public void LargeRunTest()
{
#region doc_nursery
// This example uses the Nursery Database available from the University of
// California Irvine repository of machine learning databases, available at
//
// http://archive.ics.uci.edu/ml/machine-learning-databases/nursery/nursery.names
//
// The description paragraph is listed as follows.
//
// Nursery Database was derived from a hierarchical decision model
// originally developed to rank applications for nursery schools. It
// was used during several years in 1980's when there was excessive
// enrollment to these schools in Ljubljana, Slovenia, and the
// rejected applications frequently needed an objective
// explanation. The final decision depended on three subproblems:
// occupation of parents and child's nursery, family structure and
// financial standing, and social and health picture of the family.
// The model was developed within expert system shell for decision
// making DEX (M. Bohanec, V. Rajkovic: Expert system for decision
// making. Sistemica 1(1), pp. 145-157, 1990.).
//
// Let's begin by loading the raw data. This string variable contains
// the contents of the nursery.data file as a single, continuous text.
//
string nurseryData = Resources.nursery;
// Those are the input columns available in the data
//
string[] inputColumns =
{
"parents", "has_nurs", "form", "children",
"housing", "finance", "social", "health"
};
// And this is the output, the last column of the data.
//
string outputColumn = "output";
// Let's populate a data table with this information.
//
DataTable table = new DataTable("Nursery");
table.Columns.Add(inputColumns);
table.Columns.Add(outputColumn);
string[] lines = nurseryData.Split(
new[] { Environment.NewLine }, StringSplitOptions.None);
foreach (var line in lines)
table.Rows.Add(line.Split(','));
// Now, we have to convert the textual, categorical data found
// in the table to a more manageable discrete representation.
//
// For this, we will create a codebook to translate text to
// discrete integer symbols:
//
Codification codebook = new Codification(table);
// And then convert all data into symbols
//
DataTable symbols = codebook.Apply(table);
double[][] inputs = symbols.ToArray(inputColumns);
int[] outputs = symbols.ToArray<int>(outputColumn);
// From now on, we can start creating the decision tree.
//
var attributes = DecisionVariable.FromCodebook(codebook, inputColumns);
DecisionTree tree = new DecisionTree(attributes, classes: 5);
// Now, let's create the C4.5 algorithm
C45Learning c45 = new C45Learning(tree);
// and learn a decision tree. The value of
// the error variable below should be 0.
//
double error = c45.Run(inputs, outputs);
// To compute a decision for one of the input points,
// such as the 25-th example in the set, we can use
//
int y = tree.Compute(inputs[25]);
#endregion
Assert.AreEqual(0, error);
for (int i = 0; i < inputs.Length; i++)
{
int expected = outputs[i];
int actual = tree.Compute(inputs[i]);
Assert.AreEqual(expected, actual);
}
#if !NET35
// Finally, we can also convert our tree to a native
// function, improving efficiency considerably, with
//
Func<double[], int> func = tree.ToExpression().Compile();
// Again, to compute a new decision, we can just use
//
int z = func(inputs[25]);
for (int i = 0; i < inputs.Length; i++)
{
int expected = outputs[i];
int actual = func(inputs[i]);
Assert.AreEqual(expected, actual);
}
#endif
}
private string C45(DataTable tbl)
{
int classCount = 2;
Codification codebook = new Codification(tbl);
DecisionVariable[] attributes ={
new DecisionVariable("Clump Thickness",10),
new DecisionVariable("Uniformity of Cell Size",10),new DecisionVariable("Uniformity of Cell Shape",10),
new DecisionVariable("Marginal Adhesion",10),new DecisionVariable("Single Epithelial Cell Size",10),
new DecisionVariable("Bare Nuclei",10),new DecisionVariable("Bland Chromatin",10),
new DecisionVariable("Normal Nucleoli",10),new DecisionVariable("Mitoses",10),
};
DecisionTree tree = new DecisionTree(attributes, classCount);
// ID3Learning id3learning = new ID3Learning(tree);
// Translate our training data into integer symbols using our codebook:
DataTable symbols = codebook.Apply(tbl);
double[][] inputs = symbols.ToIntArray("Clump Thickness", "Uniformity of Cell Size", "Uniformity of Cell Shape", "Marginal Adhesion", "Single Epithelial Cell Size", "Bare Nuclei", "Bland Chromatin", "Normal Nucleoli", "Mitoses").ToDouble();
int[] outputs = symbols.ToIntArray("Class").GetColumn(0);
// symbols.
