Merge e87a7e4aadc60d0d452779201bf842310d84a85d into 3e43e74895fbe667cb83c7fd8278238eb001f667

.travis.yml

@@ -1,16 +1,16 @@
 language: go
+dist: bionic
 go:
- - "1.9"
- - "1.10"
- - "1.11"
- - "1.12"
+ - "1.13"
+ - "1.14"
+arch:
+ - amd64
+ - arm64
 env:
- # Temporary workaround for go 1.6
- - GODEBUG=cgocheck=0
 before_install:
  - sudo apt-get update -qq
  - sudo apt-get install -qq libatlas-base-dev
- - cd /tmp && wget http://www.csie.ntu.edu.tw/~cjlin/liblinear/oldfiles/liblinear-1.94.tar.gz && tar xf liblinear-1.94.tar.gz && cd liblinear-1.94 && make lib && sudo install -vm644 linear.h /usr/include && sudo install -vm755 liblinear.so.1 /usr/lib && sudo ln -sfv liblinear.so.1 /usr/lib/liblinear.so
+ - cd /tmp && wget https://www.csie.ntu.edu.tw/~cjlin/liblinear/oldfiles/liblinear-1.94.tar.gz && tar xf liblinear-1.94.tar.gz && cd liblinear-1.94 && make lib && sudo install -vm644 linear.h /usr/include && sudo install -vm755 liblinear.so.1 /usr/lib && sudo ln -sfv liblinear.so.1 /usr/lib/liblinear.so
  - cd $TRAVIS_BUILD_DIR
 install:
  - go get github.com/smartystreets/goconvey/convey

ensemble/multisvc_test.go

@@ -1,11 +1,12 @@
 package ensemble
 
 import (
+	"io/ioutil"
+	"testing"
+
 	"github.com/sjwhitworth/golearn/base"
 	"github.com/sjwhitworth/golearn/evaluation"
 	. "github.com/smartystreets/goconvey/convey"
-	"io/ioutil"
-	"testing"
 )
 
 func TestMultiSVMUnweighted(t *testing.T) {
@@ -14,40 +15,43 @@ func TestMultiSVMUnweighted(t *testing.T) {
 		So(err, ShouldBeNil)
 		X, Y := base.InstancesTrainTestSplit(inst, 0.4)
 
-		m := NewMultiLinearSVC("l1", "l2", true, 1.0, 1e-4, nil)
-		m.Fit(X)
-
-		Convey("Predictions should work...", func() {
-			predictions, err := m.Predict(Y)
-			So(err, ShouldEqual, nil)
-			cf, err := evaluation.GetConfusionMatrix(Y, predictions)
-			So(err, ShouldEqual, nil)
-			So(evaluation.GetAccuracy(cf), ShouldBeGreaterThan, 0.70)
-		})
-
-		Convey("Saving should work...", func() {
-			f, err := ioutil.TempFile("", "tree")
-			So(err, ShouldBeNil)
-			err = m.Save(f.Name())
+		Convey("Fitting should work...", func() {
+			m := NewMultiLinearSVC("l1", "l2", true, 1.0, 1e-4, nil)
+			err := m.Fit(X)
 			So(err, ShouldBeNil)
 
-			Convey("Loading should work...", func() {
-				mLoaded := NewMultiLinearSVC("l1", "l2", true, 1.00, 1e-8, nil)
-				err := mLoaded.Load(f.Name())
+			Convey("Predictions should work...", func() {
+				predictions, err := m.Predict(Y)
+				So(err, ShouldEqual, nil)
+				cf, err := evaluation.GetConfusionMatrix(Y, predictions)
+				So(err, ShouldEqual, nil)
+				So(evaluation.GetAccuracy(cf), ShouldBeGreaterThan, 0.70)
+			})
+
+			Convey("Saving should work...", func() {
+				f, err := ioutil.TempFile("", "tree")
+				So(err, ShouldBeNil)
+				err = m.Save(f.Name())
 				So(err, ShouldBeNil)
 
