Skip to main content

Tapkee

Efficient dimensionality reduction library with a focus on spectral methods.

Tapkee implements over 20 dimensionality reduction algorithms and provides a simple Python interface to all of them.

Installation

pip install tapkee

Usage

import numpy as np
from matplotlib import pyplot as plt
import tapkee

# Generate a Swiss roll dataset
n = 2000
t = 1.5 * np.pi * (1 + 2 * np.random.rand(n))
x, y, z = t * np.cos(t), 30 * np.random.rand(n), t * np.sin(t)
data = np.vstack([x, y, z])  # 3 features, n samples

# Unroll with Locally Linear Embedding
embedding = tapkee.embed(data, method="lle", num_neighbors=12)

plt.scatter(embedding[:, 0], embedding[:, 1], c=t, cmap="Spectral", s=5)
plt.title("Swiss roll unrolled with LLE")
plt.show()

Supported methods

Method method= Key parameters
Isomap "isomap" num_neighbors
Landmark Isomap "l-isomap" num_neighbors, landmark_ratio
Diffusion Maps "dm" gaussian_kernel_width, diffusion_map_timesteps
Laplacian Eigenmaps "la" num_neighbors, gaussian_kernel_width
Locally Linear Embedding "lle" num_neighbors
Hessian LLE "hlle" num_neighbors
Local Tangent Space Alignment "ltsa" num_neighbors
Linear LTSA "lltsa" num_neighbors
Locality Preserving Projections "lpp" num_neighbors, gaussian_kernel_width
Neighborhood Preserving Embedding "npe" num_neighbors
PCA "pca"
Kernel PCA "kpca" gaussian_kernel_width
Factor Analysis "fa" max_iteration, fa_epsilon
Random Projection "ra"
MDS "mds"
Landmark MDS "l-mds" landmark_ratio
t-SNE "t-sne" sne_perplexity, sne_theta
Stochastic Proximity Embedding "spe" spe_global_strategy, spe_num_updates, spe_tolerance
Manifold Sculpting "manifold_sculpting" num_neighbors, squishing_rate, max_iteration

All methods accept target_dimension (default: 2). Neighbor-based methods accept num_neighbors (default: 5).

Parameters

Parameter Type Description
target_dimension int Output dimensionality
num_neighbors int Number of neighbors for local methods
gaussian_kernel_width float Width of the Gaussian kernel
landmark_ratio float Ratio of landmark points (0 to 1)
max_iteration int Maximum iterations for iterative methods
diffusion_map_timesteps int Number of timesteps for Diffusion Maps
sne_perplexity float Perplexity for t-SNE
sne_theta float Angle for Barnes-Hut approximation in t-SNE
squishing_rate float Rate for Manifold Sculpting
spe_global_strategy bool Use global strategy for SPE
spe_num_updates int Number of SPE updates
spe_tolerance float SPE convergence tolerance
nullspace_shift float Regularizer for eigenproblems
klle_shift float KLLE regularizer
fa_epsilon float Factor Analysis convergence epsilon
check_connectivity bool Check graph connectivity

Links

Citation

If you use Tapkee in a publication, please cite:

Sergey Lisitsyn, Christian Widmer, Fernando J. Iglesias Garcia. Tapkee: An Efficient Dimension Reduction Library. Journal of Machine Learning Research, 14: 2355-2359, 2013.

License

BSD 3-Clause

Metadata

Release files for tapkee 1.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for tapkee 1.4.0
File Size Uploaded
tapkee-1.4.0.tar.gz 83.4 kB Details

Built distributions (wheels)

