer.WriteEndElement();
}
public override Fuzzy_system.Class_Pittsburgh.c_Fuzzy_System TuneUpFuzzySystem(Fuzzy_system.Class_Pittsburgh.c_Fuzzy_System Classifier, Abstract_learn_algorithm_conf conf)
{
int count_iteration = ((Term_Config_Random_Search_conf)conf).Количество_итераций;
int count_c_Rules = ((Term_Config_Random_Search_conf)conf).Количество_генерируемых_баз_правил_за_итерацию;
c_Fuzzy_System result = Classifier;
for (int i = 0; i < count_iteration; i++)
{
int temp_prev_count_c_Rule = result.Rulles_Database_Set.Count;
double temp_best_result = result.Classify_Learn_Samples();
int temp_best_index = 0;
for (int j = 0; j < count_c_Rules; j++)
{
Knowlege_base_CRules temp_c_Rule = new Knowlege_base_CRules(result.Rulles_Database_Set[0]);
result.Rulles_Database_Set.Add(temp_c_Rule);
int temp_index = result.Rulles_Database_Set.Count - 1;
for (int k = 0; k < result.Rulles_Database_Set[temp_index].Terms_Set.Count; k++)
{
result.Rulles_Database_Set[temp_index].Terms_Set[k] =
randomize_term(result.Rulles_Database_Set[temp_index].Terms_Set[k]);
}
bool success = true;
double current_score = 0;
try
{
current_score = result.Classify_Learn_Samples(temp_index);
}
catch (Exception)
{
success = false;
}
if (success && (current_score >= temp_best_result))
{
temp_best_result = current_score;
temp_best_index = temp_index;
}
}
result.Rulles_Database_Set[0] = result.Rulles_Database_Set[temp_best_index];
result.Rulles_Database_Set.RemoveRange(temp_prev_count_c_Rule, result.Rulles_Database_Set.Count - temp_prev_count_c_Rule);
}
return(result);
}
private static void write_about_observation(XmlWriter writer, c_Fuzzy_System Classifier)
{
writer.WriteStartElement("Observations");
if (Classifier.Test_Samples_set != null)
{
writer.WriteAttributeString("CountTable", XmlConvert.ToString(2));
write_about_table(writer, Classifier.Learn_Samples_set, Classifier);
write_about_table(writer, Classifier.Test_Samples_set, Classifier);
}
else
{
writer.WriteAttributeString("CountTable", XmlConvert.ToString(1));
write_about_table(writer, Classifier.Learn_Samples_set, Classifier);
}
writer.WriteEndElement();
}
private static void write_about_term(XmlWriter writer, c_Fuzzy_System Classifier, Term term)
{
writer.WriteStartElement("Term");
writer.WriteAttributeString("Name",
XmlConvert.ToString(Classifier.Rulles_Database_Set[0].Terms_Set.IndexOf(term)));
switch (term.Term_Func_Type)
{
case Type_Term_Func_Enum.Треугольник:
writer.WriteAttributeString("Type", "Triangle");
break;
case Type_Term_Func_Enum.Гауссоида:
writer.WriteAttributeString("Type", "Gauss");
break;
case Type_Term_Func_Enum.Парабола:
writer.WriteAttributeString("Type", "Parabolic");
break;
case Type_Term_Func_Enum.Трапеция:
writer.WriteAttributeString("Type", "Trapezoid");
break;
}
writer.WriteStartElement("Params");
for (int i = 0; i < c_Fuzzy_System.Count_Params_For_Term(term.Term_Func_Type); i++)
{
writer.WriteStartElement("Param");
writer.WriteAttributeString("Number", XmlConvert.ToString(i));
writer.WriteAttributeString("Value", XmlConvert.ToString(term.Parametrs[i]));
writer.WriteEndElement();
}
writer.WriteEndElement();
writer.WriteEndElement();
}
