Procedural documentation for the join package (#4466)
* WIP task-based join docs * WIP join task-based docs * WIP prodedural join docs * WIP new join docs * WIP join docs, join diagrams * WIP join docs * WIP join docs * wrap up join docs * Apply suggestions from code review Co-authored-by: kelseiv <47797004+kelseiv@users.noreply.github.com> * apply updates from pr review * minor updates * fixed typo, updated update-flux-versions.js script * Apply suggestions from code review Co-authored-by: kelseiv <47797004+kelseiv@users.noreply.github.com> * Apply suggestions from code review * address PR feedback * add flux stdlib related links for join * fixed frontmatter injection Co-authored-by: kelseiv <47797004+kelseiv@users.noreply.github.com>pull/4480/head
Scott Anderson
GitHub
parent
1d34362e3c
commit
9472a6c7fc
|
|
@ -200,29 +200,16 @@ $('.tooltip').each( function(){
|
|||
$(this).prepend($toolTipElement);
|
||||
});
|
||||
|
||||
/////////////////// Style time columns in tables to not wrap ///////////////////
|
||||
//////////////////// Style time cells in tables to not wrap ////////////////////
|
||||
|
||||
$('.article--content table').each(function() {
|
||||
var table = $(this);
|
||||
var timeColumns = ['_time', '*_time', '_start', '*_start', '_stop', '*_stop'];
|
||||
let header = [];
|
||||
let timeColumnIndexes = [];
|
||||
|
||||
// Return an array of column headers
|
||||
table.find('th').each(function () {
|
||||
header.push($(this)[0].innerHTML);
|
||||
});
|
||||
|
||||
// Return indexes of time columns
|
||||
header.forEach(function(value, i) {
|
||||
if ( timeColumns.includes(value) ) { timeColumnIndexes.push(i) };
|
||||
});
|
||||
|
||||
// Add the nowrap class to cells with time column indexes
|
||||
table.find('td').each(function() {
|
||||
if (timeColumnIndexes.includes( $(this)[0].cellIndex )) {
|
||||
$(this).addClass('nowrap');
|
||||
let cellContent = $(this)[0].innerText
|
||||
|
||||
if (/\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}.*Z/.test(cellContent)) {
|
||||
$(this).addClass('nowrap')
|
||||
}
|
||||
})
|
||||
|
||||
})
|
||||
|
|
|
|||
|
|
@ -7,19 +7,20 @@
|
|||
}
|
||||
|
||||
.flex-container {
|
||||
margin-right: 1rem;
|
||||
margin-right: 1.5rem;
|
||||
|
||||
&.half { width: calc(50% - 1rem); }
|
||||
&.third { width: calc(33.33% - 1rem); }
|
||||
&.quarter { width: calc(25% - 1rem); }
|
||||
&.half { width: calc(50% - 1.5rem); }
|
||||
&.third { width: calc(33.33% - 1.5rem); }
|
||||
&.quarter { width: calc(25% - 1.5rem); }
|
||||
&.two-thirds { width: calc(66% - 2rem);}
|
||||
|
||||
&.half, &.third, &.quarter {
|
||||
table:not(:last-child) {margin-right: 1rem;}
|
||||
table:not(:last-child) {margin-right: 1.5rem;}
|
||||
}
|
||||
|
||||
img { margin-bottom: 0;}
|
||||
table { display: table; }
|
||||
p:last-child {margin-bottom: 0.5rem;}
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
|
@ -32,5 +33,6 @@
|
|||
&.third,
|
||||
&.two-thirds { width: calc(100% - 1rem); }
|
||||
&.quarter { width: calc(50% - 1rem); }
|
||||
p:last-child {margin-bottom: 1.5rem;}
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -14,6 +14,35 @@ svg {
|
|||
.st1 {fill: $article-text;}
|
||||
.st2 {font-family: $rubik; font-weight: $medium}
|
||||
}
|
||||
|
||||
//////////////////////////////// Join Diagram ////////////////////////////////
|
||||
&#join-diagram {
|
||||
$fill-color: rgba($article-text, .35);
|
||||
display: block;
|
||||
max-width: 250px;
|
||||
margin: 1rem 0 2rem;
|
||||
|
||||
&.center {margin: 0 auto 2rem auto;}
|
||||
&.small {max-width: 125px; path{stroke-width: 3;} }
|
||||
|
||||
path {
|
||||
stroke: $article-text;
|
||||
stroke-width:2;
|
||||
stroke-miterlimit:10;
|
||||
fill: none;
|
||||
}
|
||||
&.inner {path { &#center {fill:$fill-color; }}}
|
||||
&.left {path { &#left, &#center {fill:$fill-color; }}}
|
||||
&.right {path { &#center, &#right {fill:$fill-color; }}}
|
||||
&.full {path { &#left, &#center, &#right {fill:$fill-color; }}}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@include media(small) {
|
||||
svg {
|
||||
&#join-diagram {margin: 1rem auto 2rem; }
|
||||
}
|
||||
}
|
||||
|
||||
//////////////////////////// Styles for SVG legends ////////////////////////////
|
||||
|
|
|
|||
|
|
@ -39,16 +39,22 @@ that contains one value for each [row](#row).
|
|||
A **row** is a collection of associated [column](#column) values.
|
||||
|
||||
#### Group key
|
||||
A **group key** defines which columns and specific column values to include in a table.
|
||||
All rows in a table contain the same values in group key columns.
|
||||
All tables in a stream of tables have a unique group key, but group key
|
||||
modifications are applied to a stream of tables.
|
||||
A **group key** defines which columns to use to group tables in a stream of tables.
|
||||
Each table in a stream of tables represents a unique **group key instance**.
|
||||
All rows in a table contain the same values for each group key column.
|
||||
|
||||
##### Example group keys
|
||||
Group keys contain key-value pairs, where each key represents a column name and
|
||||
each value represents the column value included in the table.
|
||||
The following are examples of group keys in a stream of tables with three separate tables.
|
||||
Each group key represents a table containing data for a unique location:
|
||||
##### Example group key
|
||||
A group key can be represented by an array of column labels.
|
||||
|
||||
```
|
||||
[_measurement, facility, _field]
|
||||
```
|
||||
|
||||
##### Example group key instances
|
||||
Group key instances (unique to each table) include key-value pairs that identify
|
||||
each column name in the table that has the same value.
|
||||
The following are examples of group key instances in a stream of tables with three separate tables.
|
||||
Each represents a table containing data for a unique location:
|
||||
|
||||
```
|
||||
[_measurement: "production", facility: "us-midwest", _field: "apq"]
|
||||
|
|
|
|||
|
|
@ -0,0 +1,147 @@
|
|||
---
|
||||
title: Join data
|
||||
seotitle: Join data with Flux
|
||||
description: >
|
||||
Flux supports inner, full outer, left outer, and right outer joins.
|
||||
Learn how to use the `join` package to join two data sets with common values.
|
||||
menu:
|
||||
flux_0_x:
|
||||
name: Join data
|
||||
weight: 8
|
||||
related:
|
||||
- /flux/v0.x/stdlib/join/
|
||||
- /flux/v0.x/stdlib/join/inner/
|
||||
- /flux/v0.x/stdlib/join/left/
|
||||
- /flux/v0.x/stdlib/join/right/
|
||||
- /flux/v0.x/stdlib/join/full/
|
||||
- /flux/v0.x/stdlib/join/time/
|
||||
---
|
||||
|
||||
Use the Flux [`join` package](/flux/v0.x/stdlib/join/) to join two data sets based on common values.
|
||||
Learn how join two data sets using the following join methods:
|
||||
|
||||
{{< flex >}}
|
||||
{{< flex-content "quarter" >}}
|
||||
<a href="#perform-an-inner-join">
|
||||
<p style="text-align:center"><strong>Inner join</strong></p>
|
||||
{{< svg svg="static/svgs/join-diagram.svg" class="inner small center" >}}
|
||||
</a>
|
||||
{{< /flex-content >}}
|
||||
{{< flex-content "quarter" >}}
|
||||
<a href="#perform-a-left-outer-join">
|
||||
<p style="text-align:center"><strong>Left outer join</strong></p>
|
||||
{{< svg svg="static/svgs/join-diagram.svg" class="left small center" >}}
|
||||
</a>
|
||||
{{< /flex-content >}}
|
||||
{{< flex-content "quarter" >}}
|
||||
<a href="#perform-a-right-outer-join">
|
||||
<p style="text-align:center"><strong>Right outer join</strong></p>
|
||||
{{< svg svg="static/svgs/join-diagram.svg" class="right small center" >}}
|
||||
</a>
|
||||
{{< /flex-content >}}
|
||||
{{< flex-content "quarter" >}}
|
||||
<a href="#perform-a-full-outer-join">
|
||||
<p style="text-align:center"><strong>Full outer join</strong></p>
|
||||
{{< svg svg="static/svgs/join-diagram.svg" class="full small center" >}}
|
||||
</a>
|
||||
{{< /flex-content >}}
|
||||
{{< /flex >}}
|
||||
|
||||
{{% note %}}
|
||||
#### When to use the join package
|
||||
|
||||
We recommend using the `join` package to join streams that have mostly different
|
||||
schemas or that come from two separate data sources.
|
||||
If you're joining data from the same data source with the same schema, using
|
||||
[`union()`](/flux/v0.x/stdlib/universe/union/) and [`pivot()`](/flux/v0.x/stdlib/universe/pivot/)
|
||||
to combine the data will likely be more performant.
