A package for reducing dimension of gene expression profilesand doing clustering them.
Project description
=======================================
Topic Models for Single Cell Clustering
=======================================
.. image:: https://img.shields.io/pypi/v/tmscc.svg
:target: https://pypi.python.org/pypi/tmscc
.. image:: https://img.shields.io/travis/tarohi24/tmscc.svg
:target: https://travis-ci.org/tarohi24/tmscc
.. image:: https://readthedocs.org/projects/tmscc/badge/?version=latest
:target: https://tmscc.readthedocs.io/en/latest/?badge=latest
:alt: Documentation Status
A package for reducing dimension of gene expression profiles and doing clustering them.
Installation
-------
.. code-block:: console
$ pip install tmmsc
for more information, see https://tmscc.readthedocs.io/en/latest/installation.html.
Example
-------
.. code-block:: python
from tm import LDA
import numpy as np
import pandas as pd
from sklearn.cluster import KMeans
profile = pd.DataFrame(
np.arange(200).reshape([5, 40])
) # gene expression profile (genes*cells matrix)
profile.index = ['CHEK2', 'MSH2', 'PTEN', 'TSC1', 'HER2']
lda = tm.LDA(
n_topics=4,
profile=profile,
outdir='~/tmp',
)
# LDA's estimation (This takes some time.)
lda.estimate()
# lda's theta() can be used for clustering, such as k-means
kmeans = KMeans(n_clusters=2).fit_predict(lda.theta())
* Free software: MIT license
* Documentation: https://tmscc.readthedocs.io.
Features
--------
* TODO
Requirements
-------
* Python >= 3.5
* Java >= 1.8
Credits
-------
* This package owes what this is to `Mallet`_. Thank you for the wonderful toolkit!
.. _Mallet: http://mallet.cs.umass.edu/
=======
History
=======
0.2.0 (2018-03-16)
------------------
* Add LDA implementation.
* Add some documents.
0.1.0 (2018-03-14)
------------------
* First release on PyPI.
Topic Models for Single Cell Clustering
=======================================
.. image:: https://img.shields.io/pypi/v/tmscc.svg
:target: https://pypi.python.org/pypi/tmscc
.. image:: https://img.shields.io/travis/tarohi24/tmscc.svg
:target: https://travis-ci.org/tarohi24/tmscc
.. image:: https://readthedocs.org/projects/tmscc/badge/?version=latest
:target: https://tmscc.readthedocs.io/en/latest/?badge=latest
:alt: Documentation Status
A package for reducing dimension of gene expression profiles and doing clustering them.
Installation
-------
.. code-block:: console
$ pip install tmmsc
for more information, see https://tmscc.readthedocs.io/en/latest/installation.html.
Example
-------
.. code-block:: python
from tm import LDA
import numpy as np
import pandas as pd
from sklearn.cluster import KMeans
profile = pd.DataFrame(
np.arange(200).reshape([5, 40])
) # gene expression profile (genes*cells matrix)
profile.index = ['CHEK2', 'MSH2', 'PTEN', 'TSC1', 'HER2']
lda = tm.LDA(
n_topics=4,
profile=profile,
outdir='~/tmp',
)
# LDA's estimation (This takes some time.)
lda.estimate()
# lda's theta() can be used for clustering, such as k-means
kmeans = KMeans(n_clusters=2).fit_predict(lda.theta())
* Free software: MIT license
* Documentation: https://tmscc.readthedocs.io.
Features
--------
* TODO
Requirements
-------
* Python >= 3.5
* Java >= 1.8
Credits
-------
* This package owes what this is to `Mallet`_. Thank you for the wonderful toolkit!
.. _Mallet: http://mallet.cs.umass.edu/
=======
History
=======
0.2.0 (2018-03-16)
------------------
* Add LDA implementation.
* Add some documents.
0.1.0 (2018-03-14)
------------------
* First release on PyPI.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tmscc-0.2.0.tar.gz
(14.7 kB
view hashes)