func (*Tool) Run(args []string) {
fmt.Println("running logistic regression")
n := 1000
p := 10
beta := make([]float64, p)
beta[0] = rand.NormFloat64()
beta[1] = rand.NormFloat64()
x := la.NewMatrix(n, p)
y := la.NewVector(n)
for i := 0; i < n; i++ {
v := randVec(p)
var z float64
for j := 0; j < p; j++ {
x.Set(i, j, v[j])
z += beta[j]
}
if z > 0 {
y.Set(i, +1)
} else {
y.Set(i, -1)
}
}
rp := &model.RegressionProblem{
N: n,
P: p,
Data: x,
Response: y,
ColumnNames: names("p", p),
RowNames: names("x", n),
ResponseName: "y",
}
rc := &model.LogisticRegressionRisk{}
pc := model.NewLassoPenalty(p)
dv := 0.001
vmax := 0.07
mon := &FixedVMonitor{vmax}
oa := &model.RandomAssigner{rp.Data.Rows, 2.0 / 3.0}
tt := oa.Assign()
results := model.RunGpsFull(rp, tt, dv, rc, pc, mon.Continue)
fmt.Println(results)
}
func Load() (*model.RegressionProblem, *model.ObservationAssignments) {
scanner := bufio.NewScanner(strings.NewReader(CancerDataCSV))
var lines [][]string
for scanner.Scan() {
lines = append(lines, strings.Split(scanner.Text(), "\t"))
}
if scanner.Err() != nil {
panic("can't read data")
}
var test, train []int
var rowNames []string
header := lines[0]
m := la.NewMatrix(len(lines)-1, 8)
for i := 0; i < m.Rows; i++ {
for j := 0; j < m.Cols; j++ {
if f, err := strconv.ParseFloat(strings.TrimSpace(lines[i+1][j+1]), 64); err == nil {
m.Set(i, j, f)
}
}
switch lines[i+1][10] {
case "T":
train = append(train, i)
case "F":
test = append(test, i)
}
rowNames = append(rowNames, lines[i+1][0])
}
y := la.NewVector(len(lines) - 1)
for i := 0; i < y.Size; i++ {
if f, err := strconv.ParseFloat(strings.TrimSpace(lines[i+1][9]), 64); err == nil {
y.Set(i, f)
}
}
out := model.RegressionProblem{
N: m.Rows,
P: m.Cols,
Data: m,
Response: y,
ColumnNames: header[1 : len(header)-2],
RowNames: rowNames,
ResponseName: header[9],
}
tt := model.ObservationAssignments{
TrainingIndicies: train,
TestingIndicies: test,
}
return &out, &tt
}