|
||||
{{% /note %}}
|
||||
|
||||
- [How join functions work](#how-join-functions-work)
|
||||
- [Input streams](#input-streams)
|
||||
- [Join predicate function (on)](#join-predicate-function-on)
|
||||
- [Join output function (as)](#join-output-function-as)
|
||||
- [Perform join operations](#perform-join-operations)
|
||||
{{< children type="anchored-list" filterOut="Troubleshoot join operations" >}}
|
||||
- [Troubleshoot join operations](#troubleshoot-join-operations)
|
||||
|
||||
## How join functions work
|
||||
|
||||
`join` functions join _two_ streams of tables together based
|
||||
on common values in each input stream.
|
||||
|
||||
- [Input streams](#input-streams)
|
||||
- [Join predicate function (on)](#join-predicate-function-on)
|
||||
- [Join output function (as)](#join-output-function-as)
|
||||
|
||||
### Input streams
|
||||
|
||||
Each input stream is assigned to the `left` or `right` parameter.
|
||||
Input streams can be defined from any valid data source.
|
||||
For more information, see:
|
||||
|
||||
- [Query data sources](/flux/v0.x/query-data/)
|
||||
- Define ad hoc tables with [`array.from()`](/flux/v0.x/stdlib/array/from/)
|
||||
|
||||
#### Data requirements
|
||||
|
||||
To join data, each input stream must have the following:
|
||||
|
||||
- **One or more columns with common values to join on**.
|
||||
Columns do not need identical labels, but they do need to have comparable values.
|
||||
- **Identical [group keys](/flux/v0.x/get-started/data-model/#group-key)**.
|
||||
Functions in the `join` package use group keys to quickly determine what tables
|
||||
from each input stream should be paired and evaluated for the join operation.
|
||||
_Both input streams should have the same group key._
|
||||
If they don't, your join operation may not find any matching tables and will
|
||||
return unexpected output.
|
||||
If the group keys of your input streams are not identical, use
|
||||
[`group()`](/flux/v0.x/stdlib/universe/group/) to regroup each input
|
||||
stream before joining them together.
|
||||
|
||||
{{% note %}}
|
||||
Only tables with the same [group key instance](/flux/v0.x/get-started/data-model/#example-group-key-instances)
|
||||
are joined.
|
||||
{{% /note %}}
|
||||
|
||||
### Join predicate function (on)
|
||||
|
||||
`join` package functions require the `on` parameter to compare values from each input stream (represented by `l` (left) and `r` (right))
|
||||
and returns `true` or `false`.
|
||||
Rows that return `true` are joined.
|
||||
This parameter is a [predicate function](/flux/v0.x/get-started/syntax-basics/#predicate-functions).
|
||||
|
||||
|
||||
```js
|
||||
(l, r) => l.column == r.column
|
||||
```
|
||||
|
||||
### Join output function (as)
|
||||
|
||||
`join` package functions _(except [`join.time()`](/flux/v0.x/stdlib/join/time/))_
|
||||
require the `as` parameter to define the output schema of the join.
|
||||
The `as` parameter returns a new record using values from
|
||||
joined rows–left (`l`) and right (`r`).
|
||||
|
||||
```js
|
||||
(l, r) => ({l with name: r.name, location: r.location})
|
||||
```
|
||||
|
||||
{{% note %}}
|
||||
#### Do not modify group key columns
|
||||
|
||||
Do not modify group key columns. The `as` function must return the same group key as both input streams to successfully perform a join.
|
||||
{{% /note %}}
|
||||
|
||||
## Perform join operations
|
||||
|
||||
The `join` package supports the following join types and special use cases:
|
||||
|
||||
{{< children type="anchored-list" filterOut="Troubleshoot join operations" >}}
|
||||
|
||||
{{< children readmore=true filterOut="Troubleshoot join operations" >}}
|
||||
|
||||
## Troubleshoot join operations
|
||||
|
||||
For information about unexpected behaviors and errors when using the `join` package,
|
||||
see [Troubleshoot join operations](/flux/v0.x/join-data/troubleshoot-joins/).
|
||||
|
|
@ -0,0 +1,252 @@
|
|||
---
|
||||
title: Perform a full outer join
|
||||
description: >
|
||||
Use [`join.full()`](/flux/v0.x/stdlib/join/full/) to perform an full outer join of two streams of data.
|
||||
Full outer joins output a row for all rows in both the **left** and **right** input streams
|
||||
and join rows that match according to the `on` predicate.
|
||||
menu:
|
||||
flux_0_x:
|
||||
name: Full outer join
|
||||
parent: Join data
|
||||
weight: 103
|
||||
related:
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
- /flux/v0.x/stdlib/join/
|
||||
- /flux/v0.x/stdlib/join/full/
|
||||
list_code_example: |
|
||||
```js
|
||||
import "join"
|
||||
|
||||
left = from(bucket: "example-bucket-1") |> //...
|
||||
right = from(bucket: "example-bucket-2") |> //...
|
||||
|
||||
join.full(
|
||||
left: left,
|
||||
right: right,
|
||||
on: (l, r) => l.id== r.id,
|
||||
as: (l, r) => {
|
||||
id = if exists l.id then l.id else r.id
|
||||
|
||||
return {name: l.name, location: r.location, id: id}
|
||||
},
|
||||
)
|
||||
```
|
||||
---
|
||||
|
||||
Use [`join.full()`](/flux/v0.x/stdlib/join/full/) to perform an full outer join of two streams of data.
|
||||
Full outer joins output a row for all rows in both the **left** and **right** input streams
|
||||
and join rows that match according to the `on` predicate.
|
||||
|
||||
{{< svg svg="static/svgs/join-diagram.svg" class="full" >}}
|
||||
|
||||
{{< expand-wrapper >}}
|
||||
{{% expand "View table illustration of a full outer join" %}}
|
||||
{{< flex >}}
|
||||
{{% flex-content "third" %}}
|
||||
#### left
|
||||
| | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> |
|
||||
| r2 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> |
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content "third" %}}
|
||||
#### right
|
||||
| | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r3 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r4 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content "third" %}}
|
||||
#### Full outer join result
|
||||
|
||||
| | | | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r2 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> | | |
|
||||
| r3 | | | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r4 | | | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
{{% /flex-content %}}
|
||||
{{< /flex >}}
|
||||
{{% /expand %}}
|
||||
{{< /expand-wrapper >}}
|
||||
|
||||
## Use join.full to join your data
|
||||
|
||||
1. Import the `join` package.
|
||||
2. Define the **left** and **right** data streams to join:
|
||||
|
||||
- Each stream must have one or more columns with common values.
|
||||
Column labels do not need to match, but column values do.
|
||||
- Each stream should have identical [group keys](/flux/v0.x/get-started/data-model/#group-key).
|
||||
|
||||
_For more information, see [join data requirements](/flux/v0.x/join-data/#data-requirements)._
|
||||
|
||||
3. Use `join.full()` to join the two streams together.
|
||||
Provide the following required parameters:
|
||||
|
||||
- `left`: Stream of data representing the left side of the join.
|
||||
- `right`: Stream of data representing the right side of the join.
|
||||
- `on`: [Join predicate](/flux/v0.x/join-data/#join-predicate-function-on).
|
||||
For example: `(l, r) => l.column == r.column`.
|
||||
- `as`: [Join output function](/flux/v0.x/join-data/#join-output-function-as)
|
||||
that returns a record with values from each input stream.
|
||||
|
||||
##### Account for missing, non-group-key values
|
||||
|
||||
In a full outer join, it’s possible for either the left (`l`) or right (`r`)
|
||||
to contain _null_ values for the columns used in the join operation
|
||||
and default to a default record (group key columns are populated and
|
||||
other columns are _null_).
|
||||
`l` and `r` will never both use default records at the same time.
|
||||
|
||||
To ensure non-null values are included in the output for non-group-key columns,
|
||||
check for the existence of a value in the `l` or `r` record, and return
|
||||
the value that exists:
|
||||
|
||||
```js
|
||||
(l, r) => {
|
||||
id = if exists l.id then l.id else r.id
|
||||
|
||||
return {_time: l.time, location: r.location, id: id}
|
||||
}
|
||||
```
|
||||
|
||||
The following example uses a filtered selection from the
|
||||
[**machineProduction** sample data set](/flux/v0.x/stdlib/influxdata/influxdb/sample/data/#set)
|
||||
as the **left** data stream and an ad-hoc table created with [`array.from()`](/flux/v0.x/stdlib/array/from/)
|
||||
as the **right** data stream.
|
||||
|
||||
{{% note %}}
|
||||
#### Example data grouping
|
||||
|
||||
The example below ungroups the **left** stream to match the grouping of the **right** stream.
|
||||
After the two streams are joined together, the joined data is grouped by `stationID`
|
||||
and sorted by `_time`.
