mirror of
https://github.com/sjwhitworth/golearn.git
synced 2025-04-26 13:49:14 +08:00
Removing Clutter
Partial Modularization of best split method. Shorten method by declaring variables in same line as well. Also removing redundant functions, and adding into cart_utils.
This commit is contained in:
parent
ef751e62c4
commit
2d2af0a58f
@ -90,6 +90,16 @@ func entropy(y []int64, labels []int64) (float64, int64) {
|
||||
return entropy, maxLabel
|
||||
}
|
||||
|
||||
func calculateClassificationLoss(y []int64, labels []int64, criterion string) (float64, int64) {
|
||||
if criterion == GINI {
|
||||
return giniImpurity(y, labels)
|
||||
} else if criterion == ENTROPY {
|
||||
return entropy(y, labels)
|
||||
} else {
|
||||
panic("Invalid impurity function, choose from GINI or ENTROPY")
|
||||
}
|
||||
}
|
||||
|
||||
// Split the data into left node and right node based on feature and threshold
|
||||
func classifierCreateSplit(data [][]float64, feature int64, y []int64, threshold float64) ([][]float64, [][]float64, []int64, []int64) {
|
||||
var left [][]float64
|
||||
@ -111,37 +121,6 @@ func classifierCreateSplit(data [][]float64, feature int64, y []int64, threshold
|
||||
return left, right, lefty, righty
|
||||
}
|
||||
|
||||
// Helper Function to check if data point is unique or not.
|
||||
// We will use this to isolate unique values of a feature
|
||||
func classifierStringInSlice(a float64, list []float64) bool {
|
||||
for _, b := range list {
|
||||
if b == a {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// Isolate only unique values. This way, we can try only unique splits and not redundant ones.
|
||||
func classifierFindUnique(data []float64) []float64 {
|
||||
var unique []float64
|
||||
for i := range data {
|
||||
if !classifierStringInSlice(data[i], unique) {
|
||||
unique = append(unique, data[i])
|
||||
}
|
||||
}
|
||||
return unique
|
||||
}
|
||||
|
||||
// Isolate only the feature being considered for splitting. Reduces the complexity in managing splits.
|
||||
func classifierGetFeature(data [][]float64, feature int64) []float64 {
|
||||
var featureVals []float64
|
||||
for i := range data {
|
||||
featureVals = append(featureVals, data[i][feature])
|
||||
}
|
||||
return featureVals
|
||||
}
|
||||
|
||||
// Function to Create New Decision Tree Classifier.
|
||||
// It assigns all of the hyperparameters by user into the tree attributes.
|
||||
func NewDecisionTreeClassifier(criterion string, maxDepth int64, labels []int64) *CARTDecisionTreeClassifier {
|
||||
@ -153,19 +132,6 @@ func NewDecisionTreeClassifier(criterion string, maxDepth int64, labels []int64)
|
||||
return &tree
|
||||
}
|
||||
|
||||
// Make sure that split being considered has not been done before.
|
||||
// Else we will unnecessarily try splits that won't improve Impurity.