Table of built distributions (wheels) for tapkee 1.4.0
File
tapkee-1.4.0-cp314-cp314-win_amd64.whl CPython 3.14 CPython 3.14 Windows x86-64 Details
tapkee-1.4.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl CPython 3.14 CPython 3.14 Linux glibc 2.28+ x86-64, Linux glibc 2.27+ x86-64 Details
tapkee-1.4.0-cp314-cp314-macosx_26_0_arm64.whl CPython 3.14 CPython 3.14 macOS 26.0+ ARM64 Details
tapkee-1.4.0-cp313-cp313-win_amd64.whl CPython 3.13 CPython 3.13 Windows x86-64 Details
tapkee-1.4.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl CPython 3.13 CPython 3.13 Linux glibc 2.28+ x86-64, Linux glibc 2.27+ x86-64 Details
tapkee-1.4.0-cp313-cp313-macosx_26_0_arm64.whl CPython 3.13 CPython 3.13 macOS 26.0+ ARM64 Details
tapkee-1.4.0-cp312-cp312-win_amd64.whl CPython 3.12 CPython 3.12 Windows x86-64 Details
tapkee-1.4.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl CPython 3.12 CPython 3.12 Linux glibc 2.28+ x86-64, Linux glibc 2.27+ x86-64 Details
tapkee-1.4.0-cp312-cp312-macosx_26_0_arm64.whl CPython 3.12 CPython 3.12 macOS 26.0+ ARM64 Details
tapkee-1.4.0-cp311-cp311-win_amd64.whl CPython 3.11 CPython 3.11 Windows x86-64 Details
tapkee-1.4.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl CPython 3.11 CPython 3.11 Linux glibc 2.28+ x86-64, Linux glibc 2.27+ x86-64 Details
tapkee-1.4.0-cp311-cp311-macosx_26_0_arm64.whl CPython 3.11 CPython 3.11 macOS 26.0+ ARM64 Details

Total release size: 120.4 MB

Release files / tapkee-1.4.0.tar.gz

Download URL tapkee-1.4.0.tar.gz
Size 83.4 kB
Tags Source
SHA-256 checksum
How to use checksums
8f4663ae8448c8034c44f5e5f0614b2466e85e99ff7a856b575d84005c15827b
BLAKE2b-256 checksum
How to use checksums
1bcfe5c1c4ee6e2248635ad4573dd47cc99eea877690d3b8c25e627d50ba55c2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp314-cp314-win_amd64.whl

Download URL tapkee-1.4.0-cp314-cp314-win_amd64.whl
Size 6.5 MB
Tags CPython 3.14 Windows x86-64
SHA-256 checksum
How to use checksums
d8e858870bc6f51eeb5ebb50185ba50a2ebad8a769e710667c43e941758c11cf
BLAKE2b-256 checksum
How to use checksums
399e5e31f1badc53fceb4db2f00b4caa56652cdd9d0568407454d3f9e2e7f568
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL tapkee-1.4.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size 12.8 MB
Tags CPython 3.14 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
c47d41dcf93232a1a03f083ad1174e2eab3b3c102c7b2d4fad71707107dce597
BLAKE2b-256 checksum
How to use checksums
ea27ca9f53295f01f02100f872cf057a2152f14a8cf45cd90a80cdae7ebeeb7a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp314-cp314-macosx_26_0_arm64.whl

Download URL tapkee-1.4.0-cp314-cp314-macosx_26_0_arm64.whl
Size 10.8 MB
Tags CPython 3.14 macOS 26.0+ ARM64
SHA-256 checksum
How to use checksums
7d1f93a34eeeeae829e5bc9edb1cf7e89b0ad0dd41dbd9dacc84a613f3aff259
BLAKE2b-256 checksum
How to use checksums
6b2c40860ff3b7e50f29ddf2ef13c4c920cea77eff58c909e321b0ce03a23bcc
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp313-cp313-win_amd64.whl