|
||||
{{% /note %}}
|
||||
|
||||
```js
|
||||
import "array"
|
||||
import "influxdata/influxdb/sample"
|
||||
import "join"
|
||||
|
||||
left =
|
||||
sample.data(set: "machineProduction")
|
||||
|> filter(fn: (r) => r.stationID == "g1" or r.stationID == "g2" or r.stationID == "g3")
|
||||
|> filter(fn: (r) => r._field == "oil_temp")
|
||||
|> limit(n: 5)
|
||||
|
||||
right =
|
||||
array.from(
|
||||
rows: [
|
||||
{station: "g1", opType: "auto", last_maintained: 2021-07-15T00:00:00Z},
|
||||
{station: "g2", opType: "manned", last_maintained: 2021-07-02T00:00:00Z},
|
||||
{station: "g4", opType: "auto", last_maintained: 2021-08-04T00:00:00Z},
|
||||
],
|
||||
)
|
||||
|
||||
join.full(
|
||||
left: left |> group(),
|
||||
right: right,
|
||||
on: (l, r) => l.stationID == r.station,
|
||||
as: (l, r) => {
|
||||
stationID = if exists l.stationID then l.stationID else r.station
|
||||
|
||||
return {
|
||||
stationID: stationID,
|
||||
_time: l._time,
|
||||
_field: l._field,
|
||||
_value: l._value,
|
||||
opType: r.opType,
|
||||
maintained: r.last_maintained,
|
||||
}
|
||||
},
|
||||
)
|
||||
|> group(columns: ["stationID"])
|
||||
|> sort(columns: ["_time"])
|
||||
```
|
||||
|
||||
{{< expand-wrapper >}}
|
||||
{{% expand "View example input and output" %}}
|
||||
|
||||
### Input
|
||||
|
||||
#### left {#left-input}
|
||||
|
||||
{{% note %}}
|
||||
_`_start` and `_stop` columns have been omitted._
|
||||
{{% /note %}}
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g1 | oil_temp | 39.1 |
|
||||
| 2021-08-01T00:00:11.51Z | machinery | g1 | oil_temp | 40.3 |
|
||||
| 2021-08-01T00:00:19.53Z | machinery | g1 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:00:25.1Z | machinery | g1 | oil_temp | 40.72 |
|
||||
| 2021-08-01T00:00:36.88Z | machinery | g1 | oil_temp | 40.8 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:00:27.93Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:00:54.96Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:01:17.27Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:01:41.84Z | machinery | g2 | oil_temp | 40.6 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g3 | oil_temp | 41.4 |
|
||||
| 2021-08-01T00:00:14.46Z | machinery | g3 | oil_temp | 41.36 |
|
||||
| 2021-08-01T00:00:25.29Z | machinery | g3 | oil_temp | 41.4 |
|
||||
| 2021-08-01T00:00:38.77Z | machinery | g3 | oil_temp | 41.4 |
|
||||
| 2021-08-01T00:00:51.2Z | machinery | g3 | oil_temp | 41.4 |
|
||||
|
||||
#### right {#right-input}
|
||||
|
||||
| station | opType | last_maintained |
|
||||
| :------ | :----- | -------------------: |
|
||||
| g1 | auto | 2021-07-15T00:00:00Z |
|
||||
| g2 | manned | 2021-07-02T00:00:00Z |
|
||||
| g4 | auto | 2021-08-04T00:00:00Z |
|
||||
|
||||
### Output {#example-output}
|
||||
|
||||
| _time | stationID | _field | _value | maintained | opType |
|
||||
| :---------------------- | :-------- | :------- | -----: | :------------------- | :----- |
|
||||
| 2021-08-01T00:00:00Z | g1 | oil_temp | 39.1 | 2021-07-15T00:00:00Z | auto |
|
||||
| 2021-08-01T00:00:11.51Z | g1 | oil_temp | 40.3 | 2021-07-15T00:00:00Z | auto |
|
||||
| 2021-08-01T00:00:19.53Z | g1 | oil_temp | 40.6 | 2021-07-15T00:00:00Z | auto |
|
||||
| 2021-08-01T00:00:25.1Z | g1 | oil_temp | 40.72 | 2021-07-15T00:00:00Z | auto |
|
||||
| 2021-08-01T00:00:36.88Z | g1 | oil_temp | 40.8 | 2021-07-15T00:00:00Z | auto |
|
||||
|
||||
| _time | stationID | _field | _value | maintained | opType |
|
||||
| :---------------------- | :-------- | :------- | -----: | :------------------- | :----- |
|
||||
| 2021-08-01T00:00:00Z | g2 | oil_temp | 40.6 | 2021-07-02T00:00:00Z | manned |
|
||||
| 2021-08-01T00:00:27.93Z | g2 | oil_temp | 40.6 | 2021-07-02T00:00:00Z | manned |
|
||||
| 2021-08-01T00:00:54.96Z | g2 | oil_temp | 40.6 | 2021-07-02T00:00:00Z | manned |
|
||||
| 2021-08-01T00:01:17.27Z | g2 | oil_temp | 40.6 | 2021-07-02T00:00:00Z | manned |
|
||||
| 2021-08-01T00:01:41.84Z | g2 | oil_temp | 40.6 | 2021-07-02T00:00:00Z | manned |
|
||||
|
||||
| _time | stationID | _field | _value | maintained | opType |
|
||||
| :---------------------- | :-------- | :------- | -----: | :--------- | :----- |
|
||||
| 2021-08-01T00:00:00Z | g3 | oil_temp | 41.4 | | |
|
||||
| 2021-08-01T00:00:14.46Z | g3 | oil_temp | 41.36 | | |
|
||||
| 2021-08-01T00:00:25.29Z | g3 | oil_temp | 41.4 | | |
|
||||
| 2021-08-01T00:00:38.77Z | g3 | oil_temp | 41.4 | | |
|
||||
| 2021-08-01T00:00:51.2Z | g3 | oil_temp | 41.4 | | |
|
||||
|
||||
| _time | stationID | _field | _value | maintained | opType |
|
||||
| :---- | :-------- | :----- | -----: | :------------------- | :----- |
|
||||
| | g4 | | | 2021-08-04T00:00:00Z | auto |
|
||||
|
||||
#### Things to note about the join output
|
||||
- Because the [right stream](#right-input) does not have rows with the `g3` stationID tag,
|
||||
the joined output includes rows with the `g3` stationID tag from the [left stream](#left-input)
|
||||
with _null_ values in columns populated from the **right** stream.
|
||||
- Because the [left stream](#left-input) does not have rows with the `g4` stationID tag,
|
||||
the joined output includes rows with the `g4` stationID tag from the [right stream](#right-input)
|
||||
with _null_ values in columns populated from the **left** stream.
|
||||
|
||||
{{% /expand %}}
|
||||
{{< /expand-wrapper >}}
|
||||
|
||||
|
|
@ -0,0 +1,196 @@
|
|||
---
|
||||
title: Perform an inner join
|
||||
description: >
|
||||
Use [`join.inner()`](/flux/v0.x/stdlib/join/inner/) to perform an inner join of two streams of data.
|
||||
Inner joins drop any rows from both input streams that do not have a matching
|
||||
row in the other stream.
|
||||
menu:
|
||||
flux_0_x:
|
||||
name: Inner join
|
||||
parent: Join data
|
||||
weight: 101
|
||||
related:
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
- /flux/v0.x/stdlib/join/
|
||||
- /flux/v0.x/stdlib/join/inner/
|
||||
list_code_example: |
|
||||
```js
|
||||
import "join"
|
||||
|
||||
left = from(bucket: "example-bucket-1") |> //...
|
||||
right = from(bucket: "example-bucket-2") |> //...
|
||||
|
||||
join.inner(
|
||||
left: left,
|
||||
right: right,
|
||||
on: (l, r) => l.column == r.column,
|
||||
as: (l, r) => ({l with name: r.name, location: r.location}),
|
||||
)
|
||||
```
|
||||
---
|
||||
|
||||
Use [`join.inner()`](/flux/v0.x/stdlib/join/inner/) to perform an inner join of two streams of data.
|
||||
Inner joins drop any rows from both input streams that do not have a matching
|
||||
row in the other stream.
|
||||
|
||||
{{< svg svg="static/svgs/join-diagram.svg" class="inner" >}}
|
||||
|
||||
{{< expand-wrapper >}}
|
||||
{{% expand "View table illustration of an inner join" %}}
|
||||
{{< flex >}}
|
||||
{{% flex-content "third" %}}
|
||||
#### left
|
||||
| | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> |
|
||||
| r2 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> |
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content "third" %}}
|
||||
#### right
|
||||
| | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r3 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r4 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content "third" %}}
|
||||
#### Inner join result
|
||||
|
||||
| | | | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
{{% /flex-content %}}
|
||||
{{< /flex >}}
|
||||
{{% /expand %}}
|
||||
{{< /expand-wrapper >}}
|
||||
|
||||
## Use join.inner to join your data
|
||||
|
||||
1. Import the `join` package.
|
||||
2. Define the **left** and **right** data streams to join:
|
||||
|
||||
- Each stream must have one or more columns with common values.
|
||||
Column labels do not need to match, but column values do.
|
||||
- Each stream should have identical [group keys](/flux/v0.x/get-started/data-model/#group-key).
|
||||
|
||||
_For more information, see [join data requirements](/flux/v0.x/join-data/#data-requirements)._
|
||||
|
||||
3. Use `join.inner()` to join the two streams together.
|
||||
Provide the following required parameters:
|
||||
|
||||
- `left`: Stream of data representing the left side of the join.
|
||||
- `right`: Stream of data representing the right side of the join.
|
||||
- `on`: [Join predicate](/flux/v0.x/join-data/#join-predicate-function-on).
|
||||
For example: `(l, r) => l.column == r.column`.
|
||||
- `as`: [Join output function](/flux/v0.x/join-data/#join-output-function-as)
|
||||
that returns a record with values from each input stream.
|
||||
For example: `(l, r) => ({l with column1: r.column1, column2: r.column2})`.