-				Convey("Predictions should be the same...", func() {
-					originalPredictions, err := m.Predict(Y)
+				Convey("Loading should work...", func() {
+					mLoaded := NewMultiLinearSVC("l1", "l2", true, 1.00, 1e-8, nil)
+					err := mLoaded.Load(f.Name())
 					So(err, ShouldBeNil)
-					newPredictions, err := mLoaded.Predict(Y)
-					So(err, ShouldBeNil)
-					So(base.InstancesAreEqual(originalPredictions, newPredictions), ShouldBeTrue)
+
+					Convey("Predictions should be the same...", func() {
+						originalPredictions, err := m.Predict(Y)
+						So(err, ShouldBeNil)
+						newPredictions, err := mLoaded.Predict(Y)
+						So(err, ShouldBeNil)
+						So(base.InstancesAreEqual(originalPredictions, newPredictions), ShouldBeTrue)
+					})
+
 				})
 
 			})
 
 		})
-
 	})
 }
 

linear_models/integration.cpp

@@ -0,0 +1,93 @@
+/*
+ * This file contains functions related to creating + freeing
+ * objects on behalf of the go runtime
+ */
+
+#include "linear.h"
+#include <stdlib.h>
+
+extern "C" {
+
+/* NOTE: the Golang versions of the structures must call the corresponding
+ * Free functions via runtime.SetFinalize */
+/* CreateCProblem allocates a new struct problem outside of Golang's
+ * garbage collection. */
+struct problem *CreateCProblem() {
+    auto ret = new problem();
+    *ret = {}; // < Clear all fields
+    return ret;
+}
+
+/* CreateCModel allocates a new struct model outside of Golang's 
+ * garbage collection. */
+struct model *CreateCModel() {
+    auto ret = new model();
+    *ret = {}; // < Clear all fields
+    return ret;
+}
+
+/* CreateCParameter allocates a new struct parameter outside of
+ * Golang's garbage collection.*/
+struct parameter *CreateCParameter() {
+    return reinterpret_cast<struct parameter*>(calloc(1, sizeof(struct parameter)));
+}
+
+/* Free's a previously allocated problem and all its data */
+void FreeCProblem(struct problem *p) {
+    if (p->y != nullptr) {
+        free(p->y);
+        p->y = nullptr;
+    }
+    if (p->x != nullptr) {
+        free(p->x);
+        p->x = nullptr;
+    }
+    delete p;
+}
+
+/* free's a model with libsvm's internal routines */
+void FreeCModel(struct model *m) {
+    free_model_content(m);
+    delete m;
+}
+
+/* free's a parameter via libsvm */
+void FreeCParameter(struct parameter *p) {
+    if (p == nullptr) {
+        return;
+    }
+    free(p);
+}
+
+/* Allocates a vector of doubles for storing target values
+ * outside of Go's garbage collection */
+int AllocateLabelsForProblem (struct problem *p, int numValues) {
+    p->y = reinterpret_cast<double *>(malloc(sizeof(double) * numValues));
+    return p->y == nullptr;
+}
+
+/* Utility method used to set the target value for a particular
+ * input row */
+void AssignLabelForProblem(struct problem *p, int i, double d) {
+    p->y[i] = d;
+}
+
+/* Allocates a buffer of input rows and inserts the per-row values */
+int RiffleFeatures(struct problem *p, int num_offsets, int* row_offsets, struct feature_node *features) {
+
+    // Allocate space for the feature node buffer.
+    p->x = reinterpret_cast<struct feature_node**>(
+        calloc(num_offsets, sizeof(struct feature_node *))
+    );
+    if (p->x == nullptr) {
+        return -1;
+    }
+
+    for (int i = 0; i < num_offsets; i++) {
+        int offset = row_offsets[i];
+        p->x[i] = features + offset;
+    }
+    return 0;
+}
+
+} /* extern "C" */

linear_models/integration.h

@@ -0,0 +1,19 @@
+#ifndef _H_INTEGRATION_
+#define _H_INTEGRATION_
+
+#include "linear.h"
+
+struct problem *CreateCProblem();
+void FreeCProblem(struct problem*);
+struct model *CreateCModel();
+void FreeCModel(struct model*);
+struct parameter *CreateCParameter();
+void FreeCParameter(struct parameter*);
+// Allocates memory outside of golang for describing feature
+// vectors.
+int RiffleFeatures(struct problem *p, int num_offsets, int* row_offsets, struct feature_node *features);
+int AllocateLabelsForProblem(struct problem *, int);
+void AssignLabelForProblem(struct problem *, int, double);
+struct feature_node *GetFeatureNodeForIndex(struct problem *, int, int);
+
+#endif

linear_models/liblinear.go

@@ -1,22 +1,47 @@
 package linear_models
 
 /*
-#include "linear.h"
+#include "integration.h"
+#cgo CFLAGS: -O3
+#cgo CXXFLAGS: -std=c++11 -O3
 */
 import "C"
-import "fmt"
-import "unsafe"
+import (
+	"fmt"
+	"runtime"
+)
 
