Does this skill require a specific LLM provider?

No, this skill is designed to run locally and is compatible with all LLM providers including Claude, GPT, Gemini, and local models.

How does it handle missing values in a dataset?

It provides multiple strategies including statistical filling (mean/median), forward/backward filling, linear interpolation, and conditional row/column dropping.

Can this skill help with feature engineering for AI?

Yes, it includes built-in patterns for binning, one-hot encoding, creating interaction features, and generating time-series lag features.

Which Python libraries are used for the transformations?

The skill utilizes industry-standard libraries: pandas for data structures, numpy for numerical operations, and scikit-learn for scaling and encoding.

Universal Data Transformation

Name: Universal Data Transformation
Author: Activer007

byActiver007

데이터 과학 및 ML

Transforms, cleans, and reshapes complex datasets using standard Python libraries like pandas and numpy for seamless data preprocessing.

소개

This skill provides a comprehensive suite of data manipulation capabilities, allowing users to perform complex transformations like normalization, feature engineering, and data reshaping locally. By leveraging industry-standard libraries such as pandas, numpy, and scikit-learn, it enables developers to prepare raw data for analysis or machine learning across any LLM environment. It is particularly useful for handling missing values, merging datasets, and converting data formats without relying on cloud-hosted processing or proprietary tools.

주요 기능

Advanced data cleaning and missing value imputation strategies
Complex data reshaping via pivoting, melting, and transposing
0 GitHub stars
Automated feature engineering and categorical variable encoding
Statistical normalization and scaling including Z-score and Min-Max
Efficient merging and concatenation of disparate datasets

사용 사례

Converting bioinformatics formats like AnnData into analysis-ready DataFrames
Preprocessing raw CSV or Excel data for machine learning model training
Automating exploratory data analysis (EDA) and feature extraction workflows

소개

주요 기능

Advanced data cleaning and missing value imputation strategies
Complex data reshaping via pivoting, melting, and transposing
0 GitHub stars
Automated feature engineering and categorical variable encoding
Statistical normalization and scaling including Z-score and Min-Max
Efficient merging and concatenation of disparate datasets

사용 사례

Converting bioinformatics formats like AnnData into analysis-ready DataFrames
Preprocessing raw CSV or Excel data for machine learning model training
Automating exploratory data analysis (EDA) and feature extraction workflows