|
||||
|
||||
The following example uses a filtered selection from the
|
||||
[**machineProduction** sample data set](/flux/v0.x/stdlib/influxdata/influxdb/sample/data/#set)
|
||||
as the **left** data stream and an ad-hoc table created with [`array.from()`](/flux/v0.x/stdlib/array/from/)
|
||||
as the **right** data stream.
|
||||
|
||||
{{% note %}}
|
||||
#### Example data grouping
|
||||
|
||||
The example below ungroups the **left** stream to match the grouping of the **right** stream.
|
||||
After the two streams are joined together, the joined data is grouped by `stationID`.
|
||||
{{% /note %}}
|
||||
|
||||
```js
|
||||
import "array"
|
||||
import "influxdata/influxdb/sample"
|
||||
import "join"
|
||||
|
||||
left =
|
||||
sample.data(set: "machineProduction")
|
||||
|> filter(fn: (r) => r.stationID == "g1" or r.stationID == "g2" or r.stationID == "g3")
|
||||
|> filter(fn: (r) => r._field == "oil_temp")
|
||||
|> limit(n: 5)
|
||||
|
||||
right =
|
||||
array.from(
|
||||
rows: [
|
||||
{station: "g1", opType: "auto", last_maintained: 2021-07-15T00:00:00Z},
|
||||
{station: "g2", opType: "manned", last_maintained: 2021-07-02T00:00:00Z},
|
||||
],
|
||||
)
|
||||
|
||||
join.inner(
|
||||
left: left |> group(),
|
||||
right: right,
|
||||
on: (l, r) => l.stationID == r.station,
|
||||
as: (l, r) => ({l with opType: r.opType, maintained: r.last_maintained}),
|
||||
)
|
||||
|> group(columns: ["stationID"])
|
||||
```
|
||||
|
||||
{{< expand-wrapper >}}
|
||||
{{% expand "View example input and output" %}}
|
||||
|
||||
{{% note %}}
|
||||
_`_start` and `_stop` columns have been omitted from example input and output._
|
||||
{{% /note %}}
|
||||
|
||||
### Input
|
||||
|
||||
#### left {#left-input}
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g1 | oil_temp | 39.1 |
|
||||
| 2021-08-01T00:00:11.51Z | machinery | g1 | oil_temp | 40.3 |
|
||||
| 2021-08-01T00:00:19.53Z | machinery | g1 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:00:25.1Z | machinery | g1 | oil_temp | 40.72 |
|
||||
| 2021-08-01T00:00:36.88Z | machinery | g1 | oil_temp | 40.8 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:00:27.93Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:00:54.96Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:01:17.27Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:01:41.84Z | machinery | g2 | oil_temp | 40.6 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g3 | oil_temp | 41.4 |
|
||||
| 2021-08-01T00:00:14.46Z | machinery | g3 | oil_temp | 41.36 |
|
||||
| 2021-08-01T00:00:25.29Z | machinery | g3 | oil_temp | 41.4 |
|
||||
| 2021-08-01T00:00:38.77Z | machinery | g3 | oil_temp | 41.4 |
|
||||
| 2021-08-01T00:00:51.2Z | machinery | g3 | oil_temp | 41.4 |
|
||||
|
||||
#### right {#right-input}
|
||||
|
||||
| station | opType | last_maintained |
|
||||
| :------ | :----- | -------------------: |
|
||||
| g1 | auto | 2021-07-15T00:00:00Z |
|
||||
| g2 | manned | 2021-07-02T00:00:00Z |
|
||||
|
||||
### Output {#example-output}
|
||||
|
||||
| _time | _measurement | stationID | _field | _value | opType | maintained |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: | :----- | :------------------- |
|
||||
| 2021-08-01T00:00:00Z | machinery | g1 | oil_temp | 39.1 | auto | 2021-07-15T00:00:00Z |
|
||||
| 2021-08-01T00:00:11.51Z | machinery | g1 | oil_temp | 40.3 | auto | 2021-07-15T00:00:00Z |
|
||||
| 2021-08-01T00:00:19.53Z | machinery | g1 | oil_temp | 40.6 | auto | 2021-07-15T00:00:00Z |
|
||||
| 2021-08-01T00:00:25.1Z | machinery | g1 | oil_temp | 40.72 | auto | 2021-07-15T00:00:00Z |
|
||||
| 2021-08-01T00:00:36.88Z | machinery | g1 | oil_temp | 40.8 | auto | 2021-07-15T00:00:00Z |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value | opType | maintained |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: | :----- | :------------------- |
|
||||
| 2021-08-01T00:00:00Z | machinery | g2 | oil_temp | 40.6 | manned | 2021-07-02T00:00:00Z |
|
||||
| 2021-08-01T00:00:27.93Z | machinery | g2 | oil_temp | 40.6 | manned | 2021-07-02T00:00:00Z |
|
||||
| 2021-08-01T00:00:54.96Z | machinery | g2 | oil_temp | 40.6 | manned | 2021-07-02T00:00:00Z |
|
||||
| 2021-08-01T00:01:17.27Z | machinery | g2 | oil_temp | 40.6 | manned | 2021-07-02T00:00:00Z |
|
||||
| 2021-08-01T00:01:41.84Z | machinery | g2 | oil_temp | 40.6 | manned | 2021-07-02T00:00:00Z |
|
||||
|
||||
#### Things to note about the join output
|
||||
- Because the [right stream](#right-input) does not have a row with the `g3` station tag,
|
||||
the joined output drops all rows with the `g3` stationID tag from the [left stream](#left-input).
|
||||
`join.inner()` drops any rows that do not have a matching row in the other
|
||||
data stream.
|
||||
|
||||
{{% /expand %}}
|
||||
{{< /expand-wrapper >}}
|
||||
|
|
@ -0,0 +1,207 @@
|
|||
---
|
||||
title: Perform a left outer join
|
||||
description: >
|
||||
Use [`join.left()`](/flux/v0.x/stdlib/join/left/) to perform an outer left join of two streams of data.
|
||||
Left joins output a row for each row in the **left** data stream with data matching
|
||||
from the **right** data stream. If there is no matching data in the **right**
|
||||
data stream, non-group-key columns with values from the **right** data stream are _null_.
|
||||
menu:
|
||||
flux_0_x:
|
||||
name: Left outer join
|
||||
parent: Join data
|
||||
weight: 102
|
||||
related:
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
- /flux/v0.x/stdlib/join/
|
||||
- /flux/v0.x/stdlib/join/left/
|
||||
list_code_example: |
|
||||
```js
|
||||
import "join"
|
||||
|
||||
left = from(bucket: "example-bucket-1") |> //...
|
||||
right = from(bucket: "example-bucket-2") |> //...
|
||||
|
||||
join.left(
|
||||
left: left,
|
||||
right: right,
|
||||
on: (l, r) => l.column == r.column,
|
||||
as: (l, r) => ({l with name: r.name, location: r.location}),
|
||||
)
|
||||
```
|
||||
---
|
||||
|
||||
Use [`join.left()`](/flux/v0.x/stdlib/join/left/) to perform an left outer join of two streams of data.
|
||||
Left joins output a row for each row in the **left** data stream with data matching
|
||||
from the **right** data stream. If there is no matching data in the **right**
|
||||
data stream, non-group-key columns with values from the **right** data stream are _null_.
|
||||
|
||||
{{< svg svg="static/svgs/join-diagram.svg" class="left" >}}
|
||||
|
||||
{{< expand-wrapper >}}
|
||||
{{% expand "View table illustration of a left outer join" %}}
|
||||
{{< flex >}}
|
||||
{{% flex-content "third" %}}
|
||||
#### left
|
||||
| | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> |
|
||||
| r2 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> |
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content "third" %}}
|
||||
#### right
|
||||
| | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r3 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r4 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content "third" %}}
|
||||
#### Left outer join result
|
||||
|
||||
| | | | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r2 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> | | |
|
||||
{{% /flex-content %}}
|
||||
{{< /flex >}}
|
||||
{{% /expand %}}
|
||||
{{< /expand-wrapper >}}
|
||||
|
||||
## Use join.left to join your data
|
||||
|
||||
1. Import the `join` package.
|
||||
2. Define the **left** and **right** data streams to join:
|
||||
|
||||
- Each stream must have one or more columns with common values.
|
||||
Column labels do not need to match, but column values do.
|
||||
- Each stream should have identical [group keys](/flux/v0.x/get-started/data-model/#group-key).
|
||||
|
||||
_For more information, see [join data requirements](/flux/v0.x/join-data/#data-requirements)._
|
||||
|
||||
3. Use `join.left()` to join the two streams together.
|
||||
Provide the following parameters:
|
||||
|
||||
- `left`: Stream of data representing the left side of the join.
|
||||
- `right`: Stream of data representing the right side of the join.
|
||||
- `on`: [Join predicate](/flux/v0.x/join-data/#join-predicate-function-on).
|
||||
For example: `(l, r) => l.column == r.column`.
|
||||
- `as`: [Join output function](/flux/v0.x/join-data/#join-output-function-as)
|
||||
that returns a record with values from each input stream.
|
||||
For example: `(l, r) => ({l with column1: r.column1, column2: r.column2})`.
|
||||
|
||||
The following example uses a filtered selection from the
|
||||
[**machineProduction** sample data set](/flux/v0.x/stdlib/influxdata/influxdb/sample/data/#set)
|
||||
as the **left** data stream and an ad-hoc table created with [`array.from()`](/flux/v0.x/stdlib/array/from/)
|
||||
as the **right** data stream.