+// Problem wraps a libsvm problem struct which describes a classification/
+// regression problem. No externally-accessible fields.
 type Problem struct {
-	c_prob C.struct_problem
+	c_prob       *C.struct_problem
+	featureNodes []C.struct_feature_node
 }
 
+// Free releases resources associated with a libsvm problem.
+func (p *Problem) Free() {
+	C.FreeCProblem(p.c_prob)
+}
+
+// Parameter encasulates all the possible libsvm training options.
+// TODO: make user control of these more extensive.
 type Parameter struct {
-	c_param C.struct_parameter
+	c_param *C.struct_parameter
 }
 
+// Free releases resources associated with a Parameter.
+func (p *Parameter) Free() {
+	C.FreeCParameter(p.c_param)
+}
+
+// Model encapsulates a trained libsvm model.
 type Model struct {
-	c_model unsafe.Pointer
+	c_model *C.struct_model
+}
+
+// Free releases resources associated with a trained libsvm model.
+func (m *Model) Free() {
+	C.FreeCModel(m.c_model)
 }
 
 const (
@@ -30,8 +55,14 @@ const (
 	L2R_LR_DUAL         = C.L2R_LR_DUAL
 )
 
+// NewParameter creates a libsvm parameter structure, which controls
+// various aspects of libsvm training.
+// For more information on what these parameters do, consult the
+// "`train` usage" section of
+// https://github.com/cjlin1/liblinear/blob/master/README
 func NewParameter(solver_type int, C float64, eps float64) *Parameter {
-	param := Parameter{}
+	param := &Parameter{C.CreateCParameter()}
+	runtime.SetFinalizer(param, (*Parameter).Free)
 	param.c_param.solver_type = C.int(solver_type)
 	param.c_param.eps = C.double(eps)
 	param.c_param.C = C.double(C)
@@ -39,30 +70,37 @@ func NewParameter(solver_type int, C float64, eps float64) *Parameter {
 	param.c_param.weight_label = nil
 	param.c_param.weight = nil
 
-	return &param
+	return param
 }
 
+// NewProblem creates input to libsvm which describes a particular
+// regression/classification problem. It requires an array of float values
+// and an array of y values.
 func NewProblem(X [][]float64, y []float64, bias float64) *Problem {
-	prob := Problem{}
+	prob := &Problem{C.CreateCProblem(), nil}
+	runtime.SetFinalizer(prob, (*Problem).Free)
 	prob.c_prob.l = C.int(len(X))
 	prob.c_prob.n = C.int(len(X[0]) + 1)
 
-	prob.c_prob.x = convert_features(X, bias)
-	c_y := make([]C.double, len(y))
+	convert_features(prob, X, bias)
+	C.AllocateLabelsForProblem(prob.c_prob, C.int(len(y)))
 	for i := 0; i < len(y); i++ {
-		c_y[i] = C.double(y[i])
+		C.AssignLabelForProblem(prob.c_prob, C.int(i), C.double(y[i]))
 	}
-	prob.c_prob.y = &c_y[0]
+	// Should not go out of scope until the Problem struct
+	// is cleaned up.
 	prob.c_prob.bias = C.double(-1)
 
-	return &prob
+	return prob
 }
 
+// Train invokes libsvm and returns a trained model.
 func Train(prob *Problem, param *Parameter) *Model {
 	libLinearHookPrintFunc() // Sets up logging
-	tmpCProb := &prob.c_prob
-	tmpCParam := &param.c_param
-	return &Model{unsafe.Pointer(C.train(tmpCProb, tmpCParam))}
+	out := C.train(prob.c_prob, param.c_param)
+	m := &Model{out}
+	runtime.SetFinalizer(m, (*Model).Free)
+	return m
 }
 
 func Export(model *Model, filePath string) error {
@@ -74,19 +112,25 @@ func Export(model *Model, filePath string) error {
 }
 
 func Load(model *Model, filePath string) error {
-	model.c_model = unsafe.Pointer(C.load_model(C.CString(filePath)))
+	model.c_model = C.load_model(C.CString(filePath))
 	if model.c_model == nil {
 		return fmt.Errorf("Something went wrong")
 	}
 	return nil
+
 }
 
