LogoLogo
👨‍💻 API Reference📣 Release Notes📺 Request a Demo
  • Introduction to Fiddler
    • Monitor, Analyze, and Protect your ML Models and Gen AI Applications
  • Fiddler Doc Chatbot
  • First Steps
    • Getting Started With Fiddler Guardrails
    • Getting Started with LLM Monitoring
    • Getting Started with ML Model Observability
  • Tutorials & Quick Starts
    • LLM and GenAI
      • LLM Evaluation - Compare Outputs
      • LLM Monitoring - Simple
    • Fiddler Free Guardrails
      • Guardrails - Quick Start Guide
      • Guardrails - Faithfulness
      • Guardrails - Safety
      • Guardrails FAQ
    • ML Observability
      • ML Monitoring - Simple
      • ML Monitoring - NLP Inputs
      • ML Monitoring - Class Imbalance
      • ML Monitoring - Model Versions
      • ML Monitoring - Ranking
      • ML Monitoring - Regression
      • ML Monitoring - Feature Impact
      • ML Monitoring - CV Inputs
  • Glossary
    • Product Concepts
      • Baseline
      • Custom Metric
      • Data Drift
      • Embedding Visualization
      • Fiddler Guardrails
      • Fiddler Trust Service
      • LLM and GenAI Observability
      • Metric
      • Model Drift
      • Model Performance
      • ML Observability
      • Trust Score
  • Product Guide
    • LLM Application Monitoring & Protection
      • LLM-Based Metrics
      • Embedding Visualizations for LLM Monitoring and Analysis
      • Selecting Enrichments
      • Enrichments (Private Preview)
      • Guardrails for Proactive Application Protection
    • Optimize Your ML Models and LLMs with Fiddler's Comprehensive Monitoring
      • Alerts
      • Package-Based Alerts (Private Preview)
      • Class Imbalanced Data
      • Enhance ML and LLM Insights with Custom Metrics
      • Data Drift: Monitor Model Performance Changes with Fiddler's Insights
      • Ensuring Data Integrity in ML Models And LLMs
      • Embedding Visualization With UMAP
      • Fiddler Query Language
      • Model Versions
      • How to Effectively Use the Monitoring Chart UI
      • Performance Tracking
      • Model Segments: Analyze Cohorts for Performance Insights and Bias Detection
      • Statistics
      • Monitoring ML Model and LLM Traffic
      • Vector Monitoring
    • Enhance Model Insights with Fiddler's Slice and Explain
      • Events Table in RCA
      • Feature Analytics Creation
      • Metric Card Creation
      • Performance Charts Creation
      • Performance Charts Visualization
    • Master AI Monitoring: Create, Customize, and Compare Dashboards
      • Creating Dashboards
      • Dashboard Interactions
      • Dashboard Utilities
    • Adding and Editing Models in the UI
      • Model Editor UI
      • Model Schema Editing Guide
    • Fairness
    • Explainability
      • Model: Artifacts, Package, Surrogate
      • Global Explainability: Visualize Feature Impact and Importance in Fiddler
      • Point Explainability
      • Flexible Model Deployment
        • On Prem Manual Flexible Model Deployment XAI
  • Technical Reference
    • Python Client API Reference
    • Python Client Guides
      • Installation and Setup
      • Model Onboarding
        • Create a Project and Onboard a Model for Observation
        • Model Task Types
        • Customizing your Model Schema
        • Specifying Custom Missing Value Representations
      • Publishing Inference Data
        • Creating a Baseline Dataset
        • Publishing Batches Of Events
        • Publishing Ranking Events
        • Streaming Live Events
        • Updating Already Published Events
        • Deleting Events From Fiddler
      • Creating and Managing Alerts
      • Explainability Examples
        • Adding a Surrogate Model
        • Uploading Model Artifacts
        • Updating Model Artifacts
        • ML Framework Examples
          • Scikit Learn
          • Tensorflow HDF5
          • Tensorflow Savedmodel
          • Xgboost
        • Model Task Examples
          • Binary Classification
          • Multiclass Classification
          • Regression
          • Uploading A Ranking Model Artifact
    • Integrations
      • Data Pipeline Integrations
        • Airflow Integration
        • BigQuery Integration
        • Integration With S3
        • Kafka Integration
        • Sagemaker Integration
        • Snowflake Integration
      • ML Platform Integrations
        • Integrate Fiddler with Databricks for Model Monitoring and Explainability
        • Datadog Integration
        • ML Flow Integration
      • Alerting Integrations
        • PagerDuty Integration
    • Comprehensive REST API Reference
      • Projects REST API Guide
      • Model REST API Guide
      • File Upload REST API Guide
      • Custom Metrics REST API Guide
      • Segments REST API Guide
      • Baselines REST API Guide
      • Jobs REST API Guide
      • Alert Rules REST API Guide
      • Environments REST API Guide
      • Explainability REST API Guide
      • Server Info REST API Guide
      • Events REST API Guide
      • Fiddler Trust Service REST API Guide
    • Fiddler Free Guardrails Documentation
  • Configuration Guide
    • Authentication & Authorization
      • Adding Users
      • Overview of Role-Based Access Control
      • Email Authentication
      • Okta Integration
      • SSO with Azure AD
      • Ping Identity SAML SSO Integration
      • Mapping LDAP Groups & Users to Fiddler Teams
    • Application Settings
    • Supported Browsers
  • History
    • Release Notes
    • Python Client History
    • Compatibility Matrix
    • Product Maturity Definitions
Powered by GitBook
On this page
  • UMAP Technique for Embedding Visualization
  • Creating an Embedding Visualization Chart
  • Chart Parameters
  • Model
  • Custom Feature Column
  • Baseline
  • Display Columns
  • Sample Size
  • Number of Neighbors
  • Minimum Distance
  • Interactions on Embedding Visualization
  • Choose Different Time Periods
  • Color By
  • Zoom
  • Selection of Data Points
  • Data Cards
  • Hover on a Data Point
  • Saving the Chart

Was this helpful?

