func main() {
fm := flag.String("data",
"", "Data file to read.")
outfn := flag.String("out",
"", "The name of a file to write feature matrix too.")
libsvmtarget := flag.String("libsvmtarget",
"", "Output lib svm with the named feature in the first position.")
flag.Parse()
//Parse Data
data, err := CloudForest.LoadAFM(*fm)
if err != nil {
log.Fatal(err)
}
//anotate with type information
for _, f := range data.Data {
switch f.(type) {
case *CloudForest.DenseNumFeature:
nf := f.(*CloudForest.DenseNumFeature)
if !strings.HasPrefix(nf.Name, "N:") {
nf.Name = "N:" + nf.Name
}
case *CloudForest.DenseCatFeature:
nf := f.(*CloudForest.DenseCatFeature)
if !(strings.HasPrefix(nf.Name, "C:") || strings.HasPrefix(nf.Name, "B:")) {
nf.Name = "C:" + nf.Name
}
}
}
ncases := data.Data[0].Length()
cases := make([]int, ncases, ncases)
for i := 0; i < ncases; i++ {
cases[i] = i
}
outfile, err := os.Create(*outfn)
if err != nil {
log.Fatal(err)
}
defer outfile.Close()
if *libsvmtarget == "" {
err = data.WriteCases(outfile, cases)
if err != nil {
log.Fatal(err)
}
} else {
// targeti, ok := data.Map[*libsvmtarget]
// if !ok {
// log.Fatalf("Target '%v' not found in data.", *libsvmtarget)
// }
// target := data.Data[targeti]
// data.Data = append(data.Data[:targeti], data.Data[targeti+1:]...)
// encodedfm := data.EncodeToNum()
// oucsv := csv.NewWriter(outfile)
// oucsv.Comma = ' '
// for i := 0; i < target.Length(); i++ {
// entries := make([]string, 0, 10)
// switch target.(type) {
// case CloudForest.NumFeature:
// entries = append(entries, target.GetStr(i))
// case CloudForest.CatFeature:
// entries = append(entries, fmt.Sprintf("%v", target.(CloudForest.CatFeature).Geti(i)))
// }
// for j, f := range encodedfm.Data {
// v := f.(CloudForest.NumFeature).Get(i)
// if v != 0.0 {
// entries = append(entries, fmt.Sprintf("%v:%v", j+1, v))
// }
// }
// //fmt.Println(entries)
// err := oucsv.Write(entries)
// if err != nil {
// log.Fatalf("Error writing libsvm:\n%v", err)
// }
// }
// oucsv.Flush()
err = CloudForest.WriteLibSvm(data, *libsvmtarget, outfile)
if err != nil {
log.Fatalf("Error writing libsvm:\n%v", err)
}
}
}
func main() {
fm := flag.String("fm", "featurematrix.afm", "AFM formated feature matrix to use.")
rf := flag.String("rfpred", "rface.sf", "A predictor forest.")
outf := flag.String("leaves", "leaves.tsv", "a case by case sparse matrix of leaf co-occurrence in tsv format")
boutf := flag.String("branches", "", "a case by feature sparse matrix of leaf co-occurrence in tsv format")
soutf := flag.String("splits", "", "a file to write a json record of splite per feature")
var threads int
flag.IntVar(&threads, "threads", 1, "Parse seperate forests in n seperate threads.")
flag.Parse()
splits := make(map[string][]string)
//Parse Data
data, err := CloudForest.LoadAFM(*fm)
if err != nil {
log.Fatal(err)
}
log.Print("Data file ", len(data.Data), " by ", data.Data[0].Length())
counts := new(CloudForest.SparseCounter)
var caseFeatureCounts *CloudForest.SparseCounter
if *boutf != "" {
caseFeatureCounts = new(CloudForest.SparseCounter)
}
files := strings.Split(*rf, ",")
runtime.GOMAXPROCS(threads)
fileChan := make(chan string, 0)
doneChan := make(chan int, 0)
go func() {
for _, fn := range files {
fileChan <- fn
}
}()
for i := 0; i < threads; i++ {
go func() {
for {
fn := <-fileChan
forestfile, err := os.Open(fn) // For read access.
if err != nil {
log.Fatal(err)
}
defer forestfile.Close()
forestreader := CloudForest.NewForestReader(forestfile)
forest, err := forestreader.ReadForest()
if err != nil {
log.Fatal(err)
}
log.Print("Forest has ", len(forest.Trees), " trees ")
for i := 0; i < len(forest.Trees); i++ {
fmt.Print(".")
leaves := forest.Trees[i].GetLeaves(data, caseFeatureCounts)
for _, leaf := range leaves {
for j := 0; j < len(leaf.Cases); j++ {
for k := 0; k < len(leaf.Cases); k++ {
counts.Add(leaf.Cases[j], leaf.Cases[k], 1)
}
}
}
if *soutf != "" {
forest.Trees[i].Root.Climb(func(n *CloudForest.Node) {
if n.Splitter != nil {
name := n.Splitter.Feature
_, ok := splits[name]
if !ok {
splits[name] = make([]string, 0, 10)
}
split := ""
switch n.Splitter.Numerical {
case true:
split = fmt.Sprintf("%v", n.Splitter.Value)
case false:
keys := make([]string, 0, len(n.Splitter.Left))
for k := range n.Splitter.Left {
keys = append(keys, k)
}
split = strings.Join(keys, ",")
}
splits[name] = append(splits[name], split)
}
})
}
}
doneChan <- 1
}
}()
}
for i := 0; i < len(files); i++ {
<-doneChan
}
log.Print("Outputting Case Case Co-Occurrence Counts")
outfile, err := os.Create(*outf)
if err != nil {
log.Fatal(err)
}
defer outfile.Close()
counts.WriteTsv(outfile)
if *boutf != "" {
log.Print("Outputting Case Feature Co-Occurrence Counts")
boutfile, err := os.Create(*boutf)
if err != nil {
log.Fatal(err)
}
defer boutfile.Close()
caseFeatureCounts.WriteTsv(boutfile)
}
if *soutf != "" {
soutfile, err := os.Create(*soutf)
if err != nil {
log.Fatal(err)
}
defer soutfile.Close()
encoder := json.NewEncoder(soutfile)
encoder.Encode(splits)
}
}
func main() {
fm := flag.String("fm",
"featurematrix.afm", "AFM formated feature matrix containing data.")
rf := flag.String("rfpred",
"rface.sf", "A predictor forest.")
predfn := flag.String("preds",
"", "The name of a file to write the predictions into.")
votefn := flag.String("votes",
"", "The name of a file to write categorical vote totals to.")
var num bool
flag.BoolVar(&num, "mean", false, "Force numeric (mean) voting.")
var sum bool
flag.BoolVar(&sum, "sum", false, "Force numeric sum voting (for gradient boosting etc).")
