Do I need a Nixtla API key to use this skill?

Yes, you must set the NIXTLA_TIMEGPT_API_KEY environment variable to authenticate and utilize the TimeGPT forecasting engine.

Can this skill handle missing future exogenous data?

No, to generate a forecast using exogenous variables, you must provide the expected values for those variables across the entire future forecast horizon.

What are exogenous variables in time series forecasting?

Exogenous variables are external factors—such as weather, holidays, or promotional events—that influence a time series but are not part of the historical target data itself.

What data format is required for the integrator?

The skill requires CSV files containing a 'ds' column for timestamps, a 'unique_id' for series identification, and 'y' for the target values.

Nixtla Exogenous Integrator

Name: Nixtla Exogenous Integrator
Author: intent-solutions-io

byintent-solutions-io

Ciencia de Datos y ML

Enhances TimeGPT time series forecasts by integrating external variables like holidays, weather, and events for improved predictive accuracy.

Acerca de

The Nixtla Exogenous Integrator is a specialized Claude Code skill designed to boost the precision of time series predictions by accounting for external drivers. It automates the complex process of aligning historical time series data with external datasets—such as economic indicators, holiday calendars, or weather patterns—and leverages the TimeGPT API to generate augmented forecasts. This tool is essential for data scientists and analysts who need to account for seasonality and external shocks that univariate models might overlook, providing a streamlined workflow from data alignment to visual reporting.

Características Principales

Seamless integration with Nixtla TimeGPT API for multivariate forecasting
Built-in data validation and preprocessing for missing forecast horizon values
Automated alignment of historical and exogenous datasets via standardized 'ds' columns
Support for diverse external variables including holidays, weather, and custom events
Generates both detailed CSV forecasts and visual plot comparisons for immediate analysis
0 GitHub stars

Casos de Uso

Forecasting energy demand by integrating temperature and real-time weather pattern data
Estimating event-driven logistics traffic by adding local festival or sports schedules to historical data
Predicting retail sales spikes by incorporating national and regional holiday calendars

Acerca de

Características Principales

Seamless integration with Nixtla TimeGPT API for multivariate forecasting
Built-in data validation and preprocessing for missing forecast horizon values
Automated alignment of historical and exogenous datasets via standardized 'ds' columns
Support for diverse external variables including holidays, weather, and custom events
Generates both detailed CSV forecasts and visual plot comparisons for immediate analysis
0 GitHub stars

Casos de Uso

Forecasting energy demand by integrating temperature and real-time weather pattern data
Estimating event-driven logistics traffic by adding local festival or sports schedules to historical data
Predicting retail sales spikes by incorporating national and regional holiday calendars