func TestChiMergeDiscretization(t *testing.T) {
Convey("Chi-Merge Discretization", t, func() {
chimDatasetPath := "../examples/datasets/chim.csv"
Convey(fmt.Sprintf("With the '%s' dataset", chimDatasetPath), func() {
instances, err := base.ParseCSVToInstances(chimDatasetPath, true)
So(err, ShouldBeNil)
_, rows := instances.Size()
frequencies := chiMerge(instances, instances.AllAttributes()[0], 0.9, 0, rows)
values := []float64{}
for _, entry := range frequencies {
values = append(values, entry.Value)
}
Convey("Computes frequencies correctly", func() {
So(values, ShouldResemble, []float64{1.3, 56.2, 87.1})
})
})
irisHeadersDatasetpath := "../examples/datasets/iris_headers.csv"
Convey(fmt.Sprintf("With the '%s' dataset", irisHeadersDatasetpath), func() {
instances, err := base.ParseCSVToInstances(irisHeadersDatasetpath, true)
So(err, ShouldBeNil)
Convey("Sorting the instances first", func() {
allAttributes := instances.AllAttributes()
sortedAttributesSpecs := base.ResolveAttributes(instances, allAttributes)[0:1]
sortedInstances, err := base.Sort(instances, base.Ascending, sortedAttributesSpecs)
So(err, ShouldBeNil)
_, rows := sortedInstances.Size()
frequencies := chiMerge(sortedInstances, sortedInstances.AllAttributes()[0], 0.9, 0, rows)
values := []float64{}
for _, entry := range frequencies {
values = append(values, entry.Value)
}
Convey("Computes frequencies correctly", func() {
So(values, ShouldResemble, []float64{4.3, 5.5, 5.8, 6.3, 7.1})
})
})
})
})
}
func TestChiMerge2(testEnv *testing.T) {
//
// See http://sci2s.ugr.es/keel/pdf/algorithm/congreso/1992-Kerber-ChimErge-AAAI92.pdf
// Randy Kerber, ChiMerge: Discretisation of Numeric Attributes, 1992
inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
if err != nil {
panic(err)
}
// Sort the instances
allAttrs := inst.AllAttributes()
sortAttrSpecs := base.ResolveAttributes(inst, allAttrs)[0:1]
instSorted, err := base.Sort(inst, base.Ascending, sortAttrSpecs)
if err != nil {
panic(err)
}
// Perform Chi-Merge
_, rows := inst.Size()
freq := chiMerge(instSorted, allAttrs[0], 0.90, 0, rows)
if len(freq) != 5 {
testEnv.Errorf("Wrong length (%d)", len(freq))
testEnv.Error(freq)
}
if freq[0].Value != 4.3 {
testEnv.Error(freq[0])
}
if freq[1].Value != 5.5 {
testEnv.Error(freq[1])
}
if freq[2].Value != 5.8 {
testEnv.Error(freq[2])
}
if freq[3].Value != 6.3 {
testEnv.Error(freq[3])
}
if freq[4].Value != 7.1 {
testEnv.Error(freq[4])
}
}