|
||||
|
||||
{{% note %}}
|
||||
#### Example data grouping
|
||||
|
||||
The example below ungroups the **left** stream to match the grouping of the **right** stream.
|
||||
After the two streams are joined together, the joined data is grouped by `stationID`.
|
||||
{{% /note %}}
|
||||
|
||||
```js
|
||||
import "array"
|
||||
import "influxdata/influxdb/sample"
|
||||
import "join"
|
||||
|
||||
left =
|
||||
sample.data(set: "machineProduction")
|
||||
|> filter(fn: (r) => r.stationID == "g1" or r.stationID == "g2" or r.stationID == "g3")
|
||||
|> filter(fn: (r) => r._field == "oil_temp")
|
||||
|> limit(n: 5)
|
||||
|
||||
right =
|
||||
array.from(
|
||||
rows: [
|
||||
{station: "g1", opType: "auto", last_maintained: 2021-07-15T00:00:00Z},
|
||||
{station: "g2", opType: "manned", last_maintained: 2021-07-02T00:00:00Z},
|
||||
],
|
||||
)
|
||||
|
||||
join.left(
|
||||
left: left |> group(),
|
||||
right: right,
|
||||
on: (l, r) => l.stationID == r.station,
|
||||
as: (l, r) => ({l with opType: r.opType, maintained: r.last_maintained}),
|
||||
)
|
||||
|> group(columns: ["stationID"])
|
||||
```
|
||||
|
||||
{{< expand-wrapper >}}
|
||||
{{% expand "View example input and output" %}}
|
||||
|
||||
{{% note %}}
|
||||
_`_start` and `_stop` columns have been omitted from example input and output._
|
||||
{{% /note %}}
|
||||
|
||||
### Input
|
||||
|
||||
#### left {#left-input}
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g1 | oil_temp | 39.1 |
|
||||
| 2021-08-01T00:00:11.51Z | machinery | g1 | oil_temp | 40.3 |
|
||||
| 2021-08-01T00:00:19.53Z | machinery | g1 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:00:25.1Z | machinery | g1 | oil_temp | 40.72 |
|
||||
| 2021-08-01T00:00:36.88Z | machinery | g1 | oil_temp | 40.8 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:00:27.93Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:00:54.96Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:01:17.27Z | machinery | g2 | oil_temp | 40.6 |
|
||||
| 2021-08-01T00:01:41.84Z | machinery | g2 | oil_temp | 40.6 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g3 | oil_temp | 41.4 |
|
||||
| 2021-08-01T00:00:14.46Z | machinery | g3 | oil_temp | 41.36 |
|
||||
| 2021-08-01T00:00:25.29Z | machinery | g3 | oil_temp | 41.4 |
|
||||
| 2021-08-01T00:00:38.77Z | machinery | g3 | oil_temp | 41.4 |
|
||||
| 2021-08-01T00:00:51.2Z | machinery | g3 | oil_temp | 41.4 |
|
||||
|
||||
#### right {#right-input}
|
||||
|
||||
| station | opType | last_maintained |
|
||||
| :------ | :----- | -------------------: |
|
||||
| g1 | auto | 2021-07-15T00:00:00Z |
|
||||
| g2 | manned | 2021-07-02T00:00:00Z |
|
||||
|
||||
### Output {#example-output}
|
||||
|
||||
| _time | _measurement | stationID | _field | _value | opType | maintained |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: | :----- | :------------------- |
|
||||
| 2021-08-01T00:00:00Z | machinery | g1 | oil_temp | 39.1 | auto | 2021-07-15T00:00:00Z |
|
||||
| 2021-08-01T00:00:11.51Z | machinery | g1 | oil_temp | 40.3 | auto | 2021-07-15T00:00:00Z |
|
||||
| 2021-08-01T00:00:19.53Z | machinery | g1 | oil_temp | 40.6 | auto | 2021-07-15T00:00:00Z |
|
||||
| 2021-08-01T00:00:25.1Z | machinery | g1 | oil_temp | 40.72 | auto | 2021-07-15T00:00:00Z |
|
||||
| 2021-08-01T00:00:36.88Z | machinery | g1 | oil_temp | 40.8 | auto | 2021-07-15T00:00:00Z |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value | opType | maintained |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: | :----- | :------------------- |
|
||||
| 2021-08-01T00:00:00Z | machinery | g2 | oil_temp | 40.6 | manned | 2021-07-02T00:00:00Z |
|
||||
| 2021-08-01T00:00:27.93Z | machinery | g2 | oil_temp | 40.6 | manned | 2021-07-02T00:00:00Z |
|
||||
| 2021-08-01T00:00:54.96Z | machinery | g2 | oil_temp | 40.6 | manned | 2021-07-02T00:00:00Z |
|
||||
| 2021-08-01T00:01:17.27Z | machinery | g2 | oil_temp | 40.6 | manned | 2021-07-02T00:00:00Z |
|
||||
| 2021-08-01T00:01:41.84Z | machinery | g2 | oil_temp | 40.6 | manned | 2021-07-02T00:00:00Z |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value | opType | maintained |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: | :----- | :--------- |
|
||||
| 2021-08-01T00:00:00Z | machinery | g3 | oil_temp | 41.4 | | |
|
||||
| 2021-08-01T00:00:14.46Z | machinery | g3 | oil_temp | 41.3 | | |
|
||||
| 2021-08-01T00:00:25.29Z | machinery | g3 | oil_temp | 41.4 | | |
|
||||
| 2021-08-01T00:00:38.77Z | machinery | g3 | oil_temp | 41.4 | | |
|
||||
| 2021-08-01T00:00:51.2Z | machinery | g3 | oil_temp | 41.4 | | |
|
||||
|
||||
#### Things to note about the join output
|
||||
- Because the [right stream](#right-input) does not have a row with the `g3` station tag,
|
||||
rows from the [left stream](#left-input) with the `g3` stationID tag include
|
||||
_null_ values in columns that are populated from the right stream (`r`) in the
|
||||
`as` parameter.
|
||||
{{% /expand %}}
|
||||
{{< /expand-wrapper >}}
|
||||
|
||||
|
|
@ -0,0 +1,170 @@
|
|||
---
|
||||
title: Perform a right outer join
|
||||
description: >
|
||||
Use [`join.right()`](/flux/v0.x/stdlib/join/right/) to perform an right outer join of two streams of data.
|
||||
Right joins output a row for each row in the **right** data stream with data matching
|
||||
from the **left** data stream. If there is no matching data in the **left**
|
||||
data stream, non-group-key columns with values from the **left** data stream are _null_.
|
||||
menu:
|
||||
flux_0_x:
|
||||
name: Right outer join
|
||||
parent: Join data
|
||||
weight: 102
|
||||
related:
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
- /flux/v0.x/stdlib/join/
|
||||
- /flux/v0.x/stdlib/join/right/
|
||||
list_code_example: |
|
||||
```js
|
||||
import "join"
|
||||
|
||||
left = from(bucket: "example-bucket-1") |> //...
|
||||
right = from(bucket: "example-bucket-2") |> //...
|
||||
|
||||
join.right(
|
||||
left: left,
|
||||
right: right,
|
||||
on: (l, r) => l.column == r.column,
|
||||
as: (l, r) => ({r with name: l.name, location: l.location}),
|
||||
)
|
||||
```
|
||||
---
|
||||
|
||||
Use [`join.right()`](/flux/v0.x/stdlib/join/right/) to perform an right outer join of two streams of data.
|
||||
Right joins output a row for each row in the **right** data stream with data matching
|
||||
from the **left** data stream. If there is no matching data in the **left**
|
||||
data stream, non-group-key columns with values from the **left** data stream are _null_.
|
||||
|
||||
{{< svg svg="static/svgs/join-diagram.svg" class="right" >}}
|
||||
|
||||
{{< expand-wrapper >}}
|
||||
{{% expand "View table illustration of a right outer join" %}}
|
||||
{{< flex >}}
|
||||
{{% flex-content "third" %}}
|
||||
#### left
|
||||
| | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> |
|
||||
| r2 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> |
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content "third" %}}
|
||||
#### right
|
||||
| | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r3 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r4 | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content "third" %}}
|
||||
#### Right outer join result
|
||||
|
||||
| | | | | |
|
||||
| :-- | :----------------------------------- | :----------------------------------- | :----------------------------------- | :----------------------------------- |
|
||||
| r1 | <span style="color:#9b2aff">●</span> | <span style="color:#9b2aff">●</span> | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r3 | | | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
| r4 | | | <span style="color:#d30971">▲</span> | <span style="color:#d30971">▲</span> |
|
||||
|
||||
{{% /flex-content %}}
|
||||
{{< /flex >}}
|
||||
{{% /expand %}}
|
||||
{{< /expand-wrapper >}}
|
||||
|
||||
## Use join.right to join your data
|
||||
|
||||
1. Import the `join` package.
|
||||
2. Define the **left** and **right** data streams to join:
|
||||
|
||||
- Each stream must have one or more columns with common values.
|
||||
Column labels do not need to match, but column values do.
|
||||
- Each stream should have identical [group keys](/flux/v0.x/get-started/data-model/#group-key).
|
||||
|
||||
_For more information, see [join data requirements](/flux/v0.x/join-data/#data-requirements)._
|
||||
|
||||
3. Use `join.right()` to join the two streams together.
|
||||
Provide the following required parameters:
|
||||
|
||||
- `left`: Stream of data representing the left side of the join.
