Comments should be of the form "<Struct> ..." or "<MethodName> ..."

base/csv.go

@@ -43,7 +43,7 @@ func ParseCSVGetAttributes(filepath string, hasHeaders bool) []Attribute {
 	return attrs
 }
 
-// ParseCsvSniffAttributeNames returns a slice containing the top row
+// ParseCSVSniffAttributeNames returns a slice containing the top row
 // of a given CSV file, or placeholders if hasHeaders is false.
 func ParseCSVSniffAttributeNames(filepath string, hasHeaders bool) []string {
 	file, err := os.Open(filepath)

base/domain.go

@@ -12,17 +12,18 @@ import (
 	mat64 "github.com/gonum/matrix/mat64"
 )
 
-// An object that can ingest some data and train on it.
+// An Estimator is object that can ingest some data and train on it.
 type Estimator interface {
 	Fit()
 }
 
-// An object that provides predictions.
+// A Predictor is an object that provides predictions.
 type Predictor interface {
 	Predict()
 }
 
-// An supervised learning object, that is possible of scoring accuracy against a test set.
+// A Model is a supervised learning object, that is
+// possible of scoring accuracy against a test set.
 type Model interface {
 	Score()
 }
@@ -31,7 +32,7 @@ type BaseEstimator struct {
 	Data *mat64.Dense
 }
 
-// Serialises an estimator to a provided filepath, in gob format.
+// SaveEstimatorToGob serialises an estimator to a provided filepath, in gob format.
 // See http://golang.org/pkg/encoding/gob for further details.
 func SaveEstimatorToGob(path string, e *Estimator) {
 	b := new(bytes.Buffer)

base/instances.go

@@ -319,7 +319,7 @@ func (inst *Instances) GetRowVector(row int) []float64 {
 	return inst.storage.RowView(row)
 }
 
-// GetRowVector returns a row of system representation
+// GetRowVectorWithoutClass returns a row of system representation
 // values at the given row index, excluding the class attribute
 func (inst *Instances) GetRowVectorWithoutClass(row int) []float64 {
 	rawRow := make([]float64, inst.Cols)
@@ -336,7 +336,7 @@ func (inst *Instances) GetClass(row int) string {
 	return attr.GetStringFromSysVal(val)
 }
 
-// GetClassDist returns a map containing the count of each
+// GetClassDistribution returns a map containing the count of each
 // class type (indexed by the class' string representation)
 func (inst *Instances) GetClassDistribution() map[string]int {
 	ret := make(map[string]int)

ensemble/randomforest.go

@@ -1,10 +1,10 @@
 package ensemble
 
 import (
+	"fmt"
 	base "github.com/sjwhitworth/golearn/base"
 	meta "github.com/sjwhitworth/golearn/meta"
 	trees "github.com/sjwhitworth/golearn/trees"
-	"fmt"
 )
 
 // RandomForest classifies instances using an ensemble
@@ -16,7 +16,7 @@ type RandomForest struct {
 	Model      *meta.BaggedModel
 }
 
-// NewRandomForests generates and return a new random forests
+// NewRandomForest generates and return a new random forests
 // forestSize controls the number of trees that get built
 // features controls the number of features used to build each tree
 func NewRandomForest(forestSize int, features int) *RandomForest {
@@ -29,7 +29,7 @@ func NewRandomForest(forestSize int, features int) *RandomForest {
 	return ret
 }
 
-// Train builds the RandomForest on the specified instances
+// Fit builds the RandomForest on the specified instances
 func (f *RandomForest) Fit(on *base.Instances) {
 	f.Model = new(meta.BaggedModel)
 	f.Model.RandomFeatures = f.Features
@@ -47,4 +47,4 @@ func (f *RandomForest) Predict(with *base.Instances) *base.Instances {
 
 func (f *RandomForest) String() string {
 	return fmt.Sprintf("RandomForest(ForestSize: %d, Features:%d, %s\n)", f.ForestSize, f.Features, f.Model)
-}
+}

filters/chimerge.go

@@ -21,7 +21,7 @@ type ChiMergeFilter struct {
 	_Trained     bool
 }
 
-// Create a ChiMergeFilter with some helpful intialisations.
+// NewChiMergeFilter creates a ChiMergeFilter with some helpful initialisations.
 func NewChiMergeFilter(inst *base.Instances, significance float64) ChiMergeFilter {
 	return ChiMergeFilter{
 		make([]int, 0),

knn/knn.go

@@ -1,4 +1,4 @@
-// Package KNN implements a K Nearest Neighbors object, capable of both classification
+// Package knn implements a K Nearest Neighbors object, capable of both classification
 // and regression. It accepts data in the form of a slice of float64s, which are then reshaped
 // into a X by Y matrix.
 package knn
@@ -10,7 +10,7 @@ import (
 	util "github.com/sjwhitworth/golearn/utilities"
 )
 
