Skip to content

Refactor Kmeans to expose greater flexibility #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
rnix wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Refactor Kmeans to expose greater flexibility #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 24 additions & 6 deletions kmeans.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,18 +137,36 @@ func kmeans(data []ClusteredObservation, mean []Observation, distanceFunction Di
return data, nil
}

// K-Means Algorithm with smart seeds
// as known as K-Means ++
func Kmeans(rawData [][]float64, k int, distanceFunction DistanceFunction, threshold int) ([]int, error) {
data := make([]ClusteredObservation, len(rawData))
//
func KmeansData(rawData [][]float64) (data []ClusteredObservation) {
data = make([]ClusteredObservation, len(rawData))
for ii, jj := range rawData {
data[ii].Observation = jj
}
seeds := seed(data, k, distanceFunction)
clusteredData, err := kmeans(data, seeds, distanceFunction, threshold)
return
}

//
func KmeansSeeds(rawData [][]float64, seeds []Observation, distanceFunction DistanceFunction, threshold int) ([]int, error) {
clusteredData, err := kmeans(KmeansData(rawData), seeds, distanceFunction, threshold)
labels := make([]int, len(clusteredData))
for ii, jj := range clusteredData {
labels[ii] = jj.ClusterNumber
}
return labels, err
}

// K-Means Algorithm with smart seeds
// as known as K-Means ++
func Kmeans(rawData [][]float64, k int, distanceFunction DistanceFunction, threshold int) ([]int, error) {
return KmeansSeeds(rawData, seed(KmeansData(rawData), k, distanceFunction), distanceFunction, threshold)
}

func KmeansCenters(rawData [][]float64, centers [][]float64, distanceFunction DistanceFunction, threshold int) ([]int, error) {
var seeds []Observation
for i := range centers {
seeds = append(seeds, centers[i])
}

return KmeansSeeds(rawData, seeds, distanceFunction, threshold)
}