Related Software

The Python ecosystem contains numerous packages that can be used to store and process time series data. The following list is by no means exhaustive. If you miss anything, feel free to open a PR.

Table of contents

• Packages for machine learning, statistics or analytics with time series,

• Other time series related frameworks or database systems.

For time series data containers, see our wiki entry.

Machine learning

Libraries

Project Name	Description
adtk	Anomaly Detection Tool Kit, a Python package for unsupervised/rule-based time series anomaly detection
atspy	Collection of forecasting models, wraps existing statistical and machine learning models for forecasting, automated benchmarking
Arrow	A sensible, human-friendly approach to creating, manipulating, formatting and converting dates, times, and timestamps
cesium	Time series platform with feature extraction aiming for non uniformly sampled signals
catch22	Feature selection pipeline for hctsa and the so-called catch22 feature set
crystalball	A python library for forecasting with scikit-learn like API
darts	Python collection of time series forecasting tools, from preprocessing to models (uni-/multivariate, prophet, neural networks) and backtesting utilities
deeptime	Library for unsupervised learning with time series including dimensionality reduction, clustering, and Markov model estimation
deltapy	Collection of data augmentation tools, including feature extraction from time series, wraps existing toolkits like tsfresh
diviner	Diviner by Databricks enables large-scale time series forecasting and serves as a wrapper around other open source forecasting libraries
dtaidistance	Time series distances
dtw	Scipy-based dynamic time warping
Featuretools	Time series feature extraction, with possible conditionality on other variables with a pandas compatible relational-database-like data container
fecon235	Computational tools for financial economics
ffn	financial function library
flint	A Time Series Library for Apache Spark
GENDIS	Shapelet discovery by genetic algorithms
glm-sklearn	scikit-learn compatible wrapper around the GLM module in statsmodels
gluon-ts	Probabilistic forecasting and anomaly detection using deep learning by Amazon
greykite	A Time Series Library for rorecasting by LinkedIn which contains the interpretable “Silverkite” algorithm.
hctsa	Matlab based feature extraction which can be controlled from python
HMMLearn	Hidden Markov Models with scikit-learn compatible API
kats	A toolkit by Facebook for time series analysis, including detection, forecasting, feature extraction/embedding, multivariate analysis, etc.
khiva-python	A Time Series library with accelerated analytics on GPUS, it provides feature extraction and motif discovery among other functionalities.
lifelines	Toolkit for survival analysis
linearmodels	Add linear models including instrumental variable and panel data models that are missing from statsmodels.
loudML	Time series inference engine built on top of TensorFlow to forecast data, detect outliers, and automate your process using future knowledge.
matrixprofile-ts	A Python library for detecting patterns and anomalies in massive datasets using the Matrix Profile
mcfly	Deep learning for time series classification with automated hyperparameter selection
neuralprophet	A Neural Network based model, inspired by Facebook Prophet and AR-Net, built on PyTorch
Nitime	Time series analysis for neuroscience data
NoLiTSA	Non-linear time series analysis
orbit	Bayesian time series forecasting package by uber
pomegranate	Probabilistic models ranging from individual probability distributions to compositional models such as Bayesian networks and hidden Markov models.
Pastas	Time series analysis for hydrological data
prophet	Time series forecasting for time series data that has multiple seasonality with linear or non-linear growth
pyDSE	ARMA models for dynamic system Estimation
PyEMMA	Analysis of extensive molecular dynamics simulations based on Markov models
PyFlux	Classical time series forecasting models
PyHubs	Hubness-aware machine learning in Python including time series classification via dynamic time warping based KNN classification
PyOD	Toolbox for outlier detection
pysf	A scikit-learn compatible machine learning library for supervised/panel forecasting
pmdarima	Port of R’s auto.arima method to Python
pyts	Contains time series preprocessing, transformation as well as classification techniques
ruptures	time series annotation: change point detection, segmentation
salesforce-merlion	Library from salesforce for forecasting, anomaly detection, and change point detection
scikit-fda	A Python library to perform Functional Data Analysis, compatible with scikit-learn, including representation, preprocessing, exploratory analysis and machine learning methods
scikit-multiflow	Extension of scikit-learn to supervised learning of streaming data (dynamic online learning), including regression/classification and change detection
scikit-survival	Survival analysis built on top of scikit-learn
seasonal	Toolkit to estimate trends and seasonality in time series
seqlearn	Extends the scikit-learn pipeline concept to time series annotation
seglearn	Extends the scikit-learn pipeline concept to time series data for classification, regression and forecasting
sktime	A scikit-learn compatible library for learning with time series/panel data including time series classification/regression and (supervised/panel) forecasting
statsforecast	StatsForecast by Nixtla offers a collection of widely used univariate time series forecasting models optimized for high performance using numba
statsmodels	Contains a submodule for classical time series models and hypothesis tests
stumpy	Calculates matrix profile for time series subsequence all-pairs-similarity-search
tbats	Package provides BATS and TBATS time series forecasting methods
tensorflow_probability.sts	Bayesian Structural Time Series model in Tensorflow Probability
timechop	Toolkit for temporal cross-validation, part of the Data Science for Social Good predictive analytics framework
Traces	A library for unevenly-spaced time series analysis
ta-lib	Calculate technical indicators for financial time series (python wrapper around TA-Lib)
ta	Calculate technical indicators for financial time series
tseries	scikit-learn compatible time series regressor as a meta-estimator for forecasting
tsfresh	Extracts and filters features from time series, allowing supervised classificators and regressor to be applied to time series data
tslearn	Direct time series classifiers and regressors
tspreprocess	Preprocess time series (resampling, denoising etc.), still WIP
alibi-detect	Toolbox for Outlier, Adversarial and Drift detection

Specific model implementations

Project name	Description
ES-RNN forecasting algorithm	Python implementation of the winning forecasting method of the M4 competition combining exponential smoothing with a recurrent neural network using PyTorch
Deep learning methods for time series classification	A collection of common deep learning architectures for time series classification
M4 competition	Collection of statistical and machine learning forecasting methods
Microsoft forecasting	Collection of forecasting models and best practices, interfaces existing libraries in Python and R
LSTM-Neural-Network-for-Time-Series-Prediction	LSTM for forecasting model
LSTM_tsc	An LSTM for time series classification
shapelets-python	Shapelet classifier based on a multi layer neural network
ROCKET	Time series classification using random convolutional kernels
TensorFlow-Time-Series-Examples	Time Series Prediction with tf.contrib.timeseries
UCR_Time_Series_Classification_Deep_Learning_Baseline	Fully convolutional neural networks for state-of-the-art time series classification
WTTE-RNN	Time to event forecast by RNN based Weibull density estimation
TimeSeers	alternative to Prophet for timeseries modelling when multiple time series are expected

Time series databases and frameworks

Project Name	Description
arctic	High performance datastore for time series and tick data
automl_service	Fully automated time series classification pipeline, deployed as a web service
cesium	Time series platform with feature extraction aiming for non uniformly sampled signals
thunder	Scalable analysis of image and time series data in Python based on spark
whisper	File-based time-series database format
FinTime	Financial time series database framework, design, benchmarks
MNE	Python software for exploring, visualizing, and analyzing neurophysiological time series data (MEG, EEG, etc)

Acknowledgements

Thanks to Max Christ who started the list here.