ml-data-fetch-annotate

Name: ml-data-fetch-annotate
Availability: InStock
Author: Stream

Fetch ML datasets from Redshift and generate annotated PDFs for error analysis.

Updated Feb 24, 2026

Search Tags:#data fetching #machine learning #error analysis #pdf generation #ml #annotation #redshift

Ready to run

npx skills add https://github.com/Stream-claims/stream-engineering --skill ml-data-fetch-annotate

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ml-data-fetch-annotate
Source: https://github.com/Stream-claims/stream-engineering/tree/main/skills/ml-data-fetch-annotate
Command: npx skills add https://github.com/Stream-claims/stream-engineering --skill ml-data-fetch-annotate

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, boto3, PyMuPDF, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of fetching machine learning datasets from Redshift and generating annotated PDFs, streamlining the analysis of model errors and data quality.

Core Features & Use Cases

Data Fetching: Query and retrieve segment or case data from Redshift for ML evaluation.
PDF Annotation: Create annotated PDFs to visualize model predictions against ground truth and facilitate error analysis.
Schema Exploration: Understand the data warehouse schema relevant to ML evaluation.
Use Case: When a user needs to analyze why a classification model is making incorrect predictions, this skill can fetch the relevant data, generate reviewable PDFs highlighting the errors, and help identify patterns in misclassifications.

Quick Start

Fetch the latest 30 'BILL' segments for 'berkley_ent' and create an annotated PDF named 'segments.pdf'.

Frequently Asked Questions about ml-data-fetch-annotate

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

FAQPage Schema

How do I fetch ML datasets from Redshift for error analysis?▼

You fetch ML datasets from Redshift by executing Python scripts that use boto3 and pandas to query segment or case data. This retrieves the classification records needed to evaluate model predictions and identify misclassification patterns.

How do I generate annotated PDFs for machine learning error analysis?▼

You generate annotated PDFs for machine learning error analysis by processing fetched dataset records with PyMuPDF. This creates reviewable documents that visualize model predictions against ground truth, helping you identify and understand patterns in misclassifications.

Can I analyze classification model errors by visualizing predictions against ground truth?▼

Yes, you can analyze classification model errors by fetching segment data and generating reviewable PDFs. These documents highlight discrepancies between model predictions and ground truth, helping you identify patterns in why your classification model makes incorrect predictions.

Do I need pandas and PyMuPDF to create review PDFs from data warehouse schemas?▼

Yes, you need pandas, boto3, and PyMuPDF to create review PDFs from data warehouse schemas. Pandas handles data processing, boto3 manages Redshift connectivity, and PyMuPDF generates the annotated PDF outputs for evaluating your machine learning models.

What is the best way to explore data warehouse schemas for ML evaluation?▼

The best way to explore data warehouse schemas for ML evaluation is to use automated Python scripts to query segment and classification data. This approach helps you understand the schema structure while retrieving the exact case data needed to generate annotated review PDFs.

When should I not use automated PDF generation for model error analysis?▼

You should not use automated PDF generation for model error analysis when dealing with highly sensitive data warehouse records, as generating physical PDF outputs may create security concerns. It is also less effective for purely numerical datasets lacking visual document context.