public override Fuzzy_system.Class_Pittsburgh.c_Fuzzy_System TuneUpWeigth(Fuzzy_system.Class_Pittsburgh.c_Fuzzy_System Classifier, Abstract_weigth_config_conf conf)
{
int count_iteration = ((Weigth_Config_Random_Search_conf)conf).Количество_итераций;
int count_generation_by_iteration =
((Weigth_Config_Random_Search_conf)conf).Количество_генерируемых_векторов_веса_за_итерацию;
c_Fuzzy_System result = Classifier;
for (int i = 0; i < count_iteration; i++)
{
double [][] weigth = new double[count_generation_by_iteration + 1][];
weigth[0] = Classifier.Rulles_Database_Set[0].Weigth;
double best_result = result.Classify_Learn_Samples();
int best_index = 0;
for (int j = 1; j < count_generation_by_iteration + 1; j++)
{
weigth[j] = new double[weigth[0].Count()];
for (int k = 0; k < weigth[0].Count(); k++)
{
weigth[j][k] = rand.NextDouble();
}
result.Rulles_Database_Set[0].Weigth = weigth[j];
double current_result = result.Classify_Learn_Samples();
if (current_result > best_result)
{
best_result = current_result;
best_index = j;
}
result.Rulles_Database_Set[0].Weigth = weigth[best_index];
}
}
return(result);
}
public abstract c_Fuzzy_System TuneUpFuzzySystem(c_Fuzzy_System Classifier, Abstract_learn_algorithm_conf conf);
public override c_Fuzzy_System Generate(Fuzzy_system.Class_Pittsburgh.c_Fuzzy_System Classifier, Abstract_generator_conf config)
{
Random rand = new Random();
c_Fuzzy_System result = Classifier;
if (result.Count_Rulles_Databases == 0)
{
Knowlege_base_CRules temp_rules = new Knowlege_base_CRules();
result.Rulles_Database_Set.Add(temp_rules);
}
Type_Term_Func_Enum type_term = ((Generator_Rulles_simple_random_conf)config).Функция_принадлежности;
int stable_terms = (int)((Generator_Rulles_simple_random_conf)config).Тип_Термов;
int count_rules = ((Generator_Rulles_simple_random_conf)config).Количество_правил;
for (int j = 0; j < count_rules; j++)
{
int[] order = new int[result.Count_Vars];
Type_Term_Func_Enum temp_type_term;
if (stable_terms == 0)
{
temp_type_term = type_term;
}
else
{
temp_type_term = Generator_type_term();
}
List <Term> temp_term_list = new List <Term>();
for (int k = 0; k < result.Count_Vars; k++)
{
double[] parametrs = new double[c_Fuzzy_System.Count_Params_For_Term(temp_type_term)];
switch (temp_type_term)
{
case Type_Term_Func_Enum.Треугольник:
parametrs[0] = result.Learn_Samples_set.Attribute_Min(k) + rand.NextDouble() * (result.Learn_Samples_set.Attribute_Max(k) - result.Learn_Samples_set.Attribute_Min(k));
parametrs[1] = result.Learn_Samples_set.Attribute_Min(k) + rand.NextDouble() * (result.Learn_Samples_set.Attribute_Max(k) - result.Learn_Samples_set.Attribute_Min(k));
parametrs[2] = result.Learn_Samples_set.Attribute_Min(k) + rand.NextDouble() * (result.Learn_Samples_set.Attribute_Max(k) - result.Learn_Samples_set.Attribute_Min(k));
Array.Sort(parametrs);
break;
case Type_Term_Func_Enum.Гауссоида: parametrs[0] = result.Learn_Samples_set.Attribute_Min(k) + rand.NextDouble() * (result.Learn_Samples_set.Attribute_Max(k) - result.Learn_Samples_set.Attribute_Min(k));
parametrs[1] = (rand.NextDouble() + 0.01) * 0.5 *
(result.Learn_Samples_set.Attribute_Max(k) -