+// Predict takes a row of float values corresponding to a particular
+// input and returns the regression result.
 func Predict(model *Model, x []float64) float64 {
 	c_x := convert_vector(x, 0)
 	c_y := C.predict((*C.struct_model)(model.c_model), c_x)
 	y := float64(c_y)
 	return y
 }
+
+// convert_vector is an internal function used for converting
+// dense float64 vectors into the sparse input that libsvm accepts.
 func convert_vector(x []float64, bias float64) *C.struct_feature_node {
 	n_ele := 0
 	for i := 0; i < len(x); i++ {
@@ -113,43 +157,48 @@ func convert_vector(x []float64, bias float64) *C.struct_feature_node {
 	c_x[j].index = C.int(-1)
 	return &c_x[0]
 }
-func convert_features(X [][]float64, bias float64) **C.struct_feature_node {
-	n_samples := len(X)
-	n_elements := 0
 
-	for i := 0; i < n_samples; i++ {
+// convert_features is an internal function used for converting
+// dense 2D arrays of float values into the sparse format libsvm accepts.
+func convert_features(prob *Problem, X [][]float64, bias float64) {
+	rowCount := len(X)
+
+	// This structure remembers the start and end elements for each row.
+	// We push them back into a global list of C.struct_feature_nodes, then
+	// riffle it in C using their indices to form the **C.struct_feature_nodes
+	// input. Go retains ownership of struct_feature_nodes, C has ownership of
+	// the enclosing **C.struct_feature_nodes feature.
+	rowOffsets := make([]C.int, 0)
+	featureNodes := make([]C.struct_feature_node, 0)
+
+	// First pass, just counting through each row and counting the number of elements we find.
+	for i := 0; i < rowCount; i++ {
+		rowOffsets = append(rowOffsets, C.int(len(featureNodes))) // Push back the starting element of this row
+		if bias != 0.0 {                                          // Allocate space for a bias node
+			featureNodes = append(featureNodes, C.struct_feature_node{
+				C.int(0), C.double(bias),
+			})
+		}
 		for j := 0; j < len(X[i]); j++ {
 			if X[i][j] != 0.0 {
-				n_elements++
-			}
-			n_elements++ //for bias
-		}
-	}
-
-	x_space := make([]C.struct_feature_node, n_elements+n_samples)
-
-	cursor := 0
-	x := make([]*C.struct_feature_node, n_samples)
-	var c_x **C.struct_feature_node
-
-	for i := 0; i < n_samples; i++ {
-		x[i] = &x_space[cursor]
-
-		for j := 0; j < len(X[i]); j++ {
-			if X[i][j] != 0.0 {
-				x_space[cursor].index = C.int(j + 1)
-				x_space[cursor].value = C.double(X[i][j])
-				cursor++
-			}
-			if bias > 0 {
-				x_space[cursor].index = C.int(0)
-				x_space[cursor].value = C.double(bias)
-				cursor++
+				// For every non-zero thing in the data grid, allocate a feature node.
+				featureNodes = append(featureNodes, C.struct_feature_node{
+					C.int(j + 1), C.double(X[i][j]),
+				})
 			}
 		}
-		x_space[cursor].index = C.int(-1)
-		cursor++
+		// Finally, add a terminating element which tells libsvm that there's nothing
+		// left on this row
+		featureNodes = append(featureNodes, C.struct_feature_node{
+			C.int(-1), C.double(0),
+		})
+	}
+
+	// Transform [feature_node, feature_node, feature_node, ...] list into
+	// [*feature_node(1), *feature_node(m), ...] through the C integration bridge.
+	// C owns that particular memory.
+	// int RiffleFeatures(struct problem *p, int num_offsets, int* row_offsets, struct feature_node *features) {
+	if C.RiffleFeatures(prob.c_prob, C.int(len(featureNodes)), &rowOffsets[0], &featureNodes[0]) != 0 {
+		panic("RiffledFeatures could not allocate memory")
 	}
-	c_x = &x[0]
-	return c_x
 }

linear_models/linearsvc.go

@@ -5,10 +5,10 @@ import "C"
 import (
 	"encoding/json"
 	"fmt"
-	"github.com/sjwhitworth/golearn/base"
 	"io/ioutil"
 	"os"
-	"unsafe"
+
+	"github.com/sjwhitworth/golearn/base"
 )
 