|
||||
- `right`: Stream of data representing the right side of the join.
|
||||
- `on`: [Join predicate](/flux/v0.x/join-data/#join-predicate-function-on).
|
||||
For example: `(l, r) => l.column == r.column`.
|
||||
- `as`: [Join output function](/flux/v0.x/join-data/#join-output-function-as)
|
||||
that returns a record with values from each input stream.
|
||||
For example: `(l, r) => ({r with column1: l.column1, column2: l.column2})`.
|
||||
|
||||
The following example uses a filtered selection from the
|
||||
[**machineProduction** sample data set](/flux/v0.x/stdlib/influxdata/influxdb/sample/data/#set)
|
||||
as the **left** data stream and an ad-hoc table created with [`array.from()`](/flux/v0.x/stdlib/array/from/)
|
||||
as the **right** data stream.
|
||||
|
||||
{{% note %}}
|
||||
#### Example data grouping
|
||||
|
||||
The example below ungroups the **left** stream to match the grouping of the **right** stream.
|
||||
{{% /note %}}
|
||||
|
||||
```js
|
||||
import "array"
|
||||
import "influxdata/influxdb/sample"
|
||||
import "join"
|
||||
|
||||
left =
|
||||
sample.data(set: "machineProduction")
|
||||
|> filter(fn: (r) => r.stationID == "g1" or r.stationID == "g2" or r.stationID == "g3")
|
||||
|> filter(fn: (r) => r._field == "oil_temp")
|
||||
|> last()
|
||||
|
||||
right =
|
||||
array.from(
|
||||
rows: [
|
||||
{station: "g1", opType: "auto", last_maintained: 2021-07-15T00:00:00Z},
|
||||
{station: "g2", opType: "manned", last_maintained: 2021-07-02T00:00:00Z},
|
||||
],
|
||||
)
|
||||
|
||||
join.right(
|
||||
left: left |> group(),
|
||||
right: right,
|
||||
on: (l, r) => l.stationID == r.station,
|
||||
as: (l, r) => ({r with last_reported_val: l._value, last_reported_time: l._time}),
|
||||
)
|
||||
```
|
||||
|
||||
{{< expand-wrapper >}}
|
||||
{{% expand "View example input and output" %}}
|
||||
|
||||
### Input
|
||||
|
||||
#### left {#left-input}
|
||||
|
||||
{{% note %}}
|
||||
_`_start` and `_stop` columns have been omitted._
|
||||
{{% /note %}}
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T23:59:46.17Z | machinery | g1 | oil_temp | 40.6 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T23:59:34.57Z | machinery | g2 | oil_temp | 41.34 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -----: |
|
||||
| 2021-08-01T23:59:41.96Z | machinery | g3 | oil_temp | 41.26 |
|
||||
|
||||
#### right {#right-input}
|
||||
|
||||
| station | opType | last_maintained |
|
||||
| :------ | :----- | -------------------: |
|
||||
| g1 | auto | 2021-07-15T00:00:00Z |
|
||||
| g2 | manned | 2021-07-02T00:00:00Z |
|
||||
|
||||
### Output {#example-output}
|
||||
|
||||
| station | opType | last_maintained | last_reported_time | last_reported_val |
|
||||
| :------ | :----- | :------------------- | :---------------------- | ----------------: |
|
||||
| g1 | auto | 2021-07-15T00:00:00Z | 2021-08-01T23:59:46.17Z | 40.6 |
|
||||
| g2 | manned | 2021-07-02T00:00:00Z | 2021-08-01T23:59:34.57Z | 41.34 |
|
||||
|
||||
{{% /expand %}}
|
||||
{{< /expand-wrapper >}}
|
||||
|
|
@ -0,0 +1,205 @@
|
|||
---
|
||||
title: Join on time
|
||||
description: >
|
||||
Use [`join.time()`](/flux/v0.x/stdlib/join/time/) to join two streams of data
|
||||
based on time values in the `_time` column.
|
||||
This type of join operation is common when joining two streams of
|
||||
[time series data](/influxdb/latest/reference/glossary/#time-series-data).
|
||||
menu:
|
||||
flux_0_x:
|
||||
parent: Join data
|
||||
weight: 104
|
||||
related:
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
- /flux/v0.x/stdlib/join/
|
||||
- /flux/v0.x/stdlib/join/time/
|
||||
list_code_example: |
|
||||
```js
|
||||
import "join"
|
||||
|
||||
left = from(bucket: "example-bucket-1") |> //...
|
||||
right = from(bucket: "example-bucket-2") |> //...
|
||||
|
||||
join.time(
|
||||
left: left,
|
||||
right: right,
|
||||
as: (l, r) => ({l with field1: l._value, field2: r._value_}),
|
||||
)
|
||||
```
|
||||
---
|
||||
|
||||
Use [`join.time()`](/flux/v0.x/stdlib/join/time/) to join two streams of data
|
||||
based on time values in the `_time` column.
|
||||
This type of join operation is common when joining two streams of
|
||||
[time series data](/influxdb/latest/reference/glossary/#time-series-data).
|
||||
|
||||
`join.time()` can use any of the available join methods.
|
||||
Which method you use depends on your desired behavior:
|
||||
|
||||
- **inner** _(Default)_:
|
||||
Drop any rows from both input streams that do not have a matching
|
||||
row in the other stream.
|
||||
|
||||
- **left**:
|
||||
Output a row for each row in the **left** data stream with data matching
|
||||
from the **right** data stream. If there is no matching data in the **right**
|
||||
data stream, non-group-key columns with values from the **right** data stream
|
||||
are _null_.
|
||||
|
||||
- **right**:
|
||||
Output a row for each row in the **right** data stream with data matching
|
||||
from the **left** data stream. If there is no matching data in the **left**
|
||||
data stream, non-group-key columns with values from the **left** data stream
|
||||
are _null_.
|
||||
|
||||
- **full**:
|
||||
Output a row for all rows in both the **left** and **right** input streams
|
||||
and join rows that match based on their `_time` value.
|
||||
|
||||
## Use join.time to join your data
|
||||
|
||||
1. Import the `join` package.
|
||||
2. Define the **left** and **right** data streams to join:
|
||||
|
||||
- Each stream must also have a `_time` column.
|
||||
- Each stream must have one or more columns with common values.
|
||||
Column labels do not need to match, but column values do.
|
||||
- Each stream should have identical [group keys](/flux/v0.x/get-started/data-model/#group-key).
|
||||
|
||||
_For more information, see [join data requirements](/flux/v0.x/join-data/#data-requirements)._
|
||||
|
||||
3. Use `join.time()` to join the two streams together.
|
||||
Provide the following parameters:
|
||||
|
||||
- `left`: ({{< req >}}) Stream of data representing the left side of the join.
|
||||
- `right`: ({{< req >}}) Stream of data representing the right side of the join.
|
||||
- `as`: ({{< req >}}) [Join output function](/flux/v0.x/join-data/#join-output-function-as)
|
||||
that returns a record with values from each input stream.
|
||||
For example: `(l, r) => ({r with column1: l.column1, column2: l.column2})`.
|
||||
- `method`: Join method to use. Default is `inner`.
|
||||
|
||||
The following example uses a filtered selections from the
|
||||
[**machineProduction** sample data set](/flux/v0.x/stdlib/influxdata/influxdb/sample/data/#set)
|
||||
as the **left** and **right** data streams.
|
||||
|
||||
{{% note %}}
|
||||
#### Example data grouping
|
||||
|
||||
The example below regroups both the left and right streams to remove the
|
||||
`_field` column from the group key.
|
||||
Because `join.time()` only compares tables with matching
|
||||
[group key instances](/flux/v0.x/get-started/data-model/#example-group-key-instances),
|
||||
to join streams with different `_field` column values, `_field` cannot be part
|
||||
of the group key.
