forked from kscience/kmath
Build tools update. Cleanup
This commit is contained in:
parent
fff7377687
commit
42d130f69c
@ -15,7 +15,7 @@ allprojects {
|
||||
}
|
||||
|
||||
group = "space.kscience"
|
||||
version = "0.3.0-dev-8"
|
||||
version = "0.3.0-dev-9"
|
||||
}
|
||||
|
||||
subprojects {
|
||||
|
||||
@ -11,36 +11,32 @@ import space.kscience.kmath.tensors.core.BroadcastDoubleTensorAlgebra
|
||||
|
||||
// Dataset normalization
|
||||
|
||||
fun main() {
|
||||
fun main() = BroadcastDoubleTensorAlgebra { // work in context with broadcast methods
|
||||
// take dataset of 5-element vectors from normal distribution
|
||||
val dataset = randomNormal(intArrayOf(100, 5)) * 1.5 // all elements from N(0, 1.5)
|
||||
|
||||
// work in context with broadcast methods
|
||||
BroadcastDoubleTensorAlgebra {
|
||||
// take dataset of 5-element vectors from normal distribution
|
||||
val dataset = randomNormal(intArrayOf(100, 5)) * 1.5 // all elements from N(0, 1.5)
|
||||
|
||||
dataset += fromArray(
|
||||
intArrayOf(5),
|
||||
doubleArrayOf(0.0, 1.0, 1.5, 3.0, 5.0) // rows means
|
||||
)
|
||||
dataset += fromArray(
|
||||
intArrayOf(5),
|
||||
doubleArrayOf(0.0, 1.0, 1.5, 3.0, 5.0) // rows means
|
||||
)
|
||||
|
||||
|
||||
// find out mean and standard deviation of each column
|
||||
val mean = dataset.mean(0, false)
|
||||
val std = dataset.std(0, false)
|
||||
// find out mean and standard deviation of each column
|
||||
val mean = dataset.mean(0, false)
|
||||
val std = dataset.std(0, false)
|
||||
|
||||
println("Mean:\n$mean")
|
||||
println("Standard deviation:\n$std")
|
||||
println("Mean:\n$mean")
|
||||
println("Standard deviation:\n$std")
|
||||
|
||||
// also we can calculate other statistic as minimum and maximum of rows
|
||||
println("Minimum:\n${dataset.min(0, false)}")
|
||||
println("Maximum:\n${dataset.max(0, false)}")
|
||||
// also we can calculate other statistic as minimum and maximum of rows
|
||||
println("Minimum:\n${dataset.min(0, false)}")
|
||||
println("Maximum:\n${dataset.max(0, false)}")
|
||||
|
||||
// now we can scale dataset with mean normalization
|
||||
val datasetScaled = (dataset - mean) / std
|
||||
// now we can scale dataset with mean normalization
|
||||
val datasetScaled = (dataset - mean) / std
|
||||
|
||||
// find out mean and std of scaled dataset
|
||||
// find out mean and std of scaled dataset
|
||||
|
||||
println("Mean of scaled:\n${datasetScaled.mean(0, false)}")
|
||||
println("Mean of scaled:\n${datasetScaled.std(0, false)}")
|
||||
}
|
||||
println("Mean of scaled:\n${datasetScaled.mean(0, false)}")
|
||||
println("Mean of scaled:\n${datasetScaled.std(0, false)}")
|
||||
}
|
||||
@ -6,92 +6,88 @@
|
||||
package space.kscience.kmath.tensors
|
||||
|
||||
import space.kscience.kmath.operations.invoke
|
||||
import space.kscience.kmath.tensors.core.DoubleTensor
|
||||
import space.kscience.kmath.tensors.core.BroadcastDoubleTensorAlgebra
|
||||