var expit bool
flag.BoolVar(&expit, "expit", false, "Expit (inverst logit) transform data (for gradient boosting classification).")
var cat bool
flag.BoolVar(&cat, "mode", false, "Force categorical (mode) voting.")
flag.Parse()
//Parse Data
data, err := CloudForest.LoadAFM(*fm)
if err != nil {
log.Fatal(err)
}
forestfile, err := os.Open(*rf) // For read access.
if err != nil {
log.Fatal(err)
}
defer forestfile.Close()
forestreader := CloudForest.NewForestReader(forestfile)
forest, err := forestreader.ReadForest()
if err != nil {
log.Fatal(err)
}
var predfile *os.File
if *predfn != "" {
predfile, err = os.Create(*predfn)
if err != nil {
log.Fatal(err)
}
defer predfile.Close()
}
var bb CloudForest.VoteTallyer
switch {
case sum:
bb = CloudForest.NewSumBallotBox(data.Data[0].Length())
case !cat && (num || strings.HasPrefix(forest.Target, "N")):
bb = CloudForest.NewNumBallotBox(data.Data[0].Length())
default:
bb = CloudForest.NewCatBallotBox(data.Data[0].Length())
}
for _, tree := range forest.Trees {
tree.Vote(data, bb)
}
targeti, hasTarget := data.Map[forest.Target]
if hasTarget {
fmt.Printf("Target is %v in feature %v\n", forest.Target, targeti)
er := bb.TallyError(data.Data[targeti])
fmt.Printf("Error: %v\n", er)
}
if *predfn != "" {
fmt.Printf("Outputting label predicted actual tsv to %v\n", *predfn)
for i, l := range data.CaseLabels {
actual := "NA"
if hasTarget {
actual = data.Data[targeti].GetStr(i)
}
result := ""
if sum || forest.Intercept != 0.0 {
numresult := 0.0
if sum {
numresult = bb.(*CloudForest.SumBallotBox).TallyNum(i) + forest.Intercept
} else {
numresult = bb.(*CloudForest.NumBallotBox).TallyNum(i) + forest.Intercept
}
if expit {
numresult = CloudForest.Expit(numresult)
}
result = fmt.Sprintf("%v", numresult)
} else {
result = bb.Tally(i)
}
fmt.Fprintf(predfile, "%v\t%v\t%v\n", l, result, actual)
}
}
//Not thread safe code!
if *votefn != "" {
fmt.Printf("Outputting vote totals to %v\n", *votefn)
cbb := bb.(*CloudForest.CatBallotBox)
votefile, err := os.Create(*votefn)
if err != nil {
log.Fatal(err)
}
defer votefile.Close()
fmt.Fprintf(votefile, ".")
for _, lable := range cbb.CatMap.Back {
fmt.Fprintf(votefile, "\t%v", lable)
}
fmt.Fprintf(votefile, "\n")
for i, box := range cbb.Box {
fmt.Fprintf(votefile, "%v", data.CaseLabels[i])
for j, _ := range cbb.CatMap.Back {
total := 0.0
total = box.Map[j]
fmt.Fprintf(votefile, "\t%v", total)
}
fmt.Fprintf(votefile, "\n")
}
}
}
func main() {
fm := flag.String("train",
"featurematrix.afm", "AFM formated feature matrix containing training data.")
rf := flag.String("rfpred",
"", "File name to output predictor forest in sf format.")
targetname := flag.String("target",
"", "The row header of the target in the feature matrix.")
imp := flag.String("importance",
"", "File name to output importance.")
costs := flag.String("cost",
"", "For categorical targets, a json string to float map of the cost of falsely identifying each category.")
dentropy := flag.String("dentropy",
"", "Class disutilities for disutility entropy.")
adacosts := flag.String("adacost",
"", "Json costs for cost sentive AdaBoost.")
rfweights := flag.String("rfweights",
"", "For categorical targets, a json string to float map of the weights to use for each category in Weighted RF.")
blacklist := flag.String("blacklist",
"", "A list of feature id's to exclude from the set of predictors.")
var nCores int
flag.IntVar(&nCores, "nCores", 1, "The number of cores to use.")
var StringnSamples string
flag.StringVar(&StringnSamples, "nSamples", "0", "The number of cases to sample (with replacement) for each tree as a count (ex: 10) or portion of total (ex: .5). If <=0 set to total number of cases.")
var StringmTry string
flag.StringVar(&StringmTry, "mTry", "0", "Number of candidate features for each split as a count (ex: 10) or portion of total (ex: .5). Ceil(sqrt(nFeatures)) if <=0.")
var StringleafSize string
flag.StringVar(&StringleafSize, "leafSize", "0", "The minimum number of cases on a leaf node. If <=0 will be inferred to 1 for classification 4 for regression.")
var shuffleRE string
flag.StringVar(&shuffleRE, "shuffleRE", "", "A regular expression to identify features that should be shuffled.")
var blockRE string
flag.StringVar(&blockRE, "blockRE", "", "A regular expression to identify features that should be filtered out.")
var includeRE string
flag.StringVar(&includeRE, "includeRE", "", "Filter features that DON'T match this RE.")
var nTrees int
flag.IntVar(&nTrees, "nTrees", 100, "Number of trees to grow in the predictor.")
var ace int
flag.IntVar(&ace, "ace", 0, "Number ace permutations to do. Output ace style importance and p values.")
var cutoff float64
flag.Float64Var(&cutoff, "cutoff", 0.0, "P-value cutoff to apply to features for last forest after ACE.")
var nContrasts int
flag.IntVar(&nContrasts, "nContrasts", 0, "The number of randomized artificial contrast features to include in the feature matrix.")
var cpuprofile = flag.String("cpuprofile", "", "write cpu profile to file")
var contrastAll bool
flag.BoolVar(&contrastAll, "contrastall", false, "Include a shuffled artificial contrast copy of every feature.")
var impute bool
flag.BoolVar(&impute, "impute", false, "Impute missing values to feature mean/mode before growth.")
var extra bool
flag.BoolVar(&extra, "extra", false, "Grow Extra Random Trees (supports learning from numerical variables only).")
var splitmissing bool
flag.BoolVar(&splitmissing, "splitmissing", false, "Split missing values onto a third branch at each node (experimental).")
var l1 bool
flag.BoolVar(&l1, "l1", false, "Use l1 norm regression (target must be numeric).")
var density bool
flag.BoolVar(&density, "density", false, "Build density estimating trees instead of classification/regression trees.")
var vet bool
flag.BoolVar(&vet, "vet", false, "Penalize potential splitter impurity decrease by subtracting the best split of a permuted target.")
var NP bool
flag.BoolVar(&NP, "NP", false, "Do approximate Neyman-Pearson classification.")
var NP_pos string
flag.StringVar(&NP_pos, "NP_pos", "1", "Class label to constrain percision in NP classification.")