Download URL tapkee-1.4.0-cp313-cp313-win_amd64.whl
Size 6.3 MB
Tags CPython 3.13 Windows x86-64
SHA-256 checksum
How to use checksums
53885de098da7380c39860151a774cedda087806f1b3e97565d0298b2a754f6d
BLAKE2b-256 checksum
How to use checksums
899cbf2f11958d37429536e0edced5a3c112e179efd2d2eb0a2e76f63ec11d09
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL tapkee-1.4.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size 12.8 MB
Tags CPython 3.13 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
49bdcfac113fa6a9c589af95372742899ef42ffb6ae418572fa1e7c3ffee8daf
BLAKE2b-256 checksum
How to use checksums
45124708d12d20bfbc0375ac90cf95408ba18176a53dd704d7d3472ac28d2baf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp313-cp313-macosx_26_0_arm64.whl

Download URL tapkee-1.4.0-cp313-cp313-macosx_26_0_arm64.whl
Size 10.8 MB
Tags CPython 3.13 macOS 26.0+ ARM64
SHA-256 checksum
How to use checksums
84bd5c332ac5f3d8b28f974cdb44890bc41ae254ca5aea812e41e8db63d9ff67
BLAKE2b-256 checksum
How to use checksums
9d7e016cf44ec05446cb9fa69c7a7d57d49787e913203fa2b1ea169317266d25
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp312-cp312-win_amd64.whl

Download URL tapkee-1.4.0-cp312-cp312-win_amd64.whl
Size 6.3 MB
Tags CPython 3.12 Windows x86-64
SHA-256 checksum
How to use checksums
9c1da2f1ddf2b0e35f6802dfc12505a8e6dd2a98b6da73bc8ea96fcbfd48ed77
BLAKE2b-256 checksum
How to use checksums
842ef6ad6219c41a9cc024417bc5ae765dab680c03b867fc79194ef49ec280da
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL tapkee-1.4.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size 12.8 MB
Tags CPython 3.12 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
4895b1753edd47cac8474b2e537365de0a144fbae192b81e0eb6658f805f930c
BLAKE2b-256 checksum
How to use checksums
7cd6168d9eb4d538a39e8e9a7131638185e82ea8dcda55acbaa7ad3e615f7065
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp312-cp312-macosx_26_0_arm64.whl

Download URL tapkee-1.4.0-cp312-cp312-macosx_26_0_arm64.whl
Size 10.8 MB
Tags CPython 3.12 macOS 26.0+ ARM64
SHA-256 checksum
How to use checksums
98e7fb728cb4afd665725789f0f9824fbe57be8cfb3b2e5c7e43bf96b76bcba1
BLAKE2b-256 checksum
How to use checksums
4496b0150a3406d81f5bfc0068abaa0524a8db2cf9db0e6e658a4b6cbcaf251f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp311-cp311-win_amd64.whl

Download URL tapkee-1.4.0-cp311-cp311-win_amd64.whl
Size 6.3 MB
Tags CPython 3.11 Windows x86-64
SHA-256 checksum
How to use checksums
0bc3a665faa4619fb816e84e1cebe909938dc1691932343f46bb7d9d534550a0
BLAKE2b-256 checksum
How to use checksums
13dc3111fb969a2096842496178e55de0b2016bd061157a1564608c66d2ec3ad
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL tapkee-1.4.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size 12.8 MB
Tags CPython 3.11 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
5eaad1c81162fd50b7e8e85c332237da64386c312ef0154719384266a24c8da5
BLAKE2b-256 checksum
How to use checksums
edb37b4ed1871f6fed6146aad89a14f491b8aa2452c50e76a10997d2a87de0c0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / tapkee-1.4.0-cp311-cp311-macosx_26_0_arm64.whl

Download URL tapkee-1.4.0-cp311-cp311-macosx_26_0_arm64.whl
Size 10.9 MB
Tags CPython 3.11 macOS 26.0+ ARM64
SHA-256 checksum
How to use checksums
83efd81d48f6a0c2e0984897730baa482cf005fb750fbb692cf86ea56e010014
BLAKE2b-256 checksum
How to use checksums
bd130fdd2e4b46a8eee422c06917a30a7ff47b165cadbe2bb0d978bd3c69d507
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

1.4.0 This release

13 release files

1.3.4

10 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page