// id3learning.Run(inputs, outputs);
// Now, let's create the C4.5 algorithm
C45Learning c45 = new C45Learning(tree);
// and learn a decision tree. The value of
// the error variable below should be 0.
//
double error = c45.Run(inputs, outputs);
// To compute a decision for one of the input points,
// such as the 25-th example in the set, we can use
//
int y = tree.Compute(inputs[5]);
// Finally, we can also convert our tree to a native
// function, improving efficiency considerably, with
//
Func<double[], int> func = tree.ToExpression().Compile();
// Again, to compute a new decision, we can just use
//
int z = func(inputs[5]);
int[] query = codebook.Translate(inputlar[0], inputlar[1], inputlar[2], inputlar[3],
inputlar[4], inputlar[5], inputlar[6], inputlar[7], inputlar[8]);
int output = tree.Compute(query);
string answer = codebook.Translate("Class", output);
return answer;
// throw new NotImplementedException();
}
public void Run(String filename)
{
ReadFile(filename);
// Now, we have to convert the textual, categorical data found
// in the table to a more manageable discrete representation.
//
// For this, we will create a codebook to translate text to
// discrete integer symbols:
//
Codification codebook = new Codification(data);
// And then convert all data into symbols
//
DataTable symbols = codebook.Apply(data);
for (int i = 0; i < inputColumns.Count; i++)
if (inputTypes[i] == "string")
CreateDic(inputColumns[i], symbols);
CreateDic(outputColumn, symbols);
double[][] inputs = (from p in symbols.AsEnumerable()
select GetInputRow(p)
).Cast<double[]>().ToArray();
int[] outputs = (from p in symbols.AsEnumerable()
select GetIndex(outputColumn, p[outputColumn].ToString())).Cast<int>().ToArray();
// From now on, we can start creating the decision tree.
//
var attributes = DecisionVariable.FromCodebook(codebook, inputColumns.ToArray());
DecisionTree tree = new DecisionTree(attributes, 5); //outputClasses: 5
// Now, let's create the C4.5 algorithm
C45Learning c45 = new C45Learning(tree);
// and learn a decision tree. The value of
// the error variable below should be 0.
//
double error = c45.Run(inputs, outputs);
// To compute a decision for one of the input points,
// such as the 25-th example in the set, we can use
//
//int y = tree.Compute(inputs[25]);
// Finally, we can also convert our tree to a native
// function, improving efficiency considerably, with
//
//Func<double[], int> func = tree.ToExpression().Compile();
// Again, to compute a new decision, we can just use
//
//int z = func(inputs[25]);
var expression = tree.ToExpression();
Console.WriteLine(tree.ToCode("ClassTest"));
DecisionSet s = tree.ToRules();
Console.WriteLine(s.ToString());
}
public void Run(String filename)
{
ReadFile(filename);
// Create a new codification codebook to
// convert strings into integer symbols
Codification codebook = new Codification(data, inputColumns.ToArray());
// Translate our training data into integer symbols using our codebook:
DataTable symbols = codebook.Apply(data);
foreach (String s in inputColumns)
CreateDic(s, symbols);
CreateDic(outputColumn, symbols);
int[][] inputs = (from p in symbols.AsEnumerable()
select GetInputRow(p)
).Cast<int[]>().ToArray();
int[] outputs = (from p in symbols.AsEnumerable()
select GetIndex(outputColumn, p[outputColumn].ToString())).Cast<int>().ToArray();
// Gather information about decision variables
DecisionVariable[] attributes = GetDecisionVariables();
int classCount = GetCount(outputColumn); // 2 possible output values for playing tennis: yes or no
//Create the decision tree using the attributes and classes
DecisionTree tree = new DecisionTree(attributes, classCount);
// Create a new instance of the ID3 algorithm
ID3Learning id3learning = new ID3Learning(tree);
//C45Learning c45learning = new C45Learning(tree);
// Learn the training instances!