import space.kscience.kmath.tensors.core.DoubleTensor
|
||||
|
||||
// solving linear system with LUP decomposition
|
||||
|
||||
fun main () {
|
||||
fun main() = BroadcastDoubleTensorAlgebra {// work in context with linear operations
|
||||
|
||||
// work in context with linear operations
|
||||
BroadcastDoubleTensorAlgebra {
|
||||
// set true value of x
|
||||
val trueX = fromArray(
|
||||
intArrayOf(4),
|
||||
doubleArrayOf(-2.0, 1.5, 6.8, -2.4)
|
||||
)
|
||||
|
||||
// set true value of x
|
||||
val trueX = fromArray(
|
||||
intArrayOf(4),
|
||||
doubleArrayOf(-2.0, 1.5, 6.8, -2.4)
|
||||
// and A matrix
|
||||
val a = fromArray(
|
||||
intArrayOf(4, 4),
|
||||
doubleArrayOf(
|
||||
0.5, 10.5, 4.5, 1.0,
|
||||
8.5, 0.9, 12.8, 0.1,
|
||||
5.56, 9.19, 7.62, 5.45,
|
||||
1.0, 2.0, -3.0, -2.5
|
||||
)
|
||||
)
|
||||
|
||||
// and A matrix
|
||||
val a = fromArray(
|
||||
intArrayOf(4, 4),
|
||||
doubleArrayOf(
|
||||
0.5, 10.5, 4.5, 1.0,
|
||||
8.5, 0.9, 12.8, 0.1,
|
||||
5.56, 9.19, 7.62, 5.45,
|
||||
1.0, 2.0, -3.0, -2.5
|
||||
)
|
||||
)
|
||||
// calculate y value
|
||||
val b = a dot trueX
|
||||
|
||||
// calculate y value
|
||||
val b = a dot trueX
|
||||
// check out A and b
|
||||
println("A:\n$a")
|
||||
println("b:\n$b")
|
||||
|
||||
// check out A and b
|
||||
println("A:\n$a")
|
||||
println("b:\n$b")
|
||||
// solve `Ax = b` system using LUP decomposition
|
||||
|
||||
// solve `Ax = b` system using LUP decomposition
|
||||
// get P, L, U such that PA = LU
|
||||
val (p, l, u) = a.lu()
|
||||
|
||||
// get P, L, U such that PA = LU
|
||||
val (p, l, u) = a.lu()
|
||||
// check that P is permutation matrix
|
||||
println("P:\n$p")
|
||||
// L is lower triangular matrix and U is upper triangular matrix
|
||||
println("L:\n$l")
|
||||
println("U:\n$u")
|
||||
// and PA = LU
|
||||
println("PA:\n${p dot a}")
|
||||
println("LU:\n${l dot u}")
|
||||
|
||||
// check that P is permutation matrix
|
||||
println("P:\n$p")
|
||||
// L is lower triangular matrix and U is upper triangular matrix
|
||||
println("L:\n$l")
|
||||
println("U:\n$u")
|
||||
// and PA = LU
|
||||
println("PA:\n${p dot a}")
|
||||
println("LU:\n${l dot u}")
|
||||
|
||||
/* Ax = b;
|
||||
PAx = Pb;
|
||||
LUx = Pb;
|
||||
let y = Ux, then
|
||||
Ly = Pb -- this system can be easily solved, since the matrix L is lower triangular;
|
||||
Ux = y can be solved the same way, since the matrix L is upper triangular
|
||||
*/
|
||||
/* Ax = b;
|
||||
PAx = Pb;
|
||||
LUx = Pb;
|
||||
let y = Ux, then
|
||||
Ly = Pb -- this system can be easily solved, since the matrix L is lower triangular;
|
||||
Ux = y can be solved the same way, since the matrix L is upper triangular
|
||||
*/
|
||||
|
||||
|
||||
|
||||
// this function returns solution x of a system lx = b, l should be lower triangular
|
||||
fun solveLT(l: DoubleTensor, b: DoubleTensor): DoubleTensor {
|
||||
val n = l.shape[0]
|
||||
val x = zeros(intArrayOf(n))
|
||||