|
||||
func classifierValidate(triedSplits [][]float64, feature int64, threshold float64) bool {
|
||||
for i := range triedSplits {
|
||||
split := triedSplits[i]
|
||||
featureTried, thresholdTried := split[0], split[1]
|
||||
if int64(featureTried) == feature && thresholdTried == threshold {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// Reorder the data by feature being considered. Optimizes code by reducing the number of times we have to loop over data for splitting
|
||||
func classifierReOrderData(featureVal []float64, data [][]float64, y []int64) ([][]float64, []int64) {
|
||||
s := NewSlice(featureVal)
|
||||
@ -202,7 +168,7 @@ func classifierUpdateSplit(left [][]float64, lefty []int64, right [][]float64, r
|
||||
func (tree *CARTDecisionTreeClassifier) Fit(X base.FixedDataGrid) {
|
||||
var emptyNode classifierNode
|
||||
|
||||
data := classifierConvertInstancesToProblemVec(X)
|
||||
data := convertInstancesToProblemVec(X)
|
||||
y := classifierConvertInstancesToLabelVec(X)
|
||||
emptyNode = classifierBestSplit(*tree, data, y, tree.labels, emptyNode, tree.criterion, tree.maxDepth, 0)
|
||||
|
||||
@ -221,40 +187,29 @@ func classifierBestSplit(tree CARTDecisionTreeClassifier, data [][]float64, y []
|
||||
}
|
||||
|
||||
numFeatures := len(data[0])
|
||||
var bestGini float64
|
||||
var origGini float64
|
||||
var bestGini, origGini float64
|
||||
|
||||
// Calculate loss based on Criterion Specified by user
|
||||
if criterion == GINI {
|
||||
origGini, upperNode.LeftLabel = giniImpurity(y, labels)
|
||||
} else if criterion == ENTROPY {
|
||||
origGini, upperNode.LeftLabel = entropy(y, labels)
|
||||
} else {
|
||||
panic("Invalid impurity function, choose from GINI or ENTROPY")
|
||||
}
|
||||
origGini, upperNode.LeftLabel = calculateClassificationLoss(y, labels, criterion)
|
||||
|
||||
bestGini = origGini
|
||||
|
||||
bestLeft := data
|
||||
bestRight := data
|
||||
bestLefty := y
|
||||
bestRighty := y
|
||||
bestLeft, bestRight, bestLefty, bestRighty := data, data, y, y
|
||||
|
||||
numData := len(data)
|
||||
|
||||
bestLeftGini := bestGini
|
||||
bestRightGini := bestGini
|
||||
bestLeftGini, bestRightGini := bestGini, bestGini
|
||||
|
||||
upperNode.Use_not = true
|
||||
|
||||
var leftN classifierNode
|
||||
var rightN classifierNode
|
||||
var leftN, rightN classifierNode
|
||||
|
||||
// Iterate over all features
|
||||
for i := 0; i < numFeatures; i++ {
|
||||
featureVal := classifierGetFeature(data, int64(i))
|
||||
unique := classifierFindUnique(featureVal)
|
||||
|
||||
featureVal := getFeature(data, int64(i))
|
||||
unique := findUnique(featureVal)
|
||||
sort.Float64s(unique)
|
||||
numUnique := len(unique)
|
||||
|
||||
sortData, sortY := classifierReOrderData(featureVal, data, y)
|
||||
|
||||
@ -263,53 +218,43 @@ func classifierBestSplit(tree CARTDecisionTreeClassifier, data [][]float64, y []
|
||||
var left, right [][]float64
|
||||
var lefty, righty []int64
|
||||
// Iterate over all possible thresholds for that feature
|
||||
for j := range unique {
|
||||
if j != (numUnique - 1) {
|
||||
threshold := (unique[j] + unique[j+1]) / 2
|
||||
// Ensure that same split has not been made before
|
||||
if classifierValidate(tree.triedSplits, int64(i), threshold) {
|
||||
// We need to split data from fresh when considering new feature for the first time.
|
||||
// Otherwise, we need to update the split by moving data points from left to right.
|
||||
if firstTime {
|
||||
left, right, lefty, righty = classifierCreateSplit(sortData, int64(i), sortY, threshold)
|
||||
firstTime = false
|
||||
} else {
|
||||
left, lefty, right, righty = classifierUpdateSplit(left, lefty, right, righty, int64(i), threshold)
|
||||
}
|
||||
for j := 0; j < len(unique)-1; j++ {
|
||||
|
||||
var leftGini float64
|
||||
var rightGini float64
|
||||
var leftLabels int64
|
||||
var rightLabels int64
|
||||
|
||||
if criterion == GINI {
|
||||
leftGini, leftLabels = giniImpurity(lefty, labels)
|
||||
rightGini, rightLabels = giniImpurity(righty, labels)
|
||||
} else if criterion == ENTROPY {
|
||||
leftGini, leftLabels = entropy(lefty, labels)
|
||||
rightGini, rightLabels = entropy(righty, labels)
|
||||
}
|
||||
// Calculate weighted gini impurity of child nodes
|
||||
subGini := (leftGini * float64(len(left)) / float64(numData)) + (rightGini * float64(len(right)) / float64(numData))
|
||||
|
||||
// If we find a split that reduces impurity
|
||||
if subGini < bestGini {
|
||||
bestGini = subGini
|
||||
bestLeft = left
|
||||
bestRight = right
|
||||
bestLefty = lefty
|
||||
bestRighty = righty
|
||||
upperNode.Threshold = threshold
|
||||
upperNode.Feature = int64(i)
|
||||
|
||||
upperNode.LeftLabel = leftLabels
|
||||
upperNode.RightLabel = rightLabels
|
||||
|
||||
bestLeftGini = leftGini
|
||||
bestRightGini = rightGini
|
||||
}
|
||||
threshold := (unique[j] + unique[j+1]) / 2
|
||||
// Ensure that same split has not been made before
|
||||
if validate(tree.triedSplits, int64(i), threshold) {
|
||||
// We need to split data from fresh when considering new feature for the first time.
