// Run applies a trained BinningFilter to a set of Instances,
// discretising any numeric attributes added.
//
// IMPORTANT: Run discretises in-place, so make sure to take
// a copy if the original instances are still needed
//
// IMPORTANT: This function panic()s if the filter has not been
// trained. Call Build() before running this function
//
// IMPORTANT: Call Build() after adding any additional attributes.
// Otherwise, the training structure will be out of date from
// the values expected and could cause a panic.
func (b *BinningFilter) Run(on *base.Instances) {
if !b.trained {
panic("Call Build() beforehand")
}
for attr := range b.Attributes {
minVal := b.MinVals[attr]
maxVal := b.MaxVals[attr]
disc := 0
// Casts to float32 to replicate a floating point precision error
delta := float32(maxVal - minVal)
delta /= float32(b.BinCount)
for i := 0; i < on.Rows; i++ {
val := on.Get(i, attr)
if val <= minVal {
disc = 0
} else {
disc = int(math.Floor(float64(float32(val-minVal) / delta)))
if disc >= b.BinCount {
disc = b.BinCount - 1
}
}
on.Set(i, attr, float64(disc))
}
newAttribute := new(base.CategoricalAttribute)
newAttribute.SetName(on.GetAttr(attr).GetName())
for i := 0; i < b.BinCount; i++ {
newAttribute.GetSysValFromString(fmt.Sprintf("%d", i))
}
on.ReplaceAttr(attr, newAttribute)
}
}
// Run discretises the set of Instances `on'
//
// IMPORTANT: ChiMergeFilter discretises in place.
func (c *ChiMergeFilter) Run(on *base.Instances) {
if !c._Trained {
panic("Call Build() beforehand")
}
for attr := range c.Tables {
table := c.Tables[attr]
for i := 0; i < on.Rows; i++ {
val := on.Get(i, attr)
dis := 0
for j, k := range table {
if k.Value < val {
dis = j
continue
}
break
}
on.Set(i, attr, float64(dis))
}
newAttribute := new(base.CategoricalAttribute)
newAttribute.SetName(on.GetAttr(attr).GetName())
for _, k := range table {
newAttribute.GetSysValFromString(fmt.Sprintf("%f", k.Value))
}
on.ReplaceAttr(attr, newAttribute)
}
}