for (i in 0 until n){
|
||||
x[intArrayOf(i)] = (b[intArrayOf(i)] - l[i].dot(x).value()) / l[intArrayOf(i, i)]
|
||||
}
|
||||
return x
|
||||
}
|
||||
|
||||
val y = solveLT(l, p dot b)
|
||||
|
||||
// solveLT(l, b) function can be easily adapted for upper triangular matrix by the permutation matrix revMat
|
||||
// create it by placing ones on side diagonal
|
||||
val revMat = u.zeroesLike()
|
||||
val n = revMat.shape[0]
|
||||
// this function returns solution x of a system lx = b, l should be lower triangular
|
||||
fun solveLT(l: DoubleTensor, b: DoubleTensor): DoubleTensor {
|
||||
val n = l.shape[0]
|
||||
val x = zeros(intArrayOf(n))
|
||||
for (i in 0 until n) {
|
||||
revMat[intArrayOf(i, n - 1 - i)] = 1.0
|
||||
x[intArrayOf(i)] = (b[intArrayOf(i)] - l[i].dot(x).value()) / l[intArrayOf(i, i)]
|
||||
}
|
||||
|
||||
// solution of system ux = b, u should be upper triangular
|
||||
fun solveUT(u: DoubleTensor, b: DoubleTensor): DoubleTensor = revMat dot solveLT(
|
||||
revMat dot u dot revMat, revMat dot b
|
||||
)
|
||||
|
||||
val x = solveUT(u, y)
|
||||
|
||||
println("True x:\n$trueX")
|
||||
println("x founded with LU method:\n$x")
|
||||
return x
|
||||
}
|
||||
|
||||
val y = solveLT(l, p dot b)
|
||||
|
||||
// solveLT(l, b) function can be easily adapted for upper triangular matrix by the permutation matrix revMat
|
||||
// create it by placing ones on side diagonal
|
||||
val revMat = u.zeroesLike()
|
||||
val n = revMat.shape[0]
|
||||
for (i in 0 until n) {
|
||||
revMat[intArrayOf(i, n - 1 - i)] = 1.0
|
||||
}
|
||||
|
||||
// solution of system ux = b, u should be upper triangular
|
||||
fun solveUT(u: DoubleTensor, b: DoubleTensor): DoubleTensor = revMat dot solveLT(
|
||||
revMat dot u dot revMat, revMat dot b
|
||||
)
|
||||
|
||||
val x = solveUT(u, y)
|
||||
|
||||
println("True x:\n$trueX")
|
||||
println("x founded with LU method:\n$x")
|
||||
}
|
||||
@ -25,7 +25,7 @@ interface Layer {
|
||||
// activation layer
|
||||
open class Activation(
|
||||
val activation: (DoubleTensor) -> DoubleTensor,
|
||||
val activationDer: (DoubleTensor) -> DoubleTensor
|
||||
val activationDer: (DoubleTensor) -> DoubleTensor,
|
||||
) : Layer {
|
||||
override fun forward(input: DoubleTensor): DoubleTensor {
|
||||
return activation(input)
|
||||
@ -62,7 +62,7 @@ class Sigmoid : Activation(::sigmoid, ::sigmoidDer)
|
||||
class Dense(
|
||||
private val inputUnits: Int,
|
||||
private val outputUnits: Int,
|
||||
private val learningRate: Double = 0.1
|
||||
private val learningRate: Double = 0.1,
|
||||
) : Layer {
|
||||
|
||||
private val weights: DoubleTensor = DoubleTensorAlgebra {
|
||||
@ -74,8 +74,8 @@ class Dense(
|
||||
|
||||
private val bias: DoubleTensor = DoubleTensorAlgebra { zeros(intArrayOf(outputUnits)) }
|
||||
|
||||
override fun forward(input: DoubleTensor): DoubleTensor {
|
||||
return BroadcastDoubleTensorAlgebra { (input dot weights) + bias }
|
||||
