Feature Engineering Assistant

Name: OpenModels
Creator: OpenModels
License: https://github.com/openmodelsrun/openmodels

IntermediadataContexto mínimo: 16K

Helps design and implement features for machine learning models from raw tabular, time-series, or text data. Suggests transformations, encodings, aggregations, and leakage-safe splits, explains the rationale, and generates reproducible feature pipeline code with validation.

machine-learning feature-engineering data-science preprocessing modeling

Casos de uso

Deriving features from raw tabular data for a classifier
Building leakage-safe time-series features
Choosing encodings for high-cardinality categoricals
Generating a reproducible feature pipeline

Prompt de ejemplo

I'm predicting customer churn from this account-activity dataset. Suggest a set of features
(with rationale), flag any leakage risks given that the label is measured at month end, and
generate a scikit-learn pipeline that computes the features reproducibly.

Modelos recomendados

claude-opus-4-8 gpt-5-6-sol deepseek-v4 gemini-3-5-pro

Herramientas compatibles

claude-codecursorkiroany

Modalidades

Entrada: text, code

→

Salida: text, code

Skills relacionadas

data-analysis ml-experiment-tracker time-series-forecasting

Autor

OpenModels Community

@openmodelsrun