Merge branch 'master' into parsing-optimization

# Conflicts:
#	core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/impl/api/parse.kt

Author: Jolanrensen

.github/workflows/main.yml

@@ -17,7 +17,7 @@ env:
   ALGOLIA_INDEX_NAME: prod_DATAFRAME_HELP
   ALGOLIA_KEY: ${{ secrets.ALGOLIA_KEY }}
   CONFIG_JSON_PRODUCT: Dataframe
-  CONFIG_JSON_VERSION: '0.13'
+  CONFIG_JSON_VERSION: '0.14'
 
 jobs:
   build-job:

README.md

@@ -1,7 +1,7 @@
 # Kotlin DataFrame: typesafe in-memory structured data processing for JVM
 [![JetBrains incubator project](https://jb.gg/badges/incubator.svg)](https://confluence.jetbrains.com/display/ALL/JetBrains+on+GitHub)
 [![Kotlin component alpha stability](https://img.shields.io/badge/project-alpha-kotlin.svg?colorA=555555&colorB=DB3683&label=&logo=kotlin&logoColor=ffffff&logoWidth=10)](https://kotlinlang.org/docs/components-stability.html)
-[![Kotlin](https://img.shields.io/badge/kotlin-1.9.22-blue.svg?logo=kotlin)](http://kotlinlang.org)
+[![Kotlin](https://img.shields.io/badge/kotlin-2.0.20-blue.svg?logo=kotlin)](http://kotlinlang.org)
 [![Dynamic XML Badge](https://img.shields.io/badge/dynamic/xml?url=https%3A%2F%2Frepo1.maven.org%2Fmaven2%2Forg%2Fjetbrains%2Fkotlinx%2Fdataframe%2Fmaven-metadata.xml&query=%2F%2Fversion%5Bnot%28contains%28text%28%29%2C%22dev%22%29%29%5D%5Blast%28%29%5D&label=Release%20version)](https://search.maven.org/artifact/org.jetbrains.kotlinx/dataframe)
 [![Dynamic XML Badge](https://img.shields.io/badge/dynamic/xml?url=https%3A%2F%2Frepo1.maven.org%2Fmaven2%2Forg%2Fjetbrains%2Fkotlinx%2Fdataframe%2Fmaven-metadata.xml&query=%2F%2Fversion%5Bcontains%28text%28%29%2C%22dev%22%29%5D%5Blast%28%29%5D&label=Dev%20version&color=yellow
 )](https://search.maven.org/artifact/org.jetbrains.kotlinx/dataframe)
@@ -41,18 +41,18 @@ You could find the following articles there:
 Check out this [notebook with new features](examples/notebooks/feature_overviews/0.14.0/new_features.ipynb) in development for the next release.
 
 The DataFrame compiler plugin has reached public preview!
-Here's a [compiler plugin demo project](https://github.com/koperagen/df-plugin-demo) that works with IntelliJ IDEA 2024.2.
+Here's a [compiler plugin demo project](https://github.com/koperagen/df-plugin-demo) that works with [IntelliJ IDEA](https://www.jetbrains.com/idea/) 2024.2.
 
 ## Setup
 
 ```kotlin
-implementation("org.jetbrains.kotlinx:dataframe:0.13.1")
+implementation("org.jetbrains.kotlinx:dataframe:0.14.0")
 ```
 
 Optional Gradle plugin for enhanced type safety and schema generation
 https://kotlin.github.io/dataframe/schemasgradle.html
 ```kotlin
-id("org.jetbrains.kotlinx.dataframe") version "0.13.1"
+id("org.jetbrains.kotlinx.dataframe") version "0.14.0"
 ```
 
 Check out the [custom setup page](https://kotlin.github.io/dataframe/gettingstartedgradleadvanced.html) if you don't need some of the formats as dependencies,
@@ -77,7 +77,7 @@ df.filter { "stargazers_count"<Int>() > 50 }.print()
 
 Requires Gradle plugin to work
 ```kotlin
-id("org.jetbrains.kotlinx.dataframe") version "0.13.1"
+id("org.jetbrains.kotlinx.dataframe") version "0.14.0"
 ```
 
 Plugin generates extension properties API for provided sample of data. Column names and their types become discoverable in completion.
@@ -228,6 +228,7 @@ This table shows the mapping between main library component versions and minimum
 | 0.12.0                   | 8                    | 1.9.0          | 0.11.0-358             | 3.0.0           | 11.0.0               |
 | 0.12.1                   | 8                    | 1.9.0          | 0.11.0-358             | 3.0.0           | 11.0.0               |
 | 0.13.1                   | 8                    | 1.9.22         | 0.12.0-139             | 3.0.0           | 15.0.0               |
+| 0.14.0                   | 8                    | 2.0.20         | 0.12.0-139             | 3.0.0           | 17.0.0               |
 