override fun forward(input: DoubleTensor): DoubleTensor = BroadcastDoubleTensorAlgebra {
|
||||
(input dot weights) + bias
|
||||
}
|
||||
|
||||
override fun backward(input: DoubleTensor, outputError: DoubleTensor): DoubleTensor = DoubleTensorAlgebra {
|
||||
@ -116,7 +116,7 @@ class NeuralNetwork(private val layers: List<Layer>) {
|
||||
onesForAnswers[intArrayOf(index, label)] = 1.0
|
||||
}
|
||||
|
||||
val softmaxValue = yPred.exp() / yPred.exp().sum(dim = 1, keepDim = true)
|
||||
val softmaxValue = yPred.exp() / yPred.exp().sum(dim = 1, keepDim = true)
|
||||
|
||||
(-onesForAnswers + softmaxValue) / (yPred.shape[0].toDouble())
|
||||
}
|
||||
@ -175,67 +175,65 @@ class NeuralNetwork(private val layers: List<Layer>) {
|
||||
|
||||
|
||||
@OptIn(ExperimentalStdlibApi::class)
|
||||
fun main() {
|
||||
BroadcastDoubleTensorAlgebra {
|
||||
val features = 5
|
||||
val sampleSize = 250
|
||||
val trainSize = 180
|
||||
//val testSize = sampleSize - trainSize
|
||||
fun main() = BroadcastDoubleTensorAlgebra {
|
||||
val features = 5
|
||||
val sampleSize = 250
|
||||
val trainSize = 180
|
||||
//val testSize = sampleSize - trainSize
|
||||
|
||||
// take sample of features from normal distribution
|
||||
val x = randomNormal(intArrayOf(sampleSize, features), seed) * 2.5
|
||||
// take sample of features from normal distribution
|
||||
val x = randomNormal(intArrayOf(sampleSize, features), seed) * 2.5
|
||||
|
||||
x += fromArray(
|
||||
intArrayOf(5),
|
||||
doubleArrayOf(0.0, -1.0, -2.5, -3.0, 5.5) // rows means
|
||||
)
|
||||
x += fromArray(
|
||||
intArrayOf(5),
|
||||
doubleArrayOf(0.0, -1.0, -2.5, -3.0, 5.5) // rows means
|
||||
)
|
||||
|
||||
|
||||
// define class like '1' if the sum of features > 0 and '0' otherwise
|
||||
val y = fromArray(
|
||||
intArrayOf(sampleSize, 1),
|
||||
DoubleArray(sampleSize) { i ->
|
||||
if (x[i].sum() > 0.0) {
|
||||
1.0
|
||||
} else {
|
||||
0.0
|
||||
}
|
||||
// define class like '1' if the sum of features > 0 and '0' otherwise
|
||||
val y = fromArray(
|
||||
intArrayOf(sampleSize, 1),
|
||||
DoubleArray(sampleSize) { i ->
|
||||
if (x[i].sum() > 0.0) {
|
||||
1.0
|
||||
} else {
|
||||
0.0
|
||||
}
|
||||
)
|
||||
|
||||
// split train ans test
|
||||
val trainIndices = (0 until trainSize).toList().toIntArray()
|
||||
val testIndices = (trainSize until sampleSize).toList().toIntArray()
|
||||
|
||||
val xTrain = x.rowsByIndices(trainIndices)
|
||||
val yTrain = y.rowsByIndices(trainIndices)
|
||||
|
||||
val xTest = x.rowsByIndices(testIndices)
|
||||
val yTest = y.rowsByIndices(testIndices)
|
||||
|
||||
// build model
|
||||
val layers = buildList {
|
||||
add(Dense(features, 64))
|
||||
add(ReLU())
|
||||
add(Dense(64, 16))
|
||||
add(ReLU())
|
||||
add(Dense(16, 2))
|
||||
add(Sigmoid())
|
||||
}
|
||||
val model = NeuralNetwork(layers)
|
||||
)
|
||||
|
||||
// fit it with train data
|
||||
model.fit(xTrain, yTrain, batchSize = 20, epochs = 10)
|
||||
// split train ans test
