Customer Segmentation Pipeline
A scalable ML pipeline for customer segmentation using K-Means clustering. Includes data loading, feature scaling, clustering, and visualization — ready to run on sample data.
Density-Based Clustering Pipeline
An advanced ML pipeline using DBSCAN for density-based clustering. Handles missing values with imputation, scales features, and discovers clusters of arbitrary shape without specifying the number of clusters.
What Are Pipeline Blueprints?
Pipeline Blueprints are pre-configured machine learning workflows designed for common data science tasks. Each blueprint connects multiple processing stages — data loading, preprocessing, model training, and evaluation — into a visual, drag-and-drop pipeline that runs end-to-end on sample data.
Unlike static tutorials, blueprints are interactive: click "Try this Blueprint" on any page to load it directly into the pipeline editor, run it, inspect intermediate results at every node, and modify parameters in real time.
Who Are Blueprints For?
- Beginners who want to see how a complete ML workflow fits together before writing any code.
- Data analysts looking for a quick starting point for customer segmentation, anomaly detection, or exploratory clustering.
- Teams evaluating tools — load a blueprint to immediately test the platform's capabilities.
How It Works
- Browse the blueprints above and choose one that matches your goal.
- Read the overview to understand the processing stages and expected output.
- Click "Try this Blueprint" to load it into the interactive pipeline editor with pre-loaded sample data.
- Hit Run to execute the pipeline. Results appear on each node.
- Modify parameters, swap algorithms, or upload your own data to customize the workflow.