-
Notifications
You must be signed in to change notification settings - Fork 63
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #204 from Kotlin/sort-grouped-df
Sort grouped df
- Loading branch information
Showing
5 changed files
with
258 additions
and
12 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
72 changes: 72 additions & 0 deletions
72
core/src/test/kotlin/org/jetbrains/kotlinx/dataframe/api/sortGroupedDataframe.kt
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,72 @@ | ||
| package org.jetbrains.kotlinx.dataframe.api | ||
|
|
||
| import io.kotest.matchers.shouldBe | ||
| import org.jetbrains.kotlinx.dataframe.DataFrame | ||
| import org.jetbrains.kotlinx.dataframe.alsoDebug | ||
| import org.jetbrains.kotlinx.dataframe.io.read | ||
| import org.junit.Test | ||
|
|
||
| class SortGroupedDataframeTests { | ||
|
|
||
| @Test | ||
| fun `Sorted grouped iris dataset`() { | ||
| val irisData = DataFrame.read("src/test/resources/irisDataset.csv") | ||
| irisData.alsoDebug() | ||
|
|
||
| irisData.groupBy("variety").let { | ||
| it.sortBy("petal.length").toString() shouldBe | ||
| it.sortBy { it["petal.length"] }.toString() | ||
| } | ||
| } | ||
|
|
||
| enum class State { | ||
| Idle, Productive, Maintenance | ||
| } | ||
|
|
||
| @Test | ||
| fun test4() { | ||
| class Event(val toolId: String, val state: State, val timestamp: Long) | ||
|
|
||
| val tool1 = "tool_1" | ||
| val tool2 = "tool_2" | ||
| val tool3 = "tool_3" | ||
|
|
||
| val events = listOf( | ||
| Event(tool1, State.Idle, 0), | ||
| Event(tool1, State.Productive, 5), | ||
| Event(tool2, State.Idle, 0), | ||
| Event(tool2, State.Maintenance, 10), | ||
| Event(tool2, State.Idle, 20), | ||
| Event(tool3, State.Idle, 0), | ||
| Event(tool3, State.Productive, 25), | ||
| ).toDataFrame() | ||
|
|
||
| val lastTimestamp = events.maxOf { getValue<Long>("timestamp") } | ||
| val groupBy = events | ||
| .groupBy("toolId") | ||
| .sortBy("timestamp") | ||
| .add("stateDuration") { | ||
| (next()?.getValue("timestamp") ?: lastTimestamp) - getValue<Long>("timestamp") | ||
| } | ||
|
|
||
| groupBy.toDataFrame().alsoDebug() | ||
| groupBy.schema().print() | ||
| groupBy.keys.print() | ||
| groupBy.keys[0].print() | ||
|
|
||
| val df1 = groupBy.updateGroups { | ||
| val missingValues = State.values().asList().toDataFrame { | ||
| "state" from { it } | ||
| } | ||
|
|
||
| val df = it | ||
| .fullJoin(missingValues, "state") | ||
| .fillNulls("stateDuration") | ||
| .with { 100L } | ||
|
|
||
| df.groupBy("state").sumFor("stateDuration") | ||
| } | ||
|
|
||
