skills.rest
Moffran
MoffranCOMMUNITY
Explore all skills by this author →
GitHub

ce-regression-intervals

Configure CE regression intervals with percentile conformal and thresholded probabilistic modes.

78|15|Updated May 1, 2023
Search Tags:#calibration#uncertainty#machine-learning#explanations#regression-intervals#conformal-prediction
One-click install
npx skills add https://github.com/Moffran/calibrated_explanations --skill ce-regression-intervals
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ce-regression-intervals
Source: https://github.com/Moffran/calibrated_explanations/tree/main/.claude/skills/ce-regression-intervals
Command: npx skills add https://github.com/Moffran/calibrated_explanations --skill ce-regression-intervals

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Configure and interpret regression intervals for CE using percentile conformal and thresholded probabilistic modes, enabling calibrated interval outputs for regression tasks.

Core Features & Use Cases

  • Provide percentile conformal intervals around regression predictions
  • Offer thresholded probabilistic regression mode to estimate P(y <= t)
  • Support per-instance interval adaptation via DifficultyEstimator when available

Quick Start

Configure CE regression intervals for a fitted WrapCalibratedExplainer to obtain percentile conformal and thresholded probabilistic outputs.

Frequently Asked Questions about ce-regression-intervals

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

FAQPage Schema
How do I configure calibrated regression intervals for conformal prediction?▼

To configure calibrated regression intervals, apply CE calibration to a fitted WrapCalibratedExplainer, enabling percentile conformal and thresholded probabilistic outputs for regression predictions.

What is the difference between percentile conformal and thresholded probabilistic regression intervals?▼

Percentile conformal intervals provide bounds around regression predictions, while thresholded probabilistic mode estimates the probability P(y <= t) based on a specified threshold value.

How do I use a DifficultyEstimator for per-instance interval selection?▼

DifficultyEstimator provides optional guidance for per-instance interval adaptation, allowing CE regression intervals to adjust dynamically based on instance-specific difficulty.

Do I need a fitted WrapCalibratedExplainer before setting up CE regression intervals?▼

Yes, a fully fitted and calibrated WrapCalibratedExplainer is required before configuring CE regression intervals to ensure accurate percentile conformal and thresholded probabilistic outputs.

Can I estimate the probability that a regression target falls below a specific threshold?▼

Yes, thresholded probabilistic regression mode estimates P(y <= t) by applying CE calibration to regression explanations when a threshold value is present.

When should I use thresholded probabilistic mode versus percentile conformal intervals for regression?▼

Mode selection is based on threshold presence: use thresholded probabilistic mode to estimate P(y <= t) when a threshold exists, otherwise use percentile conformal intervals.

Related Skills

Explore More Data & Analytics Skills→
MoffranMoffran
78

ce-pipeline-builder

Orchestrate CE-first pipelines by wrapping models with WrapCalibratedExplainer.

Community
Advanced
nahisahonahisaho
3

scientific-uncertainty-quantification

Quantify machine learning predictive uncertainty with conformal prediction, MC dropout, and deep ensembles.

Community
Advanced
Yezez9Yezez9

pytdc

Load Therapeutics Data Commons datasets and tools for drug discovery tasks.

Community
Intermediate
rilicalrilical

calibration-conformal

Calibrate temperature scaling and conformal prediction artifacts for detector abstention.

Community
Advanced