id3learning.Run(inputs, outputs);
//c45learning.Run(inputs2, outputs);
/*
string answer = codebook.Translate(outputColumn,
tree.Compute(codebook.Translate("Sunny", "Hot", "High", "Strong")));
Console.WriteLine("Calculate for: Sunny, Hot, High, Strong");
Console.WriteLine("Answer: " + answer);
*/
var expression = tree.ToExpression();
Console.WriteLine(tree.ToCode("ClassTest"));
DecisionSet rules = tree.ToRules();
Console.WriteLine(rules.ToString());
// Compiles the expression to IL
var func = expression.Compile();
}
public void Run()
{
DataTable data = new DataTable("Mitchell's Tennis Example");
data.Columns.Add("Day");
data.Columns.Add("Outlook");
data.Columns.Add("Temperature");
data.Columns.Add("Humidity");
data.Columns.Add("Wind");
data.Columns.Add("PlayTennis");
data.Rows.Add("D1", "Sunny", "Hot", "High", "Weak", "No");
data.Rows.Add("D2", "Sunny", "Hot", "High", "Strong", "No");
data.Rows.Add("D3", "Overcast", "Hot", "High", "Weak", "Yes");
data.Rows.Add("D4", "Rain", "Mild", "High", "Weak", "Yes");
data.Rows.Add("D5", "Rain", "Cool", "Normal", "Weak", "Yes");
data.Rows.Add("D6", "Rain", "Cool", "Normal", "Strong", "No");
data.Rows.Add("D7", "Overcast", "Cool", "Normal", "Strong", "Yes");
data.Rows.Add("D8", "Sunny", "Mild", "High", "Weak", "No");
data.Rows.Add("D9", "Sunny", "Cool", "Normal", "Weak", "Yes");
data.Rows.Add("D10", "Rain", "Mild", "Normal", "Weak", "Yes");
data.Rows.Add("D11", "Sunny", "Mild", "Normal", "Strong", "Yes");
data.Rows.Add("D12", "Overcast", "Mild", "High", "Strong", "Yes");
data.Rows.Add("D13", "Overcast", "Hot", "Normal", "Weak", "Yes");
data.Rows.Add("D14", "Rain", "Mild", "High", "Strong", "No");
// Create a new codification codebook to
// convert strings into integer symbols
Codification codebook = new Codification(data, "Outlook", "Temperature", "Humidity", "Wind", "PlayTennis");
// Translate our training data into integer symbols using our codebook:
DataTable symbols = codebook.Apply(data);
CreateDic("Outlook", symbols);
CreateDic("Temperature", symbols);
CreateDic("Humidity", symbols);
CreateDic("Wind", symbols);
CreateDic("PlayTennis", symbols);
int[][] inputs = (from p in symbols.AsEnumerable()
select new int[]
{
GetIndex("Outlook", p["Outlook"].ToString()),
GetIndex("Temperature", p["Temperature"].ToString()),
GetIndex("Humidity", p["Humidity"].ToString()),
GetIndex("Wind", p["Wind"].ToString())
}).Cast<int[]>().ToArray();
int[] outputs = (from p in symbols.AsEnumerable()
select GetIndex("PlayTennis", p["PlayTennis"].ToString())).Cast<int>().ToArray();
/*
// Gather information about decision variables
DecisionVariable[] attributes =
{
new DecisionVariable("Outlook", 3), // 3 possible values (Sunny, overcast, rain)
new DecisionVariable("Temperature", 3), // 3 possible values (Hot, mild, cool)
new DecisionVariable("Humidity", 2), // 2 possible values (High, normal)
new DecisionVariable("Wind", 2) // 2 possible values (Weak, strong)
};
*/
DecisionVariable[] attributes =
{
new DecisionVariable("Outlook", GetCount("Outlook")), // 3 possible values (Sunny, overcast, rain)
new DecisionVariable("Temperature", GetCount("Temperature")), // 3 possible values (Hot, mild, cool)
new DecisionVariable("Humidity", GetCount("Humidity")), // 2 possible values (High, normal)
new DecisionVariable("Wind", GetCount("Wind")) // 2 possible values (Weak, strong)
};
int classCount = GetCount("PlayTennis"); // 2 possible output values for playing tennis: yes or no
//Create the decision tree using the attributes and classes
DecisionTree tree = new DecisionTree(attributes, classCount);
// Create a new instance of the ID3 algorithm
ID3Learning id3learning = new ID3Learning(tree);
// Learn the training instances!