|
||||
val trainIndices = (0 until trainSize).toList().toIntArray()
|
||||
val testIndices = (trainSize until sampleSize).toList().toIntArray()
|
||||
|
||||
// make prediction
|
||||
val prediction = model.predict(xTest)
|
||||
val xTrain = x.rowsByIndices(trainIndices)
|
||||
val yTrain = y.rowsByIndices(trainIndices)
|
||||
|
||||
// process raw prediction via argMax
|
||||
val predictionLabels = prediction.argMax(1, true)
|
||||
|
||||
// find out accuracy
|
||||
val acc = accuracy(yTest, predictionLabels)
|
||||
println("Test accuracy:$acc")
|
||||
val xTest = x.rowsByIndices(testIndices)
|
||||
val yTest = y.rowsByIndices(testIndices)
|
||||
|
||||
// build model
|
||||
val layers = buildList {
|
||||
add(Dense(features, 64))
|
||||
add(ReLU())
|
||||
add(Dense(64, 16))
|
||||
add(ReLU())
|
||||
add(Dense(16, 2))
|
||||
add(Sigmoid())
|
||||
}
|
||||
val model = NeuralNetwork(layers)
|
||||
|
||||
// fit it with train data
|
||||
model.fit(xTrain, yTrain, batchSize = 20, epochs = 10)
|
||||
|
||||
// make prediction
|
||||
val prediction = model.predict(xTest)
|
||||
|
||||
// process raw prediction via argMax
|
||||
val predictionLabels = prediction.argMax(1, true)
|
||||
|
||||
// find out accuracy
|
||||
val acc = accuracy(yTest, predictionLabels)
|
||||
println("Test accuracy:$acc")
|
||||
|
||||
}
|
||||
|
||||
@ -11,68 +11,64 @@ import space.kscience.kmath.tensors.core.BroadcastDoubleTensorAlgebra
|
||||
|
||||
// simple PCA
|
||||
|
||||
fun main(){
|
||||
fun main() = BroadcastDoubleTensorAlgebra { // work in context with broadcast methods
|
||||
val seed = 100500L
|
||||
|
||||
// work in context with broadcast methods
|
||||
BroadcastDoubleTensorAlgebra {
|
||||
// assume x is range from 0 until 10
|
||||
val x = fromArray(
|
||||
intArrayOf(10),
|
||||
(0 until 10).toList().map { it.toDouble() }.toDoubleArray()
|
||||
)
|
||||
|
||||
// assume x is range from 0 until 10
|
||||
val x = fromArray(
|
||||
intArrayOf(10),
|
||||
(0 until 10).toList().map { it.toDouble() }.toDoubleArray()
|
||||
)
|
||||
// take y dependent on x with noise
|
||||
val y = 2.0 * x + (3.0 + x.randomNormalLike(seed) * 1.5)
|
||||
|
||||
// take y dependent on x with noise
|
||||
val y = 2.0 * x + (3.0 + x.randomNormalLike(seed) * 1.5)
|
||||
println("x:\n$x")
|
||||
println("y:\n$y")
|
||||
|
||||
println("x:\n$x")
|
||||
println("y:\n$y")
|
||||
// stack them into single dataset
|
||||
val dataset = stack(listOf(x, y)).transpose()
|
||||
|
||||
// stack them into single dataset
|
||||
val dataset = stack(listOf(x, y)).transpose()
|
||||
// normalize both x and y
|
||||
val xMean = x.mean()
|
||||
val yMean = y.mean()
|
||||
|
||||
// normalize both x and y
|
||||
val xMean = x.mean()
|
||||
val yMean = y.mean()
|
||||
val xStd = x.std()
|
||||
val yStd = y.std()
|
||||
|
||||
val xStd = x.std()
|
||||
val yStd = y.std()
|
||||
val xScaled = (x - xMean) / xStd
|
||||
val yScaled = (y - yMean) / yStd
|
||||
