added trainTestSplit() function

go.mod

@@ -2,10 +2,13 @@ module github.com/Jensen-holm/ml-from-scratch
 
 go 1.19
 
+require (
+	github.com/go-gota/gota v0.12.0
+	github.com/gofiber/fiber/v2 v2.49.2
+)
+
 require (
 	github.com/andybalholm/brotli v1.0.5 // indirect
-	github.com/go-gota/gota v0.12.0 // indirect
-	github.com/gofiber/fiber/v2 v2.49.2 // indirect
 	github.com/google/uuid v1.3.1 // indirect
 	github.com/klauspost/compress v1.16.7 // indirect
 	github.com/mattn/go-colorable v0.1.13 // indirect

go.sum

@@ -53,6 +53,7 @@ golang.org/x/exp v0.0.0-20180321215751-8460e604b9de/go.mod h1:CJ0aWSM057203Lf6IL
 golang.org/x/exp v0.0.0-20180807140117-3d87b88a115f/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190125153040-c74c464bbbf2/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190306152737-a1d7652674e8/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
+golang.org/x/exp v0.0.0-20191002040644-a1355ae1e2c3 h1:n9HxLrNxWWtEb1cA950nuEEj3QnKbtsCJ6KjcgisNUs=
 golang.org/x/exp v0.0.0-20191002040644-a1355ae1e2c3/go.mod h1:NOZ3BPKG0ec/BKJQgnvsSFpcKLM5xXVWnvZS97DWHgE=
 golang.org/x/image v0.0.0-20180708004352-c73c2afc3b81/go.mod h1:ux5Hcp/YLpHSI86hEcLt0YII63i6oz57MZXIpbrjZUs=
 golang.org/x/image v0.0.0-20190227222117-0694c2d4d067/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
@@ -67,7 +68,6 @@ golang.org/x/mobile v0.0.0-20190719004257-d2bd2a29d028/go.mod h1:E/iHnbuqvinMTCc
 golang.org/x/mod v0.1.0/go.mod h1:0QHyrYULN0/3qlju5TqG8bIK38QM8yzMo5ekMj3DlcY=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
-golang.org/x/net v0.0.0-20210423184538-5f58ad60dda6 h1:0PC75Fz/kyMGhL0e1QnypqK2kQMqKt9csD1GnMJR+Zk=
 golang.org/x/net v0.0.0-20210423184538-5f58ad60dda6/go.mod h1:OJAsFXCWl8Ukc7SiCT/9KSuxbyM7479/AVlXFRxuMCk=
 golang.org/x/net v0.8.0 h1:Zrh2ngAOFYneWTAIAPethzeaQLuHwhuBkuV6ZiRnUaQ=
 golang.org/x/net v0.8.0/go.mod h1:QVkue5JL9kW//ek3r6jTKnTFis1tRmNAW2P1shuFdJc=
@@ -95,6 +95,7 @@ gonum.org/v1/gonum v0.0.0-20180816165407-929014505bf4/go.mod h1:Y+Yx5eoAFn32cQvJ
 gonum.org/v1/gonum v0.8.2/go.mod h1:oe/vMfY3deqTw+1EZJhuvEW2iwGF1bW9wwu7XCu0+v0=
 gonum.org/v1/gonum v0.9.1 h1:HCWmqqNoELL0RAQeKBXWtkp04mGk8koafcB4He6+uhc=
 gonum.org/v1/gonum v0.9.1/go.mod h1:TZumC3NeyVQskjXqmyWt4S3bINhy7B4eYwW69EbyX+0=
+gonum.org/v1/netlib v0.0.0-20190313105609-8cb42192e0e0 h1:OE9mWmgKkjJyEmDAAtGMPjXu+YNeGvK9VTSHY6+Qihc=
 gonum.org/v1/netlib v0.0.0-20190313105609-8cb42192e0e0/go.mod h1:wa6Ws7BG/ESfp6dHfk7C6KdzKA7wR7u/rKwOGE66zvw=
 gonum.org/v1/plot v0.0.0-20190515093506-e2840ee46a6b/go.mod h1:Wt8AAjI+ypCyYX3nZBvf6cAIx93T+c/OS2HFAYskSZc=
 gonum.org/v1/plot v0.9.0/go.mod h1:3Pcqqmp6RHvJI72kgb8fThyUnav364FOsdDo2aGW5lY=

nn/main.go

@@ -16,7 +16,13 @@ type NN struct {
 	HiddenSize     int      `json:"hidden_size"`
 	LearningRate   float64  `json:"learning_rate"`
 	ActivationFunc string   `json:"activation"`
-	Df             dataframe.DataFrame
+	TestSize       float64  `json:"test_size"`
+
+	Df     *dataframe.DataFrame
+	XTrain dataframe.DataFrame
+	YTrain dataframe.DataFrame
+	XTest  dataframe.DataFrame
+	YTest  dataframe.DataFrame
 }
 
 func NewNN(c *fiber.Ctx) (*NN, error) {
@@ -25,6 +31,16 @@ func NewNN(c *fiber.Ctx) (*NN, error) {
 	if err != nil {
 		return nil, fmt.Errorf("invalid JSON data: %v", err)
 	}
-	newNN.Df = dataframe.ReadCSV(strings.NewReader(newNN.CSVData))
+	df := dataframe.ReadCSV(strings.NewReader(newNN.CSVData))
+	newNN.Df = &df
 	return newNN, nil
 }
+
+func (nn *NN) Train() {
+	// train test split the data
+
+	// iterate n times where n = nn.Epochs
+	// use backprop algorithm on each iteration
+	// to fit the model to the data
+
+}

nn/split.go

@@ -1,5 +1,38 @@
 package nn
 
+import (
+	"math"
+	"math/rand"
+)
+
 // implement train test split function
 
-func trainTestSplit() {}
+func (nn *NN) trainTestSplit() {
+	// now we split the data into training
+	// and testing based on user specified
+	// nn.TestSize.
+	nRows := nn.Df.Nrow()
+	testRows := int(math.Floor(float64(nRows) * nn.TestSize))
+
+	// subset the testing data
+	// randomly select trainRows number of rows
+	randStrt := rand.Intn(int(math.Floor(float64(nRows) * nn.TestSize)))
+	test := nn.Df.Subset([]int{randStrt, randStrt + testRows})
+
+	// use what is left for training
+	allIndices := make([]int, nRows)
+	for i := range allIndices {
+		allIndices[i] = i
+	}
+
+	// Remove the test indices using slice append and variadic parameter
+	trainIndices := append(allIndices[:randStrt], allIndices[randStrt+testRows:]...)
+
+	// Create the train DataFrame using the trainIndices
+	train := nn.Df.Subset(trainIndices)
+
+	nn.XTrain = train.Select(nn.Features)
+	nn.YTrain = train.Select(nn.Target)
+	nn.XTest = test.Select(nn.Features)
+	nn.YTest = test.Select(nn.Target)
+}

wrangle/trainTestSplit.go

@@ -0,0 +1,10 @@
+package wrangle
+
+import (
+	"github.com/go-gota/gota/dataframe"
+)
+
+func TrainTestSplit(df *dataframe.DataFrame, test float64) *dataframe.DataFrame {
+
+	return
+}