var NP_a float64
flag.Float64Var(&NP_a, "NP_a", 0.1, "Constraint on percision in NP classification [0,1]")
var NP_k float64
flag.Float64Var(&NP_k, "NP_k", 100, "Weight of constraint in NP classification [0,Inf+)")
var evaloob bool
flag.BoolVar(&evaloob, "evaloob", false, "Evaluate potential splitting features on OOB cases after finding split value in bag.")
var force bool
flag.BoolVar(&force, "force", false, "Force at least one non constant feature to be tested for each split.")
var entropy bool
flag.BoolVar(&entropy, "entropy", false, "Use entropy minimizing classification (target must be categorical).")
var oob bool
flag.BoolVar(&oob, "oob", false, "Calculate and report oob error.")
var jungle bool
flag.BoolVar(&jungle, "jungle", false, "Grow unserializable and experimental decision jungle with node recombination.")
var caseoob string
flag.StringVar(&caseoob, "oobpreds", "", "Calculate and report oob predictions in the file specified.")
var progress bool
flag.BoolVar(&progress, "progress", false, "Report tree number and running oob error.")
var adaboost bool
flag.BoolVar(&adaboost, "adaboost", false, "Use Adaptive boosting for regression/classification.")
var gradboost float64
flag.Float64Var(&gradboost, "gbt", 0.0, "Use gradient boosting with the specified learning rate.")
var multiboost bool
flag.BoolVar(&multiboost, "multiboost", false, "Allow multi-threaded boosting which may have unexpected results. (highly experimental)")
var nobag bool
flag.BoolVar(&nobag, "nobag", false, "Don't bag samples for each tree.")
var balance bool
flag.BoolVar(&balance, "balance", false, "Balance bagging of samples by target class for unbalanced classification.")
var balanceby string
flag.StringVar(&balanceby, "balanceby", "", "Roughly balanced bag the target within each class of this feature.")
var ordinal bool
flag.BoolVar(&ordinal, "ordinal", false, "Use ordinal regression (target must be numeric).")
var permutate bool
flag.BoolVar(&permutate, "permute", false, "Permute the target feature (to establish random predictive power).")
var dotest bool
flag.BoolVar(&dotest, "selftest", false, "Test the forest on the data and report accuracy.")
var testfm string
flag.StringVar(&testfm, "test", "", "Data to test the model on.")
var noseed bool
flag.BoolVar(&noseed, "noseed", false, "Don't seed the random number generator from time.")
flag.Parse()
nForest := 1
if !noseed {
rand.Seed(time.Now().UTC().UnixNano())
}
if testfm != "" {
dotest = true
}
if multiboost {
fmt.Println("MULTIBOOST!!!!1!!!!1!!11 (things may break).")
}
var boostMutex sync.Mutex
boost := (adaboost || gradboost != 0.0)
if boost && !multiboost {
nCores = 1
}
if nCores > 1 {
runtime.GOMAXPROCS(nCores)
}
fmt.Printf("Threads : %v\n", nCores)
fmt.Printf("nTrees : %v\n", nTrees)
//Parse Data
fmt.Printf("Loading data from: %v\n", *fm)
data, err := CloudForest.LoadAFM(*fm)
if err != nil {
log.Fatal(err)
}
if *cpuprofile != "" {
f, err := os.Create(*cpuprofile)
if err != nil {
log.Fatal(err)
}
pprof.StartCPUProfile(f)
defer pprof.StopCPUProfile()
}
if nContrasts > 0 {
fmt.Printf("Adding %v Random Contrasts\n", nContrasts)
data.AddContrasts(nContrasts)
}
if contrastAll {
fmt.Printf("Adding Random Contrasts for All Features.\n")
data.ContrastAll()
}
blacklisted := 0
blacklistis := make([]bool, len(data.Data))
if *blacklist != "" {
fmt.Printf("Loading blacklist from: %v\n", *blacklist)
blackfile, err := os.Open(*blacklist)
if err != nil {
log.Fatal(err)
}
tsv := csv.NewReader(blackfile)
tsv.Comma = '\t'
for {
id, err := tsv.Read()
if err == io.EOF {
break
} else if err != nil {
log.Fatal(err)
}
i, ok := data.Map[id[0]]
if !ok {
fmt.Printf("Ignoring blacklist feature not found in data: %v\n", id[0])
continue
}
if !blacklistis[i] {
blacklisted += 1
blacklistis[i] = true
}
}
blackfile.Close()
}
//find the target feature
fmt.Printf("Target : %v\n", *targetname)
targeti, ok := data.Map[*targetname]
if !ok {
log.Fatal("Target not found in data.")
}
if blockRE != "" {
re := regexp.MustCompile(blockRE)
for i, feature := range data.Data {
if targeti != i && re.MatchString(feature.GetName()) {
if blacklistis[i] == false {
blacklisted += 1
blacklistis[i] = true
}
}
}
}
if includeRE != "" {
re := regexp.MustCompile(includeRE)
for i, feature := range data.Data {
if targeti != i && !re.MatchString(feature.GetName()) {
if blacklistis[i] == false {
blacklisted += 1
blacklistis[i] = true
}
}
}
}
nFeatures := len(data.Data) - blacklisted - 1
fmt.Printf("Non Target Features : %v\n", nFeatures)
mTry := CloudForest.ParseAsIntOrFractionOfTotal(StringmTry, nFeatures)
if mTry <= 0 {
mTry = int(math.Ceil(math.Sqrt(float64(nFeatures))))
}
fmt.Printf("mTry : %v\n", mTry)
if impute {
fmt.Println("Imputing missing values to feature mean/mode.")
data.ImputeMissing()
}
if permutate {
fmt.Println("Permuting target feature.")
data.Data[targeti].Shuffle()
}
if shuffleRE != "" {
re := regexp.MustCompile(shuffleRE)
shuffled := 0
for i, feature := range data.Data {
if targeti != i && re.MatchString(feature.GetName()) {
data.Data[i].Shuffle()
shuffled += 1
}
}
fmt.Printf("Shuffled %v features matching %v\n", shuffled, shuffleRE)
}
targetf := data.Data[targeti]
unboostedTarget := targetf.Copy()
var bSampler CloudForest.Bagger
if balance {
bSampler = CloudForest.NewBalancedSampler(targetf.(*CloudForest.DenseCatFeature))
}
if balanceby != "" {
bSampler = CloudForest.NewSecondaryBalancedSampler(targetf.(*CloudForest.DenseCatFeature), data.Data[data.Map[balanceby]].(*CloudForest.DenseCatFeature))
balance = true
}
nNonMissing := 0
for i := 0; i < targetf.Length(); i++ {
if !targetf.IsMissing(i) {
nNonMissing += 1
}
}
fmt.Printf("non-missing cases: %v\n", nNonMissing)
leafSize := CloudForest.ParseAsIntOrFractionOfTotal(StringleafSize, nNonMissing)
if leafSize <= 0 {
if boost {
leafSize = nNonMissing / 3
} else if targetf.NCats() == 0 {
//regression
leafSize = 4
} else {
//classification
leafSize = 1
}
}
fmt.Printf("leafSize : %v\n", leafSize)
//infer nSamples and mTry from data if they are 0
nSamples := CloudForest.ParseAsIntOrFractionOfTotal(StringnSamples, nNonMissing)
if nSamples <= 0 {
nSamples = nNonMissing
}
fmt.Printf("nSamples : %v\n", nSamples)
if progress {
oob = true
}
if caseoob != "" {
oob = true
}
var oobVotes CloudForest.VoteTallyer
if oob {
fmt.Println("Recording oob error.")
