NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI
PyPI, #3368 most downloaded on PyPI
Python's forecast::auto.arima equivalent
Latest stable
2.1.1
Last release 1 years ago
17 Nov 2025
Release timing varies
gaps range from 4 weeks to 2.1 years
Nearly every release is documented
notes for 28 of 28 stable releases
1 version withdrawn
withdrawn after publishing
8 years old
29 releases · first in 2018
Drag across the ruler to compare, or tap a release to open it.
Add support for Python 3.14 (See #614 )
Remove support for Python 3.8 (end-of-life 2024-10-07)
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Remove support for Python 3.7 (end-of-life 2023-06-23)
Remove support for Python 3.8 (end-of-life 2024-10-07)
Remove support for Python 3.9 (end-of-life 2025-10-31)
Add support for Python 3.13 (See #609)
Add support for Numpy 2.x. See #600
Increase minimum required Scipy to 1.13.0 (See #607)
Increase minimum required statsmodels to 1.14.5 (See #607)
Pin numpy to <2.0.0 while work is done to support numpy >=2.0.0
Pin numpy to <2.0.0 while work is done to support numpy >=2.0.0
Fix a bug when generating permutations using numpy>=1.24.0. See #534
numpy>=1.24.0. See #534transform when using scikit-learn>=1.2.0, addressing #539Change minimum numpy version to 1.21.2
Add support for Python 3.11
Change minimum numpy version to 1.21.2
Add support for macOS with M1 chip
Use of the exogenous keyword (deprecated in 1.8.0) will now raise a TypeError
Potentially breaking changes:
TypeError
sarimax_kwargs keyword (deprecated in 1.5.1) will now raise a TypeErrorValueErrormaxiter argument will now raise a ValueError (warning since 1.5.0)pmdarima is no longer built for 32-bit architecturesOther changes:
fittedvalues in the public API. See https://github.com/alkaline-ml/pmdarima/issues/493preserve_series, to pmdarima.utils.check_endog that will preserve or squeeze a Pandas Series object to preserve index information.!=0.29.31Remove support for Python 3.6 (EOL: 23 Dec 2021)
Add compatibility for statsmodels 0.13 and higher
statsmodels 0.13 and higherFix a bug in tsdisplay where a value of lag_max larger than the length of the series would create a cryptic numpy broadcasting error. This preconditio
Fix a bug in tsdisplay where a value of lag_max larger than the length of the series would create a cryptic numpy broadcasting error. This precondition will still cause an error, but now it is one the user can better understand. See #440
Change numpy pin to numpy>=1.19.3 (and build on lowest supported version) to no longer limit users' NumPy versions. This addresses #449
Fix a bug where scikit-learn version 1.0.0 was raising ValueError when calling if_delegate_has_method, addressing #454
Change numpy pin to ~=1.19.0 to avoid incompatibility issues, addressing #423
numpy pin to ~=1.19.0 to avoid incompatibility issues, addressing #423Address issue 370 where iterables were not accepted in the ARIMA order.
The exogenous argument has been deprecated in favor of X - See the RFC and the PR for more information. Beginning in version 2.0, the exogenous argume…
Wheels are no longer built for pmdarima on Python <3.6, and backward-compatibility is no longer guaranteed for older python versions.
The exogenous argument has been deprecated in favor of X - See the RFC and the PR for more information. Beginning in version 2.0, the exogenous argument will raise an error.
Migrate random searches into the auto-solvers interface
Random searches now perform unit root tests to prevent models with near non-invertible parameters
The default value of suppress_warnings has changed to True. The primary reason for this is that most warnings emitted come from unit root tests, which are very noisy. DeprecationWarnings and other warnings generated from user input will still be emitted.
Move ModelFitWarning from pmdarima.arima.warnings to pmdarima.warnings
Fix a bug where the pmdarima.model_selection.RollingForecastCV could produce too few splits for the given input data.
Change pin for setuptools from <50.0.0 to !=50.0.0, addressing #401
Change pin for statsmodels from <0.12.0 to !=0.12.0, addressing #376
Deprecate Python 3.5 support, which will be removed in the next release cycle
statsmodels <0.12 to get around single-step forecasts with an exog arraysetuptoolsAddress issue #341 where a combination of a large m value and D value could difference an array into being too small to test stationarity in the ADF t
Address issue #341 where a combination of a large m value and D value could difference an array into
being too small to test stationarity in the ADF test
Fix issue #351 where a large value of m could prevent the seasonality test from completing.