id3learning.Run(inputs, outputs);
string answer = codebook.Translate("PlayTennis",
tree.Compute(codebook.Translate("Sunny", "Hot", "High", "Strong")));
Console.WriteLine("Calculate for: Sunny, Hot, High, Strong");
Console.WriteLine("Answer: " + answer);
var expression = tree.ToExpression();
Console.WriteLine(tree.ToCode("ClassTest"));
DecisionSet s = tree.ToRules();
Console.WriteLine(s.ToString());
// Compiles the expression to IL
var func = expression.Compile();
}
/// <summary>
/// The main entry point for the program
/// </summary>
public static void Main()
{
try
{
#region Exploratory Data Analysis Explanation
/*
John Tukey coined the term Exploratory Data Analysis in his seminal book of the same name. There really is not a prescribed way to do an EDA.
Tools I use for EDA include Microsoft Excel, plots and visual inspection of the data. Without creating an early bias, gut feelings do play a role in a good EDA.
Some objectives of EDA are to:
• Identify the types of data in the dataset
• Examine the statistical properties of the data
• Look for invalid data (may need Domain or Subject Matter experts)
• Understand the provenance of the data
• Aide in the selection of appropriate statistical tools and techniques
For our diabetes dataset, notice that there is both quantitative and qualitative data. Note that the result or outcome variable (which indicates if the person has
diabetes) is nominal data with only two states. This is called dichotomous or binary categorical data which rules out some machine learning algorithms and directs
us to others.
*/
#endregion
// Because of time constraints, the loading of the DataTables and EDA is complete.
XmlConfigurator.Configure();
Logger.Info("Exploratory Data Analysis");
FileInfo fi = new FileInfo("training.csv");
DataTable training = DataTableCsvConvertor.GetDataTableFromCsv(fi);
fi = new FileInfo("test.csv");
DataTable test = DataTableCsvConvertor.GetDataTableFromCsv(fi);
// Print out the first few table rows.
Head.PrintHead(training);
//Logger.Info(string.Empty);
//BasicStatistics.BasicStats(training); // For most EDA's Basic Descriptive statistics are important, but this outputs a lot of information
#region Data Imputation & Cleanup Explanation
/*
Keep in mind that Machine Learning algorithms operate on numerical data only, something will have to be done with the data is text or NULL. Also predictor
variables(aka features or columns of data) that do not vary will not be predictive and may need to be removed. Due to time constraints the EDA, ETL (Extract, Transform and Load)
and data cleaning is already completed in the solution. For this analysis, the HeartRate column because it is all NULL and remove any rows of data that contain NULLs.
*/
#endregion
// Delete any columns that are not needed.
training.Columns.Remove("HeartRate");
test.Columns.Remove("HeartRate");
// How to handle rows containing missing or NA data - data imputation or deletion?
training = DataImputation.RemoveMissing(training);
test = DataImputation.RemoveMissing(test);
Codification codebook = new Codification(training);
int outputClasses = 2;
string[] inputColumns =
{
"Gender", "YearOfBirth", "SmokingEffectiveYear", "NISTcode", "Height", "Weight", "BMI", "SystolicBP", "DiastolicBP", "RespiratoryRate", "Temperature"
};
string outputColumn = "DMIndicator";
// Translate our training data into integer symbols using our codebook:
DataTable symbols = codebook.Apply(training);
double[][] inputs = symbols.ToArray(inputColumns);
int[] outputs = Matrix.ToArray<int>(training, outputColumn);
#region Decision Tree Overview
/*
Decision Trees are very powerful, especially with a binary classification model, and are somewhat resistant to over-fitting the data.