result.Learn_Samples_set.Attribute_Min(k));
break;
case Type_Term_Func_Enum.Парабола: parametrs[0] = result.Learn_Samples_set.Attribute_Min(k) + rand.NextDouble() * (result.Learn_Samples_set.Attribute_Max(k) - result.Learn_Samples_set.Attribute_Min(k));
parametrs[1] = result.Learn_Samples_set.Attribute_Min(k) + rand.NextDouble() * (result.Learn_Samples_set.Attribute_Max(k) - result.Learn_Samples_set.Attribute_Min(k));
Array.Sort(parametrs);
break;
case Type_Term_Func_Enum.Трапеция: parametrs[0] = result.Learn_Samples_set.Attribute_Min(k) + rand.NextDouble() * (result.Learn_Samples_set.Attribute_Max(k) - result.Learn_Samples_set.Attribute_Min(k));
parametrs[1] = result.Learn_Samples_set.Attribute_Min(k) + rand.NextDouble() * (result.Learn_Samples_set.Attribute_Max(k) - result.Learn_Samples_set.Attribute_Min(k));
parametrs[2] = result.Learn_Samples_set.Attribute_Min(k) + rand.NextDouble() * (result.Learn_Samples_set.Attribute_Max(k) - result.Learn_Samples_set.Attribute_Min(k));
parametrs[3] = result.Learn_Samples_set.Attribute_Min(k) + rand.NextDouble() * (result.Learn_Samples_set.Attribute_Max(k) - result.Learn_Samples_set.Attribute_Min(k));
Array.Sort(parametrs);
break;
}
Term temp_term = new Term(parametrs, temp_type_term, k);
result.Rulles_Database_Set[0].Terms_Set.Add(temp_term);
temp_term_list.Add(temp_term);
order[k] = result.Rulles_Database_Set[0].Terms_Set.Count - 1;
}
string class_label = result.Nearest_Class(temp_term_list);
CRule temp_Rule = new CRule(result.Rulles_Database_Set[0].Terms_Set, order, class_label, 1.0);
result.Rulles_Database_Set[0].Rules_Database.Add(temp_Rule);
}
result.unlaid_protection_fix();
return(result);
}
public static c_Fuzzy_System load_UFS(this c_Fuzzy_System Classifier, string file_name)
{
c_Fuzzy_System result = Classifier;
Knowlege_base_CRules New_dataBase = new Knowlege_base_CRules();
List <string> added_term = new List <string>();
XmlDocument Source = new XmlDocument();
Source.Load(file_name);
XmlNode rulles_node = Source.DocumentElement.SelectSingleNode("descendant::Rules");
if (rulles_node == null)
{
throw new System.FormatException("Нет базы правил в ufs файле");
}
int count_rulles = XmlConvert.ToInt32(rulles_node.Attributes.GetNamedItem("Count").Value);
XmlNode varibles_node = Source.DocumentElement.SelectSingleNode("descendant::Variables");
if (varibles_node == null)
{
throw new System.FormatException("Нет термов в базе правил, ошибка UFS");
}
for (int i = 0; i < count_rulles; i++)
{
XmlNode antecedent_node = rulles_node.ChildNodes[i].SelectSingleNode("Antecedent");
int count_antecedent_term = XmlConvert.ToInt32(antecedent_node.Attributes.GetNamedItem("Count").Value);
int [] Order_term = new int[count_antecedent_term];
for (int j = 0; j < count_antecedent_term; j++)
{
double[] Value_temp;
Type_Term_Func_Enum type_term = Type_Term_Func_Enum.Треугольник;
int num_var = Classifier.Learn_Samples_set.Input_Attributes.IndexOf(Classifier.Learn_Samples_set.Input_Attributes.Find(x => x.Name.Equals(antecedent_node.ChildNodes[j].Attributes.GetNamedItem("Variable").Value, StringComparison.OrdinalIgnoreCase)));
string name_term = antecedent_node.ChildNodes[j].Attributes.GetNamedItem("Term").Value;