|
||||
{{% /note %}}
|
||||
|
||||
```js
|
||||
import "influxdata/influxdb/sample"
|
||||
import "join"
|
||||
|
||||
left =
|
||||
sample.data(set: "machineProduction")
|
||||
|> filter(fn: (r) => r.stationID == "g1" or r.stationID == "g2" or r.stationID == "g3")
|
||||
|> filter(fn: (r) => r._field == "pressure")
|
||||
|> limit(n: 5)
|
||||
|> group(columns: ["_time", "_value", "_field"], mode: "except")
|
||||
|
||||
right =
|
||||
sample.data(set: "machineProduction")
|
||||
|> filter(fn: (r) => r.stationID == "g1" or r.stationID == "g2" or r.stationID == "g3")
|
||||
|> filter(fn: (r) => r._field == "pressure_target")
|
||||
|> limit(n: 5)
|
||||
|> group(columns: ["_time", "_value", "_field"], mode: "except")
|
||||
|
||||
join.time(method: "left", left: left, right: right, as: (l, r) => ({l with target: r._value}))
|
||||
```
|
||||
|
||||
{{< expand-wrapper >}}
|
||||
{{% expand "View example input and output" %}}
|
||||
|
||||
### Input
|
||||
|
||||
{{% note %}}
|
||||
_`_start` and `_stop` columns have been omitted from input examples._
|
||||
{{% /note %}}
|
||||
|
||||
#### left {#left-input}
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -------: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g1 | pressure | 110.2617 |
|
||||
| 2021-08-01T00:00:11.51Z | machinery | g1 | pressure | 110.3506 |
|
||||
| 2021-08-01T00:00:19.53Z | machinery | g1 | pressure | 110.1836 |
|
||||
| 2021-08-01T00:00:25.1Z | machinery | g1 | pressure | 109.6387 |
|
||||
| 2021-08-01T00:00:36.88Z | machinery | g1 | pressure | 110.5021 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -------: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g2 | pressure | 105.392 |
|
||||
| 2021-08-01T00:00:27.93Z | machinery | g2 | pressure | 105.3786 |
|
||||
| 2021-08-01T00:00:54.96Z | machinery | g2 | pressure | 105.4801 |
|
||||
| 2021-08-01T00:01:17.27Z | machinery | g2 | pressure | 105.5656 |
|
||||
| 2021-08-01T00:01:41.84Z | machinery | g2 | pressure | 105.5495 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -------: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g3 | pressure | 110.5309 |
|
||||
| 2021-08-01T00:00:14.46Z | machinery | g3 | pressure | 110.3746 |
|
||||
| 2021-08-01T00:00:25.29Z | machinery | g3 | pressure | 110.3719 |
|
||||
| 2021-08-01T00:00:38.77Z | machinery | g3 | pressure | 110.5362 |
|
||||
| 2021-08-01T00:00:51.2Z | machinery | g3 | pressure | 110.4514 |
|
||||
|
||||
#### right {#right-input}
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :-------------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g1 | pressure_target | 110 |
|
||||
| 2021-08-01T00:00:11.51Z | machinery | g1 | pressure_target | 110 |
|
||||
| 2021-08-01T00:00:19.53Z | machinery | g1 | pressure_target | 110 |
|
||||
| 2021-08-01T00:00:25.1Z | machinery | g1 | pressure_target | 110 |
|
||||
| 2021-08-01T00:00:36.88Z | machinery | g1 | pressure_target | 110 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :-------------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g2 | pressure_target | 105 |
|
||||
| 2021-08-01T00:00:27.93Z | machinery | g2 | pressure_target | 105 |
|
||||
| 2021-08-01T00:00:54.96Z | machinery | g2 | pressure_target | 105 |
|
||||
| 2021-08-01T00:01:17.27Z | machinery | g2 | pressure_target | 105 |
|
||||
| 2021-08-01T00:01:41.84Z | machinery | g2 | pressure_target | 105 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value |
|
||||
| :---------------------- | :----------- | :-------- | :-------------- | -----: |
|
||||
| 2021-08-01T00:00:00Z | machinery | g3 | pressure_target | 110 |
|
||||
| 2021-08-01T00:00:14.46Z | machinery | g3 | pressure_target | 110 |
|
||||
| 2021-08-01T00:00:25.29Z | machinery | g3 | pressure_target | 110 |
|
||||
| 2021-08-01T00:00:38.77Z | machinery | g3 | pressure_target | 110 |
|
||||
| 2021-08-01T00:00:51.2Z | machinery | g3 | pressure_target | 110 |
|
||||
|
||||
### Output {#example-output}
|
||||
|
||||
| _time | _measurement | stationID | _field | _value | target |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -------: | :----- |
|
||||
| 2021-08-01T00:00:00Z | machinery | g1 | pressure | 110.2617 | 110 |
|
||||
| 2021-08-01T00:00:11.51Z | machinery | g1 | pressure | 110.3506 | 110 |
|
||||
| 2021-08-01T00:00:19.53Z | machinery | g1 | pressure | 110.1836 | 110 |
|
||||
| 2021-08-01T00:00:25.1Z | machinery | g1 | pressure | 109.6387 | 110 |
|
||||
| 2021-08-01T00:00:36.88Z | machinery | g1 | pressure | 110.5021 | 110 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value | target |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -------: | :----- |
|
||||
| 2021-08-01T00:00:00Z | machinery | g2 | pressure | 105.392 | 105 |
|
||||
| 2021-08-01T00:00:27.93Z | machinery | g2 | pressure | 105.3786 | 105 |
|
||||
| 2021-08-01T00:00:54.96Z | machinery | g2 | pressure | 105.4801 | 105 |
|
||||
| 2021-08-01T00:01:17.27Z | machinery | g2 | pressure | 105.5656 | 105 |
|
||||
| 2021-08-01T00:01:41.84Z | machinery | g2 | pressure | 105.5495 | 105 |
|
||||
|
||||
| _time | _measurement | stationID | _field | _value | target |
|
||||
| :---------------------- | :----------- | :-------- | :------- | -------: | :----- |
|
||||
| 2021-08-01T00:00:00Z | machinery | g3 | pressure | 110.5309 | 110 |
|
||||
| 2021-08-01T00:00:14.46Z | machinery | g3 | pressure | 110.3746 | 110 |
|
||||
| 2021-08-01T00:00:25.29Z | machinery | g3 | pressure | 110.3719 | 110 |
|
||||
| 2021-08-01T00:00:38.77Z | machinery | g3 | pressure | 110.5362 | 110 |
|
||||
| 2021-08-01T00:00:51.2Z | machinery | g3 | pressure | 110.4514 | 110 |
|
||||
|
||||
{{% /expand %}}
|
||||
{{< /expand-wrapper >}}
|
||||
|
|
@ -0,0 +1,186 @@
|
|||
---
|
||||
title: Troubleshoot join operations
|
||||
description: >
|
||||
Learn how to troubleshoot common behaviors and errors that may occur when using
|
||||
the [`join` package](/flux/v0.x/stdlib/join).
|
||||
menu:
|
||||
flux_0_x:
|
||||
name: Troubleshoot joins
|
||||
parent: Join data
|
||||
weight: 105
|
||||
---
|
||||
|
||||
Learn how to troubleshoot common behaviors and errors that may occur when using
|
||||
the [`join` package](/flux/v0.x/stdlib/join).
|
||||
|
||||
{{% note %}}
|
||||
#### Submit issues for unexplained behaviors or errors
|
||||
|
||||
This is a "living" document that may be updated with common issues
|
||||
that users may run into when using the [`join` package](/flux/v0.x/stdlib/join).
|
||||
If you have questions about a behavior or error that is not documented here,
|
||||
please submit an issue to either the InfluxData Documentation or Flux GitHub repositories:
|
||||
|
||||
- [Submit a documentation issue](https://github.com/influxdata/docs-v2/issues/new/choose)
|
||||
- [Submit a Flux issue](https://github.com/influxdata/flux/issues/new/choose)
|
||||
{{% /note %}}
|
||||
|
||||
- [Troubleshoot join behaviors](#troubleshoot-join-behaviors)
|
||||
- [Troubleshoot join error messages](#troubleshoot-join-error-messages)
|
||||
|
||||
## Troubleshoot join behaviors
|
||||
|
||||
### Columns explicitly mapped in the join are null
|
||||
|
||||
In some cases, your join output may include _null_ values in
|
||||
columns where you expect non-null values. This may be caused by one of the following issues:
|
||||
|
||||
---
|
||||
|
||||
{{< flex class="troubleshoot-row" >}}
|
||||
{{% flex-content %}}
|
||||
#### Cause {#cause-b1}
|
||||
|
||||
**The group keys of each input stream aren't the same.**
|
||||
Functions in the `join` package use group keys to quickly identify what tables
|
||||
should be compared.
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content %}}
|
||||
#### Solution {#solution-b1}
|
||||
|
||||
Use [`group()`](/flux/v0.x/stdlib/universe/group/) to regroup
|
||||
your two input streams so their group keys match before attempting to join
|
||||
them together.
|
||||
{{% /flex-content %}}
|
||||
{{< /flex >}}
|
||||
|
||||
---
|
||||
|
||||
{{< flex >}}
|
||||
{{% flex-content %}}
|
||||
#### Cause {#cause-b2}
|
||||
|
||||
**There are no matching _group key instances_ in your data streams**.
|
||||
Functions in the `join` package only compare tables with matching
|
||||
[group key instances](/flux/v0.x/get-started/data-model/#example-group-key-instances).
|
||||
Input streams may have matching group keys, but there are no matching group
|
||||
key instances in your stream.
|
||||
|
||||
This may happen when joining two separate fields
|
||||
queried from InfluxDB. By default, InfluxDB returns data with `_field` as part
|
||||
of the group key. If each stream contains a different field, tables in the two
|
||||
streams won't be compared because they won't have any matching _group key instances_.
|
||||
{{% /flex-content %}}
|
||||
|
||||
{{% flex-content %}}
|
||||
#### Solution {#solution-b2}
|
||||
|
||||
Use [`group()`](/flux/v0.x/stdlib/universe/group/) to remove
|
||||
any columns from the group keys of each input stream that would prevent
|
||||
group key instances from matching.
|
||||
{{% /flex-content %}}
|
||||
{{< /flex >}}
|
||||
|
||||
---
|
||||
|
||||
## Troubleshoot join error messages
|
||||
|
||||
- [table is missing column \'\<column\>\'](#table-is-missing-column-column)
|
||||
- [table is missing label \<label\>](#table-is-missing-label-label)
|
||||
- [record is missing label \<label\>](#record-is-missing-label-label)
|
||||
|
||||
### table is missing column `'<column>'`
|
||||
|
||||
##### Error message
|
||||
```js
|
||||
cannot set join columns in left table stream: table is missing column '<column>'
|
||||
```
|
||||
|
||||
{{< flex >}}
|
||||
{{% flex-content %}}
|
||||
#### Cause {#cause-e1}
|
||||
|
||||
**Your `on` join predicate uses a column that doesn't exist**.
|
||||
In the `on` predicate function, you're trying to compare a column
|
||||
that doesn't exist in one of your input streams.
