Skip to main content


TODO: Update me


timegpt [--horizon HORIZON] [--freq {H,D,W,M,MS,B}] [--finetune FINETUNE] [--ci CONFIDENCE] [--cleanex] [--timecol TIMECOL] [--targetcol TARGETCOL] [--sheet-name SHEET_NAME] [--datefeatures DATE_FEATURES] [-d {AAPL}] [-c TARGET_COLUMN] [--end S_END_DATE] [--start S_START_DATE] [--residuals]


horizon--horizonForecasting horizon12TrueNone
freq--freqFrequency of the data.NoneTrueH, D, W, M, MS, B
finetune--finetuneNumber of steps used to finetune TimeGPT in the new data.0TrueNone
confidence--ciNumber of steps used to finetune TimeGPT in the new data.80, 90TrueNone
cleanex--cleanexClean exogenous signal before making forecasts using TimeGPT.TrueTrueNone
timecol--timecolDataframe column that represents datetimedsTrueNone
targetcol--targetcolDataframe column that represents the target to forecast foryTrueNone
sheet_name--sheet-nameThe name of the sheet to export to when type is XLSX.TrueNone
date_features--datefeaturesSpecifies which date attributes have highest weight according to model.TrueNone
target_dataset-d --datasetThe name of the dataset you want to selectNoneTrueAAPL
target_column-c --target-columnThe name of the specific column you want to usecloseTrueNone
s_end_date--endThe end date (format YYYY-MM-DD) to select for testingNoneTrueNone
s_start_date--startThe start date (format YYYY-MM-DD) to select for testingNoneTrueNone
residuals--residualsShow the residuals for the model.FalseTrueNone

On this page