if (added_term.Contains(name_term))
{
Order_term[j] = added_term.IndexOf(name_term);
}
else
{
XmlNode term_node = varibles_node.SelectSingleNode("descendant::Term[@Name='" + name_term + "']");
int count_MB = 0;
switch (term_node.Attributes.GetNamedItem("Type").Value)
{
case "Triangle": { count_MB = 3; type_term = Type_Term_Func_Enum.Треугольник; break; }
case "Gauss": { count_MB = 2; type_term = Type_Term_Func_Enum.Гауссоида; break; }
case "Parabolic": { count_MB = 2; type_term = Type_Term_Func_Enum.Парабола; break; }
case "Trapezoid": { count_MB = 4; type_term = Type_Term_Func_Enum.Трапеция; break; }
}
Value_temp = new double[count_MB];
term_node = term_node.SelectSingleNode("Params");
for (int p = 0; p < count_MB; p++)
{
string tett = term_node.ChildNodes[p].Attributes.GetNamedItem("Number").Value;
int number_param = XmlConvert.ToInt32(term_node.ChildNodes[p].Attributes.GetNamedItem("Number").Value);
Value_temp[number_param] = XmlConvert.ToDouble(term_node.ChildNodes[p].Attributes.GetNamedItem("Value").Value);
}
Term temp_term = new Term(Value_temp, type_term, num_var);
New_dataBase.Terms_Set.Add(temp_term);
added_term.Add(name_term);
Order_term[j] = New_dataBase.Terms_Set.Count - 1;
}
}
XmlNode consequnt_node = rulles_node.ChildNodes[i].SelectSingleNode("Consequent");
string Classifier_value = consequnt_node.Attributes.GetNamedItem("Class").Value;
double Classifier_weigth = XmlConvert.ToDouble(consequnt_node.Attributes.GetNamedItem("CF").Value);
CRule temp_rule = new CRule(New_dataBase.Terms_Set, Order_term, Classifier_value, Classifier_weigth);
New_dataBase.Rules_Database.Add(temp_rule);
}
result.Rulles_Database_Set.Clear();
result.Rulles_Database_Set.Add(New_dataBase);
GC.Collect();
return(result);
}
public override Fuzzy_system.Class_Pittsburgh.c_Fuzzy_System TuneUpFuzzySystem(Fuzzy_system.Class_Pittsburgh.c_Fuzzy_System Classifier, Abstract_learn_algorithm_conf conf)
{
count_iteration = ((Term_Config_PSO_Search_conf)conf).Количество_итераций;
c1 = ((Term_Config_PSO_Search_conf)conf).Коэффициент_c1;
c2 = ((Term_Config_PSO_Search_conf)conf).Коэффициент_c2;
w = 1;
count_particle = ((Term_Config_PSO_Search_conf)conf).Особей_в_популяции;
c_Fuzzy_System result = Classifier;
Knowlege_base_CRules[] X = new Knowlege_base_CRules[count_particle];
Knowlege_base_CRules[] V = new Knowlege_base_CRules[count_particle];
Knowlege_base_CRules[] Pi = new Knowlege_base_CRules[count_particle];
Knowlege_base_CRules Pg = new Knowlege_base_CRules();
double[] Errors = new double[count_particle];
double[] OldErrors = new double[count_particle];
double minError = 0;
Random rnd = new Random();
for (int i = 0; i < count_particle; i++)
{
Knowlege_base_CRules temp_c_Rule = new Knowlege_base_CRules(result.Rulles_Database_Set[0]);
X[i] = temp_c_Rule;
Errors[i] = result.Classify_Learn_Samples(0);
OldErrors[i] = Errors[i];
Pi[i] = new Knowlege_base_CRules(X[i]);
V[i] = new Knowlege_base_CRules(X[i]);
//
for (int j = 0; j < V[i].Terms_Set.Count; j++)
{
for (int k = 0; k < c_Fuzzy_System.Count_Params_For_Term(V[i].Terms_Set[j].Term_Func_Type); k++)
{
if (i == 0)
{
V[i].Terms_Set[j].Parametrs[k] = 0;