Fix issue #354 where models with near non-invertible roots could still be considered as candidate best-fits.
Remove legacy pickling behavior that separates the statsmodels object from the pmdarima object. This breaks backwards compatibility with versions pre-1.2.0.
Change default with_intercept in pmdarima.arima.auto_arima to 'auto' rather than
True. This will behave much like the current behavior, where a truthiness check will still return
True, but allows the stepwise search to selectively change it to False in the presence of certain
differencing conditions.
Inverse endog transformation is now supported when return_conf_int=True on pipeline predictions
Fix a bug where the pmdarima.model_selection.SlidingWindowForecastCV could produce
too few splits for the given input data.
Permit custom scoring metrics to be passed for out-of-sample scoring, as requested in #368
Pin Cython to be >=0.29,<0.29.18
>=0.29,<0.29.18>=0.11Support newest versions of matplotlib
auto_arima error actions: "trace" which will warn for errors while dumping the original stacktrace.pmdarima.preprocessing.DateFeaturizer. This can be used to create dummy and ordinal exogenous features and is useful when modeling pseudo-seasonal trends or time series with holes in them.ValueError in arima.predict_in_sample when start < dAdds first-party conda distributions as requested in #173
pmdarima.datasets.load_gasolinetrace argumentpmdarima.model_selection.cross_val_predict, as requested in #291Fixed deprecation for check_is_fitted in newer versions of scikit-learn
pmdarima.show_versions as a utility for issue filingcheck_is_fitted in newer versions of scikit-learnpmdarima.datasets.load_sunspots() method with R’s sunspots datasetpmdarima.model_selection.train_test_split() methodFixes a bug in v1.5.0 where the pmdarima.__version__ attribute returned 0.0.0
Fixes a bug in v1.5.0 where the pmdarima.__version__ attribute returned 0.0.0
Removes pmdarima.arima.ARIMA.add_new_samples, which was previously deprecated. Use pmdarima.arima.ARIMA.update instead.
No longer use statsmodels' ARIMA or ARMA class under the hood; only use
the SARIMAX model, which cuts back on a lot of errors/warnings we saw in the past.
(#211)
Defaults in the ARIMA class that have changed as a result of #211:
maxiter is now 50 (was None)method is now 'lbfgs' (was None)seasonal_order is now (0, 0, 0, 0) (was None)max_order is now 5 (was 10) and is no longer used as a constraint when stepwise=TrueCorrect bug where aicc always added 1 (for constant) to degrees of freedom,
even when df_model accounted for the constant term.
New pmdarima.arima.auto.StepwiseContext feature for more control over
fit duration (introduced by @kpsunkara in #221.
Adds the pmdarima.preprocessing.LogEndogTransformer class as discussed in
#205
Exogenous arrays are no longer cast to numpy array by default, and will pass pandas frames through to the model. This keeps variable names intact in the summary #222
Added the prefix param to exogenous featurizers to allow the addition of meaningful
names to engineered features.
Added polyroot test of near non-invertibility when stepwise=True. For
models that are near non-invertible will be deprioritized in model selection
as requested in #208
Removes pmdarima.arima.ARIMA.add_new_samples, which was previously deprecated.
Use pmdarima.arima.ARIMA.update instead.
The following args have been deprecated from the pmdarima.arima.ARIMA class
as well as pmdarima.arima.auto_arima and any other calling methods/classes:
disp<sup>[1]</sup>callback<sup>[1]</sup>transparamssolvertyp[1] These can still be passed to the fit method via **fit_kwargs, but should
no longer be passed to the model constructor.