|
||||
// Otherwise, we need to update the split by moving data points from left to right.
|
||||
if firstTime {
|
||||
left, right, lefty, righty = classifierCreateSplit(sortData, int64(i), sortY, threshold)
|
||||
firstTime = false
|
||||
} else {
|
||||
left, lefty, right, righty = classifierUpdateSplit(left, lefty, right, righty, int64(i), threshold)
|
||||
}
|
||||
|
||||
var leftGini, rightGini float64
|
||||
var leftLabels, rightLabels int64
|
||||
|
||||
leftGini, leftLabels = calculateClassificationLoss(lefty, labels, criterion)
|
||||
rightGini, rightLabels = calculateClassificationLoss(righty, labels, criterion)
|
||||
|
||||
// Calculate weighted gini impurity of child nodes
|
||||
subGini := (leftGini * float64(len(left)) / float64(numData)) + (rightGini * float64(len(right)) / float64(numData))
|
||||
|
||||
// If we find a split that reduces impurity
|
||||
if subGini < bestGini {
|
||||
bestGini = subGini
|
||||
|
||||
bestLeft, bestRight = left, right
|
||||
|
||||
bestLefty, bestRighty = lefty, righty
|
||||
|
||||
upperNode.Threshold, upperNode.Feature = threshold, int64(i)
|
||||
|
||||
upperNode.LeftLabel, upperNode.RightLabel = leftLabels, rightLabels
|
||||
|
||||
bestLeftGini, bestRightGini = leftGini, rightGini
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -366,10 +311,8 @@ func classifierPrintTreeFromNode(tree classifierNode, spacing string) string {
|
||||
returnString += spacing + "---> True" + "\n"
|
||||
returnString += " " + spacing + "PREDICT "
|
||||
returnString += strconv.FormatInt(tree.LeftLabel, 10) + "\n"
|
||||
|
||||
}
|
||||
if tree.Right == nil {
|
||||
|
||||
returnString += spacing + "---> False" + "\n"
|
||||
returnString += " " + spacing + "PREDICT "
|
||||
returnString += strconv.FormatInt(tree.RightLabel, 10) + "\n"
|
||||
@ -409,7 +352,7 @@ func classifierPredictSingle(tree classifierNode, instance []float64) int64 {
|
||||
// Given test data, return predictions for every datapoint. calls classifierPredictFromNode
|
||||
func (tree *CARTDecisionTreeClassifier) Predict(X_test base.FixedDataGrid) []int64 {
|
||||
root := *tree.RootNode
|
||||
test := classifierConvertInstancesToProblemVec(X_test)
|
||||
test := convertInstancesToProblemVec(X_test)
|
||||
return classifierPredictFromNode(root, test)
|
||||
}
|
||||
|
||||
@ -429,7 +372,7 @@ func classifierPredictFromNode(tree classifierNode, test [][]float64) []int64 {
|
||||
// Calls classifierEvaluateFromNode
|
||||
func (tree *CARTDecisionTreeClassifier) Evaluate(test base.FixedDataGrid) float64 {
|
||||
rootNode := *tree.RootNode
|
||||
xTest := classifierConvertInstancesToProblemVec(test)
|
||||
xTest := convertInstancesToProblemVec(test)
|
||||
yTest := classifierConvertInstancesToLabelVec(test)
|
||||
return classifierEvaluateFromNode(rootNode, xTest, yTest)
|
||||
}
|
||||
@ -447,31 +390,6 @@ func classifierEvaluateFromNode(tree classifierNode, xTest [][]float64, yTest []
|
||||
return accuracy
|
||||
}
|
||||
|
||||
// Helper function to convert base.FixedDataGrid into required format. Called in Fit, Predict
|
||||
func classifierConvertInstancesToProblemVec(X base.FixedDataGrid) [][]float64 {
|
||||
// Allocate problem array
|
||||
_, rows := X.Size()
|
||||
