Skip to main content

A Python toolbox for multivariate analysis using PCA and PLS methods

Project description

pyphi Release 6.0

Modules

Phi toolbox for multivariate analysis by Sal Garcia (salvadorgarciamunoz@gmail.com, sgarciam@ic.ac.uk).

  • pyphi.calc: Routines to build PCA/PLS/LPLS/JYPLS/JRPLS/TPLS/PLS-CCA(OPLS) models.
  • pyphi.plots: A variety of plotting tools for models created with pyphi.
  • pyphi.batch: Batch analysis toolbox to perform batch alightment and Multi-way models for batch data

Documentation

https://salvadorgarciamunoz.github.io/pyphi/index.html

Getting Started

pip install pyphi-mvda

Installation

NEW NEW NEW pip install pyphi-mvda

  1. Ensure you have Python 3 installed and accessible via your terminal ("python" command).
  2. Download this repository via git clone or manually using the download zip button at the top of the page.
  3. Install the pyphi, pyphi_plots and pyphi_batch modules by opening a terminal window, navigating to the root of this repository, and typing pip install -r requirements.txt.

To confirm you have a working installation, navigate to the Examples folder and copy the Example_Script.py to the directory of your choice. Run python Example_Script.py, verifying there are no errors logged to the console.

Optional External Dependencies

  • IPOPT as an executable in your system path or GAMS python module or GAMS executable in yoru system path.

    • Windows: conda install -c conda-forge IPOPT=3.11.1 or download from IPOPT releases page, extract and add the IPOPT\bin folder to your system path or add all files to your working directory.

    • Mac/Linux: conda install -c conda-forge IPOPT, download from IPOPT releases page, or Compile using coinbrew.

    • if GAMS is installed, pyphi will run ipopt via GAMS, make sure the GAMS executables are reachable through the system PATH

  • If IPOPT is not detected, pyphi will submit the pyomo models to the NEOS server to solve them remotely.

    • To use the NEOS server, the environment variable "NEOS_EMAIL" must be assigned a valid email. This can be done outside of python using set/set/export or use import os os.environ["NEOS_EMAIL"] = youremail@domain.com in your code.

Run the script '''Example_Script_testing_MD_by_NLP.py''' to verify that pyphi can execute IPOPT

Adding a folder to your system path:

  • Windows: temporary set PATH=C:\Path\To\ipopt\bin;%PATH% or persistent setx PATH=C:\Path\To\ipopt\bin;%PATH%.
  • Mac/Linux: export PATH=/path/to/ipopt:$PATH, add to .profile/.*rc file to make persistent.
  • Both via Conda: after activating your environment, use conda env config vars set and your OS-specific set or export command.

This is Release 4.0 the lastest added in terms of computation is the calculation of the Covariant scores and loadings (equivalent to what you get with OPLS) with the '''cca''' flag in the PLS routing

Project details


Download files

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

Source Distribution

pyphi_mvda-6.0.5.tar.gz (7.7 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pyphi_mvda-6.0.5-py3-none-any.whl (87.3 kB view details)

Uploaded Python 3

File details

Details for the file pyphi_mvda-6.0.5.tar.gz.

File metadata

  • Download URL: pyphi_mvda-6.0.5.tar.gz
  • Upload date:
  • Size: 7.7 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.13

File hashes

Hashes for pyphi_mvda-6.0.5.tar.gz
Algorithm Hash digest
SHA256 f313058d7c84d3f1a073dc0cbca3b2428fda598ff27ce8eeb566154b6e1abe79
MD5 077d372fa46d17e1773545ca22dc377c
BLAKE2b-256 192b096d1ad0b413a175a77dd4f0978bc5da9294da56d62bdb3bb2827ab5bb4c

See more details on using hashes here.

File details

Details for the file pyphi_mvda-6.0.5-py3-none-any.whl.

File metadata

  • Download URL: pyphi_mvda-6.0.5-py3-none-any.whl
  • Upload date:
  • Size: 87.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.13

File hashes

Hashes for pyphi_mvda-6.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 b75dcee94beb2f87921ad1cbb7c7bd7977992e4cc2d49b014ee26bdad3670404
MD5 a17579dd7d6749fedc8fb5c13517cb7f
BLAKE2b-256 8d245bdb8133b0f9473d6939910176a76f5e50d07b5e995bb868ef3fe71fda6e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page