Added diff_inv function that is in parity with R's implementation, as requested in #180
Added decompose function that is in parity with R's implementation,
as requested in #190
Fixes #191, an issue where the OCSB test could raise ValueError: negative dimensions are not allowed" in OCSB test
Fixes #191, an issue where the OCSB test could raise ValueError: negative dimensions are not allowed" in OCSB test
Add option to automatically inverse-transform endogenous transformations when predicting from pipelines (#197)
Add predict_in_sample to pipeline (#196)
Parameterize dtype option in datasets module
Adds the model_selection submodule, which defines several different cross-validation
classes as well as CV functions:
pmdarima.model_selection.RollingForecastCVpmdarima.model_selection.SlidingWindowForecastCVpmdarima.model_selection.cross_validatepmdarima.model_selection.cross_val_scoreAdds the pmdarima.datasets.load_taylor dataset
Adds a new dataset for stock prediction, along with an associated example (load_msft)
load_msft)sarimax_kwargs to ARIMA constructor and auto_arima function. This fixes #146This pins scipy at 1.12 until statsmodels releases 0.10.0 (at some point in June 2019). Additionally, deprecation warnings are fixed in the scikit-lea…
This is a patch release specifically to get around the statsmodels issue:
https://github.com/statsmodels/statsmodels/issues/5747
This pins scipy at 1.12 until statsmodels releases 0.10.0 (at some point in June 2019). Additionally, deprecation warnings are fixed in the scikit-learn dependency.
Removes the following environment variables, which are now deprecated:
OCSBTest of seasonality, as discussed in #88seasonal_test changes from "ch" to "ocsb" in auto_arimatest changes from "ch" to "ocsb" in nsdiffspytest pluginsPMDARIMA_CACHE and PYRAMID_ARIMA_CACHEPMDARIMA_CACHE_WARN_SIZE and PYRAMID_ARIMA_CACHE_WARN_SIZEPYRAMID_MPL_DEBUGPYRAMID_MPL_BACKENDis_stationary method in tests of stationarity. This will be removed in
v1.4.0. Use should_diff instead.airpassengers & austresout_of_sample, the out-of-sample predictions are now stored
under the oob_preds_ attribute.BoxCoxEndogTransformerFourierFeaturizerPipeline class resembling that of scikit-learn's, which allows the
stacking of transformers together.auto_arima: AutoARIMA. This is allows auto-ARIMA
to be used with pipelines.Deprecates the ARIMA.add_new_observations method. This method originally was designed to support updating the endogenous/exogenous arrays with new obs…
v1.1.1 is a patch release in response to #104
Deprecates the ARIMA.add_new_observations method. This method originally was designed to support updating the endogenous/exogenous arrays with new observations without changing the model parameters, but achieving this behavior for each of statsmodels' ARMA, ARIMA and SARIMAX classes proved nearly impossible, given the extremely complex internals of statmodels estimators.
Replace ARIMA.add_new_observations with ARIMA.update. This allows the user to update the model with new observations by taking maxiter new steps from the existing model coefficients and allowing the MLE to converge to an updated set of model parameters.
Change default maxiter to None, using 50 for seasonal models and 500 for non-seasonal models (as statsmodels does). The default value used to be 50 for all models.
New behavior in ARIMA.fit allows start_params and maxiter to be passed as **fit_args, overriding the use of their corresponding instance attributes.
The 'PMDARIMA_CACHE' and 'PMDARIMA_CACHE_WARN_SIZE' environment variables are now deprecated, since they no longer need to be used. They will be remov…
Release 1.1.0 adds:
ARIMA.plot_diagnostics method, as requested in #49ARIMA constructor and auto_arima: with_intercept (default is True).trend is no longer 'c', it is None.to_dict method to ARIMA class to address #54'PMDARIMA_CACHE' and 'PMDARIMA_CACHE_WARN_SIZE' environment variables are
now deprecated, since they no longer need to be used. They will be removed in v1.2.0alkaline-ml.com/pmdarima/<version>Warn for impending deprecation of various environment variable name changes. The following will be completely switched over in version 1.2.0:
Wheels will no longer be built for Python versions < 3.5. You may still be able to build from source, but support for 2.x python versions will diminish in future versions.
Migrate namespace from 'pyramid-arima' to 'pmdarima'. This is due to the fact that a growing web-framework (also named Pyramid) is causing namespace collisions when both packages are installed on a machine. See Issue #34 for more detail.
Remove redundant Travis tests
Automate documentation build on Circle CI
Move lots of the build/test functionality into the Makefile for ease.
Warn for impending deprecation of various environment variable name changes. The following will be completely switched over in version 1.2.0:
'PYRAMID_MPL_DEBUG' will become 'PMDARIMA_MPL_DEBUG''PYRAMID_MPL_BACKEND' will become 'PMDARIMA_MPL_BACKEND''PYRAMID_ARIMA_CACHE_WARN_SIZE' will become 'PMDARIMA_CACHE_WARN_SIZE'Nothing published for this version
One column per quarter.