skills.rest
hung-phan
hung-phanCOMMUNITY
Explore all skills by this author →
GitHub

feature-selection

Select informative features using filter, wrapper, embedded, stability, and VIF methods.

1|Updated Jun 4, 2026
Search Tags:#data science#machine learning#dimensionality reduction#model optimization#feature selection
One-click install
npx skills add https://github.com/hung-phan/ml-skills --skill feature-selection-hung-phan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: feature-selection
Source: https://github.com/hung-phan/ml-skills/tree/main/skills/ml-review/references/ml-training/feature-selection
Command: npx skills add https://github.com/hung-phan/ml-skills --skill feature-selection-hung-phan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires scikit-learn, pandas, numpy, scipy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of selecting the most informative features for your machine learning models, helping to reduce overfitting, improve accuracy, and enhance model interpretability.

Core Features & Use Cases

  • Filter Methods: Apply statistical tests to identify the most relevant features.
  • Wrapper Methods: Use machine learning models to evaluate subsets of features.
  • Embedded Methods: Use model training to determine feature importance.
  • Stability Selection: Identify consistently selected features across multiple models.
  • Multicollinearity Detection (VIF): Detect and remove multicollinear features.
  • Dimensionality Reduction: Reduce the number of features in high-dimensional datasets.
  • Use Case: Use this Skill to identify the most important features for an image classification model, reducing the feature set to improve model performance and interpretability.

Quick Start

Execute the feature_selection skill to perform feature selection on your dataset.

Frequently Asked Questions about feature-selection

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

FAQPage Schema
How do I select the most informative features for a machine learning model?▼

Feature selection identifies the most informative features for machine learning models using filter, wrapper, embedded, and stability selection methods to reduce overfitting and improve accuracy. This Skill automates that process using scikit-learn, pandas, and numpy.

What is the best way to detect and remove multicollinear features from my dataset?▼

Multicollinearity detection uses Variance Inflation Factor (VIF) methods to identify and remove multicollinear features from datasets. This helps reduce dimensionality and ensures your model relies on independent, non-redundant variables for better interpretability.

How does stability selection work for dimensionality reduction?▼

Stability selection identifies consistently selected features across multiple model iterations to ensure reliable dimensionality reduction. It complements standard filter and wrapper methods by validating feature importance robustly against data perturbations.

Can I use scikit-learn and pandas for feature selection on high-dimensional datasets?▼

Yes, feature selection on high-dimensional datasets requires scikit-learn, pandas, numpy, and scipy dependencies. The Skill applies statistical filter methods and embedded model training to efficiently reduce feature sets for various machine learning workflows.

When should I use wrapper methods versus embedded methods for model optimization?▼

Wrapper methods evaluate feature subsets using machine learning models directly, while embedded methods determine feature importance during model training. Use wrapper methods for precision and embedded methods for computational efficiency during model optimization.

Do I need to install scipy to perform feature selection with this Skill?▼

Yes, scipy is a required dependency alongside scikit-learn, pandas, and numpy to perform feature selection. These libraries provide the statistical tests and mathematical functions needed for filter, wrapper, and VIF calculations.

Related Skills

Explore More Data & Analytics Skills→
andikarachmanandikarachman
14

data-preprocessing

Preprocess raw data into clean, analysis-ready datasets with pandas and numpy.

Community
Advanced
robotlearning123robotlearning123

scikit-learn

Build, evaluate, and refine machine learning models with scikit-learn.

Community
Advanced
seb1nseb1n
147

exploratory-data-analysis

Perform systematic exploratory data analysis on tabular datasets with pandas and ydata-profiling.

Community
Advanced
tassiovaletassiovale
13

umap-learn

Reduce high-dimensional data to lower-dimensional embeddings with umap-learn.

Community
Advanced