-// A KNN Classifier. Consists of a data matrix, associated labels in the same order as the matrix, and a distance function.
+// A KNNClassifier consists of a data matrix, associated labels in the same order as the matrix, and a distance function.
 // The accepted distance functions at this time are 'euclidean' and 'manhattan'.
 type KNNClassifier struct {
 	base.BaseEstimator
@@ -19,7 +19,7 @@ type KNNClassifier struct {
 	NearestNeighbours int
 }
 
-// Returns a new classifier
+// NewKnnClassifier returns a new classifier
 func NewKnnClassifier(distfunc string, neighbours int) *KNNClassifier {
 	KNN := KNNClassifier{}
 	KNN.DistanceFunc = distfunc
@@ -27,12 +27,12 @@ func NewKnnClassifier(distfunc string, neighbours int) *KNNClassifier {
 	return &KNN
 }
 
-// Train stores the training data for llater
+// Fit stores the training data for later
 func (KNN *KNNClassifier) Fit(trainingData *base.Instances) {
 	KNN.TrainingData = trainingData
 }
 
-// Returns a classification for the vector, based on a vector input, using the KNN algorithm.
+// PredictOne returns a classification for the vector, based on a vector input, using the KNN algorithm.
 // See http://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm.
 func (KNN *KNNClassifier) PredictOne(vector []float64) string {
 
@@ -95,14 +95,14 @@ func (KNN *KNNClassifier) Predict(what *base.Instances) *base.Instances {
 	return ret
 }
 
-//A KNN Regressor. Consists of a data matrix, associated result variables in the same order as the matrix, and a name.
+// A KNNRegressor consists of a data matrix, associated result variables in the same order as the matrix, and a name.
 type KNNRegressor struct {
 	base.BaseEstimator
 	Values       []float64
 	DistanceFunc string
 }
 
-// Mints a new classifier.
+// NewKnnRegressor mints a new classifier.
 func NewKnnRegressor(distfunc string) *KNNRegressor {
 	KNN := KNNRegressor{}
 	KNN.DistanceFunc = distfunc
@@ -119,7 +119,6 @@ func (KNN *KNNRegressor) Fit(values []float64, numbers []float64, rows int, cols
 }
 
 func (KNN *KNNRegressor) Predict(vector *mat64.Dense, K int) float64 {
-
 	// Get the number of rows
 	rows, _ := KNN.Data.Dims()
 	rownumbers := make(map[int]float64)

meta/bagging.go

@@ -79,7 +79,7 @@ func (b *BaggedModel) AddModel(m base.Classifier) {
 	b.Models = append(b.Models, m)
 }
 
-// Train generates and trains each model on a randomised subset of
+// Fit generates and trains each model on a randomised subset of
 // Instances.
 func (b *BaggedModel) Fit(from *base.Instances) {
 	var wait sync.WaitGroup

metrics/pairwise/euclidean.go

@@ -12,14 +12,14 @@ func NewEuclidean() *Euclidean {
 	return &Euclidean{}
 }
 
-// Compute Eucledian inner product.
+// InnerProduct computes a Eucledian inner product.
 func (self *Euclidean) InnerProduct(vectorX *mat64.Dense, vectorY *mat64.Dense) float64 {
 	result := vectorX.Dot(vectorY)
 
 	return result
 }
 
-// Compute Euclidean distance (also known as L2 distance).
+// Distance computes Euclidean distance (also known as L2 distance).
 func (self *Euclidean) Distance(vectorX *mat64.Dense, vectorY *mat64.Dense) float64 {
 	subVector := mat64.NewDense(0, 0, nil)
 	subVector.Sub(vectorX, vectorY)

metrics/pairwise/manhattan.go

@@ -12,8 +12,8 @@ func NewManhattan() *Manhattan {
 	return &Manhattan{}
 }
 
-// Manhattan distance, also known as L1 distance.
-// Compute sum of absolute values of elements.
+// Distance computes the Manhattan distance, also known as L1 distance.
+// == the sum of the absolute values of elements.
 func (self *Manhattan) Distance(vectorX *mat64.Dense, vectorY *mat64.Dense) float64 {
 	r1, c1 := vectorX.Dims()
 	r2, c2 := vectorY.Dims()

metrics/pairwise/poly_kernel.go

@@ -10,12 +10,12 @@ type PolyKernel struct {
 	degree int
 }
 
-// Return a d-degree polynomial kernel
+// NewPolyKernel returns a d-degree polynomial kernel
 func NewPolyKernel(degree int) *PolyKernel {
 	return &PolyKernel{degree: degree}
 }
 