problemVec := make([][]float64, rows)
|
||||
|
||||
// Retrieve numeric non-class Attributes
|
||||
numericAttrs := base.NonClassFloatAttributes(X)
|
||||
numericAttrSpecs := base.ResolveAttributes(X, numericAttrs)
|
||||
|
||||
// Convert each row
|
||||
X.MapOverRows(numericAttrSpecs, func(row [][]byte, rowNo int) (bool, error) {
|
||||
// Allocate a new row
|
||||
probRow := make([]float64, len(numericAttrSpecs))
|
||||
// Read out the row
|
||||
for i, _ := range numericAttrSpecs {
|
||||
probRow[i] = base.UnpackBytesToFloat(row[i])
|
||||
}
|
||||
// Add the row
|
||||
problemVec[rowNo] = probRow
|
||||
return true, nil
|
||||
})
|
||||
return problemVec
|
||||
}
|
||||
|
||||
// Helper function to convert base.FixedDataGrid into required format. Called in Fit, Predict
|
||||
func classifierConvertInstancesToLabelVec(X base.FixedDataGrid) []int64 {
|
||||
// Get the class Attributes
|
||||
|
@ -81,6 +81,16 @@ func mseImpurity(y []float64) (float64, float64) {
|
||||
return meanSquaredError(y, yHat), yHat
|
||||
}
|
||||
|
||||
func calculateRegressionLoss(y []float64, criterion string) (float64, float64) {
|
||||
if criterion == MAE {
|
||||
return maeImpurity(y)
|
||||
} else if criterion == MSE {
|
||||
return mseImpurity(y)
|
||||
} else {
|
||||
panic("Invalid impurity function, choose from MAE or MSE")
|
||||
}
|
||||
}
|
||||
|
||||
// Split the data into left and right based on trehsold and feature.
|
||||
func regressorCreateSplit(data [][]float64, feature int64, y []float64, threshold float64) ([][]float64, [][]float64, []float64, []float64) {
|
||||
var left [][]float64
|
||||
@ -102,39 +112,6 @@ func regressorCreateSplit(data [][]float64, feature int64, y []float64, threshol
|
||||
return left, right, lefty, righty
|
||||
}
|
||||
|
||||
// Helper function for finding unique values.
|
||||
// Used for isolating unique values in a feature.
|
||||
func regressorStringInSlice(a float64, list []float64) bool {
|
||||
for _, b := range list {
|
||||
if b == a {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// Isolate only unique values.
|
||||
// This way we can only try unique splits.
|
||||
func regressorFindUnique(data []float64) []float64 {
|
||||
var unique []float64
|
||||
for i := range data {
|
||||
if !regressorStringInSlice(data[i], unique) {
|
||||
unique = append(unique, data[i])
|
||||
}
|
||||
}
|
||||
return unique
|
||||
}
|
||||
|
||||
// Extract out a single feature from data.
|
||||
// Reduces complexity in managing splits and sorting
|
||||
func regressorGetFeature(data [][]float64, feature int64) []float64 {
|
||||
var featureVals []float64
|
||||
for i := range data {
|
||||
featureVals = append(featureVals, data[i][feature])
|
||||
}
|
||||
return featureVals
|
||||
}
|
||||
|
||||
// Interface for creating new Decision Tree Regressor
|
||||
func NewDecisionTreeRegressor(criterion string, maxDepth int64) *CARTDecisionTreeRegressor {
|
||||
var tree CARTDecisionTreeRegressor
|
||||
@ -143,19 +120,6 @@ func NewDecisionTreeRegressor(criterion string, maxDepth int64) *CARTDecisionTre
|
||||
return &tree
|
||||
}
|
||||
|
||||
// Validate that the split being tested has not been done before.
|
||||
// This prevents redundant splits from hapenning.