if targetf.NCats() == 0 {
//regression
oobVotes = CloudForest.NewNumBallotBox(data.Data[0].Length())
} else {
//classification
oobVotes = CloudForest.NewCatBallotBox(data.Data[0].Length())
}
}
//****** Set up Target for Alternative Impurity if needed *******//
var target CloudForest.Target
if density {
fmt.Println("Estimating Density.")
target = &CloudForest.DensityTarget{&data.Data, nSamples}
} else {
switch targetf.(type) {
case CloudForest.NumFeature:
fmt.Println("Performing regression.")
if l1 {
fmt.Println("Using l1/absolute deviance error.")
targetf = &CloudForest.L1Target{targetf.(CloudForest.NumFeature)}
}
if ordinal {
fmt.Println("Using Ordinal (mode) prediction.")
targetf = CloudForest.NewOrdinalTarget(targetf.(CloudForest.NumFeature))
}
switch {
case gradboost != 0.0:
fmt.Println("Using Gradient Boosting.")
targetf = &CloudForest.GradBoostTarget{targetf.(CloudForest.NumFeature), gradboost}
case adaboost:
fmt.Println("Using Numeric Adaptive Boosting.")
targetf = CloudForest.NewNumAdaBoostTarget(targetf.(CloudForest.NumFeature))
}
target = targetf
case CloudForest.CatFeature:
fmt.Printf("Performing classification with %v categories.\n", targetf.NCats())
switch {
case NP:
fmt.Printf("Performing Approximate Neyman-Pearson Classification with constrained false \"%v\".\n", NP_pos)
fmt.Printf("False %v constraint: %v, constraint weight: %v.\n", NP_pos, NP_a, NP_k)
targetf = CloudForest.NewNPTarget(targetf.(CloudForest.CatFeature), NP_pos, NP_a, NP_k)
case *costs != "":
fmt.Println("Using misclassification costs: ", *costs)
costmap := make(map[string]float64)
err := json.Unmarshal([]byte(*costs), &costmap)
if err != nil {
log.Fatal(err)
}
regTarg := CloudForest.NewRegretTarget(targetf.(CloudForest.CatFeature))
regTarg.SetCosts(costmap)
targetf = regTarg
case *dentropy != "":
fmt.Println("Using entropy with disutilities: ", *dentropy)
costmap := make(map[string]float64)
err := json.Unmarshal([]byte(*dentropy), &costmap)
if err != nil {
log.Fatal(err)
}
deTarg := CloudForest.NewDEntropyTarget(targetf.(CloudForest.CatFeature))
deTarg.SetCosts(costmap)
targetf = deTarg
case *adacosts != "":
fmt.Println("Using cost sensative AdaBoost costs: ", *adacosts)
costmap := make(map[string]float64)
err := json.Unmarshal([]byte(*adacosts), &costmap)
if err != nil {
log.Fatal(err)
}
actarget := CloudForest.NewAdaCostTarget(targetf.(CloudForest.CatFeature))
actarget.SetCosts(costmap)
targetf = actarget
case *rfweights != "":
fmt.Println("Using rf weights: ", *rfweights)
weightmap := make(map[string]float64)
err := json.Unmarshal([]byte(*rfweights), &weightmap)
if err != nil {
log.Fatal(err)
}
wrfTarget := CloudForest.NewWRFTarget(targetf.(CloudForest.CatFeature), weightmap)
targetf = wrfTarget
case entropy:
fmt.Println("Using entropy minimization.")
targetf = &CloudForest.EntropyTarget{targetf.(CloudForest.CatFeature)}
case boost:
fmt.Println("Using Adaptive Boosting.")
targetf = CloudForest.NewAdaBoostTarget(targetf.(CloudForest.CatFeature))
}
target = targetf
}
}
var forestwriter *CloudForest.ForestWriter
if *rf != "" {
forestfile, err := os.Create(*rf)
if err != nil {
log.Fatal(err)
}
defer forestfile.Close()
forestwriter = CloudForest.NewForestWriter(forestfile)
}
//****************** Setup For ACE ********************************//
var aceImps [][]float64
firstace := len(data.Data)
if ace > 0 {
fmt.Printf("Performing ACE analysis with %v forests/permutations.\n", ace)
data.ContrastAll()
for i := 0; i < firstace; i++ {
blacklistis = append(blacklistis, blacklistis[i])
}
blacklistis[targeti+firstace] = true
aceImps = make([][]float64, len(data.Data))
for i := 0; i < len(data.Data); i++ {
aceImps[i] = make([]float64, ace)
}
nForest = ace
if cutoff > 0 {
nForest++
}
}
//****************** Needed Collections and vars ******************//
var trees []*CloudForest.Tree
trees = make([]*CloudForest.Tree, 0, nTrees)
var imppnt *[]*CloudForest.RunningMean
var mmdpnt *[]*CloudForest.RunningMean
if *imp != "" {
fmt.Println("Recording Importance Scores.")
