added tests and fixes for std and mean functions regarding Nothing(?) types

Author: Jolanrensen

core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/math/mean.kt

@@ -1,6 +1,7 @@
 package org.jetbrains.kotlinx.dataframe.math
 
 import org.jetbrains.kotlinx.dataframe.api.skipNA_default
+import org.jetbrains.kotlinx.dataframe.impl.renderType
 import java.math.BigDecimal
 import kotlin.reflect.KType
 import kotlin.reflect.full.withNullability
@@ -31,7 +32,10 @@ internal fun <T : Number> Sequence<T>.mean(type: KType, skipNA: Boolean = skipNA
 
         Number::class -> (this as Sequence<Number>).map { it.toDouble() }.mean(skipNA)
 
-        else -> throw IllegalArgumentException("Unable to compute mean for type $type")
+        // this means the sequence is empty
+        Nothing::class -> Double.NaN
+
+        else -> throw IllegalArgumentException("Unable to compute the mean for type ${renderType(type)}")
     }
 }
 

core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/math/std.kt

@@ -2,6 +2,7 @@ package org.jetbrains.kotlinx.dataframe.math
 
 import org.jetbrains.kotlinx.dataframe.api.ddof_default
 import org.jetbrains.kotlinx.dataframe.api.skipNA_default
+import org.jetbrains.kotlinx.dataframe.impl.renderType
 import java.math.BigDecimal
 import kotlin.reflect.KType
 import kotlin.reflect.full.withNullability
@@ -13,11 +14,10 @@ internal fun <T : Number> Iterable<T?>.std(
     ddof: Int = ddof_default,
 ): Double {
     if (type.isMarkedNullable) {
-        if (skipNA) {
-            return filterNotNull().std(type.withNullability(false), true, ddof)
-        } else {
-            if (contains(null)) return Double.NaN
-            return std(type.withNullability(false), skipNA, ddof)
+        return when {
+            skipNA -> filterNotNull().std(type = type.withNullability(false), skipNA = true, ddof = ddof)
+            contains(null) -> Double.NaN
+            else -> std(type = type.withNullability(false), skipNA = false, ddof = ddof)
         }
     }
     return when (type.classifier) {
@@ -26,7 +26,8 @@ internal fun <T : Number> Iterable<T?>.std(
         Int::class, Short::class, Byte::class -> (this as Iterable<Int>).std(ddof)
         Long::class -> (this as Iterable<Long>).std(ddof)
         BigDecimal::class -> (this as Iterable<BigDecimal>).std(ddof)
-        else -> throw IllegalArgumentException("Unsupported type ${type.classifier}")
+        Nothing::class -> Double.NaN
+        else -> throw IllegalArgumentException("Unable to compute the std for type ${renderType(type)}")
     }
 }
 

core/src/test/kotlin/org/jetbrains/kotlinx/dataframe/statistics/BasicMathTests.kt

@@ -1,8 +1,10 @@
 package org.jetbrains.kotlinx.dataframe.statistics
 
 import io.kotest.matchers.shouldBe
+import org.jetbrains.kotlinx.dataframe.DataColumn
 import org.jetbrains.kotlinx.dataframe.api.columnOf
 import org.jetbrains.kotlinx.dataframe.api.mean
+import org.jetbrains.kotlinx.dataframe.impl.nothingType
 import org.junit.Test
 import kotlin.reflect.typeOf
 
@@ -18,5 +20,8 @@ class BasicMathTests {
     fun `mean with nans and nulls`() {
         columnOf(10, 20, Double.NaN, null).mean() shouldBe Double.NaN
         columnOf(10, 20, Double.NaN, null).mean(skipNA = true) shouldBe 15
+
+        DataColumn.createValueColumn("", emptyList<Nothing>(), nothingType(false)).mean() shouldBe Double.NaN
+        DataColumn.createValueColumn("", listOf(null), nothingType(true)).mean() shouldBe Double.NaN
     }
 }

core/src/test/kotlin/org/jetbrains/kotlinx/dataframe/statistics/std.kt

@@ -1,11 +1,14 @@
 package org.jetbrains.kotlinx.dataframe.statistics
 
 import io.kotest.matchers.shouldBe
+import org.jetbrains.kotlinx.dataframe.DataColumn
 import org.jetbrains.kotlinx.dataframe.api.columnOf
 import org.jetbrains.kotlinx.dataframe.api.columnTypes
 import org.jetbrains.kotlinx.dataframe.api.dataFrameOf
 import org.jetbrains.kotlinx.dataframe.api.std
+import org.jetbrains.kotlinx.dataframe.impl.nothingType
 import org.jetbrains.kotlinx.dataframe.math.std
+import org.jetbrains.kotlinx.dataframe.type
 import org.junit.Test
 import kotlin.reflect.typeOf
 
@@ -37,4 +40,16 @@ class StdTests {
         df[value].std() shouldBe expected
         df.std { value } shouldBe expected
     }
+
+    @Test
+    fun `std on empty or nullable column`() {
+        val empty = DataColumn.createValueColumn("", emptyList<Nothing>(), nothingType(false))
+        val nullable = DataColumn.createValueColumn("", listOf(null), nothingType(true))
+
+        empty.values().std(empty.type) shouldBe Double.NaN
+        nullable.values().std(nullable.type) shouldBe Double.NaN
+
+        empty.std() shouldBe Double.NaN
+        nullable.std() shouldBe Double.NaN
+    }
 }

core/src/test/kotlin/org/jetbrains/kotlinx/dataframe/testSets/person/DataFrameTests.kt

@@ -7,6 +7,7 @@ import io.kotest.matchers.shouldBe
 import io.kotest.matchers.shouldNotBe
 import org.jetbrains.kotlinx.dataframe.AnyFrame
 import org.jetbrains.kotlinx.dataframe.AnyRow
+import org.jetbrains.kotlinx.dataframe.DataColumn
 import org.jetbrains.kotlinx.dataframe.DataFrame
 import org.jetbrains.kotlinx.dataframe.DataRow
 import org.jetbrains.kotlinx.dataframe.RowExpression
@@ -2196,6 +2197,9 @@ class DataFrameTests : BaseTest() {
     fun `isNumber`() {
         typed.age.isNumber() shouldBe true
         typed.weight.isNumber() shouldBe true
+
+        DataColumn.createValueColumn("a", emptyList<Nothing>(), nothingType(false)).isNumber() shouldBe true
+        DataColumn.createValueColumn("a", listOf(null), nothingType(true)).isNumber() shouldBe true
     }
 
     @Test