Data Science Lab

Structure

BDB Data Science Lab Documentation

Overview

  • Introduction

  • Key Features

  • Typical User Workflow

  • Supported Environments

Getting Started

  • Accessing the Data Science Lab

  • Navigating the Interface

  • Sidebar Navigation Guide

Projects

  • Creating a New Project

  • Project Configuration (CPU, Memory, GPU, Libraries)

  • Managing Projects (Activate, Edit, Delete)

  • Git Integration

Workspace

  • Exploring the Workspace (Repos, Utils, Files)

  • Creating & Editing Notebooks

  • Running Code and Managing Kernels

  • Version Control (Register, Publish, Push/Pull from VCS)

  • Collaboration & Sharing

  • Data

    • Add Data

  • Secrets

    • Add Secrets

  • Algorithms

    • Regression

    • Classification

    • Forecasting

    • Unsupervised

    • Natural Language Processing

  • Models

  • Transforms

  • Artifacts

  • Variable Explorer

  • Writers

Agentic Tools

  • Overview of Agentic Tools

  • Pre-Built Agents for Data Science

  • Customizing Agentic Tools

  • Deploying & Managing Agentic Tools

Models

  • Model Registry (Registering & Versioning)

  • Model Deployment (Staging/Production)

  • Endpoints & Scaling

  • Monitoring & Retraining

AutoML

  • Introduction to AutoML in BDB

  • Creating AutoML Experiments

  • Hyperparameter Tuning & Model Selection

  • Exporting AutoML Models to Data Engineering

Integrations

  • Git Repositories (Push, Pull, Branching)

  • External Libraries (Pandas, Scikit-learn, etc.)

  • Integration with Data Center & Data Engineering

Troubleshooting & Best Practices

  • Common Errors & Fixes (Kernel inactive, Package issues)

  • Notebook Recovery & Versioning

  • Efficient Resource Usage

  • Recommended Project Organization

Tutorials & Examples

  • Predictive Maintenance Use Case – Notebook (Databricks-style)

PreviousPipelineNextOverview