Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tgsmith61591/pyramid
A statistical library designed to fill the void in Python's time series analysis capabilities, including the equivalent of R's auto.arima function.
https://github.com/tgsmith61591/pyramid
arima econometrics forecasting forecasting-models machine-learning pmdarima python sarimax time-series
Last synced: 16 days ago
JSON representation
A statistical library designed to fill the void in Python's time series analysis capabilities, including the equivalent of R's auto.arima function.
- Host: GitHub
- URL: https://github.com/tgsmith61591/pyramid
- Owner: alkaline-ml
- License: mit
- Created: 2017-03-30T14:58:30.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2024-09-25T17:37:58.000Z (3 months ago)
- Last Synced: 2024-10-29T11:33:42.517Z (about 2 months ago)
- Topics: arima, econometrics, forecasting, forecasting-models, machine-learning, pmdarima, python, sarimax, time-series
- Language: Python
- Homepage: https://www.alkaline-ml.com/pmdarima
- Size: 76.1 MB
- Stars: 1,585
- Watchers: 36
- Forks: 234
- Open Issues: 63
-
Metadata Files:
- Readme: README.md
- Contributing: .github/CONTRIBUTING.md
- Funding: .github/FUNDING.yml
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Citation: CITATION.cff
- Authors: AUTHORS.md
Awesome Lists containing this project
- awesome-TS-anomaly-detection - pmdarima - learn-friendly interface. | MIT | :heavy_check_mark: (Related Software / Forecasting)
- awesome_time_series_in_python - pyramid
README
# pmdarima
[](https://badge.fury.io/py/pmdarima)
[](https://circleci.com/gh/alkaline-ml/pmdarima)
[](https://github.com/alkaline-ml/pmdarima/actions?query=workflow%3A%22Mac+and+Windows+Builds%22+branch%3Amaster)
[](https://codecov.io/gh/alkaline-ml/pmdarima)
Pmdarima (originally `pyramid-arima`, for the anagram of 'py' + 'arima') is a statistical
library designed to fill the void in Python's time series analysis capabilities. This includes:
* The equivalent of R's [`auto.arima`](https://www.rdocumentation.org/packages/forecast/versions/7.3/topics/auto.arima) functionality
* A collection of statistical tests of stationarity and seasonality
* Time series utilities, such as differencing and inverse differencing
* Numerous endogenous and exogenous transformers and featurizers, including Box-Cox and Fourier transformations
* Seasonal time series decompositions
* Cross-validation utilities
* A rich collection of built-in time series datasets for prototyping and examples
* Scikit-learn-esque pipelines to consolidate your estimators and promote productionization
Pmdarima wraps [statsmodels](https://github.com/statsmodels/statsmodels/blob/master/statsmodels)
under the hood, but is designed with an interface that's familiar to users coming
from a scikit-learn background.
## Installation
### pip
Pmdarima has binary and source distributions for Windows, Mac and Linux (`manylinux`) on pypi
under the package name `pmdarima` and can be downloaded via `pip`:
```bash
pip install pmdarima
```
### conda
Pmdarima also has Mac and Linux builds available via `conda` and can be installed like so:
```bash
conda config --add channels conda-forge
conda config --set channel_priority strict
conda install pmdarima
```
**Note:** We do not maintain our own Conda binaries, they are maintained at https://github.com/conda-forge/pmdarima-feedstock.
See that repo for further documentation on working with Pmdarima on Conda.
## Quickstart Examples
Fitting a simple auto-ARIMA on the [`wineind`](https://alkaline-ml.com/pmdarima/modules/generated/pmdarima.datasets.load_wineind.html#pmdarima.datasets.load_wineind) dataset:
```python
import pmdarima as pm
from pmdarima.model_selection import train_test_split
import numpy as np
import matplotlib.pyplot as plt
# Load/split your data
y = pm.datasets.load_wineind()
train, test = train_test_split(y, train_size=150)
# Fit your model
model = pm.auto_arima(train, seasonal=True, m=12)
# make your forecasts
forecasts = model.predict(test.shape[0]) # predict N steps into the future
# Visualize the forecasts (blue=train, green=forecasts)
x = np.arange(y.shape[0])
plt.plot(x[:150], train, c='blue')
plt.plot(x[150:], forecasts, c='green')
plt.show()
```
Fitting a more complex pipeline on the [`sunspots`](https://www.rdocumentation.org/packages/datasets/versions/3.6.1/topics/sunspots) dataset,
serializing it, and then loading it from disk to make predictions:
```python
import pmdarima as pm
from pmdarima.model_selection import train_test_split
from pmdarima.pipeline import Pipeline
from pmdarima.preprocessing import BoxCoxEndogTransformer
import pickle
# Load/split your data
y = pm.datasets.load_sunspots()
train, test = train_test_split(y, train_size=2700)
# Define and fit your pipeline
pipeline = Pipeline([
('boxcox', BoxCoxEndogTransformer(lmbda2=1e-6)), # lmbda2 avoids negative values
('arima', pm.AutoARIMA(seasonal=True, m=12,
suppress_warnings=True,
trace=True))
])
pipeline.fit(train)
# Serialize your model just like you would in scikit:
with open('model.pkl', 'wb') as pkl:
pickle.dump(pipeline, pkl)
# Load it and make predictions seamlessly:
with open('model.pkl', 'rb') as pkl:
mod = pickle.load(pkl)
print(mod.predict(15))
# [25.20580375 25.05573898 24.4263037 23.56766793 22.67463049 21.82231043
# 21.04061069 20.33693017 19.70906027 19.1509862 18.6555793 18.21577243
# 17.8250318 17.47750614 17.16803394]
```
### Availability
`pmdarima` is available on PyPi in pre-built Wheel files for Python 3.9+ for the following platforms:
* Mac (64-bit)
* Linux (64-bit manylinux)
* Windows (64-bit)
* 32-bit wheels are available for pmdarima versions below 2.0.0 and Python versions below 3.10
If a wheel doesn't exist for your platform, you can still `pip install` and it
will build from the source distribution tarball, however you'll need `cython>=0.29`
and `gcc` (Mac/Linux) or `MinGW` (Windows) in order to build the package from source.
Note that legacy versions (<1.0.0) are available under the name
"`pyramid-arima`" and can be pip installed via:
```bash
# Legacy warning:
$ pip install pyramid-arima
# python -c 'import pyramid;'
```
However, this is not recommended.
## Documentation
All of your questions and more (including examples and guides) can be answered by
the [`pmdarima` documentation](https://www.alkaline-ml.com/pmdarima). If not, always
feel free to file an issue.