public SparseVectorClassification AsClassification(StringTableBuilder stringTable)
{
var weightedIndex = new List <WeightedIndex>();
foreach (var item in Keyword)
{
weightedIndex.Add(new WeightedIndex {
Index = stringTable.GetIndex(item),
Weight = 1f
});
}
foreach (var item in Topic)
{
weightedIndex.Add(new WeightedIndex {
Index = stringTable.GetIndex(item),
Weight = 1f
});
}
return(new SparseVectorClassification {
Name = Title,
Data = weightedIndex
.GroupBy(d => d.Index)
.Select(g => new WeightedIndex {
Index = g.Key,
Weight = g.Sum(d => d.Weight)
})
.ToArray()
});
}
public (string Classification, WeightedIndexList Data) AsClassification(StringTableBuilder stringTable)
{
var weightedIndex = new List <WeightedIndexList.WeightedIndex>();
foreach (var item in Keyword)
{
weightedIndex.Add(new WeightedIndexList.WeightedIndex {
Index = stringTable.GetIndex(item),
Weight = 1f
});
}
foreach (var item in Topic)
{
weightedIndex.Add(new WeightedIndexList.WeightedIndex {
Index = stringTable.GetIndex(item),
Weight = 1f
});
}
return(Title, new WeightedIndexList {
IndexList = weightedIndex
.GroupBy(d => d.Index)
.Select(g => new WeightedIndexList.WeightedIndex {
Index = g.Key,
Weight = g.Sum(d => d.Weight)
})
.ToArray()
});
}
static IReadOnlyList <(string Classification, IndexList Data)> _BuildIndexedClassifications(IReadOnlyList <Tuple <string[], string> > data, StringTableBuilder stringTable)
{
return(data
.Select(d => (d.Item2, IndexList.Create(d.Item1.Select(str => stringTable.GetIndex(str)).ToArray())))
.ToList()
);
}
public void TestTFIDF()
{
var stringTableBuilder = new StringTableBuilder();
var bag = new ClassificationBag {
Classification = new[] {
Tuple.Create(new[] { "Chinese", "Beijing", "Chinese" }, true),
Tuple.Create(new[] { "Chinese", "Chinese", "Shanghai" }, true),
Tuple.Create(new[] { "Chinese", "Macao" }, true),
Tuple.Create(new[] { "Tokyo", "Japan", "Chinese" }, false),
}.Select(d => new IndexedClassification {
Name = d.Item2 ? "china" : "japan",
Data = d.Item1.Select(s => stringTableBuilder.GetIndex(s)).ToArray()
}).ToArray()
};
Assert.AreEqual(bag.Classification.Length, 4);
Assert.AreEqual(bag.Classification[0].Data.Length, 3);
var set = bag.ConvertToSparseVectors(true);
Assert.AreEqual(set.Classification.Length, 2);
Assert.AreEqual(set.Classification[0].Data.Length, 4);
var tfidf = set.TFIDF();
Assert.AreEqual(tfidf.Classification.Length, 2);
Assert.AreEqual(tfidf.Classification[0].Data.Length, 4);
}
static ClassificationBag _BuildClassificationBag(IReadOnlyList <Tuple <string[], string> > data, StringTableBuilder stringTable)
{
return(new ClassificationBag {
Classification = data.Select(d => new IndexedClassification {
Name = d.Item2,
Data = d.Item1.Select(str => stringTable.GetIndex(str)).ToArray()
}).ToArray()
});
}
public static ClassificationBag GetSimpleChineseSet(StringTableBuilder stringTableBuilder)
{
// sample data from: http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html
return(new ClassificationBag {
Classification = new[] {
Tuple.Create(new[] { "Chinese", "Beijing", "Chinese" }, true),
Tuple.Create(new[] { "Chinese", "Chinese", "Shanghai" }, true),
Tuple.Create(new[] { "Chinese", "Macao" }, true),
Tuple.Create(new[] { "Tokyo", "Japan", "Chinese" }, false),
}.Select(d => new IndexedClassification {
Name = d.Item2 ? "china" : "japan",
Data = d.Item1.Select(s => stringTableBuilder.GetIndex(s)).ToArray()
}).ToArray()
});
}
public static IReadOnlyList <uint> GetTestRow(StringTableBuilder stringTableBuilder)
{
return(new[] { "Chinese", "Chinese", "Chinese", "Tokyo", "Japan" }.Select(s => stringTableBuilder.GetIndex(s)).ToArray());
}
