Add initial implementation for datasets

Relate-To: #112, #113

Author: michalharakal

dataset_arch.md

@@ -0,0 +1,61 @@
+import org.jetbrains.kotlin.gradle.ExperimentalKotlinGradlePluginApi
+import org.jetbrains.kotlin.gradle.ExperimentalWasmDsl
+import org.jetbrains.kotlin.gradle.dsl.JvmTarget
+
+plugins {
+    alias(libs.plugins.kotlinMultiplatform)
+    alias(libs.plugins.androidLibrary)
+    alias(libs.plugins.vanniktech.mavenPublish)
+}
+
+kotlin {
+    explicitApi()
+
+    androidTarget {
+        @OptIn(ExperimentalKotlinGradlePluginApi::class)
+        compilerOptions {
+            jvmTarget.set(JvmTarget.JVM_11)
+        }
+    }
+
+    iosArm64()
+    iosSimulatorArm64()
+    macosArm64 ()
+    linuxX64 ()
+    linuxArm64 ()
+
+    jvm()
+
+    @OptIn(ExperimentalWasmDsl::class)
+    wasmJs {
+        browser()
+        binaries.executable()
+    }
+
+    sourceSets {
+        val commonMain by getting {
+            dependencies {
+                implementation(project(":skainet-core:skainet-tensors-api"))
+                implementation(project(":skainet-core:skainet-tensors"))
+            }
+        }
+
+        commonTest.dependencies {
+            implementation(libs.kotlin.test)
+            implementation(project(":skainet-core:skainet-performance"))
+        }
+    }
+}
+
+android {
+    namespace = "sk.ainet.core.api"
+    compileSdk = libs.versions.android.compileSdk.get().toInt()
+
+    defaultConfig {
+        minSdk = libs.versions.android.minSdk.get().toInt()
+    }
+    compileOptions {
+        sourceCompatibility = JavaVersion.VERSION_11
+        targetCompatibility = JavaVersion.VERSION_11
+    }
+}

skainet-data/skainet-data-api/build.gradle.kts

@@ -0,0 +1,2 @@
+POM_ARTIFACT_ID=data-api
+POM_NAME=skainet datasets API

skainet-data/skainet-data-api/gradle.properties

@@ -0,0 +1,24 @@
+package sk.ainet.data
+
+import sk.ainet.core.tensor.DType
+import sk.ainet.core.tensor.Tensor
+
+public data class DataBatch<T : DType, V>(val x: Array<Tensor<T, V>>, val y: Tensor<T, V>) {
+    override fun equals(other: Any?): Boolean {
+        if (this === other) return true
+        if (other == null || this::class != other::class) return false
+
+        other as DataBatch<*, *>
+
+        if (!x.contentEquals(other.x)) return false
+        if (y != other.y) return false
+
+        return true
+    }
+
+    override fun hashCode(): Int {
+        var result = x.contentHashCode()
+        result = 31 * result + y.hashCode()
+        return result
+    }
+}

skainet-data/skainet-data-api/src/commonMain/kotlin/sk/ainet/data/DatBatch.kt

@@ -0,0 +1,51 @@
+package sk.ainet.data
+
+import sk.ainet.core.tensor.DType
+import kotlin.math.min
+
+
+/** Just abstract Dataset. */
+public abstract class Dataset<T, Y> {
+    /** Splits datasets on two sub-datasets according [splitRatio].*/
+    public abstract fun split(splitRatio: Double): Pair<Dataset<T, Y>, Dataset<T, Y>>
+
+    /** Returns amount of data rows. */
+    public abstract val xSize: Int
+
+    /** Returns row by index [idx]. */
+    public abstract fun getX(idx: Int): T
+
+    /** Returns label as [Int] by index [idx]. */
+    public abstract fun getY(idx: Int): Y
+
+    /** Shuffles the dataset. */
+    public abstract fun shuffle(): Dataset<T, Y>
+
+    /**
+     * An iterator over a [Dataset].
+     */
+    public inner class BatchIterator<T : DType, V> internal constructor(
+        private val batchSize: Int
+    ) : Iterator<DataBatch<T, V>> {
+
+        private var batchStart = 0
+
+        override fun hasNext(): Boolean = batchStart < xSize
+
+        override fun next(): DataBatch<T, V> {
+            val batchLength = min(batchSize, xSize - batchStart)
+            val batch = createDataBatch<T, V>(batchStart, batchLength)
+            batchStart += batchSize
+            return batch
+        }
+    }
+
+    /** Creates data batch that starts from [batchStart] with length [batchLength]. */
+    protected abstract fun <T : DType, V> createDataBatch(batchStart: Int, batchLength: Int): DataBatch<T, V>
+
+
+    /** Returns [BatchIterator] with fixed [batchSize]. */
+    public fun <T : DType, V> batchIterator(batchSize: Int): BatchIterator<T, V> {
+        return BatchIterator(batchSize)
+    }
+}

skainet-data/skainet-data-api/src/commonMain/kotlin/sk/ainet/data/Dataset.kt

@@ -0,0 +1,61 @@
+import org.jetbrains.kotlin.gradle.ExperimentalKotlinGradlePluginApi
+import org.jetbrains.kotlin.gradle.ExperimentalWasmDsl
+import org.jetbrains.kotlin.gradle.dsl.JvmTarget
+
+plugins {
+    alias(libs.plugins.kotlinMultiplatform)
+    alias(libs.plugins.androidLibrary)
+    alias(libs.plugins.vanniktech.mavenPublish)
+}
+
+kotlin {
+    explicitApi()
+
+    androidTarget {
+        @OptIn(ExperimentalKotlinGradlePluginApi::class)
+        compilerOptions {
+            jvmTarget.set(JvmTarget.JVM_11)
+        }
+    }
+
+    iosArm64()
+    iosSimulatorArm64()
+    macosArm64 ()
+    linuxX64 ()
+    linuxArm64 ()
+
+    jvm()
+
+    @OptIn(ExperimentalWasmDsl::class)
+    wasmJs {
+        browser()
+        binaries.executable()
+    }
+
+    sourceSets {
+        val commonMain by getting {
+            dependencies {
+                implementation(project(":skainet-core:skainet-tensors-api"))
+                implementation(project(":skainet-core:skainet-tensors-api"))
+            }
+        }
+
+        commonTest.dependencies {
+            implementation(libs.kotlin.test)
+            implementation(project(":skainet-core:skainet-performance"))
+        }
+    }
+}
+
+android {
+    namespace = "sk.ainet.core.api"
+    compileSdk = libs.versions.android.compileSdk.get().toInt()
+
+    defaultConfig {
+        minSdk = libs.versions.android.minSdk.get().toInt()
+    }
+    compileOptions {
+        sourceCompatibility = JavaVersion.VERSION_11
+        targetCompatibility = JavaVersion.VERSION_11
+    }
+}

skainet-data/skainet-data-simple/build.gradle.kts

@@ -0,0 +1,2 @@
+POM_ARTIFACT_ID=data-basic
+POM_NAME=skainet neural basic datasets