 // LinearSVCParams represnts all available LinearSVC options.
@@ -153,6 +153,7 @@ func (lr *LinearSVC) Fit(X base.FixedDataGrid) error {
 	var weightClasses []C.int
 
 	// Creates the class weighting
+	fmt.Println("Generating class weights...")
 	if lr.Param.ClassWeights == nil {
 		if lr.Param.WeightClassesAutomatically {
 			weightVec = generateClassWeightVectorFromDist(X)
@@ -169,17 +170,20 @@ func (lr *LinearSVC) Fit(X base.FixedDataGrid) error {
 	}
 
 	// Convert the problem
+	fmt.Println("Converting instances...")
 	problemVec := convertInstancesToProblemVec(X)
 	labelVec := convertInstancesToLabelVec(X)
 
 	// Train
+	fmt.Println("Training...")
 	prob := NewProblem(problemVec, labelVec, 0)
 	lr.param.c_param.nr_weight = C.int(len(weightVec))
 	lr.param.c_param.weight_label = &(weightClasses[0])
-	lr.param.c_param.weight = (*C.double)(unsafe.Pointer(&weightVec[0]))
+	lr.param.c_param.weight = (*C.double)(&weightVec[0])
 
 	//	lr.param.weights = (*C.double)unsafe.Pointer(&(weightVec[0]));
 	lr.model = Train(prob, lr.param)
+	fmt.Println("Training completed")
 	return nil
 }
 

meta/one_v_all.go

@@ -2,6 +2,7 @@ package meta
 
 import (
 	"fmt"
+
 	"github.com/sjwhitworth/golearn/base"
 )
 
@@ -46,7 +47,6 @@ func (m *OneVsAllModel) Fit(using base.FixedDataGrid) {
 		}
 	}
 	attrs := m.generateAttributes(using)
-
 	// Find the highest stored value
 	val := uint64(0)
 	classVals := classAttr.GetValues()
@@ -60,6 +60,7 @@ func (m *OneVsAllModel) Fit(using base.FixedDataGrid) {
 		panic("Must have more than one class!")
 	}
 	m.maxClassVal = val
+	fmt.Println("Found maximum rows")
 
 	// If we're reloading, we may just be fitting to the structure
 	_, srcRows := using.Size()
@@ -152,9 +153,6 @@ func (m *OneVsAllModel) LoadWithPrefix(reader *base.ClassifierDeserializer, pref
 		return base.DescribeError("Can't load INSTANCE_STRUCTURE", err)
 	}
 	m.Fit(fitOn)
-	/*if err != nil {
-		base.DescribeError("Could not fit reloaded classifier to the structure", err)
-	}*/
 
 	// Reload the filters
 	numFiltersU64, err := reader.GetU64ForKey(reader.Prefix(prefix, "FILTER_COUNT"))
@@ -229,7 +227,7 @@ func (m *OneVsAllModel) LoadWithPrefix(reader *base.ClassifierDeserializer, pref
 	for i, c := range classVals {
 		cls := m.NewClassifierFunction(c)
 		clsPrefix := pI("CLASSIFIERS", i)
-
+		fmt.Println("Loading classifier...")
 		err = cls.LoadWithPrefix(reader, clsPrefix)
 		if err != nil {
 			return base.FormatError(err, "Could not reload classifier at: %s", clsPrefix)
@@ -264,7 +262,7 @@ func (m *OneVsAllModel) SaveWithPrefix(writer *base.ClassifierSerializer, prefix
 	}
 
 	// Save the instances
-	err := writer.WriteInstancesForKey(writer.Prefix(prefix, "INSTANCE_STRUCTURE"), m.fitOn, false)
+	err := writer.WriteInstancesForKey(writer.Prefix(prefix, "INSTANCE_STRUCTURE"), base.NewStructuralCopy(m.fitOn), false)
 	if err != nil {
 		return base.DescribeError("Unable to write INSTANCE_STRUCTURE", err)
 	}