| df1.toDataFrame().alsoDebug().isNotEmpty() shouldBe true | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,151 @@ | ||
| "sepal.length","sepal.width","petal.length","petal.width","variety" | ||
| 5.1,3.5,1.4,.2,"Setosa" | ||
| 4.9,3,1.4,.2,"Setosa" | ||
| 4.7,3.2,1.3,.2,"Setosa" | ||
| 4.6,3.1,1.5,.2,"Setosa" | ||
| 5,3.6,1.4,.2,"Setosa" | ||
| 5.4,3.9,1.7,.4,"Setosa" | ||
| 4.6,3.4,1.4,.3,"Setosa" | ||
| 5,3.4,1.5,.2,"Setosa" | ||
| 4.4,2.9,1.4,.2,"Setosa" | ||
| 4.9,3.1,1.5,.1,"Setosa" | ||
| 5.4,3.7,1.5,.2,"Setosa" | ||
| 4.8,3.4,1.6,.2,"Setosa" | ||
| 4.8,3,1.4,.1,"Setosa" | ||
| 4.3,3,1.1,.1,"Setosa" | ||
| 5.8,4,1.2,.2,"Setosa" | ||
| 5.7,4.4,1.5,.4,"Setosa" | ||
| 5.4,3.9,1.3,.4,"Setosa" | ||
| 5.1,3.5,1.4,.3,"Setosa" | ||
| 5.7,3.8,1.7,.3,"Setosa" | ||
| 5.1,3.8,1.5,.3,"Setosa" | ||
| 5.4,3.4,1.7,.2,"Setosa" | ||
| 5.1,3.7,1.5,.4,"Setosa" | ||
| 4.6,3.6,1,.2,"Setosa" | ||
| 5.1,3.3,1.7,.5,"Setosa" | ||
| 4.8,3.4,1.9,.2,"Setosa" | ||
| 5,3,1.6,.2,"Setosa" | ||
| 5,3.4,1.6,.4,"Setosa" | ||
| 5.2,3.5,1.5,.2,"Setosa" | ||
| 5.2,3.4,1.4,.2,"Setosa" | ||
| 4.7,3.2,1.6,.2,"Setosa" | ||
| 4.8,3.1,1.6,.2,"Setosa" | ||
| 5.4,3.4,1.5,.4,"Setosa" | ||
| 5.2,4.1,1.5,.1,"Setosa" | ||
| 5.5,4.2,1.4,.2,"Setosa" | ||
| 4.9,3.1,1.5,.2,"Setosa" | ||
| 5,3.2,1.2,.2,"Setosa" | ||
| 5.5,3.5,1.3,.2,"Setosa" | ||
| 4.9,3.6,1.4,.1,"Setosa" | ||
| 4.4,3,1.3,.2,"Setosa" | ||
| 5.1,3.4,1.5,.2,"Setosa" | ||
| 5,3.5,1.3,.3,"Setosa" | ||
| 4.5,2.3,1.3,.3,"Setosa" | ||
| 4.4,3.2,1.3,.2,"Setosa" | ||
| 5,3.5,1.6,.6,"Setosa" | ||
| 5.1,3.8,1.9,.4,"Setosa" | ||
| 4.8,3,1.4,.3,"Setosa" | ||
| 5.1,3.8,1.6,.2,"Setosa" | ||
| 4.6,3.2,1.4,.2,"Setosa" | ||
| 5.3,3.7,1.5,.2,"Setosa" | ||
| 5,3.3,1.4,.2,"Setosa" | ||
| 7,3.2,4.7,1.4,"Versicolor" | ||
| 6.4,3.2,4.5,1.5,"Versicolor" | ||
| 6.9,3.1,4.9,1.5,"Versicolor" | ||
| 5.5,2.3,4,1.3,"Versicolor" | ||
| 6.5,2.8,4.6,1.5,"Versicolor" | ||
| 5.7,2.8,4.5,1.3,"Versicolor" | ||
| 6.3,3.3,4.7,1.6,"Versicolor" | ||
| 4.9,2.4,3.3,1,"Versicolor" | ||
| 6.6,2.9,4.6,1.3,"Versicolor" | ||
| 5.2,2.7,3.9,1.4,"Versicolor" | ||
| 5,2,3.5,1,"Versicolor" | ||
| 5.9,3,4.2,1.5,"Versicolor" | ||
| 6,2.2,4,1,"Versicolor" | ||
| 6.1,2.9,4.7,1.4,"Versicolor" | ||
| 5.6,2.9,3.6,1.3,"Versicolor" | ||
| 6.7,3.1,4.4,1.4,"Versicolor" | ||
| 5.6,3,4.5,1.5,"Versicolor" | ||
| 5.8,2.7,4.1,1,"Versicolor" | ||
| 6.2,2.2,4.5,1.5,"Versicolor" | ||
| 5.6,2.5,3.9,1.1,"Versicolor" | ||
| 5.9,3.2,4.8,1.8,"Versicolor" | ||
| 6.1,2.8,4,1.3,"Versicolor" | ||
| 6.3,2.5,4.9,1.5,"Versicolor" | ||
| 6.1,2.8,4.7,1.2,"Versicolor" | ||
| 6.4,2.9,4.3,1.3,"Versicolor" | ||