}
else
{
V[i].Terms_Set[j].Parametrs[k] = rnd.NextDouble() - 0.5;
}
}
double[] bf = new double[V[i].Weigth.Length];
for (int k = 0; k < V[i].Weigth.Length; k++)
{
if (i == 0)
{
bf[k] = 1;
}
else
{
//System.Windows.Forms.MessageBox.Show(rnd.NextDouble().ToString());
bf[k] = rnd.NextDouble() / 200;
}
}
V[i].Weigth = bf;
}
}
Pg = new Knowlege_base_CRules(result.Rulles_Database_Set[0]);
minError = Errors[0];
for (int i = 0; i < count_iteration; i++)
{
for (int j = 0; j < count_particle; j++)
{
w = 1 / (1 + Math.Exp(-(Errors[j] - OldErrors[j]) / 0.01));
for (int k = 0; k < X[j].Terms_Set.Count; k++)
{
for (int q = 0; q < c_Fuzzy_System.Count_Params_For_Term(X[j].Terms_Set[k].Term_Func_Type); q++)
{
double bp = Pi[j].Terms_Set[k].Parametrs[q];
V[j].Terms_Set[k].Parametrs[q] = V[j].Terms_Set[k].Parametrs[q] * w + c1 * rnd.NextDouble() * (bp - X[j].Terms_Set[k].Parametrs[q]) +
c2 * rnd.NextDouble() * (Pg.Terms_Set[k].Parametrs[q] - X[j].Terms_Set[k].Parametrs[q]);
X[j].Terms_Set[k].Parametrs[q] += V[j].Terms_Set[k].Parametrs[q];
}
}
double[] bf = new double[V[j].Weigth.Length];
double[] bfw = new double[V[j].Weigth.Length];
for (int k = 0; k < V[j].Weigth.Length; k++)
{
bfw[k] = V[j].Weigth[k] * w + c1 * rnd.NextDouble() * (Pi[j].Weigth[k] - X[j].Weigth[k]) +
c2 * rnd.NextDouble() * (Pg.Weigth[k] - X[j].Weigth[k]);
double sw = X[j].Weigth[k] + bfw[k];
if (sw > 0 && sw <= 2)
{
bf[k] = sw;
}
else
{
bf[k] = X[j].Weigth[k];
bfw[k] = V[j].Weigth[k];
}
}
X[j].Weigth = bf;
V[j].Weigth = bfw;
double newError = 0;
result.Rulles_Database_Set.Add(X[j]);
int temp_index = result.Rulles_Database_Set.Count - 1;
bool success = true;
try
{
newError = result.Classify_Learn_Samples(temp_index);
}
catch (Exception)
{
success = false;
}
result.Rulles_Database_Set.RemoveAt(temp_index);
if (success && (newError > Errors[j]))
{
OldErrors[j] = Errors[j];
Errors[j] = newError;
Pi[j] = new Knowlege_base_CRules(X[j]);
}
if (minError < newError)
{
minError = newError;
Pg = new Knowlege_base_CRules(X[j]);
}
}
}
result.Rulles_Database_Set[0] = Pg;
return(result);
}
public static c_Fuzzy_System load_UFS(string file_name)
{
c_Fuzzy_System result = null;
return(result);
}
private static void write_about_table(XmlWriter writer, c_samples_set samplesSet, c_Fuzzy_System Classifier)
{
writer.WriteStartElement("Table");
writer.WriteAttributeString("Name", samplesSet.File_Name.Remove(samplesSet.File_Name.Length - 4, 4));
if (samplesSet == Classifier.Learn_Samples_set)
{
writer.WriteAttributeString("Type", "Training");
}
else
{
writer.WriteAttributeString("Type", "Testing");
}
writer.WriteAttributeString("Output", samplesSet.Output_Attributes.Name);
writer.WriteStartElement("Attributes");
writer.WriteAttributeString("Count", XmlConvert.ToString(samplesSet.Count_Vars));
for (int i = 0; i < samplesSet.Count_Vars; i++)
{
write_about_attribute(writer, samplesSet.Input_Attribute(i));
}
write_about_attribute(writer, samplesSet.Output_Attributes);
writer.WriteEndElement();
write_about_rows(writer, samplesSet);
writer.WriteEndElement();
}
abstract public c_Fuzzy_System Generate(c_Fuzzy_System Classifier, Abstract_generator_conf config);
