data-transform

What problem does it solve?

This Skill automates data transformation tasks that are laborious and error-prone when done manually. It provides a local pipeline for cleaning, normalizing, reshaping, and feature engineering using pandas, numpy, and scikit-learn, ensuring privacy and provider-agnostic workflows.

Core Features & Use Cases

• Data Cleaning: handle missing values, remove duplicates, drop outliers, and unify formats.
• Normalization and Scaling: apply StandardScaler, MinMaxScaler, RobustScaler for numeric features.
• Data Reshaping: melt/pivot between wide and long formats, and create summary tables.
• Filtering and Subsetting: conditional selection, grouping, and feature engineering.
• Use Case: From a raw CSV, clean data, scale numeric features, reshape to long format, and prepare for modeling.

Quick Start

Load data.csv, drop duplicates and missing values, apply median imputation for numeric columns, and save cleaned_data.csv.