func populateWithColumns(t *testing.T, dataset *tabula.Dataset) {
for x := range datasetCols {
col, e := tabula.NewColumnString(datasetCols[x], datasetTypes[x],
datasetNames[x])
if e != nil {
t.Fatal(e)
}
dataset.PushColumn(*col)
}
}
/*
getAsInputColumn return feature values as in input column.
*/
func getAsInputColumn(reader *wvcgen.Reader, colName string,
ftrValues *tabula.Dataset,
) {
ds := reader.GetDataset().(tabula.DatasetInterface)
ftr := ds.GetColumnByName(colName)
if ftr == nil {
return
}
// Add column in input as feature
ftrValues.PushColumn(*ftr)
}
func populateWithRows(t *testing.T, dataset *tabula.Dataset) {
for _, rowin := range datasetRows {
row := make(tabula.Row, len(rowin))
for x, recin := range rowin {
rec, e := tabula.NewRecordBy(recin, datasetTypes[x])
if e != nil {
t.Fatal(e)
}
row[x] = rec
}
dataset.PushRow(&row)
}
}
func TestComputeEuclidianDistance(t *testing.T) {
var exp = []string{
`[0.302891 0.608544 0.47413 1.42718 -0.811085 1]`,
`[0.243474 0.505146 0.472892 1.34802 -0.844252 1]` +
`[0.202343 0.485983 0.527533 1.47307 -0.809672 1]` +
`[0.215496 0.523418 0.51719 1.43548 -0.933981 1]` +
`[0.214331 0.546086 0.414773 1.38542 -0.702336 1]` +
`[0.301676 0.554505 0.594757 1.21258 -0.873084 1]`,
}
var expDistances = "[0.5257185558832786" +
" 0.5690474496911485" +
" 0.5888777462258191" +
" 0.6007362149895741" +
" 0.672666336306493]"
// Reading data
dataset := tabula.Dataset{}
_, e := dsv.SimpleRead("../testdata/phoneme/phoneme.dsv", &dataset)
if nil != e {
return
}
// Processing
knnIn := knn.Runtime{
DistanceMethod: knn.TEuclidianDistance,
ClassIndex: 5,
K: 5,
}
classes := dataset.GetRows().GroupByValue(knnIn.ClassIndex)
_, minoritySet := classes.GetMinority()
kneighbors := knnIn.FindNeighbors(&minoritySet, minoritySet[0])
var got string
rows := kneighbors.Rows()
for _, row := range *rows {
got += fmt.Sprint(*row)
}
assert(t, exp[1], got, true)
distances := kneighbors.Distances()
got = fmt.Sprint(*distances)
assert(t, expDistances, got, true)
}
func main() {
defer un(trace("Unified PAN-WVC-2011"))
dataset := tabula.Dataset{}
readset, e := dsv.SimpleRead(fEditsDsv, &dataset)
if e != nil {
panic(e)
}
fmt.Printf(">>> merging %d rows\n", dataset.GetNRow())
fmt.Println(">>> diffing ...")
doDiff(readset, &dataset)
fmt.Println(">>> writing ...")
n, e := dsv.SimpleWrite(readset, fEditsDsv)
if e != nil {
panic(e)
}
fmt.Printf(">>> writing %d rows\n", n)
}
func runFeature(reader *wvcgen.Reader, ftrValues *tabula.Dataset,
md dsv.Metadata,
) {
defer un(trace(">>> computing feature " + md.Name))
ftr := feature.GetByName(md.Name)
// No feature name found, search the column name in
// input metadata.
if ftr == nil {
getAsInputColumn(reader, md.Name, ftrValues)
return
}
ds := reader.GetDataset().(tabula.DatasetInterface)
ftr.Compute(ds)
col := ftr.Interface().(*tabula.Column)
ftrValues.PushColumn(*col)
}