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content %}}
|
||||
#### Solution {#solution-e1}
|
||||
|
||||
Ensure the columns that you're comparing in the `on` predicate
|
||||
function exist in the input streams.
|
||||
If necessary, update column names in the predicate function.
|
||||
{{% /flex-content %}}
|
||||
{{< /flex >}}
|
||||
|
||||
---
|
||||
|
||||
### table is missing label `<label>`
|
||||
|
||||
##### Error message
|
||||
```js
|
||||
table is missing label <label>
|
||||
```
|
||||
|
||||
{{< flex >}}
|
||||
{{% flex-content %}}
|
||||
#### Cause {#cause-e2}
|
||||
|
||||
**Your `on` join predicate uses a column that doesn't exist**.
|
||||
In the `on` predicate function for an outer join, you're trying to use a value
|
||||
from a column that doesn't exist in the "primary" input stream
|
||||
(`left` for `join.left()` and `right` for `join.right()`).
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content %}}
|
||||
#### Solution {#solution-e2}
|
||||
|
||||
Ensure the columns that you're comparing in the `on` predicate
|
||||
function actually exist in the input streams.
|
||||
If necessary, update column names in the predicate function.
|
||||
{{% /flex-content %}}
|
||||
{{< /flex >}}
|
||||
|
||||
---
|
||||
|
||||
### record is missing label `<label>`
|
||||
|
||||
##### Error message
|
||||
```js
|
||||
record is missing label <label> (argument <left or right>)
|
||||
```
|
||||
|
||||
{{< flex >}}
|
||||
{{% flex-content %}}
|
||||
#### Cause {#cause-e3}
|
||||
|
||||
**Your `on` join predicate uses a column that doesn't exist**.
|
||||
In the `on` predicate function, you're trying to compare a column
|
||||
that doesn't exist in one of your input streams.
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content %}}
|
||||
#### Solution {#solution-e3}
|
||||
|
||||
Ensure the columns that you're comparing in the `on` predicate
|
||||
function actually exist in the input streams.
|
||||
If necessary, update column names in the predicate function.
|
||||
{{% /flex-content %}}
|
||||
{{< /flex >}}
|
||||
|
||||
---
|
||||
|
||||
{{< flex >}}
|
||||
{{% flex-content %}}
|
||||
#### Cause {#cause-e4}
|
||||
|
||||
**Your `as` output schema function uses a column that doesn't exist**.
|
||||
If using an **outer join**, the `as` is trying to use a value
|
||||
from a column that doesn't exist in the "primary" input stream
|
||||
(`left` for `join.left()` and `right` for `join.right()`).
|
||||
{{% /flex-content %}}
|
||||
{{% flex-content %}}
|
||||
#### Solution {#solution-e4}
|
||||
|
||||
Ensure the columns that you're using in the `as` output function to assign
|
||||
values to the output actually exist in the input streams.
|
||||
{{% /flex-content %}}
|
||||
{{< /flex >}}
|
||||
|
|
@ -5,19 +5,19 @@
|
|||
# build/deploy process.
|
||||
|
||||
flux:
|
||||
latest: 0.175.0
|
||||
latest: 0.184.1
|
||||
cloud:
|
||||
current: 0.174.1
|
||||
current: 0.181.0
|
||||
oss:
|
||||
'2.4': 0.179.0
|
||||
'2.3': 0.171.0
|
||||
'2.2': 0.161.0
|
||||
'2.2': 0.162.0
|
||||
'2.1': 0.139.0
|
||||
'2.0': 0.131.0
|
||||
'1.8': 0.65.1
|
||||
'1.7': 0.50.2
|
||||
nightly: 0.174.1
|
||||
nightly: 0.181.0
|
||||
enterprise:
|
||||
'1.10': 0.170.0
|
||||
'1.9': 0.161.0
|
||||
'1.8': 0.65.1
|
||||
'1.7': 0.50.2
|
||||
|
|
|
|||
|
|
@ -1535,6 +1535,41 @@
|
|||
- /influxdb/v2.0/reference/flux/stdlib/interpolate/linear/
|
||||
- /influxdb/cloud/reference/flux/stdlib/interpolate/linear/
|
||||
|
||||
/flux/v0.x/stdlib/join/_index.md: |
|
||||
related:
|
||||
- /flux/v0.x/join-data/
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
|
||||
/flux/v0.x/stdlib/join/full.md: |
|
||||
related:
|
||||
- /flux/v0.x/join-data/full-outer/
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
|
||||
/flux/v0.x/stdlib/join/inner.md: |
|
||||
related:
|
||||
- /flux/v0.x/join-data/inner/
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
|
||||
/flux/v0.x/stdlib/join/left.md: |
|
||||
related:
|
||||
- /flux/v0.x/join-data/left-outer/
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
|
||||
/flux/v0.x/stdlib/join/right.md: |
|
||||
related:
|
||||
- /flux/v0.x/join-data/right-outer/
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
|
||||
/flux/v0.x/stdlib/join/tables.md: |
|
||||
related:
|
||||
- /flux/v0.x/join-data/
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
|
||||
/flux/v0.x/stdlib/join/time.md: |
|
||||
related:
|
||||
- /flux/v0.x/join-data/time/
|
||||
- /flux/v0.x/join-data/troubleshoot-joins/
|
||||
|
||||
/flux/v0.x/stdlib/json/_index.md: |
|
||||
aliases:
|
||||
- /influxdb/v2.0/reference/flux/functions/json/
|
||||
|
|
|
|||
|
|
@ -10,6 +10,14 @@ const path = require('path')
|
|||
// GitHub token to access files in the private InfluxDB Enterprise repo
|
||||
const githubToken = process.env.GITHUB_TOKEN
|
||||
|
||||
if (typeof githubToken === 'undefined') {
|
||||
console.error(`
|
||||
A GitHub token is required for this operation. Please set a GITHUB_TOKEN environment variable.
|
||||
Use the GitHub token stored in the Docs Team vault in 1Password.
|
||||
`);
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Get the latest version of Flux
|
||||
async function getLatestFlux() {
|
||||
const { request } = await axios
|
||||
|
|
|
|||
|
|
@ -3,6 +3,7 @@
|
|||
{{ $hlevel := .Get "hlevel" | default "h3"}}
|
||||
{{ $readMore := .Get "readmore" | default false }}
|
||||
{{ $hr := .Get "hr" | default false }}
|
||||
{{ $doNotList := .Get "filterOut" | default "" }}
|
||||
|
||||
{{ if eq $show "all" }}
|
||||
{{ .Scratch.Set "pages" (union .Page.Pages .Page.Sections) }}
|
||||
|
|
@ -12,7 +13,7 @@
|
|||
{{ .Scratch.Set "pages" .Page.RegularPages }}
|
||||
{{ end }}
|
||||
|
||||
{{ $pages := .Scratch.Get "pages" }}
|
||||
{{ $pages := where (.Scratch.Get "pages") "Title" "not in" (split $doNotList ", ") }}
|
||||
|
||||
{{ if eq $type "articles" }}
|
||||
<div class="children-links">
|
||||
|
|
|
|||
|
|
@ -1,2 +1,14 @@
|
|||
{{ $svg := .Get 0 }}
|
||||
{{ $svg | readFile | safeHTML }}
|
||||
{{ $implicitSvg := .Get 0 }}
|
||||
{{ $svg := .Get "svg" | default $implicitSvg }}
|
||||
{{ $implicitClass := .Get 1 | default "" }}
|
||||
{{ $class := .Get "class" | default $implicitClass }}
|
||||
{{ $svgCode := $svg | readFile }}
|
||||
|
||||
{{ $scratch := newScratch }}
|
||||
{{ $scratch.Set "svgOutput" $svgCode }}
|
||||
|
||||
{{ if ne $class "" }}
|
||||
{{ $scratch.Set "svgOutput" ($scratch.Get "svgOutput" | replaceRE `<svg ` (print "<svg class='" $class "'")) }}
|
||||
{{ end }}
|
||||
|
||||
{{ $scratch.Get "svgOutput" | safeHTML }}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,10 @@
|
|||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<svg id="join-diagram" version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
|
||||
viewBox="0 0 98 64" xml:space="preserve">
|
||||
<path id="left" d="M37.9,31.8c0-9.1,4.3-17.1,11-22.2c-4.7-3.6-10.6-5.8-17-5.8c-15.5,0-28,12.5-28,28c0,15.5,12.5,28,28,28
|
||||
c6.4,0,12.3-2.1,17-5.8C42.2,48.9,37.9,40.8,37.9,31.8z"/>
|
||||
<path id="center" d="M59.9,31.8c0-9.1-4.3-17.1-11-22.2c-6.7,5.1-11,13.2-11,22.2c0,9.1,4.3,17.1,11,22.2
|
||||
C55.5,48.9,59.9,40.8,59.9,31.8z"/>
|
||||
<path id="right" d="M65.9,3.8c-6.4,0-12.3,2.1-17,5.8c6.7,5.1,11,13.2,11,22.2c0,9.1-4.3,17.1-11,22.2c4.7,3.6,10.6,5.8,17,5.8
|
||||
c15.5,0,28-12.5,28-28C93.9,16.3,81.3,3.8,65.9,3.8z"/>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 721 B |
Loading…
Reference in New Issue