Document node regression pipeline create proc

Co-authored-by: Mats Rydberg <mats@neotechnology.com>

Author: FlorentinD

doc-test/src/test/java/org/neo4j/gds/doc/NodeRegressionPipelineDocTest.java

@@ -0,0 +1,46 @@
+/*
+ * Copyright (c) "Neo4j"
+ * Neo4j Sweden AB [http://neo4j.com]
+ *
+ * This file is part of Neo4j.
+ *
+ * Neo4j is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+package org.neo4j.gds.doc;
+
+import org.junit.jupiter.api.AfterAll;
+import org.neo4j.gds.ml.pipeline.PipelineCatalog;
+import org.neo4j.gds.ml.pipeline.node.regression.configure.NodeRegressionPipelineCreateProc;
+
+import java.util.List;
+
+class NodeRegressionPipelineDocTest extends DocTestBase {
+
+    @AfterAll
+    static void tearDown() {
+        PipelineCatalog.removeAll();
+    }
+
+    @Override
+    protected List<Class<?>> procedures() {
+        return List.of(
+            NodeRegressionPipelineCreateProc.class
+        );
+    }
+
+    @Override
+    protected String adocFile() {
+        return "machine-learning/node-property-prediction/noderegression-pipeline/noderegression.adoc";
+    }
+}

doc-test/src/test/java/org/neo4j/gds/doc/syntax/NodeRegressionPipelineSyntaxTest.java

@@ -0,0 +1,37 @@
+/*
+ * Copyright (c) "Neo4j"
+ * Neo4j Sweden AB [http://neo4j.com]
+ *
+ * This file is part of Neo4j.
+ *
+ * Neo4j is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+package org.neo4j.gds.doc.syntax;
+
+import java.util.List;
+
+class NodeRegressionPipelineSyntaxTest extends SyntaxTestBase {
+
+    @Override
+    protected Iterable<SyntaxModeMeta> syntaxModes() {
+        return List.of(
+            SyntaxModeMeta.of(SyntaxMode.PIPELINE_CREATE)
+        );
+    }
+
+    @Override
+    protected String adocFile() {
+        return "machine-learning/node-property-prediction/noderegression-pipeline/noderegression.adoc";
+    }
+}

doc/antora/content-nav.adoc

@@ -105,6 +105,7 @@
 **** xref:machine-learning/node-property-prediction/nodeclassification-pipelines/training/index.adoc[]
 **** xref:machine-learning/node-property-prediction/nodeclassification-pipelines/predict/index.adoc[]
 *** xref:machine-learning/node-property-prediction/noderegression-pipelines/index.adoc[]
+**** xref:machine-learning/node-property-prediction/noderegression-pipelines/config/index.adoc[]
 ** xref:machine-learning/linkprediction-pipelines/index.adoc[]
 *** xref:machine-learning/linkprediction-pipelines/config/index.adoc[]
 *** xref:machine-learning/linkprediction-pipelines/training/index.adoc[]

doc/asciidoc/machine-learning/node-property-prediction/noderegression-pipeline/config.adoc

@@ -0,0 +1,71 @@
+[[noderegression-pipelines-config]]
+= Configuring the pipeline
+:max-trials: 10
+
+This page explains how to create and configure a node classification pipeline.
+It consists of the following sections:
+
+* <<nodregression-creating-a-pipeline, Creating the pipeline>>
+
+
+[[nodregression-creating-a-pipeline]]
+== Creating a pipeline
+
+The first step of building a new pipeline is to create one using `gds.alpha.pipeline.nodeRegression.create`.
+This stores a trainable pipeline object in the pipeline catalog of type `Node regression training pipeline`.
+This represents a configurable pipeline that can later be invoked for training, which in turn creates a regression model.
+The latter is also a model which is stored in the catalog with type `NodeRegression`.
+
+
+=== Syntax
+
+[.pipeline-create-syntax]
+--
+.Create pipeline syntax
+[source, cypher, role=noplay]
+----
+CALL gds.alpha.pipeline.nodeRegression.create(
+  pipelineName: String
+)
+YIELD
+  name: String,
+  nodePropertySteps: List of Map,
+  featureProperties: List of String,
+  splitConfig: Map,
+  autoTuningConfig: Map,
+  parameterSpace: List of Map
+----
+
+.Parameters
+[opts="header",cols="1,1,4"]
+|===
+| Name            | Type    | Description
+| pipelineName    | String  | The name of the created pipeline.
+|===
+
+include::../pipelineInfoResult.adoc[]
+--
+
+
+=== Example
+
+[role=query-example,group=nr]
+--
+.The following will create a pipeline:
+[source, cypher, role=noplay]
+----
+CALL gds.alpha.pipeline.nodeRegression.create('pipe')
+----
+
+.Results
+[opts="header",cols="1,1,1,1,1,1"]
+|===
+| name     | nodePropertySteps | featureProperties | splitConfig | autoTuningConfig | parameterSpace
+| "pipe"   | []                | []
+| {testFraction=0.3, validationFolds=3}
+| {maxTrials={max-trials}}
+| {RandomForest=[], LinearRegression=[]}
+|===
+--
+
+This shows that the newly created pipeline does not contain any steps yet, and has defaults for the split and train parameters.

doc/asciidoc/machine-learning/node-property-prediction/noderegression-pipeline/noderegression.adoc

@@ -1,4 +1,28 @@
 [[noderegression-pipelines]]
 = Node regression pipelines
+:max-trials: 10
 
-// TODO add config content
+[abstract]
+--
+This section describes Node regression pipelines in the Neo4j Graph Data Science library.
+--
+
+
+Node Regression is a common machine learning task applied to graphs: training models to predict node property values.
+Concretely, Node Regression models are used to predict the value of node property based on other node properties.
+During training, the property to predict is referred to as the target property.
+
+In GDS, we have Node Regression pipelines which offer an end-to-end workflow, from feature extraction to predicting node property values.
+The training pipelines reside in the <<pipeline-catalog-ops,pipeline catalog>>.
+When a training pipeline is <<nodeclassification-pipelines-train,executed>>, a regression model is created and stored in the <<model-catalog-ops,model catalog>>.
+
+A training pipeline is a sequence of two phases:
+[upperroman]
+. The graph is augmented with new node properties in a series of steps.
+. The augmented graph is used for training a node regression model.
+
+This segment is divided into the following pages:
+
+* <<noderegression-pipelines-config, Configuring the pipeline>>
+
+include::config.adoc[leveloffset =+ 1]

doc/docbook/content-map.xml

@@ -305,6 +305,8 @@
                 </d:tocentry>
             </d:tocentry>
             <d:tocentry linkend="noderegression-pipelines"><?dbhtml filename="machine-learning/node-property-prediction/noderegression-pipelines/index.html"?>
+                <d:tocentry linkend="noderegression-pipelines-config"><?dbhtml filename="machine-learning/node-property-prediction/noderegression-pipelines/config/index.html"?>
+                </d:tocentry>
             </d:tocentry>
         </d:tocentry>