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

feature-engineering

Transform raw datasets into machine learning features with scaling, encoding, and vectorization.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of converting raw data into informative features suitable for machine learning models, enhancing model performance and interpretability.

Core Features & Use Cases

  • Numeric Transforms: Apply log, Box-Cox, binning, and polynomial features to numeric data.
  • Categorical Encoding: Implement one-hot, ordinal, target, frequency, and binary encoding for categorical data.
  • Text Vectorization: Utilize TF-IDF, count vectorization, and sentence embeddings for text data.
  • Datetime Features: Decompose and encode datetime features into cyclical and rolling representations.
  • Interaction and Cross Features: Create interaction terms and cross features to capture complex relationships.
  • Automated Feature Engineering: Use featuretools and tsfresh for automated feature engineering and time-series feature extraction.
  • Pipeline Integration: Combine preprocessing and modeling steps into a single, integrated pipeline.
  • Use Case: When building a machine learning model, this Skill can be used to preprocess a dataset with various data types and transform it into a format suitable for training.

Quick Start

Apply the feature-engineering skill to transform your dataset into a format ready for machine learning.

Frequently Asked Questions about feature-engineering

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

FAQPage Schema
How do I preprocess raw data for machine learning models?▼

Automated feature engineering uses featuretools and tsfresh to generate features and extract time-series characteristics automatically. This reduces manual effort by systematically creating interaction terms and cross features to capture complex relationships in your dataset.

What is the best way to encode categorical data for modeling?▼

Encode categorical data for modeling using one-hot, ordinal, target, frequency, or binary encoding. Choosing the right categorical encoding method ensures model interpretability and enhances overall model performance with your specific dataset.

How does datetime cyclical encoding work for time-series data?▼

Datetime cyclical encoding decomposes timestamps into cyclical and rolling representations for time-series data. This datetime feature transformation captures periodic patterns, ensuring machine learning models recognize the continuous nature of time-based features.

Can I use TF-IDF and sentence embeddings for text vectorization?▼

Yes, you can use TF-IDF, count vectorization, and sentence embeddings for text vectorization. These text transformation techniques convert raw text data into numerical features that machine learning models can process effectively.

How do I integrate data preprocessing steps into a single pipeline?▼

Integrate data preprocessing and modeling steps into a single pipeline by combining numeric transforms, categorical encoding, and feature generation. This pipeline integration ensures consistent data transformation applied uniformly during both model training and inference.

Related Skills

Explore More Data & Analytics Skills→
h4vzzh4vzz
33

data-cleaning

Clean raw datasets into analysis-ready tables using pandas, pyjanitor, and great_expectations.

Community
Advanced
zongtingweizongtingwei
25

machine-learning-for-omics

Train supervised models on omics feature matrices and output metrics and explanations.

Community
Advanced
StarlitnightlyStarlitnightly
1.2k

data-stats-analysis

Perform statistical tests and corrections on datasets using SciPy, statsmodels, and NumPy.

Community
Advanced
inbharataiinbharatai
22

feature-engineer

Generate machine learning features with encoding, scaling, and selection in Python.

Community
Intermediate