deeptime-ml
deeptime
Python

Python library for analysis of time series data including dimensionality reduction, clustering, and Markov model estimation

Last updated Jul 6, 2026
874
Stars
88
Forks
13
Issues
+1
Stars/day
Attention Score
66
Language breakdown
Python 88.0%
C++ 11.7%
CMake 0.2%
Cython 0.1%
โ–ธ Files click to expand
README

deeptime

License: LGPL v3 Tests codecov DOI

Deeptime is a general purpose Python library offering various tools to estimate dynamical models based on time-series data including conventional linear learning methods, such as Markov State Models (MSMs), Hidden Markov Models (HMMs) and Koopman models, as well as kernel and deep learning approaches such as VAMPnets and deep MSMs. The library is largely compatible with scikit-learn, having a range of Estimator classes for these different models, but in contrast to scikit-learn also provides Model classes, e.g., in the case of an MSM, which provide a multitude of analysis methods to compute interesting thermodynamic, kinetic and dynamical quantities, such as free energies, relaxation times and transition paths.

Installation via conda or pip. Both provide compiled binaries for Linux, Windows, and MacOS (x86_64 and arm64).

| conda-forge | PyPI | |:-: |:-: | | conda install -c conda-forge deeptime | pip install deeptime |

Documentation: deeptime-ml.github.io.

Main components of deeptime

| | | | | :---: | :---: | :---: | | Dimension reduction | Deep dimension reduction | SINDy | | Dimension reduction | Deep dimension reduction | SINDy | | Markov state models | Hidden Markov models | Datasets | | MSMs | HMMs | Datasets |

Building the latest trunk version of the package:

Using pip with a local clone and pulling dependencies:

git clone https://github.com/deeptime-ml/deeptime.git

cd deeptime pip install .

Or using pip directly on the remote:

pip install git+https://github.com/deeptime-ml/deeptime.git@main

Building as a standalone CMake project

The C++ library and tests can be built directly with CMake. This requires Python (with development headers), NumPy, and pybind11 to be available.

cmake -B build \
  -DDEEPTIMEBUILDCPP_TESTS=ON \
  -DPythonROOTDIR=/path/to/venv \
  -DPythonFINDVIRTUALENV=ONLY \
  -Dpybind11DIR=$(python -c "import pybind11; print(pybind11.getcmake_dir())")

cmake --build build --target tests ./build/tests/tests

CMake options

| Variable | Default | Description | |---|---|---| | DEEPTIMEBUILDCPP_TESTS | OFF | Build the C++ unit tests (Catch2) | | DEEPTIME_VERSION | 0.0.0 | Version string without commit offset | | DEEPTIMEVERSIONINFO | 0.0.0 | Full version string |

Required CMake variables for dependency discovery

| Variable | Description | |---|---| | pybind11DIR | Path to pybind11's CMake config (e.g. from python -c "import pybind11; print(pybind11.getcmake_dir())") | | PythonROOTDIR | Python installation or virtualenv prefix (helps CMake find the right interpreter) | | PythonFINDVIRTUALENV | Set to ONLY when using a virtualenv to prevent CMake from picking up the system Python |

ยฉ 2026 GitRepoTrend ยท deeptime-ml/deeptime ยท Updated daily from GitHub