|
||||
func regressorValidate(triedSplits [][]float64, feature int64, threshold float64) bool {
|
||||
for i := range triedSplits {
|
||||
split := triedSplits[i]
|
||||
featureTried, thresholdTried := split[0], split[1]
|
||||
if int64(featureTried) == feature && thresholdTried == threshold {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// Re order data based on a feature for optimizing code
|
||||
// Helps in updating splits without reiterating entire dataset
|
||||
func regressorReOrderData(featureVal []float64, data [][]float64, y []float64) ([][]float64, []float64) {
|
||||
@ -204,6 +168,7 @@ func (tree *CARTDecisionTreeRegressor) Fit(X base.FixedDataGrid) {
|
||||
// Recursive function - stops if maxDepth is reached or nodes are pure
|
||||
func regressorBestSplit(tree CARTDecisionTreeRegressor, data [][]float64, y []float64, upperNode regressorNode, criterion string, maxDepth int64, depth int64) regressorNode {
|
||||
|
||||
// Ensure that we have not reached maxDepth. maxDepth =-1 means split until nodes are pure
|
||||
depth++
|
||||
|
||||
if depth > maxDepth && maxDepth != -1 {
|
||||
@ -211,39 +176,27 @@ func regressorBestSplit(tree CARTDecisionTreeRegressor, data [][]float64, y []fl
|
||||
}
|
||||
|
||||
numFeatures := len(data[0])
|
||||
var bestLoss float64
|
||||
var origLoss float64
|
||||
var bestLoss, origLoss float64
|
||||
|
||||
if criterion == MAE {
|
||||
origLoss, upperNode.LeftPred = maeImpurity(y)
|
||||
} else if criterion == MSE {
|
||||
origLoss, upperNode.LeftPred = mseImpurity(y)
|
||||
} else {
|
||||
panic("Invalid impurity function, choose from MAE or MSE")
|
||||
}
|
||||
origLoss, upperNode.LeftPred = calculateRegressionLoss(y, criterion)
|
||||
|
||||
bestLoss = origLoss
|
||||
|
||||
bestLeft := data
|
||||
bestRight := data
|
||||
bestLefty := y
|
||||
bestRighty := y
|
||||
bestLeft, bestRight, bestLefty, bestRighty := data, data, y, y
|
||||
|
||||
numData := len(data)
|
||||
|
||||
bestLeftLoss := bestLoss
|
||||
bestRightLoss := bestLoss
|
||||
bestLeftLoss, bestRightLoss := bestLoss, bestLoss
|
||||
|
||||
upperNode.Use_not = true
|
||||
|
||||
var leftN regressorNode
|
||||
var rightN regressorNode
|
||||
var leftN, rightN regressorNode
|
||||
// Iterate over all features
|
||||
for i := 0; i < numFeatures; i++ {
|
||||
featureVal := regressorGetFeature(data, int64(i))
|
||||
unique := regressorFindUnique(featureVal)
|
||||
|
||||
featureVal := getFeature(data, int64(i))
|
||||
unique := findUnique(featureVal)
|
||||
sort.Float64s(unique)
|
||||
numUnique := len(unique)
|
||||
|
||||
sortData, sortY := regressorReOrderData(featureVal, data, y)
|
||||
|
||||
@ -252,49 +205,36 @@ func regressorBestSplit(tree CARTDecisionTreeRegressor, data [][]float64, y []fl
|
||||
var left, right [][]float64
|
||||
var lefty, righty []float64
|
||||
|
||||
for j := range unique {
|
||||
if j != (numUnique - 1) {
|
||||
threshold := (unique[j] + unique[j+1]) / 2
|
||||
if regressorValidate(tree.triedSplits, int64(i), threshold) {
|
||||
if firstTime {
|
||||
left, right, lefty, righty = regressorCreateSplit(sortData, int64(i), sortY, threshold)
|
||||
firstTime = false
|
||||
} else {
|
||||
left, lefty, right, righty = regressorUpdateSplit(left, lefty, right, righty, int64(i), threshold)
|
||||
}
|
||||
|
||||
var leftLoss float64
|
||||
var rightLoss float64
|
||||
var leftPred float64
|
||||
var rightPred float64
|
||||
|
||||
if criterion == MAE {
|
||||
leftLoss, leftPred = maeImpurity(lefty)
|
||||
rightLoss, rightPred = maeImpurity(righty)
|
||||
} else if criterion == MSE {
|
||||
leftLoss, leftPred = mseImpurity(lefty)
