Aporia Documentation
Get StartedBook a Demo🚀 Cool StuffBlog
V2
V2
  • 📖Aporia Docs
  • 🤗Introduction
    • Quickstart
    • Support
  • 💡Core Concepts
    • Why Monitor ML Models?
    • Understanding Data Drift
    • Analyzing Performance
    • Tracking Data Segments
    • Models & Versions
  • 🚀Deployment
    • AWS
    • Google Cloud
    • Azure
    • Databricks
    • Offline / On-Prem
    • Platform Architecture
  • 🏠Storing your Predictions
    • Overview
    • Real-time Models (Postgres)
    • Real-time Models (Kafka)
    • Batch Models
    • Kubeflow / KServe
  • 🧠Model Types
    • Regression
    • Binary Classification
    • Multiclass Classification
    • Multi-Label Classification
    • Ranking
  • 🌈Explainability
    • SHAP values
  • 📜NLP
    • Intro to NLP Monitoring
    • Example: Text Classification
    • Example: Token Classification
    • Example: Question Answering
  • 🍪Data Sources
    • Overview
    • Amazon S3
    • Athena
    • BigQuery
    • Databricks
    • Glue Data Catalog
    • Google Cloud Storage
    • PostgreSQL
    • Redshift
    • Snowflake
    • Microsoft SQL Server
    • Oracle
  • ⚡Monitors & Alerts
    • Overview
    • Data Drift
    • Metric Change
    • Missing Values
    • Model Activity
    • Model Staleness
    • Performance Degradation
    • Prediction Drift
    • Value Range
    • Custom Metric
    • New Values
    • Alerts Consolidation
  • 🎨Dashboards
    • Overview
  • 🤖ML Monitoring as Code
    • Getting started
    • Adding new models
    • Data Segments
    • Custom metrics
    • Querying metrics
    • Monitors
    • Dashboards
  • 📡Integrations
    • Slack
    • Webhook
    • Teams
    • Single Sign On (SAML)
    • Cisco
  • 🔐Administration
    • Role Based Access Control (RBAC)
  • 🔑API Reference
    • REST API
    • API Extended Reference
    • Custom Segment Syntax
    • Custom Metric Syntax
    • Code-Based Metrics
    • Metrics Glossary
  • ⏩Release Notes
    • Release Notes 2024
    • Release Notes 2023
Powered by GitBook
On this page
  • Widgets
  • Add a widget
  • Comparison
  • Edit/ Delete a widget
  • Multiple dashboards
  • It's time to create your first dashboard!
  1. Dashboards

Overview

PreviousAlerts ConsolidationNextGetting started

Last updated 1 year ago

With the introduction of Dashboards, you now have the ability to create customizable and interactive visualizations of your ML model data. Dashboards provide a centralized view of your model's key metrics and performance indicators, allowing you to gain a complete understanding into your model and data health.

When creating your model we will create a dashboard for you based on your model type. You can use our suggestion as is, change it to your needs, or create a custom dashboard from scratch.

Widgets

There are 5 types of widgets currently supported in the system:

  • Metric Widget - allows you to visualize the value of a specific model metric.

  • Timeseries Widget - allows you to visualize the value of a specific model metric over time.

  • Histogram Widget - allows you to visualize the distribution of a specific field in your model schema.

  • Text Widget - allows your to create sections within your dashboard for easy orientation within the dashboard.

  • Data Health Widget - allows you to identify data issues like missing values and drift between datasets quickly.

Add a widget

To create a new widget just click on the actions button in the top right corner of the dashboard and click "Add new widget".

Each widget is fully customizable. For example, configurations include fields, versions, and/or segments of choice. Widgets are resizable and can be moved around to your preferred layout.

Comparison

Widgets also supports comparison to allow you to easily identify changes across model versions, time periods, and/or segments. Within your widget configuration just click on the compare tab and select your comparison configuration.

Edit/ Delete a widget

Multiple dashboards

If you work with a team there is a good chance that different people want to see different widget types and configurations on their own version of a dashboard. For this reason, Aporia lets you create multiple dashboards per model. Just click on the create dashboard button on the sidebar and name your new dashboard.

If you want to change your dashboard name or delete it, select the dashboard, click on the actions button on its top right, and just choose your desired action.

Within the actions, you'll also see the option to duplicate your dashboard, in case you want to base your new dashboard on an existing one.

Each widget is editable. Just hover on the widget you want to edit and you'll see the actions button on the top right of the widget. Click there and you'll see the options to edit/ delete the widget.

It's time to create your first dashboard!

🎨
🎨
Custom Dashboard
Creating a new widget