 ## Code of Conduct
 

core/generated-sources/src/main/kotlin/org/jetbrains/kotlinx/dataframe/api/groupBy.kt

@@ -11,7 +11,6 @@ import org.jetbrains.kotlinx.dataframe.annotations.Interpretable
 import org.jetbrains.kotlinx.dataframe.annotations.Refine
 import org.jetbrains.kotlinx.dataframe.columns.FrameColumn
 import org.jetbrains.kotlinx.dataframe.columns.toColumnSet
-import org.jetbrains.kotlinx.dataframe.impl.GroupByImpl
 import org.jetbrains.kotlinx.dataframe.impl.aggregation.PivotImpl
 import org.jetbrains.kotlinx.dataframe.impl.api.getPivotColumnPaths
 import org.jetbrains.kotlinx.dataframe.impl.api.groupByImpl
@@ -85,24 +84,17 @@ public interface GroupBy<out T, out G> : Grouped<G> {
 
     public fun filter(predicate: GroupedRowFilter<T, G>): GroupBy<T, G>
 
+    @Refine
+    @Interpretable("GroupByToDataFrame")
+    public fun toDataFrame(groupedColumnName: String? = null): DataFrame<T>
+
     public data class Entry<T, G>(val key: DataRow<T>, val group: DataFrame<G>)
 
     public companion object {
         internal val groupedColumnAccessor = column<AnyFrame>("group")
     }
 }
 
-@Refine
-@Interpretable("GroupByToDataFrame")
-public fun <T, G> GroupBy<T, G>.toDataFrame(groupedColumnName: String? = null): DataFrame<T> =
-    if (groupedColumnName == null || groupedColumnName == groups.name()) {
-        internal().df
-    } else {
-        internal().df.rename(groups).into(groupedColumnName)
-    }
-
-internal fun <T, G> GroupBy<T, G>.internal(): GroupByImpl<T, G> = this as GroupByImpl<T, G>
-
 public interface Grouped<out T> : Aggregatable<T>
 
 public class ReducedGroupBy<T, G>(

core/generated-sources/src/main/kotlin/org/jetbrains/kotlinx/dataframe/impl/GroupByImpl.kt

@@ -13,9 +13,11 @@ import org.jetbrains.kotlinx.dataframe.api.concat
 import org.jetbrains.kotlinx.dataframe.api.convert
 import org.jetbrains.kotlinx.dataframe.api.getColumn
 import org.jetbrains.kotlinx.dataframe.api.getColumnsWithPaths
+import org.jetbrains.kotlinx.dataframe.api.into
 import org.jetbrains.kotlinx.dataframe.api.isColumnGroup
 import org.jetbrains.kotlinx.dataframe.api.minus
 import org.jetbrains.kotlinx.dataframe.api.pathOf
+import org.jetbrains.kotlinx.dataframe.api.rename
 import org.jetbrains.kotlinx.dataframe.columns.FrameColumn
 import org.jetbrains.kotlinx.dataframe.impl.aggregation.AggregatableInternal
 import org.jetbrains.kotlinx.dataframe.impl.aggregation.GroupByReceiverImpl
@@ -56,6 +58,13 @@ internal class GroupByImpl<T, G>(
         }
         return df[indices].asGroupBy(groups)
     }
+
+    override fun toDataFrame(groupedColumnName: String?): DataFrame<T> =
+        if (groupedColumnName == null || groupedColumnName == groups.name()) {
+            df
+        } else {
+            df.rename(groups).into(groupedColumnName)
+        }
 }
 
 internal fun <T, G, R> aggregateGroupBy(

core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/api/colGroups.kt

@@ -212,7 +212,6 @@ public interface ColGroupsColumnsSelectionDsl {
 @Suppress("UNCHECKED_CAST")
 internal fun ColumnsResolver<*>.columnGroupsInternal(
     filter: (ColumnGroup<*>) -> Boolean,
-): TransformableColumnSet<AnyRow> =
-    colsInternal { it.isColumnGroup() && filter(it.asColumnGroup()) } as TransformableColumnSet<AnyRow>
+): TransformableColumnSet<AnyRow> = colsInternal { it.isColumnGroup() && filter(it) } as TransformableColumnSet<AnyRow>
 