|
||||
rightLoss, rightPred = mseImpurity(righty)
|
||||
}
|
||||
|
||||
subLoss := (leftLoss * float64(len(left)) / float64(numData)) + (rightLoss * float64(len(right)) / float64(numData))
|
||||
|
||||
if subLoss < bestLoss {
|
||||
bestLoss = subLoss
|
||||
bestLeft = left
|
||||
bestRight = right
|
||||
bestLefty = lefty
|
||||
bestRighty = righty
|
||||
upperNode.Threshold = threshold
|
||||
upperNode.Feature = int64(i)
|
||||
|
||||
upperNode.LeftPred = leftPred
|
||||
upperNode.RightPred = rightPred
|
||||
|
||||
bestLeftLoss = leftLoss
|
||||
bestRightLoss = rightLoss
|
||||
}
|
||||
for j := 0; j < len(unique)-1; j++ {
|
||||
threshold := (unique[j] + unique[j+1]) / 2
|
||||
if validate(tree.triedSplits, int64(i), threshold) {
|
||||
if firstTime {
|
||||
left, right, lefty, righty = regressorCreateSplit(sortData, int64(i), sortY, threshold)
|
||||
firstTime = false
|
||||
} else {
|
||||
left, lefty, right, righty = regressorUpdateSplit(left, lefty, right, righty, int64(i), threshold)
|
||||
}
|
||||
|
||||
var leftLoss, rightLoss float64
|
||||
var leftPred, rightPred float64
|
||||
|
||||
leftLoss, leftPred = calculateRegressionLoss(lefty, criterion)
|
||||
rightLoss, rightPred = calculateRegressionLoss(righty, criterion)
|
||||
|
||||
subLoss := (leftLoss * float64(len(left)) / float64(numData)) + (rightLoss * float64(len(right)) / float64(numData))
|
||||
|
||||
if subLoss < bestLoss {
|
||||
bestLoss = subLoss
|
||||
|
||||
bestLeft, bestRight = left, right
|
||||
bestLefty, bestRighty = lefty, righty
|
||||
|
||||
upperNode.Threshold, upperNode.Feature = threshold, int64(i)
|
||||
|
||||
upperNode.LeftPred, upperNode.RightPred = leftPred, rightPred
|
||||
|
||||
bestLeftLoss, bestRightLoss = leftLoss, rightLoss
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -312,19 +252,16 @@ func regressorBestSplit(tree CARTDecisionTreeRegressor, data [][]float64, y []fl
|
||||
if leftN.Use_not == true {
|
||||
upperNode.Left = &leftN
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
if bestRightLoss > 0 {
|
||||
tree.triedSplits = append(tree.triedSplits, []float64{float64(upperNode.Feature), upperNode.Threshold})
|
||||
rightN = regressorBestSplit(tree, bestRight, bestRighty, rightN, criterion, maxDepth, depth)
|
||||
if rightN.Use_not == true {
|
||||
upperNode.Right = &rightN
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
return upperNode
|
||||
}
|
||||
|
||||
@ -349,20 +286,17 @@ func regressorPrintTreeFromNode(tree regressorNode, spacing string) string {
|
||||
returnString += fmt.Sprintf("%.3f", tree.LeftPred) + "\n"
|
||||
}
|
||||
if tree.Right == nil {
|
||||
|
||||
returnString += spacing + "---> False" + "\n"
|
||||
returnString += " " + spacing + "PREDICT "
|
||||
returnString += fmt.Sprintf("%.3f", tree.RightPred) + "\n"
|
||||
}
|
||||
|
||||
if tree.Left != nil {
|
||||
// fmt.Println(spacing + "---> True")
|
||||
returnString += spacing + "---> True" + "\n"
|
||||
returnString += regressorPrintTreeFromNode(*tree.Left, spacing+" ")
|
||||
}
|
||||
|
||||
if tree.Right != nil {
|
||||
// fmt.Println(spacing + "---> False")
|
||||
returnString += spacing + "---> False" + "\n"
|
||||
returnString += regressorPrintTreeFromNode(*tree.Right, spacing+" ")
|
||||
}
|
||||
|
@ -38,10 +38,10 @@ func TestRegressor(t *testing.T) {
|
||||
So(len(righty), ShouldEqual, 2)
|
||||
|
||||
// Is isolating unique values working properly
|
||||
So(len(classifierFindUnique([]float64{10, 1, 1})), ShouldEqual, 2)
|
||||
So(len(findUnique([]float64{10, 1, 1})), ShouldEqual, 2)
|
||||
|
||||
// is data reordered correctly
|
||||