-// Compute inner product through kernel trick
+// InnerProduct computes the inner product through a kernel trick
 // K(x, y) = (x^T y + 1)^d
 func (self *PolyKernel) InnerProduct(vectorX *mat64.Dense, vectorY *mat64.Dense) float64 {
 	result := vectorX.Dot(vectorY)
@@ -24,7 +24,7 @@ func (self *PolyKernel) InnerProduct(vectorX *mat64.Dense, vectorY *mat64.Dense)
 	return result
 }
 
-// Compute distance under the polynomial kernel, maybe no need.
+// Distance computes distance under the polynomial kernel (maybe not needed?)
 func (self *PolyKernel) Distance(vectorX *mat64.Dense, vectorY *mat64.Dense) float64 {
 	subVector := mat64.NewDense(0, 0, nil)
 	subVector.Sub(vectorX, vectorY)

metrics/pairwise/rbf_kernel.go

@@ -10,12 +10,12 @@ type RBFKernel struct {
 	gamma float64
 }
 
-// Radial Basis Function Kernel
+// NewRBFKernel returns a representation of a Radial Basis Function Kernel
 func NewRBFKernel(gamma float64) *RBFKernel {
 	return &RBFKernel{gamma: gamma}
 }
 
-// Compute inner product through kernel trick
+// InnerProduct computes the inner product through a kernel trick
 // K(x, y) = exp(-gamma * ||x - y||^2)
 func (self *RBFKernel) InnerProduct(vectorX *mat64.Dense, vectorY *mat64.Dense) float64 {
 	euclidean := NewEuclidean()

optimisation/gradient_descent.go

@@ -2,7 +2,7 @@ package optimisation
 
 import "github.com/gonum/matrix/mat64"
 
-// Batch gradient descent finds the local minimum of a function.
+// BatchGradientDescent finds the local minimum of a function.
 // See http://en.wikipedia.org/wiki/Gradient_descent for more details.
 func BatchGradientDescent(x, y, theta *mat64.Dense, alpha float64, epoch int) *mat64.Dense {
 	m, _ := y.Dims()
@@ -35,7 +35,7 @@ func BatchGradientDescent(x, y, theta *mat64.Dense, alpha float64, epoch int) *m
 	return theta
 }
 
-// Stochastic gradient descent updates the parameters of theta on a random row selection from a matrix.
+// StochasticGradientDescent updates the parameters of theta on a random row selection from a matrix.
 // It is faster as it does not compute the cost function over the entire dataset every time.
 // It instead calculates the error parameters over only one row of the dataset at a time.
 // In return, there is a trade off for accuracy. This is minimised by running multiple SGD processes

trees/entropy.go

@@ -12,7 +12,7 @@ import (
 type InformationGainRuleGenerator struct {
 }
 
-// GetSplitAttribute returns the non-class Attribute which maximises the
+// GenerateSplitAttribute returns the non-class Attribute which maximises the
 // information gain.
 //
 // IMPORTANT: passing a base.Instances with no Attributes other than the class
@@ -27,7 +27,7 @@ func (r *InformationGainRuleGenerator) GenerateSplitAttribute(f *base.Instances)
 	return r.GetSplitAttributeFromSelection(allAttributes, f)
 }
 
-// GetSplitAttribute from selection returns the class Attribute which maximises
+// GetSplitAttributeFromSelection returns the class Attribute which maximises
 // the information gain amongst consideredAttributes
 //
 // IMPORTANT: passing a zero-length consideredAttributes parameter will panic()

trees/id3.go

@@ -234,7 +234,7 @@ type ID3DecisionTree struct {
 	PruneSplit float64
 }
 
-// Returns a new ID3DecisionTree with the specified test-prune
+// NewID3DecisionTree returns a new ID3DecisionTree with the specified test-prune
 // ratio. Of the ratio is less than 0.001, the tree isn't pruned
 func NewID3DecisionTree(prune float64) *ID3DecisionTree {
 	return &ID3DecisionTree{

trees/random.go

@@ -66,7 +66,7 @@ func NewRandomTree(attrs int) *RandomTree {
 	}
 }
 
-// Train builds a RandomTree suitable for prediction
+// Fit builds a RandomTree suitable for prediction
 func (rt *RandomTree) Fit(from *base.Instances) {
 	rt.Root = InferID3Tree(from, rt.Rule)
 }