imppnt = CloudForest.NewRunningMeans(len(data.Data))
mmdpnt = CloudForest.NewRunningMeans(len(data.Data))
} else if ace > 0 {
imppnt = CloudForest.NewRunningMeans(len(data.Data))
}
//****************** Good Stuff Stars Here ;) ******************//
trainingStart := time.Now()
for foresti := 0; foresti < nForest; foresti++ {
var treesStarted, treesFinished int
treesStarted = nCores
var recordingTree sync.Mutex
var waitGroup sync.WaitGroup
waitGroup.Add(nCores)
treechan := make(chan *CloudForest.Tree, 0)
//fmt.Println("forest ", foresti)
//Grow a single forest on nCores
for core := 0; core < nCores; core++ {
grow := func() {
weight := -1.0
canidates := make([]int, 0, len(data.Data))
for i := 0; i < len(data.Data); i++ {
if i != targeti && !blacklistis[i] {
canidates = append(canidates, i)
}
}
tree := CloudForest.NewTree()
tree.Target = *targetname
cases := make([]int, 0, nSamples)
oobcases := make([]int, 0, nSamples)
if nobag {
for i := 0; i < nSamples; i++ {
if !targetf.IsMissing(i) {
cases = append(cases, i)
}
}
}
var depthUsed *[]int
if mmdpnt != nil {
du := make([]int, len(data.Data))
depthUsed = &du
}
allocs := CloudForest.NewBestSplitAllocs(nSamples, targetf)
for {
nCases := data.Data[0].Length()
//sample nCases case with replacement
if !nobag {
cases = cases[0:0]
if balance {
bSampler.Sample(&cases, nSamples)
} else {
for j := 0; len(cases) < nSamples; j++ {
r := rand.Intn(nCases)
if !targetf.IsMissing(r) {
cases = append(cases, r)
}
}
}
}
if nobag && nSamples != nCases {
cases = cases[0:0]
for i := 0; i < nSamples; i++ {
if !targetf.IsMissing(i) {
cases = append(cases, i)
}
}
CloudForest.SampleFirstN(&cases, nil, nCases, 0)
}
if oob || evaloob {
ibcases := make([]bool, nCases)
for _, v := range cases {
ibcases[v] = true
}
oobcases = oobcases[0:0]
for i, v := range ibcases {
if !v {
oobcases = append(oobcases, i)
}
}
}
if jungle {
tree.GrowJungle(data, target, cases, canidates, oobcases, mTry, leafSize, splitmissing, force, vet, evaloob, extra, imppnt, depthUsed, allocs)
} else {
tree.Grow(data, target, cases, canidates, oobcases, mTry, leafSize, splitmissing, force, vet, evaloob, extra, imppnt, depthUsed, allocs)
}
if mmdpnt != nil {
for i, v := range *depthUsed {
if v != 0 {
(*mmdpnt)[i].Add(float64(v))
(*depthUsed)[i] = 0
}
}
}
if boost {
boostMutex.Lock()
weight = targetf.(CloudForest.BoostingTarget).Boost(tree.Partition(data))
boostMutex.Unlock()
if weight == math.Inf(1) {
fmt.Printf("Boosting Reached Weight of %v\n", weight)
close(treechan)
break
}
tree.Weight = weight
}
if oob && foresti == nForest-1 {
tree.VoteCases(data, oobVotes, oobcases)
}
////////////// Lock mutext to ouput tree ////////
if nCores > 1 {
recordingTree.Lock()
}
if forestwriter != nil && foresti == nForest-1 {
forestwriter.WriteTree(tree, treesStarted)
}
if dotest && foresti == nForest-1 {
trees = append(trees, tree)
if treesStarted < nTrees-1 {
//newtree := new(CloudForest.Tree)
tree = CloudForest.NewTree()
tree.Target = *targetname
}
}
if progress {
treesFinished++
fmt.Printf("Model oob error after tree %v : %v\n", treesFinished, oobVotes.TallyError(unboostedTarget))
}
if treesStarted < nTrees {
treesStarted++
} else {
if nCores > 1 {
recordingTree.Unlock()
waitGroup.Done()
}
break
}
if nCores > 1 {
recordingTree.Unlock()
}
//////// Unlock //////////////////////////
// treechan <- tree
// tree = <-treechan
}
}
if nCores > 1 {
go grow()
} else {
grow()
}
}
if nCores > 1 {
waitGroup.Wait()
}
// for i := 0; i < nTrees; i++ {
// tree := <-treechan
// if tree == nil {
// break
// }
// if forestwriter != nil && foresti == nForest-1 {
// forestwriter.WriteTree(tree, i)
// }
// if dotest && foresti == nForest-1 {
// trees = append(trees, tree)
// if i < nTrees-1 {
// //newtree := new(CloudForest.Tree)
// treechan <- CloudForest.NewTree()
// }
// } else {
// if i < nTrees-1 {
// treechan <- tree
// }
// }
// if progress {
// fmt.Printf("Model oob error after tree %v : %v\n", i, oobVotes.TallyError(unboostedTarget))
// }
// }
//Single forest growth is over.
//Record importance scores from this forest for ace
if ace > 0 && (cutoff == 0.0 || foresti < nForest-1) {
if foresti < nForest-1 {
fmt.Printf("Finished ACE forest %v.\n", foresti)
}
//Record Importance scores
for i := 0; i < len(data.Data); i++ {
mean, count := (*imppnt)[i].Read()
aceImps[i][foresti] = mean * float64(count) / float64(nTrees)
}
//Reset importance scores
imppnt = CloudForest.NewRunningMeans(len(data.Data))
//Reshuffle contrast features
for i := firstace; i < len(data.Data); i++ {
if !blacklistis[i] {
data.Data[i].Shuffle()
}
}
if cutoff > 0 && foresti == nForest-2 {
sigcount := 0
for i := range blacklistis {
if i < firstace && !blacklistis[i] {
p, _, _, m := stats.Ttest(&aceImps[i], &aceImps[i+firstace])
if p < cutoff && m > 0.0 && i != targeti {
blacklistis[i] = false
sigcount++
} else {
blacklistis[i] = true
}
}
if i >= firstace {
blacklistis[i] = true
}
}
mTry = CloudForest.ParseAsIntOrFractionOfTotal(StringmTry, sigcount)
if mTry <= 0 {
mTry = int(math.Ceil(math.Sqrt(float64(sigcount))))
}
fmt.Printf("Growing non-ACE forest with %v features with p-value < %v.\nmTry: %v\n", sigcount, cutoff, mTry)
}
}
}
trainingEnd := time.Now()
fmt.Printf("Total training time (seconds): %v\n", trainingEnd.Sub(trainingStart).Seconds())
if oob {
fmt.Printf("Out of Bag Error : %v\n", oobVotes.TallyError(unboostedTarget))
}
if caseoob != "" {
caseoobfile, err := os.Create(caseoob)
if err != nil {
log.Fatal(err)
}
defer caseoobfile.Close()
for i := 0; i < unboostedTarget.Length(); i++ {
fmt.Fprintf(caseoobfile, "%v\t%v\t%v\n", data.CaseLabels[i], oobVotes.Tally(i), unboostedTarget.GetStr(i))
}
}
if *imp != "" {
impfile, err := os.Create(*imp)
if err != nil {
log.Fatal(err)
}
defer impfile.Close()
if ace > 0 {
for i := 0; i < firstace; i++ {
p, _, _, m := stats.Ttest(&aceImps[i], &aceImps[i+firstace])
fmt.Fprintf(impfile, "%v\t%v\t%v\t%v\n", *targetname, data.Data[i].GetName(), p, m)
}
} else {
//Write standard importance file
for i, v := range *imppnt {
mean, count := v.Read()
meanMinDepth, treeCount := (*mmdpnt)[i].Read()
fmt.Fprintf(impfile, "%v\t%v\t%v\t%v\t%v\t%v\t%v\n", data.Data[i].GetName(), mean, count, mean*float64(count)/float64(nTrees), mean*float64(count)/float64(treeCount), treeCount, meanMinDepth)
}
}
}
if dotest {
var bb CloudForest.VoteTallyer
testdata := data
testtarget := unboostedTarget
if testfm != "" {
var err error
testdata, err = CloudForest.LoadAFM(testfm)
if err != nil {
log.Fatal(err)
}
targeti, ok = testdata.Map[*targetname]
if !ok {
log.Fatal("Target not found in test data.")