|
||||
val xScaled = (x - xMean) / xStd
|
||||
val yScaled = (y - yMean) / yStd
|
||||
// save means ans standard deviations for further recovery
|
||||
val mean = fromArray(
|
||||
intArrayOf(2),
|
||||
doubleArrayOf(xMean, yMean)
|
||||
)
|
||||
println("Means:\n$mean")
|
||||
|
||||
// save means ans standard deviations for further recovery
|
||||
val mean = fromArray(
|
||||
intArrayOf(2),
|
||||
doubleArrayOf(xMean, yMean)
|
||||
)
|
||||
println("Means:\n$mean")
|
||||
val std = fromArray(
|
||||
intArrayOf(2),
|
||||
doubleArrayOf(xStd, yStd)
|
||||
)
|
||||
println("Standard deviations:\n$std")
|
||||
|
||||
val std = fromArray(
|
||||
intArrayOf(2),
|
||||
doubleArrayOf(xStd, yStd)
|
||||
)
|
||||
println("Standard deviations:\n$std")
|
||||
// calculate the covariance matrix of scaled x and y
|
||||
val covMatrix = cov(listOf(xScaled, yScaled))
|
||||
println("Covariance matrix:\n$covMatrix")
|
||||
|
||||
// calculate the covariance matrix of scaled x and y
|
||||
val covMatrix = cov(listOf(xScaled, yScaled))
|
||||
println("Covariance matrix:\n$covMatrix")
|
||||
// and find out eigenvector of it
|
||||
val (_, evecs) = covMatrix.symEig()
|
||||
val v = evecs[0]
|
||||
println("Eigenvector:\n$v")
|
||||
|
||||
// and find out eigenvector of it
|
||||
val (_, evecs) = covMatrix.symEig()
|
||||
val v = evecs[0]
|
||||
println("Eigenvector:\n$v")
|
||||
// reduce dimension of dataset
|
||||
val datasetReduced = v dot stack(listOf(xScaled, yScaled))
|
||||
println("Reduced data:\n$datasetReduced")
|
||||
|
||||
// reduce dimension of dataset
|
||||
val datasetReduced = v dot stack(listOf(xScaled, yScaled))
|
||||
println("Reduced data:\n$datasetReduced")
|
||||
|
||||
// we can restore original data from reduced data.
|
||||
// for example, find 7th element of dataset
|
||||
val n = 7
|
||||
val restored = (datasetReduced[n] dot v.view(intArrayOf(1, 2))) * std + mean
|
||||
println("Original value:\n${dataset[n]}")
|
||||
println("Restored value:\n$restored")
|
||||
}
|
||||
// we can restore original data from reduced data.
|
||||
// for example, find 7th element of dataset
|
||||
val n = 7
|
||||
val restored = (datasetReduced[n] dot v.view(intArrayOf(1, 2))) * std + mean
|
||||
println("Original value:\n${dataset[n]}")
|
||||
println("Restored value:\n$restored")
|
||||
}
|
||||
|
||||
@ -19,6 +19,9 @@ import space.kscience.kmath.structures.Buffer
|
||||
public interface ColumnarData<out T> {
|
||||
public val size: Int
|
||||
|
||||
/**
|
||||
* Provide a column by symbol or null if column with given symbol is not defined
|
||||
*/
|
||||
public operator fun get(symbol: Symbol): Buffer<T>?
|
||||
}
|
||||
|
||||
|
||||
@ -5,7 +5,7 @@ pluginManagement {
|
||||
maven("https://repo.kotlin.link")
|
||||
}
|
||||
|
||||
val toolsVersion = "0.9.6"
|
||||
val toolsVersion = "0.9.7"
|
||||
val kotlinVersion = "1.5.0"
|
||||
|
||||
plugins {
|
||||
|
||||
Loading…
Reference in New Issue
Block a user