| 6.6,3,4.4,1.4,"Versicolor" | ||
| 6.8,2.8,4.8,1.4,"Versicolor" | ||
| 6.7,3,5,1.7,"Versicolor" | ||
| 6,2.9,4.5,1.5,"Versicolor" | ||
| 5.7,2.6,3.5,1,"Versicolor" | ||
| 5.5,2.4,3.8,1.1,"Versicolor" | ||
| 5.5,2.4,3.7,1,"Versicolor" | ||
| 5.8,2.7,3.9,1.2,"Versicolor" | ||
| 6,2.7,5.1,1.6,"Versicolor" | ||
| 5.4,3,4.5,1.5,"Versicolor" | ||
| 6,3.4,4.5,1.6,"Versicolor" | ||
| 6.7,3.1,4.7,1.5,"Versicolor" | ||
| 6.3,2.3,4.4,1.3,"Versicolor" | ||
| 5.6,3,4.1,1.3,"Versicolor" | ||
| 5.5,2.5,4,1.3,"Versicolor" | ||
| 5.5,2.6,4.4,1.2,"Versicolor" | ||
| 6.1,3,4.6,1.4,"Versicolor" | ||
| 5.8,2.6,4,1.2,"Versicolor" | ||
| 5,2.3,3.3,1,"Versicolor" | ||
| 5.6,2.7,4.2,1.3,"Versicolor" | ||
| 5.7,3,4.2,1.2,"Versicolor" | ||
| 5.7,2.9,4.2,1.3,"Versicolor" | ||
| 6.2,2.9,4.3,1.3,"Versicolor" | ||
| 5.1,2.5,3,1.1,"Versicolor" | ||
| 5.7,2.8,4.1,1.3,"Versicolor" | ||
| 6.3,3.3,6,2.5,"Virginica" | ||
| 5.8,2.7,5.1,1.9,"Virginica" | ||
| 7.1,3,5.9,2.1,"Virginica" | ||
| 6.3,2.9,5.6,1.8,"Virginica" | ||
| 6.5,3,5.8,2.2,"Virginica" | ||
| 7.6,3,6.6,2.1,"Virginica" | ||
| 4.9,2.5,4.5,1.7,"Virginica" | ||
| 7.3,2.9,6.3,1.8,"Virginica" | ||
| 6.7,2.5,5.8,1.8,"Virginica" | ||
| 7.2,3.6,6.1,2.5,"Virginica" | ||
| 6.5,3.2,5.1,2,"Virginica" | ||
| 6.4,2.7,5.3,1.9,"Virginica" | ||
| 6.8,3,5.5,2.1,"Virginica" | ||
| 5.7,2.5,5,2,"Virginica" | ||
| 5.8,2.8,5.1,2.4,"Virginica" | ||
| 6.4,3.2,5.3,2.3,"Virginica" | ||
| 6.5,3,5.5,1.8,"Virginica" | ||
| 7.7,3.8,6.7,2.2,"Virginica" | ||
| 7.7,2.6,6.9,2.3,"Virginica" | ||
| 6,2.2,5,1.5,"Virginica" | ||
| 6.9,3.2,5.7,2.3,"Virginica" | ||
| 5.6,2.8,4.9,2,"Virginica" | ||
| 7.7,2.8,6.7,2,"Virginica" | ||
| 6.3,2.7,4.9,1.8,"Virginica" | ||
| 6.7,3.3,5.7,2.1,"Virginica" | ||
| 7.2,3.2,6,1.8,"Virginica" | ||
| 6.2,2.8,4.8,1.8,"Virginica" | ||
| 6.1,3,4.9,1.8,"Virginica" | ||
| 6.4,2.8,5.6,2.1,"Virginica" | ||
| 7.2,3,5.8,1.6,"Virginica" | ||
| 7.4,2.8,6.1,1.9,"Virginica" | ||
| 7.9,3.8,6.4,2,"Virginica" | ||
| 6.4,2.8,5.6,2.2,"Virginica" | ||
| 6.3,2.8,5.1,1.5,"Virginica" | ||
| 6.1,2.6,5.6,1.4,"Virginica" | ||
| 7.7,3,6.1,2.3,"Virginica" | ||
| 6.3,3.4,5.6,2.4,"Virginica" | ||
| 6.4,3.1,5.5,1.8,"Virginica" | ||
| 6,3,4.8,1.8,"Virginica" | ||
| 6.9,3.1,5.4,2.1,"Virginica" | ||
| 6.7,3.1,5.6,2.4,"Virginica" | ||
| 6.9,3.1,5.1,2.3,"Virginica" | ||
| 5.8,2.7,5.1,1.9,"Virginica" | ||
| 6.8,3.2,5.9,2.3,"Virginica" | ||
| 6.7,3.3,5.7,2.5,"Virginica" | ||
| 6.7,3,5.2,2.3,"Virginica" | ||
| 6.3,2.5,5,1.9,"Virginica" | ||
| 6.5,3,5.2,2,"Virginica" | ||
| 6.2,3.4,5.4,2.3,"Virginica" | ||
| 5.9,3,5.1,1.8,"Virginica" |