Nixtla/statsforecast

Issues

• AutoARIMA with CSS method fails if residuals are zero

  #958 opened 3 days ago by andrewscottm
  3

• AutoARIMA with CSS method does not initialise residuals to zero

  #957 opened 3 days ago by andrewscottm
  1

• Original vs Optimized Functions

  #952 opened 20 days ago by yotambraun
  1

• Ability to set the multiprocessing context (to "spawn") in `core.StatsForecast`.

  #948 opened 23 days ago by christian-hnz
  3

• [<Library component: Models|Core|etc...>] Unable to find details for the returned values

  #950 opened 25 days ago by laniakea
  0

• auto arima "xreg is rank deficient" test is incorrect

  #902 opened a month ago by andrewscottm
  3

• seasonal naive confidence intervals are incorrect

  #903 opened a month ago by andrewscottm
  0

• Misalignment of Forecast Dates in StatsForecast.plot()

  #943 opened a month ago by stevefatz95
  2

• [ARIMA] Invalid memory accesses, integer overflows

  #937 opened a month ago by filipcacky
  3

• [MFLES] Seasonality prediction incorrect when forecasting multi-seasonal time series beyond one period

  #938 opened a month ago by tehunter
  0

• AutoETS Exception no model able to be fitted

  #929 opened 2 months ago by webert6
  4

• Add non weighted moving average model

  #928 opened 2 months ago by tackes
  2

• Prophet API integration

  #920 opened 3 months ago by marcozanotti
  0

• ADAM model from R

  #886 opened 4 months ago by ncooder
  4

• [AutoARIMA] Incorrect default parameters in AutoARIMA

  #896 opened 3 months ago by robert-robison
  0

• `SeasonalNaive` (and other models) spend a lot of time acquiring thread locks

  #898 opened 3 months ago by caseytomlin
  13

• [Core] ImportError: cannot import name 'ThreadpoolController' from 'threadpoolctl' on Databricks

  #912 opened 3 months ago by michal-mmm
  1

• Auto MFLES - add forward method

  #911 opened 3 months ago by GGA-PERSO
  0

• make python requirements static

  #909 opened 3 months ago by dimbleby
  0

• [AutoARIMA] Major hidden bug in `auto_arima_f`

  #897 opened 4 months ago by robert-robison
  3

• How to update fitted Arima model with new values

  #890 opened 4 months ago by eshnEnergiDanmark
  1

• StatsForecast: MSTL - confidence level gives same result as the point estimate - bug

  #887 opened 4 months ago by lken-stripe
  0

• [mstl_decomposition] add exogenous features support

  #884 opened 5 months ago by JustM57
  2

• Add exogenous features support to statsforecast's cross-validation

  #872 opened 4 months ago by quansun
  2

• statsforecast coherence with R solution

  #880 opened 5 months ago by ncooder
  2

• MFLES clip number of arguments

  #882 opened 5 months ago by atsangarides
  2

• AutoARIMA coefficients names

  #879 opened 5 months ago by Chaptyziok
  0

• [Spark, cross-validation] Issue with ":" as model aliases using cross_validation in Spark

  #878 opened 5 months ago by javiomotero
  1

• fail to run ray example NotImplementedError: no registered dataset conversion for <class 'ray.data.dataset.Dataset'>"

  #871 opened 5 months ago by lushunn
  6

• ARIMA fit asymmetrical var_coef for some parameters

  #847 opened 5 months ago by rlshuhart
  0

• Exogenous Regressor having ValueError: could not broadcast input array from shape (53,3) into shape (52,3)

  #867 opened 6 months ago by sm-ak-r33
  8

• add feature importance for statsforecast models that accept exogenous features

  #868 opened 6 months ago by GGA-PERSO
  1

• [AutoARIMA] when using AutoARIMA on a constant time series the forecast fitted values are zero no matter the constant.

  #870 opened 6 months ago by omriKramer
  0

• Problem with statsforecast mstl_decomposition

  #857 opened 6 months ago by Jonathan-87
  2

• Theta Parameter to speed up training

  #860 opened 6 months ago by tackes
  0

• Can I use Exogenous features with AutoETS

  #841 opened 6 months ago by sm-ak-r33
  2

• [Core StatsForecast] Bottom unbound confidence intervals?

  #855 opened 6 months ago by concimuscb
  0

• Dead links for several pages in docs

  #838 opened 6 months ago by quant5
  2

• MSTL is very slow and not using all CPU cores at all

  #851 opened 7 months ago by VictorDonjuan
  2

• statsforecast: prediction fails if more than one model uses fallbackheuristic

  #845 opened 7 months ago by EddyXorb
  2

• ValueError: xreg is rank deficient

  #826 opened 7 months ago by obiii
  4

• MSTL can't use AutoETS as trend_forecaster

  #840 opened 7 months ago by sm-ak-r33
  1

• Models: documented public methods/attributes to extract best parameters for Auto* models

  #829 opened 8 months ago by yarnabrina
  3

• Model evaluation documentation asserts that datasetsforecast is required, but it isn't

  #833 opened 7 months ago by quant5
  2

• Can statsforecast detect season_length automatically?

  #817 opened 8 months ago by wwulfric
  2

• Auto_Ces "Exception: no model able to be fitted"

  #830 opened 8 months ago by LGsus20
  4

• Should `forecast_fitted_values` also work for fitted models in addition to when forecast(fitted=True) is called?

  #835 opened 8 months ago by quant5
  1

• Deprecate references to custom `evaluate_performace` function in favor of `utilsforecast.evaluation.evaluate`?

  #834 opened 8 months ago by quant5
  2

• Problem getting fitted values using cross validation with a spark dataframe

  #831 opened 8 months ago by Jonathan-87
  2

• Problem using fit and predict or fit_predict using a spark dataframe

  #832 opened 8 months ago by Jonathan-87
  1