Nixtla 
Statistical ⚡️ Forecast
Lightning fast forecasting with statistical and econometric models
StatsForecast offers a collection of widely used univariate time series forecasting models, including automatic ARIMA and ETS modeling optimized for high performance using numba. It also includes a large battery of benchmarking models.
💻 Installation
PyPI
You can install the released version of StatsForecast from the Python package index pip with:
pip install statsforecast
(Installing inside a python virtualenvironment or a conda environment is recommended.)
Conda
Also you can install the released version of StatsForecast from conda with:
conda install -c conda-forge statsforecast
(Installing inside a python virtualenvironment or a conda environment is recommended.)
Dev Mode
If you want to make some modifications to the code and see the effects in real time (without reinstalling), follow the steps below:git clone https://github.com/Nixtla/statsforecast.git
cd statsforecast
pip install -e .
🏃🏻♀️🏃 Getting Started
To get started just follow this guide.
In the guide, we showcase AutoARIMA and AutoETS, and go further into probabilistic predictions, exogenous variables, and other baseline models.
🎉 New!
ETS Example: 4x faster than StatsModels with improved accuracy and robustness.
🔥 Highlights
-
Fastest and most accurate
AutoARIMAinPythonandR. -
Fastest and most accurate
ETSinPythonandR. -
Replace FB-Prophet in two lines of code and gain speed and accuracy. Check the experiments here.
-
Distributed computation in clusters with ray. (Forecast 1M series in 30min)
-
Good Ol' sklearn interface with
AutoARIMA().fit(y).predict(h=7).
🎊 Features
-
Inclusion of
exogenous variablesandprediction intervalsfor ARIMA. -
20x faster than
pmdarima. -
1.5x faster than
R. -
500x faster than
Prophet. -
100x faster than
NeuralProphet. -
4x faster than
statsmodels. -
Compiled to high performance machine code through
numba. -
Out of the box implementation of
ADIDA,HistoricAverage,CrostonClassic,CrostonSBA,CrostonOptimized,SeasonalWindowAverage,SeasonalNaive,IMAPANaive,RandomWalkWithDrift,WindowAverage,SeasonalExponentialSmoothing,TSB,AutoARIMAandETS.
Missing something? Please open an issue or write us in
📖 Why?
Current Python alternatives for statistical models are slow, inaccurate and don't scale well. So we created a library that can be used to forecast in production environments or as benchmarks. StatsForecast includes an extensive battery of models that can efficiently fit millions of time series.
🔬 Accuracy & ⏲ Speed
ARIMA
The AutoARIMA model implemented in StatsForecast is 20x faster than pmdarima and 1.5x faster than R while improving accuracy. You can see the exact comparison and reproduce the results here.
ETS
StatsForecast's exponential smoothing is 4x faster than StatsModels' and 1.6x faster than R's, with improved accuracy and robustness. You can see the exact comparison and reproduce the results here
Benchmarks at Scale
With StatsForecast you can fit 9 benchmark models on 1,000,000 series in under 5 min. Reproduce the results here.
🧬 Getting Started
You can run this notebooks to get you started.
-
Example of different
AutoARIMAmodels on M4 data- In this notebook we present Nixtla's
AutoARIMA. TheAutoARIMAmodel is widely used to forecast time series in production and as a benchmark. However, the alternative python implementation (pmdarima) is so slow that prevents data scientists from quickly iterating and deployingAutoARIMAin production for a large number of time series.
- In this notebook we present Nixtla's
-
Shorter Example of fitting and
AutoARIMAand anETSmodel. -
Benchmarking 9 models on millions of series.
📖 Documentation (WIP)
Here is a link to the documentation.
🔨 How to contribute
See CONTRIBUTING.md.
📃 References
- The
AutoARIMAmodel is based (translated) from the R implementation included in the forecast package developed by Rob Hyndman. - The
ETSmodel is based (translated) from the R implementation included in the forecast package developed by Rob Hyndman.
Contributors ✨
Thanks goes to these wonderful people (emoji key):
This project follows the all-contributors specification. Contributions of any kind welcome!
3 maintainers
Release files for statsforecast 1.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| statsforecast-1.1.0.tar.gz | 76.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| statsforecast-1.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 154.2 kB
Release files / statsforecast-1.1.0.tar.gz
| Download URL | statsforecast-1.1.0.tar.gz |
|---|---|
| Size | 76.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b21d2d7e1e9a53d669a161c1457f2fff56d9684fceee7d9c4b79bd06744ee72e
|
|
BLAKE2b-256 checksum How to use checksums |
20d81fda829d4da999760b4e584e4367f5f0c4344b0d636d8581df64b44183a5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.9.14
|
Release files / statsforecast-1.1.0-py3-none-any.whl
| Download URL | statsforecast-1.1.0-py3-none-any.whl |
|---|---|
| Size | 77.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1e74b61d77c42b022e99251baf96672e94a27aeebd8bb8c3d05d3e8326e79991
|
|
BLAKE2b-256 checksum How to use checksums |
4cc87977d0a2aa35149f8ea26c276880580c2173e571817ce29de4b9ab74ebd6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.9.14
|
