菜单
Incorporates external variables (holidays, weather, events) into TimeGPT forecasts to improve accuracy. Use when forecasts require external data, holidays impact sales, or weather affects demand. Trigger with 'include holidays', 'add weather data', 'integrate events'.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generate and configure Nixtla Skills using the CLI for forecasting workflows. Use when installing or updating skills. Trigger with 'install nixtla skills' or 'update nixtla'.
Generate benchmarking pipelines to compare forecasting models and summarize accuracy/speed trade-offs. Use when evaluating TimeGPT vs StatsForecast/MLForecast/NeuralForecast on a dataset. Trigger with "benchmark models", "compare TimeGPT vs StatsForecast", or "model selection".
Research and summarize Nixtla ecosystem updates and time-series forecasting content from the web and GitHub. Use when gathering release notes, recent changes, or best-practice references. Trigger with "Nixtla updates", "what's new with TimeGPT", or "find time-series papers".
Generate production-ready TimeGPT forecasting pipeline code from requirements. Use when scaffolding a pipeline with validation, logging, visualization, and repeatable runs. Trigger with "create TimeGPT pipeline", "build TimeGPT integration", or "generate forecast code".
Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other benchmark datasets). Use when the user asks about baseline performance, model comparisons, or metric interpretation for Nixtla time-series experiments. Trigger with "baseline review", "interpret sMAPE/MASE", or "compare AutoETS vs AutoTheta".
Orchestrate 6-phase changelog generation workflow with AI synthesis, multi-source data fetching (GitHub/Slack/Git), quality validation, and automated PR creation. Use when automating release notes, weekly changelogs, or documentation updates. Trigger with "generate changelog", "weekly changelog", or "automate release notes".
| name | nixtla-exogenous-integrator |
| description | Incorporates external variables (holidays, weather, events) into TimeGPT forecasts to improve accuracy. Use when forecasts require external data, holidays impact sales, or weather affects demand. Trigger with 'include holidays', 'add weather data', 'integrate events'. |
| version | 1.0.0 |
| author | Jeremy Longshore <jeremy@intentsolutions.io> |
| license | MIT |
| allowed-tools | Read,Write,Bash(python:*),Glob,Grep |
Augments TimeGPT forecasts with exogenous variables for increased accuracy.
Enhances time series predictions by integrating external data sources like holidays, weather, and events.
This skill enriches TimeGPT forecasts by considering external factors influencing time series data. It reads exogenous data from CSV files, aligns it with the historical data, and passes both to the TimeGPT API. This integration improves forecast accuracy, especially when events or external conditions affect the time series. The skill outputs an augmented forecast incorporating the impact of these exogenous variables.
Tools: Read, Write, Bash, Glob, Grep
Environment: NIXTLA_TIMEGPT_API_KEY
Packages:
pip install nixtla pandas matplotlib
Read historical time series CSV and exogenous variables CSVs. Ensure they have a common date ('ds') column.
Script: {baseDir}/scripts/load_data.py
Usage:
python {baseDir}/scripts/load_data.py data.csv holidays.csv
The loader expects:
unique_id, ds, y columnsds column plus feature columnsMerge historical and exogenous dataframes based on the 'ds' column using the alignment script.
Script: {baseDir}/scripts/align_data.py
The script validates that both datasets share a 'ds' column and checks for column name conflicts. It performs a left join to preserve all historical timestamps.
Run the integration script with your data files and forecast parameters.
Script: {baseDir}/scripts/integrate_exogenous.py
Usage:
python {baseDir}/scripts/integrate_exogenous.py \
--input data.csv \
--exogenous holidays.csv \
--horizon 14 \
--freq D
Parameters:
--input: Historical time series CSV file--exogenous: Exogenous variables CSV file (optional)--horizon: Number of periods to forecast--freq: Time series frequency (D=daily, H=hourly, M=monthly, etc.)The script automatically:
Error: Exogenous data missing 'ds' column
Solution: Rename the date column in the exogenous data to 'ds'.
Error: Mismatch in date range between historical and exogenous data
Solution: Ensure the exogenous data covers the entire historical and forecast period.
Error: Exogenous variables have NaN values in the forecast horizon
Solution: Provide future values for exogenous variables for the entire forecast horizon.
Error: TimeGPT API rejected exogenous variables
Solution: Ensure exogenous variables are numeric and compatible with the TimeGPT API schema.
Error: NIXTLA_TIMEGPT_API_KEY environment variable not set
Solution: Set your TimeGPT API key as an environment variable before running the script.
Input (data.csv):
unique_id,ds,y
store_1,2024-01-01,100
store_1,2024-01-02,120
store_1,2024-01-03,115
Input (holidays.csv):
ds,holiday
2024-01-01,1
2024-01-02,0
2024-01-03,0
2024-01-04,0
Command:
python {baseDir}/scripts/integrate_exogenous.py \
--input data.csv \
--exogenous holidays.csv \
--horizon 7 \
--freq D
Output (forecast_exogenous.csv):
unique_id,ds,TimeGPT,TimeGPT-lo-90,TimeGPT-hi-90
store_1,2024-01-04,125,110,140
store_1,2024-01-05,128,113,143
Input (data.csv):
unique_id,ds,y
grid_1,2024-01-01 00:00,5000
grid_1,2024-01-01 01:00,5100
Input (weather.csv):
ds,temperature
2024-01-01 00:00,10
2024-01-01 01:00,8
2024-01-01 02:00,7
Command:
python {baseDir}/scripts/integrate_exogenous.py \
--input data.csv \
--exogenous weather.csv \
--horizon 24 \
--freq H
Output: Hourly forecast incorporating temperature trends.
{baseDir}/scripts/ directory contains all executable code