 // endregion

core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/api/groupBy.kt

@@ -11,7 +11,6 @@ import org.jetbrains.kotlinx.dataframe.annotations.Interpretable
 import org.jetbrains.kotlinx.dataframe.annotations.Refine
 import org.jetbrains.kotlinx.dataframe.columns.FrameColumn
 import org.jetbrains.kotlinx.dataframe.columns.toColumnSet
-import org.jetbrains.kotlinx.dataframe.impl.GroupByImpl
 import org.jetbrains.kotlinx.dataframe.impl.aggregation.PivotImpl
 import org.jetbrains.kotlinx.dataframe.impl.api.getPivotColumnPaths
 import org.jetbrains.kotlinx.dataframe.impl.api.groupByImpl
@@ -85,24 +84,17 @@ public interface GroupBy<out T, out G> : Grouped<G> {
 
     public fun filter(predicate: GroupedRowFilter<T, G>): GroupBy<T, G>
 
+    @Refine
+    @Interpretable("GroupByToDataFrame")
+    public fun toDataFrame(groupedColumnName: String? = null): DataFrame<T>
+
     public data class Entry<T, G>(val key: DataRow<T>, val group: DataFrame<G>)
 
     public companion object {
         internal val groupedColumnAccessor = column<AnyFrame>("group")
     }
 }
 
-@Refine
-@Interpretable("GroupByToDataFrame")
-public fun <T, G> GroupBy<T, G>.toDataFrame(groupedColumnName: String? = null): DataFrame<T> =
-    if (groupedColumnName == null || groupedColumnName == groups.name()) {
-        internal().df
-    } else {
-        internal().df.rename(groups).into(groupedColumnName)
-    }
-
-internal fun <T, G> GroupBy<T, G>.internal(): GroupByImpl<T, G> = this as GroupByImpl<T, G>
-
 public interface Grouped<out T> : Aggregatable<T>
 
 public class ReducedGroupBy<T, G>(

core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/api/parse.kt

@@ -58,7 +58,7 @@ public data class ParserOptions(
 public fun DataColumn<String?>.tryParse(options: ParserOptions? = null): DataColumn<*> = tryParseImpl(options)
 
 public fun <T> DataFrame<T>.parse(options: ParserOptions? = null): DataFrame<T> =
-    parseImpl(options) {
+    parse(options) {
         colsAtAnyDepth { !it.isColumnGroup() }
     }
 

core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/api/select.kt

@@ -252,8 +252,7 @@ internal fun <C, R> SingleColumn<DataRow<C>>.selectInternal(selector: ColumnsSel
                 "Column ${col.path} is not a ColumnGroup and can thus not be selected from."
             }
 
-            col.asColumnGroup()
-                .getColumnsWithPaths(selector as ColumnsSelector<*, R>)
+            col.getColumnsWithPaths(selector as ColumnsSelector<*, R>)
                 .map { it.changePath(col.path + it.path) }
         } ?: emptyList()
     }

core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/api/valueCols.kt

@@ -179,6 +179,6 @@ public interface ValueColsColumnsSelectionDsl {
  * @return A [TransformableColumnSet] containing the value columns that satisfy the filter.
  */
 internal fun ColumnsResolver<*>.valueColumnsInternal(filter: (ValueColumn<*>) -> Boolean): TransformableColumnSet<*> =
-    colsInternal { it.isValueColumn() && filter(it.asValueColumn()) }
+    colsInternal { it.isValueColumn() && filter(it) }
 
 // endregion

core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/impl/DataFrameReceiver.kt

@@ -4,7 +4,6 @@ import org.jetbrains.kotlinx.dataframe.ColumnSelector
 import org.jetbrains.kotlinx.dataframe.DataColumn
 import org.jetbrains.kotlinx.dataframe.DataFrame
 import org.jetbrains.kotlinx.dataframe.DataRow
-import org.jetbrains.kotlinx.dataframe.api.asColumnGroup
 import org.jetbrains.kotlinx.dataframe.api.asDataColumn
 import org.jetbrains.kotlinx.dataframe.api.cast
 import org.jetbrains.kotlinx.dataframe.api.isColumnGroup
@@ -78,7 +77,9 @@ internal open class DataFrameReceiver<T>(
         DataColumn.createColumnGroup("", df).addPath(emptyPath())
 
     override fun columns() =
-        df.columns().map { if (it.isColumnGroup()) ColumnGroupWithParent(null, it.asColumnGroup()) else it }
+        df.columns().map {
+            if (it.isColumnGroup()) ColumnGroupWithParent(null, it) else it
+        }
 
     override fun columnNames() = df.columnNames()