Skip to content

aeon-toolkit/aeon

Folders and files

NameName
Last commit message
Last commit date

Latest commit

4a58c4d · Mar 4, 2024
Jan 19, 2024
Mar 4, 2024
Mar 4, 2024
Feb 19, 2024
Mar 4, 2024
Mar 4, 2024
Feb 25, 2024
Feb 27, 2024
Jan 13, 2024
Feb 6, 2024
Oct 19, 2023
Jan 17, 2024
Mar 4, 2024
Feb 16, 2024
Jan 19, 2024
Jan 15, 2024
Jan 19, 2024
Jan 19, 2024
Feb 28, 2024
Jan 19, 2024
Mar 8, 2023
Feb 4, 2024
Mar 4, 2024
Feb 25, 2024
Mar 4, 2024

Repository files navigation

aeon logo

⌛ Welcome to aeon

aeon is an open-source toolkit for learning from time series. It is compatible with scikit-learn and provides access to the very latest algorithms for time series machine learning, in addition to a range of classical techniques for learning tasks such as forecasting and classification.

We strive to provide a broad library of time series algorithms including the latest advances, offer efficient implementations using numba, and interfaces with other time series packages to provide a single framework for algorithm comparison.

The latest aeon release is v0.7.1. You can view the full changelog here.

Our webpage and documentation is available at https://aeon-toolkit.org.

Overview
CI/CD github-actions-release github-actions-main github-actions-nightly docs-main docs-main !codecov
Code !pypi !conda !python-versions !black license binder
Community !slack !linkedin !twitter

⚙️ Installation

aeon requires a Python version of 3.8 or greater. Our full installation guide is available in our documentation.

The easiest way to install aeon is via pip:

pip install aeon

Some estimators require additional packages to be installed. If you want to install the full package with all optional dependencies, you can use:

pip install aeon[all_extras]

Instructions for installation from the GitHub source can be found here.

⏲️ Getting started

The best place to get started for all aeon packages is our getting started guide.

Below we provide a quick example of how to use aeon for forecasting and classification.

Forecasting

import pandas as pd
from aeon.forecasting.trend import TrendForecaster

y = pd.Series([20.0, 40.0, 60.0, 80.0, 100.0])
>>> 0     20.0
>>> 1     40.0
>>> 2     60.0
>>> 3     80.0
>>> 4    100.0
>>> dtype: float64

forecaster = TrendForecaster()
forecaster.fit(y)  # fit the forecaster
>>> TrendForecaster()

pred = forecaster.predict(fh=[1, 2, 3])  # forecast the next 3 values
>>> 5    120.0
>>> 6    140.0
>>> 7    160.0
>>> dtype: float64

Classification

import numpy as np
from aeon.classification.distance_based import KNeighborsTimeSeriesClassifier

X = [[[1, 2, 3, 4, 5, 5]],  # 3D array example (univariate)
     [[1, 2, 3, 4, 4, 2]],  # Three samples, one channel, six series length,
     [[8, 7, 6, 5, 4, 4]]]
y = ['low', 'low', 'high']  # class labels for each sample
X = np.array(X)
y = np.array(y)

clf = KNeighborsTimeSeriesClassifier(distance="dtw")
clf.fit(X, y)  # fit the classifier on train data
>>> KNeighborsTimeSeriesClassifier()

X_test = np.array(
    [[[2, 2, 2, 2, 2, 2]], [[5, 5, 5, 5, 5, 5]], [[6, 6, 6, 6, 6, 6]]]
)
y_pred = clf.predict(X_test)  # make class predictions on new data
>>> ['low' 'high' 'high']

💬 Where to ask questions

Type Platforms
🐛 Bug Reports GitHub Issue Tracker
Feature Requests & Ideas GitHub Issue Tracker & Slack
💻 Usage Questions GitHub Discussions & Slack
💬 General Discussion GitHub Discussions & Slack
🏭 Contribution & Development Slack