A unified interface for machine learning with time series
๐ Version 0.16.0 out now! Check out the release notes here.
sktime is a library for time series analysis in Python. It provides a unified interface for multiple time series learning tasks. Currently, this includes time series classification, regression, clustering, annotation and forecasting. It comes with time series algorithms and scikit-learn compatible tools to build, tune and validate time series models.
Overview | |
---|---|
CI/CD | |
Code | |
Downloads | |
Community | |
Citation |
Documentation | |
---|---|
โญ Tutorials | New to sktime? Here's everything you need to know! |
๐ Binder Notebooks | Example notebooks to play with in your browser. |
๐ฉโ๐ป User Guides | How to use sktime and its features. |
โ๏ธ Extension Templates | How to build your own estimator using sktime's API. |
๐๏ธ API Reference | The detailed reference for sktime's API. |
๐บ Video Tutorial | Our video tutorial from 2021 PyData Global. |
๐ ๏ธ Changelog | Changes and version history. |
๐ณ Roadmap | sktime's software and community development plan. |
๐ Related Software | A list of related software. |
Questions and feedback are extremely welcome! Please understand that we won't be able to provide individual support via email. We also believe that help is much more valuable if it's shared publicly, so that more people can benefit from it.
Type | Platforms |
---|---|
๐ Bug Reports | GitHub Issue Tracker |
โจ Feature Requests & Ideas | GitHub Issue Tracker |
๐ฉโ๐ป Usage Questions | GitHub Discussions ยท Stack Overflow |
๐ฌ General Discussion | GitHub Discussions |
๐ญ Contribution & Development | Slack, contributors channel ยท Discord |
๐ Community collaboration session | Discord - Fridays 1pm UTC, dev/meet-ups channel |
Our aim is to make the time series analysis ecosystem more interoperable and usable as a whole. sktime provides a unified interface for distinct but related time series learning tasks. It features dedicated time series algorithms and tools for composite model building including pipelining, ensembling, tuning and reduction that enables users to apply an algorithm for one task to another.
sktime also provides interfaces to related libraries, for example scikit-learn, statsmodels, tsfresh, PyOD and fbprophet, among others.
For deep learning, see our companion package: sktime-dl.
Module | Status | Links |
---|---|---|
Forecasting | stable | Tutorial ยท API Reference ยท Extension Template |
Time Series Classification | stable | Tutorial ยท API Reference ยท Extension Template |
Time Series Regression | stable | API Reference |
Transformations | stable | API Reference ยท Extension Template |
Time Series Clustering | maturing | Extension Template |
Time Series Distances/Kernels | experimental | Extension Template |
Annotation | experimental | Extension Template |
For trouble shooting and detailed installation instructions, see the documentation.
- Operating system: macOS X ยท Linux ยท Windows 8.1 or higher
- Python version: Python 3.7, 3.8, 3.9, and 3.10 (only 64 bit)
- Package managers: pip ยท conda (via
conda-forge
)
Using pip, sktime releases are available as source packages and binary wheels. You can see all available wheels here.
pip install sktime
or, with maximum dependencies,
pip install sktime[all_extras]
You can also install sktime from conda
via the conda-forge
channel. For the feedstock including the build recipe and configuration, check out this repository.
conda install -c conda-forge sktime
or, with maximum dependencies,
conda install -c conda-forge sktime-all-extras
from sktime.datasets import load_airline
from sktime.forecasting.base import ForecastingHorizon
from sktime.forecasting.model_selection import temporal_train_test_split
from sktime.forecasting.theta import ThetaForecaster
from sktime.performance_metrics.forecasting import mean_absolute_percentage_error
y = load_airline()
y_train, y_test = temporal_train_test_split(y)
fh = ForecastingHorizon(y_test.index, is_relative=False)
forecaster = ThetaForecaster(sp=12) # monthly seasonal periodicity
forecaster.fit(y_train)
y_pred = forecaster.predict(fh)
mean_absolute_percentage_error(y_test, y_pred)
>>> 0.08661467738190656
from sktime.classification.interval_based import TimeSeriesForestClassifier
from sktime.datasets import load_arrow_head
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
X, y = load_arrow_head()
X_train, X_test, y_train, y_test = train_test_split(X, y)
classifier = TimeSeriesForestClassifier()
classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
accuracy_score(y_test, y_pred)
>>> 0.8679245283018868
There are many ways to join the sktime community. We follow the all-contributors specification: all kinds of contributions are welcome - not just code.
Documentation | |
---|---|
๐ Contribute | How to contribute to sktime. |
๐ Mentoring | New to open source? Apply to our mentoring program! |
๐ Meetings | Join our discussions, tutorials, workshops and sprints! |
๐ฉโ๐ง Developer Guides | How to further develop sktime's code base. |
๐ง Enhancement Proposals | Design a new feature for sktime. |
๐ Contributors | A list of all contributors. |
๐ Roles | An overview of our core community roles. |
๐ธ Donate | Fund sktime maintenance and development. |
๐๏ธ Governance | How and by whom decisions are made in sktime's community. |
- by the community, for the community -- developed by a friendly and collaborative community.
- the right tool for the right task -- helping users to diagnose their learning problem and suitable scientific model types.
- embedded in state-of-art ecosystems and provider of interoperable interfaces -- interoperable with scikit-learn, statsmodels, tsfresh, and other community favourites.
- rich model composition and reduction functionality -- build tuning and feature extraction pipelines, solve forecasting tasks with scikit-learn regressors.
- clean, descriptive specification syntax -- based on modern object-oriented design principles for data science.
- fair model assessment and benchmarking -- build your models, inspect your models, check your models, avoid pitfalls.
- easily extensible -- easy extension templates to add your own algorithms compatible with sktime's API.