}
testtarget = testdata.Data[targeti]
for _, tree := range trees {
tree.StripCodes()
}
}
if unboostedTarget.NCats() == 0 {
//regression
bb = CloudForest.NewNumBallotBox(testdata.Data[0].Length())
} else {
//classification
bb = CloudForest.NewCatBallotBox(testdata.Data[0].Length())
}
for _, tree := range trees {
tree.Vote(testdata, bb)
}
fmt.Printf("Error: %v\n", bb.TallyError(testtarget))
if testtarget.NCats() != 0 {
falsesbypred := make([]int, testtarget.NCats())
predtotals := make([]int, testtarget.NCats())
truebytrue := make([]int, testtarget.NCats())
truetotals := make([]int, testtarget.NCats())
correct := 0
nas := 0
length := testtarget.Length()
for i := 0; i < length; i++ {
truei := testtarget.(*CloudForest.DenseCatFeature).Geti(i)
truetotals[truei]++
pred := bb.Tally(i)
if pred == "NA" {
nas++
} else {
predi := testtarget.(*CloudForest.DenseCatFeature).CatToNum(pred)
predtotals[predi]++
if pred == testtarget.GetStr(i) {
correct++
truebytrue[truei]++
} else {
falsesbypred[predi]++
}
}
}
fmt.Printf("Classified: %v / %v = %v\n", correct, length, float64(correct)/float64(length))
for i, v := range testtarget.(*CloudForest.DenseCatFeature).Back {
fmt.Printf("Label %v Percision (Actuall/Predicted): %v / %v = %v\n", v, falsesbypred[i], predtotals[i], float64(falsesbypred[i])/float64(predtotals[i]))
falses := truetotals[i] - truebytrue[i]
fmt.Printf("Label %v Missed/Actuall Rate: %v / %v = %v\n", v, falses, truetotals[i], float64(falses)/float64(truetotals[i]))
}
if nas != 0 {
fmt.Printf("Couldn't predict %v cases due to missing values.\n", nas)
}
}
}
}
func main() {
fm := flag.String("fm",
"featurematrix.afm", "AFM formated feature matrix containing data.")
blacklist := flag.String("blacklist",
"", "A list of feature id's to exclude from the set of predictors.")
targetname := flag.String("target",
"", "The row header of the target in the feature matrix.")
train := flag.String("train",
"train_%v.fm", "Format string for training fms.")
test := flag.String("test",
"test_%v.fm", "Format string for testing fms.")
// var zipoutput bool
// flag.BoolVar(&zipoutput, "zip", false, "Output ziped files.")
var unstratified bool
flag.BoolVar(&unstratified, "unstratified", false, "Force unstratified sampeling of categorical target.")
var writelibsvm bool
flag.BoolVar(&writelibsvm, "writelibsvm", false, "Output libsvm.")
var writearff bool
flag.BoolVar(&writearff, "writearff", false, "Output arff.")
var writeall bool
flag.BoolVar(&writeall, "writeall", false, "Output all three formats.")
var folds int
flag.IntVar(&folds, "folds", 5, "Number of folds to generate.")
var maxcats int
flag.IntVar(&maxcats, "maxcats", -1, "Maximum number of categories to allow in a feature.")
var impute bool
flag.BoolVar(&impute, "impute", false, "Impute missing values to feature mean/mode.")
var onehot bool
flag.BoolVar(&onehot, "onehot", false, "Do one hot encoding of categorical features to boolean true false.")
var num bool
flag.BoolVar(&num, "num", false, "Do one hot encoding of categorical features to numerical features.")
flag.Parse()
//Parse Data
data, err := CloudForest.LoadAFM(*fm)
if err != nil {
log.Fatal(err)
}
blacklisted := 0
blacklistis := make([]bool, len(data.Data))
if *blacklist != "" {
fmt.Printf("Loading blacklist from: %v\n", *blacklist)
blackfile, err := os.Open(*blacklist)
if err != nil {
log.Fatal(err)
}
tsv := csv.NewReader(blackfile)
tsv.Comma = '\t'
for {
id, err := tsv.Read()
if err == io.EOF {
break
} else if err != nil {
log.Fatal(err)
}
if id[0] == *targetname {
continue
}
i, ok := data.Map[id[0]]
if !ok {
fmt.Printf("Ignoring blacklist feature not found in data: %v\n", id[0])
continue
}
if !blacklistis[i] {
blacklisted += 1
blacklistis[i] = true
}
}
blackfile.Close()
}
newdata := make([]CloudForest.Feature, 0, len(data.Data)-blacklisted)
newmap := make(map[string]int, len(data.Data)-blacklisted)
for i, f := range data.Data {
if !blacklistis[i] && (maxcats == -1 || f.NCats() <= maxcats) {
newmap[f.GetName()] = len(newdata)
newdata = append(newdata, f)
}
}
data.Data = newdata
data.Map = newmap
if impute {
fmt.Println("Imputing missing values to feature mean/mode.")
data.ImputeMissing()
}
if onehot {
fmt.Println("OneHot encoding.")
data.OneHot()
}
if num {
fmt.Println("Numerical OneHot encoding.")
data = data.EncodeToNum()
}
foldis := make([][]int, 0, folds)
foldsize := len(data.CaseLabels) / folds
fmt.Printf("%v cases, foldsize %v\n", len(data.CaseLabels), foldsize)
for i := 0; i < folds; i++ {
foldis = append(foldis, make([]int, 0, foldsize))
}
var targetf CloudForest.Feature
//find the target feature
fmt.Printf("Target : %v\n", *targetname)
targeti, ok := data.Map[*targetname]
if !ok {
fmt.Println("Target not found in data, doing unstratified sampeling.")