Additionally, they are intuitive to explain to stakeholders.
*/
#endregion
Logger.Info(string.Empty);
Logger.Info("Decision Tree");
DecisionVariable[] attributes =
{
new DecisionVariable("Gender", 2), // 2 possible values (Male, Female)
new DecisionVariable("YearOfBirth", DecisionVariableKind.Continuous),
new DecisionVariable("SmokingEffectiveYear", DecisionVariableKind.Continuous),
new DecisionVariable("NISTcode", DecisionVariableKind.Continuous),
new DecisionVariable("Height", DecisionVariableKind.Continuous),
new DecisionVariable("Weight", DecisionVariableKind.Continuous),
new DecisionVariable("BMI", DecisionVariableKind.Continuous),
new DecisionVariable("SystolicBP", DecisionVariableKind.Continuous),
new DecisionVariable("DiastolicBP", DecisionVariableKind.Continuous),
new DecisionVariable("RespiratoryRate", DecisionVariableKind.Continuous),
new DecisionVariable("Temperature", DecisionVariableKind.Continuous)
};
DecisionTree tree = new DecisionTree(attributes, outputClasses);
C45Learning c45learning = new C45Learning(tree);
// Learn the training instances!
c45learning.Run(inputs, outputs);
// The next two lines are optional to save the model into IL for future use.
// Convert to an expression tree
var expression = tree.ToExpression();
// Compiles the expression to IL
var func = expression.Compile();
#region Evaluation Explanation
/*
To evaluate the model, now use each row of the test dataset to predict the output variable (DMIndicator) using the DecisionTree’s compute method passing in the same
variables that were used to train the model. Store the test dataset’s value of DMIndicator and the predicted value in a DataTable and integer collection for future
validation of the model.
*/
#endregion
Evaluator.Evaluate(test, tree);
#region Validation Explanation
/*
There are many ways to validate models, but we will use a confusion matrix because it is intuitive and a very accepted way to validate binary classification models.
Most conveniently the Accord.Net has a ConfusionMatrix class to create this matrix for you. Passing in the collection of integers of predicted and actual values
stored earlier to the ConfusionMatrix class and output the matrix and accuracy.
*/
#endregion
Validator.Validate(test, tree);
#region Support Vector Machine Overview
/*
Support Vector Machines are powerful classification machine learning algorithms with very few knobs to turn. The kernel of the SVM can be exchanged to use
a number of different mathematical algorithms including polynomials, neural networks and Gaussian functions.
*/
#endregion
Logger.Info(string.Empty);
Logger.Info("Support Vector Machine");
// Add SVM code here
IKernel kernel = new Linear();
// Create the Multi-class Support Vector Machine using the selected Kernel
int inputDimension = inputs[0].Length;
var ksvm = new MulticlassSupportVectorMachine(inputDimension, kernel, outputClasses);
// Create the learning algorithm using the machine and the training data
var ml = new MulticlassSupportVectorLearning(ksvm, inputs, outputs)
{
Algorithm = (svm, classInputs, classOutputs, i, j) =>
{
return new SequentialMinimalOptimization(svm, classInputs, classOutputs)
{
CacheSize = 0
};
}
};
double svmError = ml.Run();
#region Evaluation Explanation
/*
To evaluate the model, now use each row of the test dataset to predict the output variable (DMIndicator) using the DecisionTree’s compute method passing in the same
variables that were used to train the model. Store the test dataset’s value of DMIndicator and the predicted value in a DataTable and integer collection for future
validation of the model.
*/
#endregion
Evaluator.Evaluate(test, ksvm);
#region Validation Explanation
/*
There are many ways to validate models, but we will use a confusion matrix because it is intuitive and a very accepted way to validate binary classification models.
Most conveniently the Accord.Net has a ConfusionMatrix class to create this matrix for you. Passing in the collection of integers of predicted and actual values
stored earlier to the ConfusionMatrix class and output the matrix and accuracy.
*/
#endregion
Validator.Validate(test, ksvm);
}
catch (Exception ex)
{
Logger.Error(ex.ToString());
}
}