Install

You can install the released version of StatsForecast from the Python package index with:

pip install statsforecast

or

conda install -c conda-forge statsforecast

Warning

We are constantly updating StatsForecast, so we suggest fixing the version to avoid issues. pip install statsforecast=="1.0.0"

Tip

We recommend installing your libraries inside a python virtual or conda environment.

​

User our env (optional)

If you don’t have a Conda environment and need tools like Numba, Pandas, NumPy, Jupyter, StatsModels, and Nbdev you can use ours by following these steps:

1. Clone the StatsForecast repo:

$ git clone https://github.com/Nixtla/statsforecast.git && cd statsforecast

1. Create the environment using the environment.yml file:

$ conda env create -f environment.yml

1. Activate the environment:

$ conda activate statsforecast

​

Extras

The following features can also be installed by specifying the extra inside the install command, e.g. pip install 'statsforecast[extra1,extra2]'

• polars: provide polars dataframes to StatsForecast.
• plotly: use StatsForecast.plot with the plotly backend.
• dask: perform distributed forecasting with dask.
• spark: perform distributed forecasting with spark.
• ray: perform distributed forecasting with ray.