unstratified = true
}
if ok {
targetf = data.Data[targeti]
switch targetf.(type) {
case *CloudForest.DenseNumFeature:
unstratified = true
}
}
if unstratified {
ncases := len(data.CaseLabels)
cases := make([]int, ncases, ncases)
for i := 0; i < ncases; i++ {
cases[i] = i
}
CloudForest.SampleFirstN(&cases, nil, len(cases), 0)
for j := 0; j < folds; j++ {
for k := j * foldsize; k < (j+1)*foldsize; k++ {
foldis[j] = append(foldis[j], cases[k])
}
}
} else {
//sample folds stratified by case
fmt.Printf("Stratifying by %v classes.\n", targetf.(*CloudForest.DenseCatFeature).NCats())
bSampler := CloudForest.NewBalancedSampler(targetf.(*CloudForest.DenseCatFeature))
fmt.Printf("Stratifying by %v classes.\n", len(bSampler.Cases))
var samples []int
for i := 0; i < len(bSampler.Cases); i++ {
fmt.Printf("%v cases in class %v.\n", len(bSampler.Cases[i]), i)
//shuffle in place
CloudForest.SampleFirstN(&bSampler.Cases[i], &samples, len(bSampler.Cases[i]), 0)
stratFoldSize := len(bSampler.Cases[i]) / folds
for j := 0; j < folds; j++ {
for k := j * stratFoldSize; k < (j+1)*stratFoldSize; k++ {
foldis[j] = append(foldis[j], bSampler.Cases[i][k])
}
}
}
}
encode := false
for _, f := range data.Data {
if f.NCats() > 0 {
encode = true
}
}
encoded := data
if encode && (writelibsvm || writeall) {
encoded = data.EncodeToNum()
}
trainis := make([]int, 0, foldsize*(folds-1))
//Write training and testing matrixes
for i := 0; i < folds; i++ {
trainfn := fmt.Sprintf(*train, i)
testfn := fmt.Sprintf(*test, i)
trainis = trainis[0:0]
for j := 0; j < folds; j++ {
if i != j {
trainis = append(trainis, foldis[j]...)
}
}
if writearff || writeall {
trainW, testW := openfiles(trainfn+".arff", testfn+".arff")
CloudForest.WriteArffCases(data, foldis[i], *targetname, testW)
CloudForest.WriteArffCases(data, trainis, *targetname, trainW)
}
if ((!writelibsvm) && (!writearff)) || writeall {
trainW, testW := openfiles(trainfn, testfn)
data.WriteCases(testW, foldis[i])
data.WriteCases(trainW, trainis)
}
if writelibsvm || writeall {
trainW, testW := openfiles(trainfn+".libsvm", testfn+".libsvm")
CloudForest.WriteLibSvmCases(encoded, foldis[i], *targetname, testW)
CloudForest.WriteLibSvmCases(encoded, trainis, *targetname, trainW)
}
fmt.Printf("Wrote fold %v. %v testing cases and %v training cases.\n", i, len(foldis[i]), len(trainis))
}
}
func main() {
fm := flag.String("fm",
"featurematrix.afm", "AFM formated feature matrix containing data.")
targetname := flag.String("target",
"", "The row header of the target in the feature matrix.")
train := flag.String("train",
"train_%v.fm", "Format string for training fms.")
test := flag.String("test",
"test_%v.fm", "Format string for testing fms.")
// var zipoutput bool
// flag.BoolVar(&zipoutput, "zip", false, "Output ziped files.")
var unstratified bool
flag.BoolVar(&unstratified, "unstratified", false, "Force unstratified sampeling of categorical target.")
var writelibsvm bool
flag.BoolVar(&writelibsvm, "writelibsvm", false, "Output libsvm.")
var writearff bool
flag.BoolVar(&writearff, "writearff", false, "Output arff.")
var writeall bool
flag.BoolVar(&writeall, "writeall", false, "Output all three formats.")
var folds int
flag.IntVar(&folds, "folds", 5, "Number of folds to generate.")
flag.Parse()
//Parse Data
data, err := CloudForest.LoadAFM(*fm)
if err != nil {
log.Fatal(err)
}
foldis := make([][]int, 0, folds)
foldsize := len(data.CaseLabels) / folds
fmt.Printf("%v cases, foldsize %v\n", len(data.CaseLabels), foldsize)
for i := 0; i < folds; i++ {
foldis = append(foldis, make([]int, 0, foldsize))
}
var targetf CloudForest.Feature
//find the target feature
fmt.Printf("Target : %v\n", *targetname)
targeti, ok := data.Map[*targetname]
if !ok {
fmt.Println("Target not found in data, doing unstratified sampeling.")
unstratified = true
}
if ok {
targetf = data.Data[targeti]
switch targetf.(type) {
case *CloudForest.DenseNumFeature:
unstratified = true
}
}
if unstratified {
ncases := len(data.CaseLabels)
cases := make([]int, ncases, ncases)
for i := 0; i < ncases; i++ {
cases[i] = i
}
CloudForest.SampleFirstN(&cases, nil, len(cases), 0)
for j := 0; j < folds; j++ {
for k := j * foldsize; k < (j+1)*foldsize; k++ {
foldis[j] = append(foldis[j], cases[k])
}
}
} else {
//sample folds stratified by case
fmt.Printf("Stratifying by %v classes.\n", targetf.(*CloudForest.DenseCatFeature).NCats())
bSampler := CloudForest.NewBalancedSampler(targetf.(*CloudForest.DenseCatFeature))
fmt.Printf("Stratifying by %v classes.\n", len(bSampler.Cases))
var samples []int
for i := 0; i < len(bSampler.Cases); i++ {
fmt.Printf("%v cases in class %v.\n", len(bSampler.Cases[i]), i)
//shuffle in place
CloudForest.SampleFirstN(&bSampler.Cases[i], &samples, len(bSampler.Cases[i]), 0)
stratFoldSize := len(bSampler.Cases[i]) / folds
for j := 0; j < folds; j++ {
for k := j * stratFoldSize; k < (j+1)*stratFoldSize; k++ {
foldis[j] = append(foldis[j], bSampler.Cases[i][k])
}
}
}
}
trainis := make([]int, 0, foldsize*(folds-1))
//Write training and testing matrixes
for i := 0; i < folds; i++ {
trainfn := fmt.Sprintf(*train, i)
testfn := fmt.Sprintf(*test, i)
trainis = trainis[0:0]
for j := 0; j < folds; j++ {
if i != j {
trainis = append(trainis, foldis[j]...)
