func TestWordsCountsOf(t *testing.T) {
data := []string{"A", "B", "A", "C"}
class := []string{"A", "B"}
exp := []int{2, 1}
got := tekstus.WordsCountTokens(data, class, false)
assert(t, exp, got, true)
}
//
// computePerfByProbs will compute classifier performance using probabilities
// or score `probs`.
//
// This currently only work for two class problem.
//
func (rt *Runtime) computePerfByProbs(samples tabula.ClasetInterface,
actuals []string, probs []float64,
) {
vs := samples.GetClassValueSpace()
nactuals := numerus.IntsTo64(samples.Counts())
nclass := tekstus.WordsCountTokens(actuals, vs, false)
pprev := math.Inf(-1)
tp := int64(0)
fp := int64(0)
tpprev := int64(0)
fpprev := int64(0)
auc := float64(0)
for x, p := range probs {
if p != pprev {
stat := Stat{}
stat.SetTPRate(tp, nactuals[0])
stat.SetFPRate(fp, nactuals[1])
stat.SetPrecisionFromRate(nactuals[0], nactuals[1])
auc = auc + trapezoidArea(fp, fpprev, tp, tpprev)
stat.SetAUC(auc)
rt.perfs = append(rt.perfs, &stat)
pprev = p
tpprev = tp
fpprev = fp
}
if actuals[x] == vs[0] {
tp++
} else {
fp++
}
}
stat := Stat{}
stat.SetTPRate(tp, nactuals[0])
stat.SetFPRate(fp, nactuals[1])
stat.SetPrecisionFromRate(nactuals[0], nactuals[1])
auc = auc + trapezoidArea(fp, fpprev, tp, tpprev)
auc = auc / float64(nclass[0]*nclass[1])
stat.SetAUC(auc)
rt.perfs = append(rt.perfs, &stat)
if len(rt.perfs) >= 2 {
// Replace the first stat with second stat, because of NaN
// value on the first precision.
rt.perfs[0] = rt.perfs[1]
}
}
/*
compute value for attribute T.
Return Gini value in the form of,
1 - sum (probability of each classes in T)
*/
func (gini *Gini) compute(T *[]string, C *[]string) float64 {
n := float64(len(*T))
if n == 0 {
return 0
}
classCount := tekstus.WordsCountTokens(*T, *C, true)
var sump2 float64
for x, v := range classCount {
p := float64(v) / n
sump2 += (p * p)
if DEBUG >= 3 {
fmt.Printf("[gini] compute (%s): (%f/%f)^2 = %f\n",
(*C)[x], v, n, p*p)
}
}
return 1 - sump2
}