orderedData, orderedY := classifierReOrderData(classifierGetFeature(classifierData, 1), classifierData, classifiery)
|
||||
orderedData, orderedY := classifierReOrderData(getFeature(classifierData, 1), classifierData, classifiery)
|
||||
fmt.Println(orderedData)
|
||||
fmt.Println(orderedY)
|
||||
So(orderedData[1][1], ShouldEqual, 3.0)
|
||||
@ -85,11 +85,8 @@ func TestRegressor(t *testing.T) {
|
||||
So(len(rightData), ShouldEqual, 2)
|
||||
So(len(righty), ShouldEqual, 2)
|
||||
|
||||
// Is isolating unique values working properly
|
||||
So(len(regressorFindUnique([]float64{10, 1, 1})), ShouldEqual, 2)
|
||||
|
||||
// is data reordered correctly
|
||||
regressorOrderedData, regressorOrderedY := regressorReOrderData(regressorGetFeature(data, 1), data, y)
|
||||
regressorOrderedData, regressorOrderedY := regressorReOrderData(getFeature(data, 1), data, y)
|
||||
|
||||
So(regressorOrderedData[1][1], ShouldEqual, 3.0)
|
||||
So(regressorOrderedY[0], ShouldEqual, 2)
|
||||
|
74
trees/cart_utils.go
Normal file
74
trees/cart_utils.go
Normal file
@ -0,0 +1,74 @@
|
||||
package trees
|
||||
|
||||
import (
|
||||
"github.com/sjwhitworth/golearn/base"
|
||||
)
|
||||
|
||||
// Helper Function to check if data point is unique or not.
|
||||
// We will use this to isolate unique values of a feature
|
||||
func stringInSlice(a float64, list []float64) bool {
|
||||
for _, b := range list {
|
||||
if b == a {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// Isolate only unique values. This way, we can try only unique splits and not redundant ones.
|
||||
func findUnique(data []float64) []float64 {
|
||||
var unique []float64
|
||||
for i := range data {
|
||||
if !stringInSlice(data[i], unique) {
|
||||
unique = append(unique, data[i])
|
||||
}
|
||||
}
|
||||
return unique
|
||||
}
|
||||
|
||||
// Isolate only the feature being considered for splitting. Reduces the complexity in managing splits.
|
||||
func getFeature(data [][]float64, feature int64) []float64 {
|
||||
var featureVals []float64
|
||||
for i := range data {
|
||||
featureVals = append(featureVals, data[i][feature])
|
||||
}
|
||||
return featureVals
|
||||
}
|
||||
|
||||
// Make sure that split being considered has not been done before.
|
||||
// Else we will unnecessarily try splits that won't improve Impurity.
|
||||
func validate(triedSplits [][]float64, feature int64, threshold float64) bool {
|
||||
for i := range triedSplits {
|
||||
split := triedSplits[i]
|
||||
featureTried, thresholdTried := split[0], split[1]
|
||||
if int64(featureTried) == feature && thresholdTried == threshold {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// Helper function to convert base.FixedDataGrid into required format. Called in Fit, Predict
|
||||
func convertInstancesToProblemVec(X base.FixedDataGrid) [][]float64 {
|
||||
// Allocate problem array
|
||||
_, rows := X.Size()
|
||||
problemVec := make([][]float64, rows)
|
||||
|
||||
// Retrieve numeric non-class Attributes
|
||||
numericAttrs := base.NonClassFloatAttributes(X)
|
||||
numericAttrSpecs := base.ResolveAttributes(X, numericAttrs)
|
||||
|
||||
// Convert each row
|
||||
X.MapOverRows(numericAttrSpecs, func(row [][]byte, rowNo int) (bool, error) {
|
||||
// Allocate a new row
|
||||
probRow := make([]float64, len(numericAttrSpecs))
|
||||
// Read out the row
|
||||
for i, _ := range numericAttrSpecs {
|
||||
probRow[i] = base.UnpackBytesToFloat(row[i])
|
||||
}
|
||||
// Add the row
|
||||
problemVec[rowNo] = probRow
|
||||
return true, nil
|
||||
})
|
||||
return problemVec
|
||||
}
|
Loading…
x
Reference in New Issue
Block a user