}
}
if writearff || writeall {
trainW, testW := openfiles(trainfn+".arff", testfn+".arff")
CloudForest.WriteArffCases(data, foldis[i], *targetname, testW)
CloudForest.WriteArffCases(data, trainis, *targetname, trainW)
}
if ((!writelibsvm) && (!writearff)) || writeall {
trainW, testW := openfiles(trainfn, testfn)
data.WriteCases(testW, foldis[i])
data.WriteCases(trainW, trainis)
}
if writelibsvm || writeall {
trainW, testW := openfiles(trainfn+".libsvm", testfn+".libsvm")
CloudForest.WriteLibSvmCases(data, foldis[i], *targetname, testW)
CloudForest.WriteLibSvmCases(data, trainis, *targetname, trainW)
}
fmt.Printf("Wrote fold %v. %v testing cases and %v training cases.\n", i, len(foldis[i]), len(trainis))
}
}
func main() {
fm := flag.String("fm", "featurematrix.afm", "AFM formated feature matrix to use.")
rf := flag.String("rfpred", "rface.sf", "A predictor forest.")
outf := flag.String("leaves", "leaves.tsv", "a case by case sparse matrix of leaf co-occurrence in tsv format")
boutf := flag.String("branches", "", "a case by feature sparse matrix of leaf co-occurrence in tsv format")
var threads int
flag.IntVar(&threads, "threads", 1, "Parse seperate forests in n seperate threads.")
flag.Parse()
//Parse Data
data, err := CloudForest.LoadAFM(*fm)
if err != nil {
log.Fatal(err)
}
log.Print("Data file ", len(data.Data), " by ", data.Data[0].Length())
counts := new(CloudForest.SparseCounter)
var caseFeatureCounts *CloudForest.SparseCounter
if *boutf != "" {
caseFeatureCounts = new(CloudForest.SparseCounter)
}
files := strings.Split(*rf, ",")
runtime.GOMAXPROCS(threads)
fileChan := make(chan string, 0)
doneChan := make(chan int, 0)
go func() {
for _, fn := range files {
fileChan <- fn
}
}()
for i := 0; i < threads; i++ {
go func() {
for {
fn := <-fileChan
forestfile, err := os.Open(fn) // For read access.
if err != nil {
log.Fatal(err)
}
defer forestfile.Close()
forestreader := CloudForest.NewForestReader(forestfile)
forest, err := forestreader.ReadForest()
if err != nil {
log.Fatal(err)
}
log.Print("Forest has ", len(forest.Trees), " trees ")
for i := 0; i < len(forest.Trees); i++ {
leaves := forest.Trees[i].GetLeaves(data, caseFeatureCounts)
for _, leaf := range leaves {
for j := 0; j < len(leaf.Cases); j++ {
for k := 0; k < len(leaf.Cases); k++ {
counts.Add(leaf.Cases[j], leaf.Cases[k], 1)
}
}
}
}
doneChan <- 1
}
}()
}
for i := 0; i < len(files); i++ {
<-doneChan
}
log.Print("Outputting Case Case Co-Occurrence Counts")
outfile, err := os.Create(*outf) // For read access.
if err != nil {
log.Fatal(err)
}
defer outfile.Close()
counts.WriteTsv(outfile)
if *boutf != "" {
log.Print("Outputting Case Feature Co-Occurrence Counts")
boutfile, err := os.Create(*boutf) // For read access.
if err != nil {
log.Fatal(err)
}
defer boutfile.Close()
caseFeatureCounts.WriteTsv(boutfile)
}
}
func main() {
fm := flag.String("data",
"", "Data file to read.")
outfn := flag.String("out",
"", "The name of a file to write feature matrix too.")
libsvmtarget := flag.String("libsvmtarget",
"", "Output lib svm with the named feature in the first position.")
anontarget := flag.String("anontarget",
"", "Strip strings with named feature in the first position.")
blacklist := flag.String("blacklist",
"", "A list of feature id's to exclude from the set of predictors.")
flag.Parse()
//Parse Data
data, err := CloudForest.LoadAFM(*fm)
if err != nil {
log.Fatal(err)
}
blacklisted := 0
blacklistis := make([]bool, len(data.Data))
if *blacklist != "" {
fmt.Printf("Loading blacklist from: %v\n", *blacklist)
blackfile, err := os.Open(*blacklist)
if err != nil {
log.Fatal(err)
}
tsv := csv.NewReader(blackfile)
tsv.Comma = '\t'
for {
id, err := tsv.Read()
if err == io.EOF {
break
} else if err != nil {
log.Fatal(err)
}
if id[0] == *anontarget || id[0] == *libsvmtarget {
continue
}
i, ok := data.Map[id[0]]
if !ok {
fmt.Printf("Ignoring blacklist feature not found in data: %v\n", id[0])
continue
}
if !blacklistis[i] {
blacklisted += 1
blacklistis[i] = true
}
}
blackfile.Close()
}
newdata := make([]CloudForest.Feature, 0, len(data.Data)-blacklisted)
newmap := make(map[string]int, len(data.Data)-blacklisted)
for i, f := range data.Data {
if !blacklistis[i] {
newmap[f.GetName()] = len(newdata)
newdata = append(newdata, f)
}
}
data.Data = newdata
data.Map = newmap
if *anontarget != "" {
data.StripStrings(*anontarget)
}
//anotate with type information
for _, f := range data.Data {
switch f.(type) {
case *CloudForest.DenseNumFeature:
nf := f.(*CloudForest.DenseNumFeature)
if !strings.HasPrefix(nf.Name, "N:") {
nf.Name = "N:" + nf.Name
}
case *CloudForest.DenseCatFeature:
nf := f.(*CloudForest.DenseCatFeature)
if !(strings.HasPrefix(nf.Name, "C:") || strings.HasPrefix(nf.Name, "B:")) {
nf.Name = "C:" + nf.Name
}
}
}
ncases := data.Data[0].Length()
cases := make([]int, ncases, ncases)
for i := 0; i < ncases; i++ {
cases[i] = i
}
outfile, err := os.Create(*outfn)
if err != nil {
log.Fatal(err)
}
defer outfile.Close()
if *libsvmtarget == "" {
err = data.WriteCases(outfile, cases)
if err != nil {
log.Fatal(err)
}
} else {
// targeti, ok := data.Map[*libsvmtarget]
// if !ok {
// log.Fatalf("Target '%v' not found in data.", *libsvmtarget)
// }
// target := data.Data[targeti]
// data.Data = append(data.Data[:targeti], data.Data[targeti+1:]...)
// encodedfm := data.EncodeToNum()
// oucsv := csv.NewWriter(outfile)
// oucsv.Comma = ' '
// for i := 0; i < target.Length(); i++ {
// entries := make([]string, 0, 10)
// switch target.(type) {
// case CloudForest.NumFeature:
// entries = append(entries, target.GetStr(i))
// case CloudForest.CatFeature:
// entries = append(entries, fmt.Sprintf("%v", target.(CloudForest.CatFeature).Geti(i)))
// }
// for j, f := range encodedfm.Data {
// v := f.(CloudForest.NumFeature).Get(i)
// if v != 0.0 {
// entries = append(entries, fmt.Sprintf("%v:%v", j+1, v))
// }
// }
// //fmt.Println(entries)
// err := oucsv.Write(entries)
// if err != nil {
// log.Fatalf("Error writing libsvm:\n%v", err)
// }
// }
// oucsv.Flush()
err = CloudForest.WriteLibSvm(data, *libsvmtarget, outfile)
if err != nil {
log.Fatalf("Error writing libsvm:\n%v", err)
}
}
}