Skip to main content
Python Software Foundation 20th Year Anniversary Fundraiser  Donate today!

Support vector machines (SVMs) and related kernel-based learning algorithms are a well-known class of machine learning algorithms, for non- parametric classification and regression. liquidSVM is an implementation of SVMs whose key features are: fully integrated hyper-parameter selection, extreme speed on both small and large data sets, inclusion of a variety of different classification and regression scenarios, and full flexibility for experts.

Project description

Welcome to the Python bindings for liquidSVM.

Summary:

Then to try it out issue on the command line

python -m liquidSVM covtype.1000 mc --display=1

**NOTE**: it might be possible that there is a problem with the last
line if there are files called ``liquidSVM*`` in the current
directory, so change to some other or a newly created one.

Or use it in an interactive shell

from liquidSVM import *
model = mcSVM(iris, iris_labs, display=1,threads=2)
result, err = model.test(iris, iris_labs)
result = model.predict(iris)

reg = LiquidData('reg-1d')
model = lsSVM(reg.test, display=1)
result, err = model.test(reg.test)

More Information can be found in the demo [jupyter notebook] and in

from liquidSVM import *
help(SVM)
help(doc.configuration)

Both liquidSVM and these bindings are provided under the AGPL 3.0 license.

Native Library Compilation

liquidSVM is implemented in C++ therefore a native library needs to be compiled and included in the Python process. Binaries for Windows are included, however if it is possible for you, we recommend you compile it for every machine to get full performance.

To set compiler options use the the environment variable LIQUIDSVM_CONFIGURE_ARGS. The first word in it can be any of the following:

native
usually the fastest, but the resulting library is usually not portable to other machines.
generic
should be portable to most machines, yet slower (factor 2 to 4?)
debug
compiles with debugging activated (can be debugged e.g. with gdb)
empty
No special compilation options activated.

The remainder of the environment variable will be passed to the compiler. Extract http://www.isa.uni-stuttgart.de/software/python/liquidSVM-python.tar.gz and change into the directory. On Linux and MacOS X command line use for instance:

LIQUIDSVM_CONFIGURE_ARGS="native -mavx2" python setup.py bdist
LIQUIDSVM_CONFIGURE_ARGS=generic python setup.py bdist
MacOS:
Install Xcode and then the optional command line tools are installed from therein.
Windows:

If you have VisualStudio installed then you should have an environment variable like %VS90COMNTOOLS% (for VisualStudio 2015). Still it seems that setup.py needs to have this information in %VS90COMNTOOLS% so copy that environment variable or use for example:

set VS90COMNTOOLS=%VS140COMNTOOLS%

**Note:** At the moment the Visual Studio for Python only gives
Version 9.0 and this is too old for compilation.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for liquidSVM, version 1.0.1
Filename, size File type Python version Upload date Hashes
Filename, size liquidSVM-1.0.1-cp27-cp27m-macosx_10_7_x86_64.whl (808.5 kB) File type Wheel Python version cp27 Upload date Hashes View
Filename, size liquidSVM-1.0.1-cp27-cp27m-win_amd64.whl (695.0 kB) File type Wheel Python version cp27 Upload date Hashes View
Filename, size liquidSVM-1.0.1-cp35-cp35m-win_amd64.whl (677.9 kB) File type Wheel Python version cp35 Upload date Hashes View
Filename, size liquidSVM-1.0.1-cp36-cp36m-macosx_10_7_x86_64.whl (817.3 kB) File type Wheel Python version cp36 Upload date Hashes View
Filename, size liquidSVM-1.0.1-cp36-cp36m-win_amd64.whl (677.9 kB) File type Wheel Python version cp36 Upload date Hashes View
Filename, size liquidSVM-1.0.1-py2.7-macosx-10.7-x86_64.egg (807.0 kB) File type Egg Python version 2.7 Upload date Hashes View
Filename, size liquidSVM-1.0.1-py2.7-win-amd64.egg (693.6 kB) File type Egg Python version 2.7 Upload date Hashes View
Filename, size liquidSVM-1.0.1-py3.5-win-amd64.egg (697.5 kB) File type Egg Python version 3.5 Upload date Hashes View
Filename, size liquidSVM-1.0.1-py3.6-macosx-10.7-x86_64.egg (836.7 kB) File type Egg Python version 3.6 Upload date Hashes View
Filename, size liquidSVM-1.0.1-py3.6-win-amd64.egg (697.2 kB) File type Egg Python version 3.6 Upload date Hashes View
Filename, size liquidSVM-1.0.1.tar.gz (560.4 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page