Neo4j Graph Database Fundamentals · レッスン

GDSパイプラインと機械学習

GDS内でグラフデータサイエンスのパイプラインを構築・管理し、機械学習のワークフローと統合する方法を学びます。

「GDSパイプラインと機械学習」はCoddyKit上の無料Neo4j Graph Database Fundamentalsレッスンです。これはレッスン3/4です。下記で完全なレッスンを無料で読むことができます。その後、ブラウザ内の組み込みコードエディタと24時間対応のAIチューターでハンズオン演習できます。これはNeo4j Graph Database Fundamentals学習パスの一部であり、ウェブとCoddyKitアプリ全体で進捗が同期されます。 Neo4j Graph Database Fundamentalsコースには全4レッスンが含まれています。

このレッスンの一部はまだ翻訳されておらず、英語で表示されています。

What are GDS Pipelines?

Welcome to GDS Pipelines! In the Neo4j Graph Data Science (GDS) library, a pipeline is a structured workflow for common graph data science tasks.

Think of it as a blueprint that defines a sequence of steps, from feature engineering using graph algorithms to training and deploying machine learning models.

Why Use GDS Pipelines?

GDS Pipelines offer several key benefits:

Reproducibility: Define your entire workflow once and reuse it.
Automation: Streamline complex tasks involving multiple graph algorithms and ML steps.
Operationalization: Easily deploy graph-based machine learning models for continuous prediction.

They help bridge the gap between experimentation and production.

Creating a Prediction Pipeline

One common pipeline type is the Node Property Prediction Pipeline. This helps predict a specific property on nodes based on other node features and graph structure.

Let's create an empty pipeline named 'myChurnPrediction':

CALL gds.pipeline.nodePropertyPrediction.create('myChurnPrediction')
YIELD pipeline
RETURN pipeline.name AS name, pipeline.type AS type

Projecting Your Graph Data

Before using a pipeline, you need to project your graph into GDS memory. This makes nodes and relationships accessible for algorithms and features.

Here, we project a simple 'User' graph with 'KNOWS' relationships:

CALL gds.graph.project(
    'mySocialGraph',
    'User',
    { KNOWS: { orientation: 'UNDIRECTED' } }
)
YIELD graphName, nodeCount, relationshipCount
RETURN graphName, nodeCount, relationshipCount

Adding Node Property Features

Pipelines allow you to specify which existing node properties should be used as features for your machine learning model. These are direct attributes of your nodes.

Let's add 'age' and 'income' properties as features to our pipeline:

CALL gds.pipeline.nodePropertyPrediction.addNodePropertySteps('myChurnPrediction', {
    nodeProperties: ['age', 'income']
})
YIELD pipeline
RETURN pipeline.name, pipeline.nodePropertySteps

Integrating Graph Algorithm Features

The real power of GDS pipelines is integrating graph algorithm results as features. These capture structural insights that simple node properties can't.

We can add PageRank scores as a feature to our pipeline:

CALL gds.pipeline.nodePropertyPrediction.addPageRank('myChurnPrediction', {
    maxIterations: 10,
    dampingFactor: 0.85,
    mutateProperty: 'pageRankScore' // This becomes a feature
})
YIELD pipeline
RETURN pipeline.name, pipeline.pageRankSteps

Configuring the Machine Learning Model

After defining your features, you specify the machine learning model that will perform the prediction. GDS supports various models like Logistic Regression, Random Forest, and GNNs.

Let's add a Logistic Regression model to predict 'isChurned':

CALL gds.pipeline.nodePropertyPrediction.addLogisticRegression('myChurnPrediction', {
    targetProperty: 'isChurned', // The node property we want to predict
    maxIterations: 100,
    penalty: 'l2'
})
YIELD pipeline
RETURN pipeline.name, pipeline.logisticRegressionSteps

Training Your GDS Pipeline

With features and a model defined, you can now train the pipeline. This executes all feature generation steps, then trains the specified ML model on the generated features.

We'll train our pipeline on 'mySocialGraph' and name the resulting model 'churnPredictionModel':

CALL gds.pipeline.nodePropertyPrediction.train('myChurnPrediction', {
    modelName: 'churnPredictionModel',
    graphName: 'mySocialGraph',
    nodeLabels: ['User'],
    randomSeed: 42
})
YIELD modelInfo
RETURN modelInfo.modelName AS modelName, modelInfo.trainingMetrics.f1Score.weighted AS f1Score

Making Predictions with the Model

Once trained, your model (which is part of the pipeline) can be used to generate predictions on your graph data. You can either stream results or mutate the graph with new properties.

Let's stream predictions for our 'churnPredictionModel':

CALL gds.pipeline.nodePropertyPrediction.predict.stream('churnPredictionModel', {
    graphName: 'mySocialGraph',
    nodeLabels: ['User'],
    topN: 1 // Get the top predicted class
})
YIELD nodeId, predictedProperty, probability
RETURN gds.util.asNode(nodeId).name AS user, predictedProperty, probability
LIMIT 5

Managing Your Pipelines

You can list all active pipelines and their configurations using gds.pipeline.list(). When a pipeline is no longer needed, you can remove it with gds.pipeline.drop().

Let's see the pipelines we currently have:

CALL gds.pipeline.list()
YIELD name, type, creationTime
RETURN name, type, creationTime

GDS Pipeline Components

A GDS pipeline combines various steps to create a complete data science workflow. Which of the following are valid components or steps you can add to a GDS Node Property Prediction Pipeline?

Recap: Pipelines for ML

Great job! You've learned how GDS Pipelines provide a structured and reproducible way to integrate graph algorithms with machine learning workflows.

Pipelines define a sequence of steps.
They combine feature engineering (from existing properties and graph algorithms) with ML model training.
They enable efficient prediction and operationalization of graph-based insights.

Keep exploring GDS to unlock more advanced graph analytics!

よくある質問

「GDSパイプラインと機械学習」レッスンは無料ですか？

はい。「GDSパイプラインと機械学習」の完全なテキストはこのウェブで無料で読めます。インタラクティブに演習し（組み込みコードエディタと24時間対応のAIチューター）、Neo4j Graph Database Fundamentalsコースの残りをアンロックするには、CoddyKit PROにアップグレードしてください。 Neo4j Graph Database Fundamentalsコースには全4レッスンが含まれています。

「GDSパイプラインと機械学習」で何を学びますか？

GDS内でグラフデータサイエンスのパイプラインを構築・管理し、機械学習のワークフローと統合する方法を学びます。ブラウザで直接実行するハンズオンコードでNeo4j Graph Database Fundamentalsを演習し、24時間対応のAIチューターがレッスンを進める中での質問に答えます。

Neo4j Graph Database Fundamentalsを始めるのに経験は必要ですか？

事前経験は必要ありません。CoddyKitのNeo4j Graph Database Fundamentalsは初級者から上級者向けに構成されているため、ここから始めるか最初から始めて、自分のペースで進むことができます。これはレッスン3/4です。

「GDSパイプラインと機械学習」レッスンにはどのくらい時間がかかりますか？

ほとんどのCoddyKitレッスンは約5～10分かかります。各レッスンはコンパクトでインタラクティブなので、着実に進歩し、ウェブとアプリ全体で正確に前回の場所から再開できます。

このNeo4j Graph Database Fundamentalsレッスンでコードを書いて実行できますか？

はい。すべてのNeo4j Graph Database Fundamentalsレッスンに組み込みコードエディタが含まれているため、ブラウザでリアルコードを書いて実行し、即座のAIフィードバックを取得できます。ローカル設定は不要です。

このコースのすべてのレッスン

← Neo4j Graph Database Fundamentalsに戻る