skills.rest
logicalclocks
logicalclocksOFFICIAL
Explore all skills by this author →
Website𝕏@hopsworksGitHub

hops-batch-inference

Automate batch inference in Hopsworks using Python or PySpark.

15|32|Updated Nov 13, 2021
Search Tags:#batch inference#Hopsworks#feature view#model prediction#Spine Groups
One-click install
npx skills add https://github.com/logicalclocks/hopsworks-api --skill hops-batch-inference
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hops-batch-inference
Source: https://github.com/logicalclocks/hopsworks-api/tree/main/skills/hops/hops-batch-inference
Command: npx skills add https://github.com/logicalclocks/hopsworks-api --skill hops-batch-inference

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires hopsworks, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates batch inference with Hopsworks models and feature views, simplifying the process of making predictions on large datasets.

Core Features & Use Cases

  • Batch Inference: Automatically retrieve batch data from feature views, download models from the model registry, and generate predictions.
  • Spine Groups: Supports point-in-time joins using spine groups for accurate feature retrieval.
  • Model Management: Integrates with the Hopsworks model registry for easy model management.
  • Use Case: Ideal for automating predictions on large datasets, such as analyzing customer behavior or predicting stock prices.

Quick Start

Use the hops-batch-inference skill to predict fraud probabilities for the last 24 hours using the 'fraud_features_fv' feature view and the 'fraud_detector' model.

Frequently Asked Questions about hops-batch-inference

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate batch inference in Hopsworks using feature views?▼

Use this Skill to retrieve batch data from feature views, download models from the registry, and generate predictions using Python or PySpark for large datasets.

What are spine groups for point-in-time joins in Hopsworks batch inference?▼

Spine groups in Hopsworks batch inference define the primary keys and event timestamps to ensure accurate point-in-time feature retrieval, preventing data leakage when joining features for predictions.

Does Hopsworks batch inference support both Python and PySpark?▼

Yes, Hopsworks batch inference supports both Python and PySpark, allowing you to process large datasets and generate predictions using your preferred data processing framework.

How do I download models from the Hopsworks model registry for batch prediction?▼

Download models from the Hopsworks model registry for batch prediction by integrating the registry with your inference pipeline, automatically retrieving the required model artifacts before generating predictions.

When should I use Hopsworks feature views for batch inference?▼

Use Hopsworks feature views for batch inference when you need to automate predictions on large datasets, such as analyzing customer behavior or predicting stock prices, requiring consistent feature retrieval.

Related Skills

Explore More Data & Analytics Skills→
logicalclockslogicalclocks

hops

Manage Hopsworks Feature Store resources via the hops CLI with JSON output.

Official
Advanced
ZardLi1115ZardLi1115
4

polymarket

Retrieve Polymarket prediction market data via public REST endpoints.

Community
Intermediate
logicalclockslogicalclocks
15

hops-online-inference

Deploys ML models and runs online inference in Hopsworks via Python SDK.

Official
Advanced
readtheskillreadtheskill
3

allora-intelligence

Generate AI-driven price predictions for tokens via Allora GOAT plugin APIs.

Official
Intermediate