  1. Product Guide
  2. Optimize Your ML Models and LLMs with Fiddler's Comprehensive Monitoring

Embedding Visualization With UMAP

PreviousEnsuring Data Integrity in ML Models And LLMsNextFiddler Query Language

Last updated 1 month ago

Was this helpful?

© 2024 Fiddler Labs, Inc.

Embedding visualization is a powerful technique used to understand and interpret complex relationships in high-dimensional data. Reducing the dimensionality of custom features into a 2D or 3D space makes it easier to identify patterns, clusters, and outliers.

In Fiddler, high-dimensional data like embeddings and vectors are ingested as a .

Our goal in this document is to visualize these custom features.

UMAP Technique for Embedding Visualization

We utilize the UMAP (Uniform Manifold Approximation and Projection) technique for embedding visualizations. UMAP is a dimension reduction technique that is particularly good at preserving the local structure of the data, making it ideal for visualizing embeddings. We reduce the high-dimensional embeddings to a 3D space.

Creating an Embedding Visualization Chart

To create an embedding Visualization chart, follow these steps:

  1. Navigate to the Charts tab in your Fiddler AI instance

  2. Click on the Add Chart button on the top right

  3. In the modal, Select the project that has a model with Custom features

  4. Select Embedding Visualization.

Chart Parameters

When creating an embedding visualization chart, you will need to specify the following parameters:

  • Model

  • Custom Feature Column

  • Baseline

  • Display Columns

  • Sample size

  • Number of Neighbors

  • Minimum distance

Please see below for details on these parameters.

Model

Select the model (with custom features) for which you want to visualize the embeddings.

Custom Feature Column

Choose the custom feature column from your dataset that you wish to visualize.

Baseline

Define a baseline for comparison. This is optional and will be useful when you want to compare datasets such as a pre-production dataset with a production dataset or two time periods in production.

Display Columns

Select the columns that you want to display additional information for when hovering over points in the visualization. These additional display columns will also be available in the data cards when points are selected.

Sample Size

Decide on the number of samples you want to include in the visualization for performance and clarity. Currently, a sample size of either 100, 500, or 1000 can be selected. In future releases, we will enable support for larger sample sizes.

Number of Neighbors

This parameter controls how UMAP balances local versus global structure in the data. It determines the number of neighboring points used in the manifold approximation. Low values (for example: 5) of this parameter will lead UMAP to focus too much on the local structure losing sight of the big picture, alternatively, bigger values will lead to a focus on the broader data. It is important to experiment on your dataset and use case to identify a value that works best for you.

Minimum Distance

Set the minimum distance apart that points are allowed to be in the low-dimensional representation. Smaller values (for example: 0.1) will result in a more clustered embedding, which can highlight finer details.

Interactions on Embedding Visualization

Choose Different Time Periods

When generating the embedding visualization, you have the flexibility to choose different time periods of production data to analyze. To do this:

  • Access the time period selector.

  • Choose the start and end dates for the time period you are interested in.

  • The visualization will update to reflect the embeddings from the selected time range.

Color By

The 'Color By' feature enriches the visualization by categorizing your data points using different colors based on attributes.

  • Find the 'Color By' dropdown in your control panel.

  • Choose a categorical feature to color-code the data points. For instance, in the above image, the data points are assigned colors based on a 'target' categorical column. This attribute includes categories like Sandal, Trouser, and Pullover, as indicated in the legend.

Using the 'Color By' feature can assist in uncovering patterns in your data. For instance, in the above image, data points with varying 'target' column values demonstrate clustering, where similar values tend to group together.

You can also select points to delve deeper for further inspection. You may find this ability to interactively color and select data points very useful for root cause analysis.

Zoom

Zooming in on the UMAP chart provides a closer look at clusters and individual data points.

  • Use the mouse scroll wheel to zoom in or out.

  • Click and drag the mouse to move the zoomed-in area around the chart.

  • Zooming helps to focus on areas of interest or to distinguish between closely packed points.

Selection of Data Points

You can select individual or groups of data points to analyze further.

  • Click on a data point to select it. or use the Selector on the top right to select multiple points

Data Cards

  • Selected points will be highlighted on the chart and details of the display columns of these cards are displayed in data cards as shown below

  • Use this feature to identify and analyze specific data points

In the following example, we use the categorical attribute feedback, which contains three possible values: Like, Dislike, or Null, as indicated in the legend. After applying the 'color by' feature, the user selects specific data points to examine in greater detail. The selected data points are then presented as data cards below.

Hover on a Data Point

Hovering over a data point reveals additional information about it, providing immediate insight without the need for selection.

  • Move the cursor over a data point on the chart.

  • A tooltip will appear, displaying the data associated with that point, such as values of different display columns

  • Use this feature for a quick look-up of data without altering your current selection on the chart.

Saving the Chart

Once you're satisfied with your visualization, you can save the chart. This chart can then be added to a Dashboard. This allows you to revisit the UMAP visualization at any time easily either directly going to the Chart or to the dashboard

UMAP is supported for both Text and Image embeddings in .

Custom feature

Questions? to a product expert or a demo.

Need help? Contact us at .

Custom feature
❓
💡
Talk
request
help@fiddler.ai
Example of embedding data rendered as a UMAP visualization chart.
The Add Chart modal dialog form.
The chart date range filter selector.
Example of embedding data rendered as a UMAP visualization with data points colored by category.
Data cards displayed below UMAP chart upon data point selection.