public NaiveBayesClassifier(DataSample[] samples, int classes, ColumnDataType[] columnDataTypes)
{
_classes = classes;
_distribution = new IDistribution[classes, columnDataTypes.Length];
_classesProbablityDistribution = new CategoricalDistribution(
samples.Select(item => item.ClassId).ToArray(), classes);
var splitDataPerClass = SplitDataPerClass(samples, _classes, columnDataTypes.Length);
var groups = GetClassGroups(samples, _classes);
for (int index = 0; index < columnDataTypes.Length; index++)
{
//var values = GetDataPerClass(samples, _classes, index);
Double[][] values = new double[classes][];
for (int classIndex = 0; classIndex < classes; classIndex++)
{
values[classIndex] = splitDataPerClass[index, classIndex];
}
//var values = splitDataPerClass[index,_]
if (values.All(item => item == null))
{
continue;
}
for (int classIndex = 0; classIndex < classes; classIndex++)
{
var itemsOnClass = values[classIndex] ?? new double[0];
if (!columnDataTypes[index].IsDiscrete)
{
_distribution[classIndex, index] = new GaussianDistribution(itemsOnClass);
}
else
{
_distribution[classIndex, index] =
new CategoricalDistribution(itemsOnClass.Select(Convert.ToInt32).ToArray(),
columnDataTypes[index].NumberOfCategories, groups[classIndex]);
}
}
}
}
private void BuildSymbols()
{
_labelsDictionary = new Dictionary <string, int> [Attributes.Length];
ColumnDataTypes = new ColumnDataType[Attributes.Length];
var noOfRows = Count;
for (int index = 0; index < Attributes.Length; index++)
{
if (_labelsDictionary[index] == null)
{
_labelsDictionary[index] = new Dictionary <string, int>();
}
if (this[0, index].IsNumeric())
{
ColumnDataTypes[index] = new ColumnDataType();
continue;
}
var symbols = _labelsDictionary[index];
var newSymbol = 0;
for (int rowIndex = 0; rowIndex < noOfRows; rowIndex++)
{
var currentValue = this[rowIndex, index].ToString();
if (!symbols.ContainsKey(currentValue))
{
symbols.Add(currentValue, newSymbol);
newSymbol++;
}
}
ColumnDataTypes[index] = new ColumnDataType {
IsDiscrete = true, NumberOfCategories = newSymbol
};
}
}
